diff options
| author | Jean-Baptiste Queru <jbq@google.com> | 2011-02-04 14:12:08 -0800 |
|---|---|---|
| committer | Jean-Baptiste Queru <jbq@google.com> | 2011-02-04 14:12:08 -0800 |
| commit | 6516b99bb74dfb7187a08f7090bf7ca22a006f15 (patch) | |
| tree | 2cda04a3eee460c97f0411722bce3e9d9e54663d | |
| parent | e46e2414e0d5f0405da714c6531c176643aed09c (diff) | |
| download | markdown-6516b99bb74dfb7187a08f7090bf7ca22a006f15.tar.gz | |
Import python-markdown
This is from git://gitorious.org/python-markdown/mainline.git
at tag 2.0.3 (commit 067d88bc41c7924c9087b724ff5247235243ce6b)
Change-Id: I5091438ce3243b87a099b8a75dd6307921966e76
420 files changed, 28007 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..0238e63 --- /dev/null +++ b/.gitignore @@ -0,0 +1,7 @@ +*.pyc +*.bak +*.tmp +*.swp +tmp/* +build/* +dist/* diff --git a/MANIFEST.in b/MANIFEST.in new file mode 100644 index 0000000..4558938 --- /dev/null +++ b/MANIFEST.in @@ -0,0 +1,6 @@ +recursive-include bin * +recursive-include markdown *.py +recursive-include docs * +prune markdown/extensions/legacy.py +include setup.py +include MANIFEST diff --git a/MarkdownTest/MarkdownTest.pl b/MarkdownTest/MarkdownTest.pl new file mode 100755 index 0000000..8e7048f --- /dev/null +++ b/MarkdownTest/MarkdownTest.pl @@ -0,0 +1,165 @@ +#!/usr/bin/perl + +# +# MarkdownTester -- Run tests for Markdown implementations +# +# Copyright (c) 2004-2005 John Gruber +# <http://daringfireball.net/projects/markdown/> +# + +use strict; +use warnings; +use Getopt::Long; +use Benchmark; + +our $VERSION = '1.0.2'; +# Sat 24 Dec 2005 + +my $time_start = new Benchmark; +my $test_dir = "Tests"; +my $script = "./Markdown.pl"; +my $use_tidy = 0; +my ($flag_version); + +GetOptions ( + "script=s" => \$script, + "testdir=s" => \$test_dir, + "tidy" => \$use_tidy, + "version" => \$flag_version, + ); + +if($flag_version) { + my $progname = $0; + $progname =~ s{.*/}{}; + die "$progname version $VERSION\n"; +} + +unless (-d $test_dir) { die "'$test_dir' is not a directory.\n"; } +unless (-f $script) { die "$script does not exist.\n"; } +unless (-x $script) { die "$script is not executable.\n"; } + +my $tests_passed = 0; +my $tests_failed = 0; + +TEST: +foreach my $testfile (glob "$test_dir/*.text") { + my $testname = $testfile; + $testname =~ s{.*/(.+)\.text$}{$1}i; + print "$testname ... "; + + # Look for a corresponding .html file for each .text file: + my $resultfile = $testfile; + $resultfile =~ s{\.text$}{\.html}i; + unless (-f $resultfile) { + print "'$resultfile' does not exist.\n\n"; + next TEST; + } + + # open(TEST, $testfile) || die("Can't open testfile: $!"); + open(RESULT, $resultfile) || die("Can't open resultfile: $!"); + undef $/; + # my $t_input = <TEST>; + my $t_result = <RESULT>; + + my $t_output = `'$script' '$testfile'`; + + # Normalize the output and expected result strings: + $t_result =~ s/\s+\z//; # trim trailing whitespace + $t_output =~ s/\s+\z//; # trim trailing whitespace + if ($use_tidy) { + # Escape the strings, pass them through to CLI tidy tool for tag-level equivalency + $t_result =~ s{'}{'\\''}g; # escape ' chars for shell + $t_output =~ s{'}{'\\''}g; + $t_result = `echo '$t_result' | tidy -quiet --show-warnings n`; + $t_output = `echo '$t_output' | tidy -quiet --show-warnings n`; + } + + if ($t_output eq $t_result) { + print "OK\n"; + $tests_passed++; + } + else { + print "FAILED\n\n"; + $tests_failed++; + } +} + +print "\n\n"; +print "$tests_passed passed; $tests_failed failed.\n"; + +my $time_end = new Benchmark; +my $time_diff = timediff($time_end, $time_start); +print "Benchmark: ", timestr($time_diff), "\n"; + + +__END__ + +=pod + +=head1 NAME + +B<MarkdownTest> + + +=head1 SYNOPSIS + +B<MarkdownTest.pl> [ B<--options> ] [ I<file> ... ] + + +=head1 DESCRIPTION + + +=head1 OPTIONS + +Use "--" to end switch parsing. For example, to open a file named "-z", use: + + MarkdownTest.pl -- -z + +=over 4 + +=item B<--script> + +Specify the path to the Markdown script to test. Defaults to +"./Markdown.pl". Example: + + ./MarkdownTest.pl --script ./PHP-Markdown/php-markdown + +=item B<--testdir> + +Specify the path to a directory containing test data. Defaults to "Tests". + +=item B<--tidy> + +Flag to turn on using the command line 'tidy' tool to normalize HTML +output before comparing script output to the expected test result. +Assumes that the 'tidy' command is available in your PATH. Defaults to +off. + +=back + + + +=head1 BUGS + + + +=head1 VERSION HISTORY + +1.0 Mon 13 Dec 2004-2005 + +1.0.1 Mon 19 Sep 2005 + + + Better handling of case when foo.text exists, but foo.html doesn't. + It now prints a message and moves on, rather than dying. + + +=head1 COPYRIGHT AND LICENSE + +Copyright (c) 2004-2005 John Gruber +<http://daringfireball.net/> +All rights reserved. + +This is free software; you may redistribute it and/or modify it under +the same terms as Perl itself. + +=cut diff --git a/MarkdownTest/Tests_2004/Amps and angle encoding.html b/MarkdownTest/Tests_2004/Amps and angle encoding.html new file mode 100644 index 0000000..9606860 --- /dev/null +++ b/MarkdownTest/Tests_2004/Amps and angle encoding.html @@ -0,0 +1,17 @@ +<p>AT&T has an ampersand in their name.</p> + +<p>AT&T is another way to write it.</p> + +<p>This & that.</p> + +<p>4 < 5.</p> + +<p>6 > 5.</p> + +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link</a> with an ampersand in the URL.</p> + +<p>Here's a link with an amersand in the link text: <a href="http://att.com/" title="AT&T">AT&T</a>.</p> + +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> + +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> diff --git a/MarkdownTest/Tests_2004/Amps and angle encoding.text b/MarkdownTest/Tests_2004/Amps and angle encoding.text new file mode 100644 index 0000000..0e9527f --- /dev/null +++ b/MarkdownTest/Tests_2004/Amps and angle encoding.text @@ -0,0 +1,21 @@ +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Here's a [link] [1] with an ampersand in the URL. + +Here's a link with an amersand in the link text: [AT&T] [2]. + +Here's an inline [link](/script?foo=1&bar=2). + +Here's an inline [link](</script?foo=1&bar=2>). + + +[1]: http://example.com/?foo=1&bar=2 +[2]: http://att.com/ "AT&T"
\ No newline at end of file diff --git a/MarkdownTest/Tests_2004/Amps and angle encoding.text-out b/MarkdownTest/Tests_2004/Amps and angle encoding.text-out new file mode 100644 index 0000000..d52a97e --- /dev/null +++ b/MarkdownTest/Tests_2004/Amps and angle encoding.text-out @@ -0,0 +1,21 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>AT&T has an ampersand in their name.</p> +<p>AT&T is another way to write it.</p> +<p>This & that.</p> +<p>4 < 5.</p> +<p>6 > 5.</p> +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link</a> +with an ampersand in the URL.</p> +<p>Here's a link with an amersand in the link text: <a href= +"http://att.com/" title="AT&T">AT&T</a>.</p> +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Amps and angle encoding.text-res b/MarkdownTest/Tests_2004/Amps and angle encoding.text-res new file mode 100644 index 0000000..d52a97e --- /dev/null +++ b/MarkdownTest/Tests_2004/Amps and angle encoding.text-res @@ -0,0 +1,21 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>AT&T has an ampersand in their name.</p> +<p>AT&T is another way to write it.</p> +<p>This & that.</p> +<p>4 < 5.</p> +<p>6 > 5.</p> +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link</a> +with an ampersand in the URL.</p> +<p>Here's a link with an amersand in the link text: <a href= +"http://att.com/" title="AT&T">AT&T</a>.</p> +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Auto links.html b/MarkdownTest/Tests_2004/Auto links.html new file mode 100644 index 0000000..f8df985 --- /dev/null +++ b/MarkdownTest/Tests_2004/Auto links.html @@ -0,0 +1,18 @@ +<p>Link: <a href="http://example.com/">http://example.com/</a>.</p> + +<p>With an ampersand: <a href="http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</a></p> + +<ul> +<li>In a list?</li> +<li><a href="http://example.com/">http://example.com/</a></li> +<li>It should.</li> +</ul> + +<blockquote> + <p>Blockquoted: <a href="http://example.com/">http://example.com/</a></p> +</blockquote> + +<p>Auto-links should not occur here: <code><http://example.com/></code></p> + +<pre><code>or here: <http://example.com/> +</code></pre> diff --git a/MarkdownTest/Tests_2004/Auto links.text b/MarkdownTest/Tests_2004/Auto links.text new file mode 100644 index 0000000..abbc488 --- /dev/null +++ b/MarkdownTest/Tests_2004/Auto links.text @@ -0,0 +1,13 @@ +Link: <http://example.com/>. + +With an ampersand: <http://example.com/?foo=1&bar=2> + +* In a list? +* <http://example.com/> +* It should. + +> Blockquoted: <http://example.com/> + +Auto-links should not occur here: `<http://example.com/>` + + or here: <http://example.com/>
\ No newline at end of file diff --git a/MarkdownTest/Tests_2004/Auto links.text-out b/MarkdownTest/Tests_2004/Auto links.text-out new file mode 100644 index 0000000..3b20890 --- /dev/null +++ b/MarkdownTest/Tests_2004/Auto links.text-out @@ -0,0 +1,28 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Link: <a href="http://example.com/">http://example.com/</a>.</p> +<p>With an ampersand: <a href= +"http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</a></p> +<ul> +<li>In a list?</li> +<li><a href="http://example.com/">http://example.com/</a></li> +<li>It should.</li> +</ul> +<blockquote> +<p>Blockquoted: <a href= +"http://example.com/">http://example.com/</a></p> +</blockquote> +<p>Auto-links should not occur here: +<code><http://example.com/></code></p> +<pre> +<code>or here: <http://example.com/> +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Auto links.text-res b/MarkdownTest/Tests_2004/Auto links.text-res new file mode 100644 index 0000000..3b20890 --- /dev/null +++ b/MarkdownTest/Tests_2004/Auto links.text-res @@ -0,0 +1,28 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Link: <a href="http://example.com/">http://example.com/</a>.</p> +<p>With an ampersand: <a href= +"http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</a></p> +<ul> +<li>In a list?</li> +<li><a href="http://example.com/">http://example.com/</a></li> +<li>It should.</li> +</ul> +<blockquote> +<p>Blockquoted: <a href= +"http://example.com/">http://example.com/</a></p> +</blockquote> +<p>Auto-links should not occur here: +<code><http://example.com/></code></p> +<pre> +<code>or here: <http://example.com/> +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Backslash escapes.html b/MarkdownTest/Tests_2004/Backslash escapes.html new file mode 100644 index 0000000..77823c3 --- /dev/null +++ b/MarkdownTest/Tests_2004/Backslash escapes.html @@ -0,0 +1,102 @@ +<p>These should all get escaped:</p> + +<p>Backslash: \</p> + +<p>Backtick: `</p> + +<p>Asterisk: *</p> + +<p>Underscore: _</p> + +<p>Left brace: {</p> + +<p>Right brace: }</p> + +<p>Left bracket: [</p> + +<p>Right bracket: ]</p> + +<p>Left paren: (</p> + +<p>Right paren: )</p> + +<p>Greater-than: ></p> + +<p>Hash: #</p> + +<p>Period: .</p> + +<p>Bang: !</p> + +<p>Plus: +</p> + +<p>Minus: -</p> + +<p>These should not, because they occur within a code block:</p> + +<pre><code>Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- +</code></pre> + +<p>Nor should these, which occur in code spans:</p> + +<p>Backslash: <code>\\</code></p> + +<p>Backtick: <code>\`</code></p> + +<p>Asterisk: <code>\*</code></p> + +<p>Underscore: <code>\_</code></p> + +<p>Left brace: <code>\{</code></p> + +<p>Right brace: <code>\}</code></p> + +<p>Left bracket: <code>\[</code></p> + +<p>Right bracket: <code>\]</code></p> + +<p>Left paren: <code>\(</code></p> + +<p>Right paren: <code>\)</code></p> + +<p>Greater-than: <code>\></code></p> + +<p>Hash: <code>\#</code></p> + +<p>Period: <code>\.</code></p> + +<p>Bang: <code>\!</code></p> + +<p>Plus: <code>\+</code></p> + +<p>Minus: <code>\-</code></p> diff --git a/MarkdownTest/Tests_2004/Backslash escapes.text b/MarkdownTest/Tests_2004/Backslash escapes.text new file mode 100644 index 0000000..16447a0 --- /dev/null +++ b/MarkdownTest/Tests_2004/Backslash escapes.text @@ -0,0 +1,104 @@ +These should all get escaped: + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- + + + +These should not, because they occur within a code block: + + Backslash: \\ + + Backtick: \` + + Asterisk: \* + + Underscore: \_ + + Left brace: \{ + + Right brace: \} + + Left bracket: \[ + + Right bracket: \] + + Left paren: \( + + Right paren: \) + + Greater-than: \> + + Hash: \# + + Period: \. + + Bang: \! + + Plus: \+ + + Minus: \- + + +Nor should these, which occur in code spans: + +Backslash: `\\` + +Backtick: `` \` `` + +Asterisk: `\*` + +Underscore: `\_` + +Left brace: `\{` + +Right brace: `\}` + +Left bracket: `\[` + +Right bracket: `\]` + +Left paren: `\(` + +Right paren: `\)` + +Greater-than: `\>` + +Hash: `\#` + +Period: `\.` + +Bang: `\!` + +Plus: `\+` + +Minus: `\-` diff --git a/MarkdownTest/Tests_2004/Backslash escapes.text-out b/MarkdownTest/Tests_2004/Backslash escapes.text-out new file mode 100644 index 0000000..1aae6cc --- /dev/null +++ b/MarkdownTest/Tests_2004/Backslash escapes.text-out @@ -0,0 +1,79 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>These should all get escaped:</p> +<p>Backslash: \</p> +<p>Backtick: `</p> +<p>Asterisk: *</p> +<p>Underscore: _</p> +<p>Left brace: {</p> +<p>Right brace: }</p> +<p>Left bracket: [</p> +<p>Right bracket: ]</p> +<p>Left paren: (</p> +<p>Right paren: )</p> +<p>Greater-than: ></p> +<p>Hash: #</p> +<p>Period: .</p> +<p>Bang: !</p> +<p>Plus: +</p> +<p>Minus: -</p> +<p>These should not, because they occur within a code block:</p> +<pre> +<code>Backslash: \ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- +</code> +</pre> +<p>Nor should these, which occur in code spans:</p> +<p>Backslash: <code>\</code></p> +<p>Backtick: <code>\`</code></p> +<p>Asterisk: <code>\*</code></p> +<p>Underscore: <code>\_</code></p> +<p>Left brace: <code>\{</code></p> +<p>Right brace: <code>\}</code></p> +<p>Left bracket: <code>\[</code></p> +<p>Right bracket: <code>\]</code></p> +<p>Left paren: <code>\(</code></p> +<p>Right paren: <code>\)</code></p> +<p>Greater-than: <code>\></code></p> +<p>Hash: <code>\#</code></p> +<p>Period: <code>\.</code></p> +<p>Bang: <code>\!</code></p> +<p>Plus: <code>\+</code></p> +<p>Minus: <code>\-</code></p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Backslash escapes.text-res b/MarkdownTest/Tests_2004/Backslash escapes.text-res new file mode 100644 index 0000000..1aae6cc --- /dev/null +++ b/MarkdownTest/Tests_2004/Backslash escapes.text-res @@ -0,0 +1,79 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>These should all get escaped:</p> +<p>Backslash: \</p> +<p>Backtick: `</p> +<p>Asterisk: *</p> +<p>Underscore: _</p> +<p>Left brace: {</p> +<p>Right brace: }</p> +<p>Left bracket: [</p> +<p>Right bracket: ]</p> +<p>Left paren: (</p> +<p>Right paren: )</p> +<p>Greater-than: ></p> +<p>Hash: #</p> +<p>Period: .</p> +<p>Bang: !</p> +<p>Plus: +</p> +<p>Minus: -</p> +<p>These should not, because they occur within a code block:</p> +<pre> +<code>Backslash: \ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- +</code> +</pre> +<p>Nor should these, which occur in code spans:</p> +<p>Backslash: <code>\</code></p> +<p>Backtick: <code>\`</code></p> +<p>Asterisk: <code>\*</code></p> +<p>Underscore: <code>\_</code></p> +<p>Left brace: <code>\{</code></p> +<p>Right brace: <code>\}</code></p> +<p>Left bracket: <code>\[</code></p> +<p>Right bracket: <code>\]</code></p> +<p>Left paren: <code>\(</code></p> +<p>Right paren: <code>\)</code></p> +<p>Greater-than: <code>\></code></p> +<p>Hash: <code>\#</code></p> +<p>Period: <code>\.</code></p> +<p>Bang: <code>\!</code></p> +<p>Plus: <code>\+</code></p> +<p>Minus: <code>\-</code></p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Blockquotes with code blocks.html b/MarkdownTest/Tests_2004/Blockquotes with code blocks.html new file mode 100644 index 0000000..990202a --- /dev/null +++ b/MarkdownTest/Tests_2004/Blockquotes with code blocks.html @@ -0,0 +1,15 @@ +<blockquote> + <p>Example:</p> + +<pre><code>sub status { + print "working"; +} +</code></pre> + + <p>Or:</p> + +<pre><code>sub status { + return "working"; +} +</code></pre> +</blockquote> diff --git a/MarkdownTest/Tests_2004/Blockquotes with code blocks.text b/MarkdownTest/Tests_2004/Blockquotes with code blocks.text new file mode 100644 index 0000000..c31d171 --- /dev/null +++ b/MarkdownTest/Tests_2004/Blockquotes with code blocks.text @@ -0,0 +1,11 @@ +> Example: +> +> sub status { +> print "working"; +> } +> +> Or: +> +> sub status { +> return "working"; +> } diff --git a/MarkdownTest/Tests_2004/Blockquotes with code blocks.text-out b/MarkdownTest/Tests_2004/Blockquotes with code blocks.text-out new file mode 100644 index 0000000..75ef055 --- /dev/null +++ b/MarkdownTest/Tests_2004/Blockquotes with code blocks.text-out @@ -0,0 +1,25 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<blockquote> +<p>Example:</p> +<pre> +<code>sub status { + print "working"; +} +</code> +</pre> +<p>Or:</p> +<pre> +<code>sub status { + return "working"; +} +</code> +</pre></blockquote> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Blockquotes with code blocks.text-res b/MarkdownTest/Tests_2004/Blockquotes with code blocks.text-res new file mode 100644 index 0000000..75ef055 --- /dev/null +++ b/MarkdownTest/Tests_2004/Blockquotes with code blocks.text-res @@ -0,0 +1,25 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<blockquote> +<p>Example:</p> +<pre> +<code>sub status { + print "working"; +} +</code> +</pre> +<p>Or:</p> +<pre> +<code>sub status { + return "working"; +} +</code> +</pre></blockquote> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.html b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.html new file mode 100644 index 0000000..e21ac79 --- /dev/null +++ b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.html @@ -0,0 +1,8 @@ +<p>In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item.</p> + +<p>Here's one with a bullet. +* criminey.</p> diff --git a/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text new file mode 100644 index 0000000..f8a5b27 --- /dev/null +++ b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text @@ -0,0 +1,8 @@ +In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item. + +Here's one with a bullet. +* criminey. diff --git a/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text-out b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text-out new file mode 100644 index 0000000..e044b46 --- /dev/null +++ b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text-out @@ -0,0 +1,14 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a +list item. Because a hard-wrapped line in the middle of a paragraph +looked like a list item.</p> +<p>Here's one with a bullet. * criminey.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text-res b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text-res new file mode 100644 index 0000000..e044b46 --- /dev/null +++ b/MarkdownTest/Tests_2004/Hard-wrapped paragraphs with list-like lines.text-res @@ -0,0 +1,14 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a +list item. Because a hard-wrapped line in the middle of a paragraph +looked like a list item.</p> +<p>Here's one with a bullet. * criminey.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Horizontal rules.html b/MarkdownTest/Tests_2004/Horizontal rules.html new file mode 100644 index 0000000..2dc2ab6 --- /dev/null +++ b/MarkdownTest/Tests_2004/Horizontal rules.html @@ -0,0 +1,71 @@ +<p>Dashes:</p> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>--- +</code></pre> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>- - - +</code></pre> + +<p>Asterisks:</p> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>*** +</code></pre> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>* * * +</code></pre> + +<p>Underscores:</p> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>___ +</code></pre> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>_ _ _ +</code></pre> diff --git a/MarkdownTest/Tests_2004/Horizontal rules.text b/MarkdownTest/Tests_2004/Horizontal rules.text new file mode 100644 index 0000000..1594bda --- /dev/null +++ b/MarkdownTest/Tests_2004/Horizontal rules.text @@ -0,0 +1,67 @@ +Dashes: + +--- + + --- + + --- + + --- + + --- + +- - - + + - - - + + - - - + + - - - + + - - - + + +Asterisks: + +*** + + *** + + *** + + *** + + *** + +* * * + + * * * + + * * * + + * * * + + * * * + + +Underscores: + +___ + + ___ + + ___ + + ___ + + ___ + +_ _ _ + + _ _ _ + + _ _ _ + + _ _ _ + + _ _ _ diff --git a/MarkdownTest/Tests_2004/Horizontal rules.text-out b/MarkdownTest/Tests_2004/Horizontal rules.text-out new file mode 100644 index 0000000..71e4d27 --- /dev/null +++ b/MarkdownTest/Tests_2004/Horizontal rules.text-out @@ -0,0 +1,61 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Dashes:</p> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>--- +</code> +</pre> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>- - - +</code> +</pre> +<p>Asterisks:</p> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>*** +</code> +</pre> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>* * * +</code> +</pre> +<p>Underscores:</p> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>___ +</code> +</pre> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>_ _ _ +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Horizontal rules.text-res b/MarkdownTest/Tests_2004/Horizontal rules.text-res new file mode 100644 index 0000000..71e4d27 --- /dev/null +++ b/MarkdownTest/Tests_2004/Horizontal rules.text-res @@ -0,0 +1,61 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Dashes:</p> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>--- +</code> +</pre> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>- - - +</code> +</pre> +<p>Asterisks:</p> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>*** +</code> +</pre> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>* * * +</code> +</pre> +<p>Underscores:</p> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>___ +</code> +</pre> +<hr> +<hr> +<hr> +<hr> +<pre> +<code>_ _ _ +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Inline HTML (Advanced).html b/MarkdownTest/Tests_2004/Inline HTML (Advanced).html new file mode 100644 index 0000000..1972d87 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Advanced).html @@ -0,0 +1,14 @@ +<p>Simple block on one line:</p> + +<div>foo</div> + +<p>And nested without indentation:</p> + +<div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div> diff --git a/MarkdownTest/Tests_2004/Inline HTML (Advanced).text b/MarkdownTest/Tests_2004/Inline HTML (Advanced).text new file mode 100644 index 0000000..9d71ddc --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Advanced).text @@ -0,0 +1,14 @@ +Simple block on one line: + +<div>foo</div> + +And nested without indentation: + +<div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div> diff --git a/MarkdownTest/Tests_2004/Inline HTML (Advanced).text-out b/MarkdownTest/Tests_2004/Inline HTML (Advanced).text-out new file mode 100644 index 0000000..ee84e31 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Advanced).text-out @@ -0,0 +1,19 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Simple block on one line:</p> +<div>foo</div> +<p>And nested without indentation:</p> +<div> +<div> +<div>foo</div> +</div> +<div>bar</div> +</div> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Inline HTML (Advanced).text-res b/MarkdownTest/Tests_2004/Inline HTML (Advanced).text-res new file mode 100644 index 0000000..ee84e31 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Advanced).text-res @@ -0,0 +1,19 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Simple block on one line:</p> +<div>foo</div> +<p>And nested without indentation:</p> +<div> +<div> +<div>foo</div> +</div> +<div>bar</div> +</div> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Inline HTML (Simple).html b/MarkdownTest/Tests_2004/Inline HTML (Simple).html new file mode 100644 index 0000000..6bf78f8 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Simple).html @@ -0,0 +1,72 @@ +<p>Here's a simple block:</p> + +<div> + foo +</div> + +<p>This should be a code block, though:</p> + +<pre><code><div> + foo +</div> +</code></pre> + +<p>As should this:</p> + +<pre><code><div>foo</div> +</code></pre> + +<p>Now, nested:</p> + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +<p>This should just be an HTML comment:</p> + +<!-- Comment --> + +<p>Multiline:</p> + +<!-- +Blah +Blah +--> + +<p>Code block:</p> + +<pre><code><!-- Comment --> +</code></pre> + +<p>Just plain comment, with trailing spaces on the line:</p> + +<!-- foo --> + +<p>Code:</p> + +<pre><code><hr /> +</code></pre> + +<p>Hr's:</p> + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > diff --git a/MarkdownTest/Tests_2004/Inline HTML (Simple).text b/MarkdownTest/Tests_2004/Inline HTML (Simple).text new file mode 100644 index 0000000..14aa2dc --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Simple).text @@ -0,0 +1,69 @@ +Here's a simple block: + +<div> + foo +</div> + +This should be a code block, though: + + <div> + foo + </div> + +As should this: + + <div>foo</div> + +Now, nested: + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +This should just be an HTML comment: + +<!-- Comment --> + +Multiline: + +<!-- +Blah +Blah +--> + +Code block: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +<!-- foo --> + +Code: + + <hr /> + +Hr's: + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > + diff --git a/MarkdownTest/Tests_2004/Inline HTML (Simple).text-out b/MarkdownTest/Tests_2004/Inline HTML (Simple).text-out new file mode 100644 index 0000000..a5022e0 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Simple).text-out @@ -0,0 +1,59 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Here's a simple block:</p> +<div>foo</div> +<p>This should be a code block, though:</p> +<pre> +<code><div> + foo +</div> +</code> +</pre> +<p>As should this:</p> +<pre> +<code><div>foo</div> +</code> +</pre> +<p>Now, nested:</p> +<div> +<div> +<div>foo</div> +</div> +</div> +<p>This should just be an HTML comment:</p> +<!-- Comment --> +<p>Multiline:</p> +<!-- +Blah +Blah +--> +<p>Code block:</p> +<pre> +<code><!-- Comment --> +</code> +</pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<!-- foo --> +<p>Code:</p> +<pre> +<code><hr /> +</code> +</pre> +<p>Hr's:</p> +<hr> +<hr> +<hr> +<hr> +<hr> +<hr> +<hr class="foo" id="bar"> +<hr class="foo" id="bar"> +<hr class="foo" id="bar"> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Inline HTML (Simple).text-res b/MarkdownTest/Tests_2004/Inline HTML (Simple).text-res new file mode 100644 index 0000000..a5022e0 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML (Simple).text-res @@ -0,0 +1,59 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Here's a simple block:</p> +<div>foo</div> +<p>This should be a code block, though:</p> +<pre> +<code><div> + foo +</div> +</code> +</pre> +<p>As should this:</p> +<pre> +<code><div>foo</div> +</code> +</pre> +<p>Now, nested:</p> +<div> +<div> +<div>foo</div> +</div> +</div> +<p>This should just be an HTML comment:</p> +<!-- Comment --> +<p>Multiline:</p> +<!-- +Blah +Blah +--> +<p>Code block:</p> +<pre> +<code><!-- Comment --> +</code> +</pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<!-- foo --> +<p>Code:</p> +<pre> +<code><hr /> +</code> +</pre> +<p>Hr's:</p> +<hr> +<hr> +<hr> +<hr> +<hr> +<hr> +<hr class="foo" id="bar"> +<hr class="foo" id="bar"> +<hr class="foo" id="bar"> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Inline HTML comments.html b/MarkdownTest/Tests_2004/Inline HTML comments.html new file mode 100644 index 0000000..3f167a1 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML comments.html @@ -0,0 +1,13 @@ +<p>Paragraph one.</p> + +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +<p>Paragraph two.</p> + +<!-- one comment block -- -- with two comments --> + +<p>The end.</p> diff --git a/MarkdownTest/Tests_2004/Inline HTML comments.text b/MarkdownTest/Tests_2004/Inline HTML comments.text new file mode 100644 index 0000000..41d830d --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML comments.text @@ -0,0 +1,13 @@ +Paragraph one. + +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +Paragraph two. + +<!-- one comment block -- -- with two comments --> + +The end. diff --git a/MarkdownTest/Tests_2004/Inline HTML comments.text-out b/MarkdownTest/Tests_2004/Inline HTML comments.text-out new file mode 100644 index 0000000..6e2f425 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML comments.text-out @@ -0,0 +1,18 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Paragraph one.</p> +<!-- This is a simple comment --> +<!-- + This is another comment. +--> +<p>Paragraph two.</p> +<!-- one comment block == == with two comments --> +<p>The end.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Inline HTML comments.text-res b/MarkdownTest/Tests_2004/Inline HTML comments.text-res new file mode 100644 index 0000000..6e2f425 --- /dev/null +++ b/MarkdownTest/Tests_2004/Inline HTML comments.text-res @@ -0,0 +1,18 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Paragraph one.</p> +<!-- This is a simple comment --> +<!-- + This is another comment. +--> +<p>Paragraph two.</p> +<!-- one comment block == == with two comments --> +<p>The end.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Links, inline style.html b/MarkdownTest/Tests_2004/Links, inline style.html new file mode 100644 index 0000000..bdfabb5 --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, inline style.html @@ -0,0 +1,9 @@ +<p>Just a <a href="/url/">URL</a>.</p> + +<p><a href="/url/" title="title">URL and title</a>.</p> + +<p><a href="/url/" title="title preceded by two spaces">URL and title</a>.</p> + +<p><a href="/url/" title="title preceded by a tab">URL and title</a>.</p> + +<p><a href="">Empty</a>.</p> diff --git a/MarkdownTest/Tests_2004/Links, inline style.text b/MarkdownTest/Tests_2004/Links, inline style.text new file mode 100644 index 0000000..4d0c1c2 --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, inline style.text @@ -0,0 +1,9 @@ +Just a [URL](/url/). + +[URL and title](/url/ "title"). + +[URL and title](/url/ "title preceded by two spaces"). + +[URL and title](/url/ "title preceded by a tab"). + +[Empty](). diff --git a/MarkdownTest/Tests_2004/Links, inline style.text-out b/MarkdownTest/Tests_2004/Links, inline style.text-out new file mode 100644 index 0000000..0125b63 --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, inline style.text-out @@ -0,0 +1,17 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Just a <a href="/url/">URL</a>.</p> +<p><a href="/url/" title="title">URL and title</a>.</p> +<p><a href="/url/" title="title preceded by two spaces">URL and +title</a>.</p> +<p><a href="/url/" title="title preceded by a tab">URL and +title</a>.</p> +<p><a href="">Empty</a>.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Links, inline style.text-res b/MarkdownTest/Tests_2004/Links, inline style.text-res new file mode 100644 index 0000000..0125b63 --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, inline style.text-res @@ -0,0 +1,17 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Just a <a href="/url/">URL</a>.</p> +<p><a href="/url/" title="title">URL and title</a>.</p> +<p><a href="/url/" title="title preceded by two spaces">URL and +title</a>.</p> +<p><a href="/url/" title="title preceded by a tab">URL and +title</a>.</p> +<p><a href="">Empty</a>.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Links, reference style.html b/MarkdownTest/Tests_2004/Links, reference style.html new file mode 100644 index 0000000..cf4d833 --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, reference style.html @@ -0,0 +1,18 @@ +<p>Foo <a href="/url/" title="Title">bar</a>.</p> + +<p>Foo <a href="/url/" title="Title">bar</a>.</p> + +<p>Foo <a href="/url/" title="Title">bar</a>.</p> + +<p>With <a href="/url/">embedded [brackets]</a>.</p> + +<p>Indented <a href="/url">once</a>.</p> + +<p>Indented <a href="/url">twice</a>.</p> + +<p>Indented <a href="/url">thrice</a>.</p> + +<p>Indented [four][] times.</p> + +<pre><code>[four]: /url +</code></pre> diff --git a/MarkdownTest/Tests_2004/Links, reference style.text b/MarkdownTest/Tests_2004/Links, reference style.text new file mode 100644 index 0000000..b2fa734 --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, reference style.text @@ -0,0 +1,31 @@ +Foo [bar] [1]. + +Foo [bar][1]. + +Foo [bar] +[1]. + +[1]: /url/ "Title" + + +With [embedded [brackets]] [b]. + + +Indented [once][]. + +Indented [twice][]. + +Indented [thrice][]. + +Indented [four][] times. + + [once]: /url + + [twice]: /url + + [thrice]: /url + + [four]: /url + + +[b]: /url/ diff --git a/MarkdownTest/Tests_2004/Links, reference style.text-out b/MarkdownTest/Tests_2004/Links, reference style.text-out new file mode 100644 index 0000000..04ae0cd --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, reference style.text-out @@ -0,0 +1,22 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>With <a href="/url/">embedded [brackets]</a>.</p> +<p>Indented <a href="/url">once</a>.</p> +<p>Indented <a href="/url">twice</a>.</p> +<p>Indented <a href="/url">thrice</a>.</p> +<p>Indented [four][] times.</p> +<pre> +<code>[four]: /url +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Links, reference style.text-res b/MarkdownTest/Tests_2004/Links, reference style.text-res new file mode 100644 index 0000000..04ae0cd --- /dev/null +++ b/MarkdownTest/Tests_2004/Links, reference style.text-res @@ -0,0 +1,22 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>With <a href="/url/">embedded [brackets]</a>.</p> +<p>Indented <a href="/url">once</a>.</p> +<p>Indented <a href="/url">twice</a>.</p> +<p>Indented <a href="/url">thrice</a>.</p> +<p>Indented [four][] times.</p> +<pre> +<code>[four]: /url +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Links-in-Headers.text-out b/MarkdownTest/Tests_2004/Links-in-Headers.text-out new file mode 100644 index 0000000..defddbf --- /dev/null +++ b/MarkdownTest/Tests_2004/Links-in-Headers.text-out @@ -0,0 +1,9 @@ +<h2>A plain header</h2> +<p>Let's first have a plain header</p> +<h1>An underlined header</h1> +<p>(That's also useful)</p> +<h1>A header with a <a href="http://www.link.com">link</a></h1> +<p>First with a hash</p> +<h2>Another with a <a href="http://www.link.com/">link</a></h2> +<p>This time underlined</p> + diff --git a/MarkdownTest/Tests_2004/Links-in-Headers.text-res b/MarkdownTest/Tests_2004/Links-in-Headers.text-res new file mode 100644 index 0000000..cc6cfcf --- /dev/null +++ b/MarkdownTest/Tests_2004/Links-in-Headers.text-res @@ -0,0 +1,9 @@ +<h2><span class="markdown">A plain header</span></h2> +<p>Let's first have a plain header</p> +<h1>An underlined header</h1> +<p>(That's also useful)</p> +<h1>A header with a <a href="http://www.link.com">link</a></h1> +<p>First with a hash</p> +<h2>Another with a <a href="http://www.link.com/">link</a></h2> +<p>This time underlined</p> + diff --git a/MarkdownTest/Tests_2004/Literal quotes in titles.html b/MarkdownTest/Tests_2004/Literal quotes in titles.html new file mode 100644 index 0000000..611c1ac --- /dev/null +++ b/MarkdownTest/Tests_2004/Literal quotes in titles.html @@ -0,0 +1,3 @@ +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> + +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> diff --git a/MarkdownTest/Tests_2004/Literal quotes in titles.text b/MarkdownTest/Tests_2004/Literal quotes in titles.text new file mode 100644 index 0000000..29d0e42 --- /dev/null +++ b/MarkdownTest/Tests_2004/Literal quotes in titles.text @@ -0,0 +1,7 @@ +Foo [bar][]. + +Foo [bar](/url/ "Title with "quotes" inside"). + + + [bar]: /url/ "Title with "quotes" inside" + diff --git a/MarkdownTest/Tests_2004/Literal quotes in titles.text-out b/MarkdownTest/Tests_2004/Literal quotes in titles.text-out new file mode 100644 index 0000000..3fd6fbc --- /dev/null +++ b/MarkdownTest/Tests_2004/Literal quotes in titles.text-out @@ -0,0 +1,14 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Foo <a href="/url/" title= +"Title with "quotes" inside">bar</a>.</p> +<p>Foo <a href="/url/" title= +"Title with "quotes" inside">bar</a>.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Literal quotes in titles.text-res b/MarkdownTest/Tests_2004/Literal quotes in titles.text-res new file mode 100644 index 0000000..3fd6fbc --- /dev/null +++ b/MarkdownTest/Tests_2004/Literal quotes in titles.text-res @@ -0,0 +1,14 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Foo <a href="/url/" title= +"Title with "quotes" inside">bar</a>.</p> +<p>Foo <a href="/url/" title= +"Title with "quotes" inside">bar</a>.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Basics.html b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.html new file mode 100644 index 0000000..d5bdbb2 --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.html @@ -0,0 +1,314 @@ +<h1>Markdown: Basics</h1> + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a class="selected" title="Markdown Basics">Basics</a></li> + <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<h2>Getting the Gist of Markdown's Formatting Syntax</h2> + +<p>This page offers a brief overview of what it's like to use Markdown. +The <a href="/projects/markdown/syntax" title="Markdown Syntax">syntax page</a> provides complete, detailed documentation for +every feature, but Markdown should be very easy to pick up simply by +looking at a few examples of it in action. The examples on this page +are written in a before/after style, showing example syntax and the +HTML output produced by Markdown.</p> + +<p>It's also helpful to simply try Markdown out; the <a href="/projects/markdown/dingus" title="Markdown Dingus">Dingus</a> is a +web application that allows you type your own Markdown-formatted text +and translate it to XHTML.</p> + +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/basics.text">see the source for it by adding '.text' to the URL</a>.</p> + +<h2>Paragraphs, Headers, Blockquotes</h2> + +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> + +<p>Markdown offers two styles of headers: <em>Setext</em> and <em>atx</em>. +Setext-style headers for <code><h1></code> and <code><h2></code> are created by +"underlining" with equal signs (<code>=</code>) and hyphens (<code>-</code>), respectively. +To create an atx-style header, you put 1-6 hash marks (<code>#</code>) at the +beginning of the line -- the number of hashes equals the resulting +HTML header level.</p> + +<p>Blockquotes are indicated using email-style '<code>></code>' angle brackets.</p> + +<p>Markdown:</p> + +<pre><code>A First Level Header +==================== + +A Second Level Header +--------------------- + +Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph. + +The quick brown fox jumped over the lazy +dog's back. + +### Header 3 + +> This is a blockquote. +> +> This is the second paragraph in the blockquote. +> +> ## This is an H2 in a blockquote +</code></pre> + +<p>Output:</p> + +<pre><code><h1>A First Level Header</h1> + +<h2>A Second Level Header</h2> + +<p>Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph.</p> + +<p>The quick brown fox jumped over the lazy +dog's back.</p> + +<h3>Header 3</h3> + +<blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> +</blockquote> +</code></pre> + +<h3>Phrase Emphasis</h3> + +<p>Markdown uses asterisks and underscores to indicate spans of emphasis.</p> + +<p>Markdown:</p> + +<pre><code>Some of these words *are emphasized*. +Some of these words _are emphasized also_. + +Use two asterisks for **strong emphasis**. +Or, if you prefer, __use two underscores instead__. +</code></pre> + +<p>Output:</p> + +<pre><code><p>Some of these words <em>are emphasized</em>. +Some of these words <em>are emphasized also</em>.</p> + +<p>Use two asterisks for <strong>strong emphasis</strong>. +Or, if you prefer, <strong>use two underscores instead</strong>.</p> +</code></pre> + +<h2>Lists</h2> + +<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens (<code>*</code>, +<code>+</code>, and <code>-</code>) as list markers. These three markers are +interchangable; this:</p> + +<pre><code>* Candy. +* Gum. +* Booze. +</code></pre> + +<p>this:</p> + +<pre><code>+ Candy. ++ Gum. ++ Booze. +</code></pre> + +<p>and this:</p> + +<pre><code>- Candy. +- Gum. +- Booze. +</code></pre> + +<p>all produce the same output:</p> + +<pre><code><ul> +<li>Candy.</li> +<li>Gum.</li> +<li>Booze.</li> +</ul> +</code></pre> + +<p>Ordered (numbered) lists use regular numbers, followed by periods, as +list markers:</p> + +<pre><code>1. Red +2. Green +3. Blue +</code></pre> + +<p>Output:</p> + +<pre><code><ol> +<li>Red</li> +<li>Green</li> +<li>Blue</li> +</ol> +</code></pre> + +<p>If you put blank lines between items, you'll get <code><p></code> tags for the +list item text. You can create multi-paragraph list items by indenting +the paragraphs by 4 spaces or 1 tab:</p> + +<pre><code>* A list item. + + With multiple paragraphs. + +* Another item in the list. +</code></pre> + +<p>Output:</p> + +<pre><code><ul> +<li><p>A list item.</p> +<p>With multiple paragraphs.</p></li> +<li><p>Another item in the list.</p></li> +</ul> +</code></pre> + +<h3>Links</h3> + +<p>Markdown supports two styles for creating links: <em>inline</em> and +<em>reference</em>. With both styles, you use square brackets to delimit the +text you want to turn into a link.</p> + +<p>Inline-style links use parentheses immediately after the link text. +For example:</p> + +<pre><code>This is an [example link](http://example.com/). +</code></pre> + +<p>Output:</p> + +<pre><code><p>This is an <a href="http://example.com/"> +example link</a>.</p> +</code></pre> + +<p>Optionally, you may include a title attribute in the parentheses:</p> + +<pre><code>This is an [example link](http://example.com/ "With a Title"). +</code></pre> + +<p>Output:</p> + +<pre><code><p>This is an <a href="http://example.com/" title="With a Title"> +example link</a>.</p> +</code></pre> + +<p>Reference-style links allow you to refer to your links by names, which +you define elsewhere in your document:</p> + +<pre><code>I get 10 times more traffic from [Google][1] than from +[Yahoo][2] or [MSN][3]. + +[1]: http://google.com/ "Google" +[2]: http://search.yahoo.com/ "Yahoo Search" +[3]: http://search.msn.com/ "MSN Search" +</code></pre> + +<p>Output:</p> + +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from <a href="http://search.yahoo.com/" +title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" +title="MSN Search">MSN</a>.</p> +</code></pre> + +<p>The title attribute is optional. Link names may contain letters, +numbers and spaces, but are <em>not</em> case sensitive:</p> + +<pre><code>I start my morning with a cup of coffee and +[The New York Times][NY Times]. + +[ny times]: http://www.nytimes.com/ +</code></pre> + +<p>Output:</p> + +<pre><code><p>I start my morning with a cup of coffee and +<a href="http://www.nytimes.com/">The New York Times</a>.</p> +</code></pre> + +<h3>Images</h3> + +<p>Image syntax is very much like link syntax.</p> + +<p>Inline (titles are optional):</p> + +<pre><code> +</code></pre> + +<p>Reference-style:</p> + +<pre><code>![alt text][id] + +[id]: /path/to/img.jpg "Title" +</code></pre> + +<p>Both of the above examples produce the same output:</p> + +<pre><code><img src="/path/to/img.jpg" alt="alt text" title="Title" /> +</code></pre> + +<h3>Code</h3> + +<p>In a regular paragraph, you can create code span by wrapping text in +backtick quotes. Any ampersands (<code>&</code>) and angle brackets (<code><</code> or +<code>></code>) will automatically be translated into HTML entities. This makes +it easy to use Markdown to write about HTML example code:</p> + +<pre><code>I strongly recommend against using any `<blink>` tags. + +I wish SmartyPants used named entities like `&mdash;` +instead of decimal-encoded entites like `&#8212;`. +</code></pre> + +<p>Output:</p> + +<pre><code><p>I strongly recommend against using any +<code>&lt;blink&gt;</code> tags.</p> + +<p>I wish SmartyPants used named entities like +<code>&amp;mdash;</code> instead of decimal-encoded +entites like <code>&amp;#8212;</code>.</p> +</code></pre> + +<p>To specify an entire block of pre-formatted code, indent every line of +the block by 4 spaces or 1 tab. Just like with code spans, <code>&</code>, <code><</code>, +and <code>></code> characters will be escaped automatically.</p> + +<p>Markdown:</p> + +<pre><code>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> +</code></pre> + +<p>Output:</p> + +<pre><code><p>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes:</p> + +<pre><code>&lt;blockquote&gt; + &lt;p&gt;For example.&lt;/p&gt; +&lt;/blockquote&gt; +</code></pre> +</code></pre> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text new file mode 100644 index 0000000..486055c --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text @@ -0,0 +1,306 @@ +Markdown: Basics +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a class="selected" title="Markdown Basics">Basics</a></li> + <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +Getting the Gist of Markdown's Formatting Syntax +------------------------------------------------ + +This page offers a brief overview of what it's like to use Markdown. +The [syntax page] [s] provides complete, detailed documentation for +every feature, but Markdown should be very easy to pick up simply by +looking at a few examples of it in action. The examples on this page +are written in a before/after style, showing example syntax and the +HTML output produced by Markdown. + +It's also helpful to simply try Markdown out; the [Dingus] [d] is a +web application that allows you type your own Markdown-formatted text +and translate it to XHTML. + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL] [src]. + + [s]: /projects/markdown/syntax "Markdown Syntax" + [d]: /projects/markdown/dingus "Markdown Dingus" + [src]: /projects/markdown/basics.text + + +## Paragraphs, Headers, Blockquotes ## + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +Markdown offers two styles of headers: *Setext* and *atx*. +Setext-style headers for `<h1>` and `<h2>` are created by +"underlining" with equal signs (`=`) and hyphens (`-`), respectively. +To create an atx-style header, you put 1-6 hash marks (`#`) at the +beginning of the line -- the number of hashes equals the resulting +HTML header level. + +Blockquotes are indicated using email-style '`>`' angle brackets. + +Markdown: + + A First Level Header + ==================== + + A Second Level Header + --------------------- + + Now is the time for all good men to come to + the aid of their country. This is just a + regular paragraph. + + The quick brown fox jumped over the lazy + dog's back. + + ### Header 3 + + > This is a blockquote. + > + > This is the second paragraph in the blockquote. + > + > ## This is an H2 in a blockquote + + +Output: + + <h1>A First Level Header</h1> + + <h2>A Second Level Header</h2> + + <p>Now is the time for all good men to come to + the aid of their country. This is just a + regular paragraph.</p> + + <p>The quick brown fox jumped over the lazy + dog's back.</p> + + <h3>Header 3</h3> + + <blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> + </blockquote> + + + +### Phrase Emphasis ### + +Markdown uses asterisks and underscores to indicate spans of emphasis. + +Markdown: + + Some of these words *are emphasized*. + Some of these words _are emphasized also_. + + Use two asterisks for **strong emphasis**. + Or, if you prefer, __use two underscores instead__. + +Output: + + <p>Some of these words <em>are emphasized</em>. + Some of these words <em>are emphasized also</em>.</p> + + <p>Use two asterisks for <strong>strong emphasis</strong>. + Or, if you prefer, <strong>use two underscores instead</strong>.</p> + + + +## Lists ## + +Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`, +`+`, and `-`) as list markers. These three markers are +interchangable; this: + + * Candy. + * Gum. + * Booze. + +this: + + + Candy. + + Gum. + + Booze. + +and this: + + - Candy. + - Gum. + - Booze. + +all produce the same output: + + <ul> + <li>Candy.</li> + <li>Gum.</li> + <li>Booze.</li> + </ul> + +Ordered (numbered) lists use regular numbers, followed by periods, as +list markers: + + 1. Red + 2. Green + 3. Blue + +Output: + + <ol> + <li>Red</li> + <li>Green</li> + <li>Blue</li> + </ol> + +If you put blank lines between items, you'll get `<p>` tags for the +list item text. You can create multi-paragraph list items by indenting +the paragraphs by 4 spaces or 1 tab: + + * A list item. + + With multiple paragraphs. + + * Another item in the list. + +Output: + + <ul> + <li><p>A list item.</p> + <p>With multiple paragraphs.</p></li> + <li><p>Another item in the list.</p></li> + </ul> + + + +### Links ### + +Markdown supports two styles for creating links: *inline* and +*reference*. With both styles, you use square brackets to delimit the +text you want to turn into a link. + +Inline-style links use parentheses immediately after the link text. +For example: + + This is an [example link](http://example.com/). + +Output: + + <p>This is an <a href="http://example.com/"> + example link</a>.</p> + +Optionally, you may include a title attribute in the parentheses: + + This is an [example link](http://example.com/ "With a Title"). + +Output: + + <p>This is an <a href="http://example.com/" title="With a Title"> + example link</a>.</p> + +Reference-style links allow you to refer to your links by names, which +you define elsewhere in your document: + + I get 10 times more traffic from [Google][1] than from + [Yahoo][2] or [MSN][3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from <a href="http://search.yahoo.com/" + title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" + title="MSN Search">MSN</a>.</p> + +The title attribute is optional. Link names may contain letters, +numbers and spaces, but are *not* case sensitive: + + I start my morning with a cup of coffee and + [The New York Times][NY Times]. + + [ny times]: http://www.nytimes.com/ + +Output: + + <p>I start my morning with a cup of coffee and + <a href="http://www.nytimes.com/">The New York Times</a>.</p> + + +### Images ### + +Image syntax is very much like link syntax. + +Inline (titles are optional): + +  + +Reference-style: + + ![alt text][id] + + [id]: /path/to/img.jpg "Title" + +Both of the above examples produce the same output: + + <img src="/path/to/img.jpg" alt="alt text" title="Title" /> + + + +### Code ### + +In a regular paragraph, you can create code span by wrapping text in +backtick quotes. Any ampersands (`&`) and angle brackets (`<` or +`>`) will automatically be translated into HTML entities. This makes +it easy to use Markdown to write about HTML example code: + + I strongly recommend against using any `<blink>` tags. + + I wish SmartyPants used named entities like `—` + instead of decimal-encoded entites like `—`. + +Output: + + <p>I strongly recommend against using any + <code><blink></code> tags.</p> + + <p>I wish SmartyPants used named entities like + <code>&mdash;</code> instead of decimal-encoded + entites like <code>&#8212;</code>.</p> + + +To specify an entire block of pre-formatted code, indent every line of +the block by 4 spaces or 1 tab. Just like with code spans, `&`, `<`, +and `>` characters will be escaped automatically. + +Markdown: + + If you want your page to validate under XHTML 1.0 Strict, + you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> + +Output: + + <p>If you want your page to validate under XHTML 1.0 Strict, + you've got to put paragraph tags in your blockquotes:</p> + + <pre><code><blockquote> + <p>For example.</p> + </blockquote> + </code></pre> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text-out b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text-out new file mode 100644 index 0000000..65b90fa --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text-out @@ -0,0 +1,321 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h1>Markdown: Basics</h1> +<ul id="ProjectSubmenu"> +<li><a href="/projects/markdown/" title= +"Markdown Project Page">Main</a></li> +<li><a class="selected" title="Markdown Basics">Basics</a></li> +<li><a href="/projects/markdown/syntax" title= +"Markdown Syntax Documentation">Syntax</a></li> +<li><a href="/projects/markdown/license" title= +"Pricing and License Information">License</a></li> +<li><a href="/projects/markdown/dingus" title= +"Online Markdown Web Form">Dingus</a></li> +</ul> +<h2>Getting the Gist of Markdown's Formatting Syntax</h2> +<p>This page offers a brief overview of what it's like to use +Markdown. The <a href="/projects/markdown/syntax" title= +"Markdown Syntax">syntax page</a> provides complete, detailed +documentation for every feature, but Markdown should be very easy +to pick up simply by looking at a few examples of it in action. The +examples on this page are written in a before/after style, showing +example syntax and the HTML output produced by Markdown.</p> +<p>It's also helpful to simply try Markdown out; the <a href= +"/projects/markdown/dingus" title="Markdown Dingus">Dingus</a> is a +web application that allows you type your own Markdown-formatted +text and translate it to XHTML.</p> +<p><strong>Note:</strong> This document is itself written using +Markdown; you can <a href="/projects/markdown/basics.text">see the +source for it by adding '.text' to the URL</a>.</p> +<h2>Paragraphs, Headers, Blockquotes</h2> +<p>A paragraph is simply one or more consecutive lines of text, +separated by one or more blank lines. (A blank line is any line +that looks like a blank line -- a line containing nothing spaces or +tabs is considered blank.) Normal paragraphs should not be intended +with spaces or tabs.</p> +<p>Markdown offers two styles of headers: <em>Setext</em> and +<em>atx</em>. Setext-style headers for <code><h1></code> and +<code><h2></code> are created by "underlining" with equal +signs (<code>=</code>) and hyphens (<code>-</code>), respectively. +To create an atx-style header, you put 1-6 hash marks +(<code>#</code>) at the beginning of the line -- the number of +hashes equals the resulting HTML header level.</p> +<p>Blockquotes are indicated using email-style '<code>></code>' +angle brackets.</p> +<p>Markdown:</p> +<pre> +<code>A First Level Header +==================== + +A Second Level Header +--------------------- + +Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph. + +The quick brown fox jumped over the lazy +dog's back. + +### Header 3 + +> This is a blockquote. +> +> This is the second paragraph in the blockquote. +> +> ## This is an H2 in a blockquote +</code> +</pre> +<p>Output:</p> +<pre> +<code><h1>A First Level Header</h1> + +<h2>A Second Level Header</h2> + +<p>Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph.</p> + +<p>The quick brown fox jumped over the lazy +dog's back.</p> + +<h3>Header 3</h3> + +<blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> +</blockquote> +</code> +</pre> +<h3>Phrase Emphasis</h3> +<p>Markdown uses asterisks and underscores to indicate spans of +emphasis.</p> +<p>Markdown:</p> +<pre> +<code>Some of these words *are emphasized*. +Some of these words _are emphasized also_. + +Use two asterisks for **strong emphasis**. +Or, if you prefer, __use two underscores instead__. +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>Some of these words <em>are emphasized</em>. +Some of these words <em>are emphasized also</em>.</p> + +<p>Use two asterisks for <strong>strong emphasis</strong>. +Or, if you prefer, <strong>use two underscores instead</strong>.</p> +</code> +</pre> +<h2>Lists</h2> +<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens +(<code>*</code>, <code>+</code>, and <code>-</code>) as list +markers. These three markers are interchangable; this:</p> +<pre> +<code>* Candy. +* Gum. +* Booze. +</code> +</pre> +<p>this:</p> +<pre> +<code>+ Candy. ++ Gum. ++ Booze. +</code> +</pre> +<p>and this:</p> +<pre> +<code>- Candy. +- Gum. +- Booze. +</code> +</pre> +<p>all produce the same output:</p> +<pre> +<code><ul> +<li>Candy.</li> +<li>Gum.</li> +<li>Booze.</li> +</ul> +</code> +</pre> +<p>Ordered (numbered) lists use regular numbers, followed by +periods, as list markers:</p> +<pre> +<code>1. Red +2. Green +3. Blue +</code> +</pre> +<p>Output:</p> +<pre> +<code><ol> +<li>Red</li> +<li>Green</li> +<li>Blue</li> +</ol> +</code> +</pre> +<p>If you put blank lines between items, you'll get +<code><p></code> tags for the list item text. You can create +multi-paragraph list items by indenting the paragraphs by 4 spaces +or 1 tab:</p> +<pre> +<code>* A list item. + + With multiple paragraphs. + +* Another item in the list. +</code> +</pre> +<p>Output:</p> +<pre> +<code><ul> +<li><p>A list item.</p> +<p>With multiple paragraphs.</p></li> +<li><p>Another item in the list.</p></li> +</ul> +</code> +</pre> +<h3>Links</h3> +<p>Markdown supports two styles for creating links: <em>inline</em> +and <em>reference</em>. With both styles, you use square brackets +to delimit the text you want to turn into a link.</p> +<p>Inline-style links use parentheses immediately after the link +text. For example:</p> +<pre> +<code>This is an [example link](http://example.com/). +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>This is an <a href="http://example.com/"> +example link</a>.</p> +</code> +</pre> +<p>Optionally, you may include a title attribute in the +parentheses:</p> +<pre> +<code>This is an [example link](http://example.com/ "With a Title"). +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>This is an <a href="http://example.com/" title="With a Title"> +example link</a>.</p> +</code> +</pre> +<p>Reference-style links allow you to refer to your links by names, +which you define elsewhere in your document:</p> +<pre> +<code>I get 10 times more traffic from [Google][1] than from +[Yahoo][2] or [MSN][3]. + +[1]: http://google.com/ "Google" +[2]: http://search.yahoo.com/ "Yahoo Search" +[3]: http://search.msn.com/ "MSN Search" +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from <a href="http://search.yahoo.com/" +title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" +title="MSN Search">MSN</a>.</p> +</code> +</pre> +<p>The title attribute is optional. Link names may contain letters, +numbers and spaces, but are <em>not</em> case sensitive:</p> +<pre> +<code>I start my morning with a cup of coffee and +[The New York Times][NY Times]. + +[ny times]: http://www.nytimes.com/ +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>I start my morning with a cup of coffee and +<a href="http://www.nytimes.com/">The New York Times</a>.</p> +</code> +</pre> +<h3>Images</h3> +<p>Image syntax is very much like link syntax.</p> +<p>Inline (titles are optional):</p> +<pre> +<code> +</code> +</pre> +<p>Reference-style:</p> +<pre> +<code>![alt text][id] + +[id]: /path/to/img.jpg "Title" +</code> +</pre> +<p>Both of the above examples produce the same output:</p> +<pre> +<code><img src="/path/to/img.jpg" alt="alt text" title="Title" /> +</code> +</pre> +<h3>Code</h3> +<p>In a regular paragraph, you can create code span by wrapping +text in backtick quotes. Any ampersands (<code>&</code>) and +angle brackets (<code><</code> or <code>></code>) will +automatically be translated into HTML entities. This makes it easy +to use Markdown to write about HTML example code:</p> +<pre> +<code>I strongly recommend against using any `<blink>` tags. + +I wish SmartyPants used named entities like `&mdash;` +instead of decimal-encoded entites like `&#8212;`. +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>I strongly recommend against using any +<code>&lt;blink&gt;</code> tags.</p> + +<p>I wish SmartyPants used named entities like +<code>&amp;mdash;</code> instead of decimal-encoded +entites like <code>&amp;#8212;</code>.</p> +</code> +</pre> +<p>To specify an entire block of pre-formatted code, indent every +line of the block by 4 spaces or 1 tab. Just like with code spans, +<code>&</code>, <code><</code>, and <code>></code> +characters will be escaped automatically.</p> +<p>Markdown:</p> +<pre> +<code>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes:</p> + +<pre><code>&lt;blockquote&gt; + &lt;p&gt;For example.&lt;/p&gt; +&lt;/blockquote&gt; +</code></pre> +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text-res b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text-res new file mode 100644 index 0000000..65b90fa --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Basics.text-res @@ -0,0 +1,321 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h1>Markdown: Basics</h1> +<ul id="ProjectSubmenu"> +<li><a href="/projects/markdown/" title= +"Markdown Project Page">Main</a></li> +<li><a class="selected" title="Markdown Basics">Basics</a></li> +<li><a href="/projects/markdown/syntax" title= +"Markdown Syntax Documentation">Syntax</a></li> +<li><a href="/projects/markdown/license" title= +"Pricing and License Information">License</a></li> +<li><a href="/projects/markdown/dingus" title= +"Online Markdown Web Form">Dingus</a></li> +</ul> +<h2>Getting the Gist of Markdown's Formatting Syntax</h2> +<p>This page offers a brief overview of what it's like to use +Markdown. The <a href="/projects/markdown/syntax" title= +"Markdown Syntax">syntax page</a> provides complete, detailed +documentation for every feature, but Markdown should be very easy +to pick up simply by looking at a few examples of it in action. The +examples on this page are written in a before/after style, showing +example syntax and the HTML output produced by Markdown.</p> +<p>It's also helpful to simply try Markdown out; the <a href= +"/projects/markdown/dingus" title="Markdown Dingus">Dingus</a> is a +web application that allows you type your own Markdown-formatted +text and translate it to XHTML.</p> +<p><strong>Note:</strong> This document is itself written using +Markdown; you can <a href="/projects/markdown/basics.text">see the +source for it by adding '.text' to the URL</a>.</p> +<h2>Paragraphs, Headers, Blockquotes</h2> +<p>A paragraph is simply one or more consecutive lines of text, +separated by one or more blank lines. (A blank line is any line +that looks like a blank line -- a line containing nothing spaces or +tabs is considered blank.) Normal paragraphs should not be intended +with spaces or tabs.</p> +<p>Markdown offers two styles of headers: <em>Setext</em> and +<em>atx</em>. Setext-style headers for <code><h1></code> and +<code><h2></code> are created by "underlining" with equal +signs (<code>=</code>) and hyphens (<code>-</code>), respectively. +To create an atx-style header, you put 1-6 hash marks +(<code>#</code>) at the beginning of the line -- the number of +hashes equals the resulting HTML header level.</p> +<p>Blockquotes are indicated using email-style '<code>></code>' +angle brackets.</p> +<p>Markdown:</p> +<pre> +<code>A First Level Header +==================== + +A Second Level Header +--------------------- + +Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph. + +The quick brown fox jumped over the lazy +dog's back. + +### Header 3 + +> This is a blockquote. +> +> This is the second paragraph in the blockquote. +> +> ## This is an H2 in a blockquote +</code> +</pre> +<p>Output:</p> +<pre> +<code><h1>A First Level Header</h1> + +<h2>A Second Level Header</h2> + +<p>Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph.</p> + +<p>The quick brown fox jumped over the lazy +dog's back.</p> + +<h3>Header 3</h3> + +<blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> +</blockquote> +</code> +</pre> +<h3>Phrase Emphasis</h3> +<p>Markdown uses asterisks and underscores to indicate spans of +emphasis.</p> +<p>Markdown:</p> +<pre> +<code>Some of these words *are emphasized*. +Some of these words _are emphasized also_. + +Use two asterisks for **strong emphasis**. +Or, if you prefer, __use two underscores instead__. +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>Some of these words <em>are emphasized</em>. +Some of these words <em>are emphasized also</em>.</p> + +<p>Use two asterisks for <strong>strong emphasis</strong>. +Or, if you prefer, <strong>use two underscores instead</strong>.</p> +</code> +</pre> +<h2>Lists</h2> +<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens +(<code>*</code>, <code>+</code>, and <code>-</code>) as list +markers. These three markers are interchangable; this:</p> +<pre> +<code>* Candy. +* Gum. +* Booze. +</code> +</pre> +<p>this:</p> +<pre> +<code>+ Candy. ++ Gum. ++ Booze. +</code> +</pre> +<p>and this:</p> +<pre> +<code>- Candy. +- Gum. +- Booze. +</code> +</pre> +<p>all produce the same output:</p> +<pre> +<code><ul> +<li>Candy.</li> +<li>Gum.</li> +<li>Booze.</li> +</ul> +</code> +</pre> +<p>Ordered (numbered) lists use regular numbers, followed by +periods, as list markers:</p> +<pre> +<code>1. Red +2. Green +3. Blue +</code> +</pre> +<p>Output:</p> +<pre> +<code><ol> +<li>Red</li> +<li>Green</li> +<li>Blue</li> +</ol> +</code> +</pre> +<p>If you put blank lines between items, you'll get +<code><p></code> tags for the list item text. You can create +multi-paragraph list items by indenting the paragraphs by 4 spaces +or 1 tab:</p> +<pre> +<code>* A list item. + + With multiple paragraphs. + +* Another item in the list. +</code> +</pre> +<p>Output:</p> +<pre> +<code><ul> +<li><p>A list item.</p> +<p>With multiple paragraphs.</p></li> +<li><p>Another item in the list.</p></li> +</ul> +</code> +</pre> +<h3>Links</h3> +<p>Markdown supports two styles for creating links: <em>inline</em> +and <em>reference</em>. With both styles, you use square brackets +to delimit the text you want to turn into a link.</p> +<p>Inline-style links use parentheses immediately after the link +text. For example:</p> +<pre> +<code>This is an [example link](http://example.com/). +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>This is an <a href="http://example.com/"> +example link</a>.</p> +</code> +</pre> +<p>Optionally, you may include a title attribute in the +parentheses:</p> +<pre> +<code>This is an [example link](http://example.com/ "With a Title"). +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>This is an <a href="http://example.com/" title="With a Title"> +example link</a>.</p> +</code> +</pre> +<p>Reference-style links allow you to refer to your links by names, +which you define elsewhere in your document:</p> +<pre> +<code>I get 10 times more traffic from [Google][1] than from +[Yahoo][2] or [MSN][3]. + +[1]: http://google.com/ "Google" +[2]: http://search.yahoo.com/ "Yahoo Search" +[3]: http://search.msn.com/ "MSN Search" +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from <a href="http://search.yahoo.com/" +title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" +title="MSN Search">MSN</a>.</p> +</code> +</pre> +<p>The title attribute is optional. Link names may contain letters, +numbers and spaces, but are <em>not</em> case sensitive:</p> +<pre> +<code>I start my morning with a cup of coffee and +[The New York Times][NY Times]. + +[ny times]: http://www.nytimes.com/ +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>I start my morning with a cup of coffee and +<a href="http://www.nytimes.com/">The New York Times</a>.</p> +</code> +</pre> +<h3>Images</h3> +<p>Image syntax is very much like link syntax.</p> +<p>Inline (titles are optional):</p> +<pre> +<code> +</code> +</pre> +<p>Reference-style:</p> +<pre> +<code>![alt text][id] + +[id]: /path/to/img.jpg "Title" +</code> +</pre> +<p>Both of the above examples produce the same output:</p> +<pre> +<code><img src="/path/to/img.jpg" alt="alt text" title="Title" /> +</code> +</pre> +<h3>Code</h3> +<p>In a regular paragraph, you can create code span by wrapping +text in backtick quotes. Any ampersands (<code>&</code>) and +angle brackets (<code><</code> or <code>></code>) will +automatically be translated into HTML entities. This makes it easy +to use Markdown to write about HTML example code:</p> +<pre> +<code>I strongly recommend against using any `<blink>` tags. + +I wish SmartyPants used named entities like `&mdash;` +instead of decimal-encoded entites like `&#8212;`. +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>I strongly recommend against using any +<code>&lt;blink&gt;</code> tags.</p> + +<p>I wish SmartyPants used named entities like +<code>&amp;mdash;</code> instead of decimal-encoded +entites like <code>&amp;#8212;</code>.</p> +</code> +</pre> +<p>To specify an entire block of pre-formatted code, indent every +line of the block by 4 spaces or 1 tab. Just like with code spans, +<code>&</code>, <code><</code>, and <code>></code> +characters will be escaped automatically.</p> +<p>Markdown:</p> +<pre> +<code>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> +</code> +</pre> +<p>Output:</p> +<pre> +<code><p>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes:</p> + +<pre><code>&lt;blockquote&gt; + &lt;p&gt;For example.&lt;/p&gt; +&lt;/blockquote&gt; +</code></pre> +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.html b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.html new file mode 100644 index 0000000..5c01306 --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.html @@ -0,0 +1,942 @@ +<h1>Markdown: Syntax</h1> + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<ul> +<li><a href="#overview">Overview</a> +<ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#html">Inline HTML</a></li> +<li><a href="#autoescape">Automatic Escaping for Special Characters</a></li> +</ul></li> +<li><a href="#block">Block Elements</a> +<ul> +<li><a href="#p">Paragraphs and Line Breaks</a></li> +<li><a href="#header">Headers</a></li> +<li><a href="#blockquote">Blockquotes</a></li> +<li><a href="#list">Lists</a></li> +<li><a href="#precode">Code Blocks</a></li> +<li><a href="#hr">Horizontal Rules</a></li> +</ul></li> +<li><a href="#span">Span Elements</a> +<ul> +<li><a href="#link">Links</a></li> +<li><a href="#em">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#img">Images</a></li> +</ul></li> +<li><a href="#misc">Miscellaneous</a> +<ul> +<li><a href="#backslash">Backslash Escapes</a></li> +<li><a href="#autolink">Automatic Links</a></li> +</ul></li> +</ul> + +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/syntax.text">see the source for it by adding '.text' to the URL</a>.</p> + +<hr /> + +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +<p>Markdown is intended to be as easy-to-read and easy-to-write as is feasible.</p> + +<p>Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, <a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href="http://textism.com/tools/textile/">Textile</a>, <a href="http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href="http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and <a href="http://ettext.taint.org/doc/">EtText</a> -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email.</p> + +<p>To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like *emphasis*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email.</p> + +<h3 id="html">Inline HTML</h3> + +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> + +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a <em>publishing</em> format; Markdown is a <em>writing</em> +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text.</p> + +<p>For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags.</p> + +<p>The only restrictions are that block-level HTML elements -- e.g. <code><div></code>, +<code><table></code>, <code><pre></code>, <code><p></code>, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) <code><p></code> tags around HTML block-level tags.</p> + +<p>For example, to add an HTML table to a Markdown article:</p> + +<pre><code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code></pre> + +<p>Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style <code>*emphasis*</code> inside an +HTML block.</p> + +<p>Span-level HTML tags -- e.g. <code><span></code>, <code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML <code><a></code> or <code><img></code> tags instead of Markdown's +link or image syntax, go right ahead.</p> + +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> processed within +span-level tags.</p> + +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +<p>In HTML, there are two characters that demand special treatment: <code><</code> +and <code>&</code>. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> + +<p>Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '<code>AT&amp;T</code>'. You even need to +escape ampersands within URLs. Thus, if you want to link to:</p> + +<pre><code>http://images.google.com/images?num=30&q=larry+bird +</code></pre> + +<p>you need to encode the URL as:</p> + +<pre><code>http://images.google.com/images?num=30&amp;q=larry+bird +</code></pre> + +<p>in your anchor tag <code>href</code> attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites.</p> + +<p>Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into <code>&amp;</code>.</p> + +<p>So, if you want to include a copyright symbol in your article, you can write:</p> + +<pre><code>&copy; +</code></pre> + +<p>and Markdown will leave it alone. But if you write:</p> + +<pre><code>AT&T +</code></pre> + +<p>Markdown will translate it to:</p> + +<pre><code>AT&amp;T +</code></pre> + +<p>Similarly, because Markdown supports <a href="#html">inline HTML</a>, if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write:</p> + +<pre><code>4 < 5 +</code></pre> + +<p>Markdown will translate it to:</p> + +<pre><code>4 &lt; 5 +</code></pre> + +<p>However, inside Markdown code spans and blocks, angle brackets and +ampersands are <em>always</em> encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single <code><</code> +and <code>&</code> in your example code needs to be escaped.)</p> + +<hr /> + +<h2 id="block">Block Elements</h2> + +<h3 id="p">Paragraphs and Line Breaks</h3> + +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> + +<p>The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a <code><br /></code> tag.</p> + +<p>When you <em>do</em> want to insert a <code><br /></code> break tag using Markdown, you +end a line with two or more spaces, then type return.</p> + +<p>Yes, this takes a tad more effort to create a <code><br /></code>, but a simplistic +"every line break is a <code><br /></code>" rule wouldn't work for Markdown. +Markdown's email-style <a href="#blockquote">blockquoting</a> and multi-paragraph <a href="#list">list items</a> +work best -- and look better -- when you format them with hard breaks.</p> + +<h3 id="header">Headers</h3> + +<p>Markdown supports two styles of headers, <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and <a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> + +<p>Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example:</p> + +<pre><code>This is an H1 +============= + +This is an H2 +------------- +</code></pre> + +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s will work.</p> + +<p>Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example:</p> + +<pre><code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code></pre> + +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) :</p> + +<pre><code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code></pre> + +<h3 id="blockquote">Blockquotes</h3> + +<p>Markdown uses email-style <code>></code> characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a <code>></code> before every line:</p> + +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>Markdown allows you to be lazy and only put the <code>></code> before the first +line of a hard-wrapped paragraph:</p> + +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> + +<pre><code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code></pre> + +<p>Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks:</p> + +<pre><code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code></pre> + +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> + +<h3 id="list">Lists</h3> + +<p>Markdown supports ordered (numbered) and unordered (bulleted) lists.</p> + +<p>Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers:</p> + +<pre><code>* Red +* Green +* Blue +</code></pre> + +<p>is equivalent to:</p> + +<pre><code>+ Red ++ Green ++ Blue +</code></pre> + +<p>and:</p> + +<pre><code>- Red +- Green +- Blue +</code></pre> + +<p>Ordered lists use numbers followed by periods:</p> + +<pre><code>1. Bird +2. McHale +3. Parish +</code></pre> + +<p>It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is:</p> + +<pre><code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code></pre> + +<p>If you instead wrote the list in Markdown like this:</p> + +<pre><code>1. Bird +1. McHale +1. Parish +</code></pre> + +<p>or even:</p> + +<pre><code>3. Bird +1. McHale +8. Parish +</code></pre> + +<p>you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to.</p> + +<p>If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number.</p> + +<p>List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab.</p> + +<p>To make lists look nice, you can wrap items with hanging indents:</p> + +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>But if you want to be lazy, you don't have to:</p> + +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>If list items are separated by blank lines, Markdown will wrap the +items in <code><p></code> tags in the HTML output. For example, this input:</p> + +<pre><code>* Bird +* Magic +</code></pre> + +<p>will turn into:</p> + +<pre><code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code></pre> + +<p>But this:</p> + +<pre><code>* Bird + +* Magic +</code></pre> + +<p>will turn into:</p> + +<pre><code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code></pre> + +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab:</p> + +<pre><code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy:</p> + +<pre><code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code></pre> + +<p>To put a blockquote within a list item, the blockquote's <code>></code> +delimiters need to be indented:</p> + +<pre><code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code></pre> + +<p>To put a code block within a list item, the code block needs +to be indented <em>twice</em> -- 8 spaces or two tabs:</p> + +<pre><code>* A list item with a code block: + + <code goes here> +</code></pre> + +<p>It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this:</p> + +<pre><code>1986. What a great season. +</code></pre> + +<p>In other words, a <em>number-period-space</em> sequence at the beginning of a +line. To avoid this, you can backslash-escape the period:</p> + +<pre><code>1986\. What a great season. +</code></pre> + +<h3 id="precode">Code Blocks</h3> + +<p>Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both <code><pre></code> and <code><code></code> tags.</p> + +<p>To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input:</p> + +<pre><code>This is a normal paragraph: + + This is a code block. +</code></pre> + +<p>Markdown will generate:</p> + +<pre><code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code></pre> + +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this:</p> + +<pre><code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code></pre> + +<p>will turn into:</p> + +<pre><code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code></pre> + +<p>A code block continues until it reaches a line that is not indented +(or the end of the article).</p> + +<p>Within a code block, ampersands (<code>&</code>) and angle brackets (<code><</code> and <code>></code>) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> + +<pre><code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code></pre> + +<p>will turn into:</p> + +<pre><code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code></pre> + +<p>Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax.</p> + +<h3 id="hr">Horizontal Rules</h3> + +<p>You can produce a horizontal rule tag (<code><hr /></code>) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule:</p> + +<pre><code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code></pre> + +<hr /> + +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +<p>Markdown supports two style of links: <em>inline</em> and <em>reference</em>.</p> + +<p>In both styles, the link text is delimited by [square brackets].</p> + +<p>To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an <em>optional</em> +title for the link, surrounded in quotes. For example:</p> + +<pre><code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code></pre> + +<p>Will produce:</p> + +<pre><code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code></pre> + +<p>If you're referring to a local resource on the same server, you can +use relative paths:</p> + +<pre><code>See my [About](/about/) page for details. +</code></pre> + +<p>Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link:</p> + +<pre><code>This is [an example][id] reference-style link. +</code></pre> + +<p>You can optionally use a space to separate the sets of brackets:</p> + +<pre><code>This is [an example] [id] reference-style link. +</code></pre> + +<p>Then, anywhere in the document, you define your link label like this, +on a line by itself:</p> + +<pre><code>[id]: http://example.com/ "Optional Title Here" +</code></pre> + +<p>That is:</p> + +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> + +<p>The link URL may, optionally, be surrounded by angle brackets:</p> + +<pre><code>[id]: <http://example.com/> "Optional Title Here" +</code></pre> + +<p>You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs:</p> + +<pre><code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code></pre> + +<p>Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output.</p> + +<p>Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are <em>not</em> case sensitive. E.g. these two links:</p> + +<pre><code>[link text][a] +[link text][A] +</code></pre> + +<p>are equivalent.</p> + +<p>The <em>implicit link name</em> shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write:</p> + +<pre><code>[Google][] +</code></pre> + +<p>And then define the link:</p> + +<pre><code>[Google]: http://google.com/ +</code></pre> + +<p>Because link names may contain spaces, this shortcut even works for +multiple words in the link text:</p> + +<pre><code>Visit [Daring Fireball][] for more information. +</code></pre> + +<p>And then define the link:</p> + +<pre><code>[Daring Fireball]: http://daringfireball.net/ +</code></pre> + +<p>Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes.</p> + +<p>Here's an example of reference links in action:</p> + +<pre><code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code></pre> + +<p>Using the implicit link name shortcut, you could instead write:</p> + +<pre><code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code></pre> + +<p>Both of the above examples will produce the following HTML output:</p> + +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code></pre> + +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> + +<pre><code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code></pre> + +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text.</p> + +<p>With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose.</p> + +<h3 id="em">Emphasis</h3> + +<p>Markdown treats asterisks (<code>*</code>) and underscores (<code>_</code>) as indicators of +emphasis. Text wrapped with one <code>*</code> or <code>_</code> will be wrapped with an +HTML <code><em></code> tag; double <code>*</code>'s or <code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> + +<pre><code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code></pre> + +<p>will produce:</p> + +<pre><code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code></pre> + +<p>You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span.</p> + +<p>Emphasis can be used in the middle of a word:</p> + +<pre><code>un*fucking*believable +</code></pre> + +<p>But if you surround an <code>*</code> or <code>_</code> with spaces, it'll be treated as a +literal asterisk or underscore.</p> + +<p>To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it:</p> + +<pre><code>\*this text is surrounded by literal asterisks\* +</code></pre> + +<h3 id="code">Code</h3> + +<p>To indicate a span of code, wrap it with backtick quotes (<code>`</code>). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example:</p> + +<pre><code>Use the `printf()` function. +</code></pre> + +<p>will produce:</p> + +<pre><code><p>Use the <code>printf()</code> function.</p> +</code></pre> + +<p>To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters:</p> + +<pre><code>``There is a literal backtick (`) here.`` +</code></pre> + +<p>which will produce this:</p> + +<pre><code><p><code>There is a literal backtick (`) here.</code></p> +</code></pre> + +<p>The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span:</p> + +<pre><code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code></pre> + +<p>will produce:</p> + +<pre><code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code></pre> + +<p>With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this:</p> + +<pre><code>Please don't use any `<blink>` tags. +</code></pre> + +<p>into:</p> + +<pre><code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code></pre> + +<p>You can write this:</p> + +<pre><code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code></pre> + +<p>to produce:</p> + +<pre><code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code></pre> + +<h3 id="img">Images</h3> + +<p>Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format.</p> + +<p>Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: <em>inline</em> and <em>reference</em>.</p> + +<p>Inline image syntax looks like this:</p> + +<pre><code> + + +</code></pre> + +<p>That is:</p> + +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the <code>alt</code> +attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in double +or single quotes.</li> +</ul> + +<p>Reference-style image syntax looks like this:</p> + +<pre><code>![Alt text][id] +</code></pre> + +<p>Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references:</p> + +<pre><code>[id]: url/to/image "Optional title attribute" +</code></pre> + +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> + +<hr /> + +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +<p>Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:</p> + +<pre><code><http://example.com/> +</code></pre> + +<p>Markdown will turn this into:</p> + +<pre><code><a href="http://example.com/">http://example.com/</a> +</code></pre> + +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this:</p> + +<pre><code><address@example.com> +</code></pre> + +<p>into something like this:</p> + +<pre><code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code></pre> + +<p>which will render in a browser as a clickable link to "address@example.com".</p> + +<p>(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.)</p> + +<h3 id="backslash">Backslash Escapes</h3> + +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML <code><em></code> tag), you can backslashes +before the asterisks, like this:</p> + +<pre><code>\*literal asterisks\* +</code></pre> + +<p>Markdown provides backslash escapes for the following characters:</p> + +<pre><code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code></pre> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text new file mode 100644 index 0000000..dabd75c --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text @@ -0,0 +1,888 @@ +Markdown: Syntax +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +* [Overview](#overview) + * [Philosophy](#philosophy) + * [Inline HTML](#html) + * [Automatic Escaping for Special Characters](#autoescape) +* [Block Elements](#block) + * [Paragraphs and Line Breaks](#p) + * [Headers](#header) + * [Blockquotes](#blockquote) + * [Lists](#list) + * [Code Blocks](#precode) + * [Horizontal Rules](#hr) +* [Span Elements](#span) + * [Links](#link) + * [Emphasis](#em) + * [Code](#code) + * [Images](#img) +* [Miscellaneous](#misc) + * [Backslash Escapes](#backslash) + * [Automatic Links](#autolink) + + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL][src]. + + [src]: /projects/markdown/syntax.text + +* * * + +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +Markdown is intended to be as easy-to-read and easy-to-write as is feasible. + +Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4], +[Grutatext] [5], and [EtText] [6] -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email. + + [1]: http://docutils.sourceforge.net/mirror/setext.html + [2]: http://www.aaronsw.com/2002/atx/ + [3]: http://textism.com/tools/textile/ + [4]: http://docutils.sourceforge.net/rst.html + [5]: http://www.triptico.com/software/grutatxt.html + [6]: http://ettext.taint.org/doc/ + +To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like \*emphasis\*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email. + + + +<h3 id="html">Inline HTML</h3> + +Markdown's syntax is intended for one purpose: to be used as a +format for *writing* for the web. + +Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is *not* to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a *publishing* format; Markdown is a *writing* +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text. + +For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags. + +The only restrictions are that block-level HTML elements -- e.g. `<div>`, +`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) `<p>` tags around HTML block-level tags. + +For example, to add an HTML table to a Markdown article: + + This is a regular paragraph. + + <table> + <tr> + <td>Foo</td> + </tr> + </table> + + This is another regular paragraph. + +Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an +HTML block. + +Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's +link or image syntax, go right ahead. + +Unlike block-level HTML tags, Markdown syntax *is* processed within +span-level tags. + + +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +In HTML, there are two characters that demand special treatment: `<` +and `&`. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. `<`, and +`&`. + +Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '`AT&T`'. You even need to +escape ampersands within URLs. Thus, if you want to link to: + + http://images.google.com/images?num=30&q=larry+bird + +you need to encode the URL as: + + http://images.google.com/images?num=30&q=larry+bird + +in your anchor tag `href` attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites. + +Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into `&`. + +So, if you want to include a copyright symbol in your article, you can write: + + © + +and Markdown will leave it alone. But if you write: + + AT&T + +Markdown will translate it to: + + AT&T + +Similarly, because Markdown supports [inline HTML](#html), if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write: + + 4 < 5 + +Markdown will translate it to: + + 4 < 5 + +However, inside Markdown code spans and blocks, angle brackets and +ampersands are *always* encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single `<` +and `&` in your example code needs to be escaped.) + + +* * * + + +<h2 id="block">Block Elements</h2> + + +<h3 id="p">Paragraphs and Line Breaks</h3> + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a `<br />` tag. + +When you *do* want to insert a `<br />` break tag using Markdown, you +end a line with two or more spaces, then type return. + +Yes, this takes a tad more effort to create a `<br />`, but a simplistic +"every line break is a `<br />`" rule wouldn't work for Markdown. +Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l] +work best -- and look better -- when you format them with hard breaks. + + [bq]: #blockquote + [l]: #list + + + +<h3 id="header">Headers</h3> + +Markdown supports two styles of headers, [Setext] [1] and [atx] [2]. + +Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example: + + This is an H1 + ============= + + This is an H2 + ------------- + +Any number of underlining `=`'s or `-`'s will work. + +Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example: + + # This is an H1 + + ## This is an H2 + + ###### This is an H6 + +Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) : + + # This is an H1 # + + ## This is an H2 ## + + ### This is an H3 ###### + + +<h3 id="blockquote">Blockquotes</h3> + +Markdown uses email-style `>` characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a `>` before every line: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + > + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + > id sem consectetuer libero luctus adipiscing. + +Markdown allows you to be lazy and only put the `>` before the first +line of a hard-wrapped paragraph: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + id sem consectetuer libero luctus adipiscing. + +Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of `>`: + + > This is the first level of quoting. + > + > > This is nested blockquote. + > + > Back to the first level. + +Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks: + + > ## This is a header. + > + > 1. This is the first list item. + > 2. This is the second list item. + > + > Here's some example code: + > + > return shell_exec("echo $input | $markdown_script"); + +Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu. + + +<h3 id="list">Lists</h3> + +Markdown supports ordered (numbered) and unordered (bulleted) lists. + +Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers: + + * Red + * Green + * Blue + +is equivalent to: + + + Red + + Green + + Blue + +and: + + - Red + - Green + - Blue + +Ordered lists use numbers followed by periods: + + 1. Bird + 2. McHale + 3. Parish + +It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is: + + <ol> + <li>Bird</li> + <li>McHale</li> + <li>Parish</li> + </ol> + +If you instead wrote the list in Markdown like this: + + 1. Bird + 1. McHale + 1. Parish + +or even: + + 3. Bird + 1. McHale + 8. Parish + +you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to. + +If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number. + +List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab. + +To make lists look nice, you can wrap items with hanging indents: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +But if you want to be lazy, you don't have to: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +If list items are separated by blank lines, Markdown will wrap the +items in `<p>` tags in the HTML output. For example, this input: + + * Bird + * Magic + +will turn into: + + <ul> + <li>Bird</li> + <li>Magic</li> + </ul> + +But this: + + * Bird + + * Magic + +will turn into: + + <ul> + <li><p>Bird</p></li> + <li><p>Magic</p></li> + </ul> + +List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab: + + 1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + + 2. Suspendisse id sem consectetuer libero luctus adipiscing. + +It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy: + + * This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're + only required to indent the first line. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. + + * Another item in the same list. + +To put a blockquote within a list item, the blockquote's `>` +delimiters need to be indented: + + * A list item with a blockquote: + + > This is a blockquote + > inside a list item. + +To put a code block within a list item, the code block needs +to be indented *twice* -- 8 spaces or two tabs: + + * A list item with a code block: + + <code goes here> + + +It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this: + + 1986. What a great season. + +In other words, a *number-period-space* sequence at the beginning of a +line. To avoid this, you can backslash-escape the period: + + 1986\. What a great season. + + + +<h3 id="precode">Code Blocks</h3> + +Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both `<pre>` and `<code>` tags. + +To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input: + + This is a normal paragraph: + + This is a code block. + +Markdown will generate: + + <p>This is a normal paragraph:</p> + + <pre><code>This is a code block. + </code></pre> + +One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this: + + Here is an example of AppleScript: + + tell application "Foo" + beep + end tell + +will turn into: + + <p>Here is an example of AppleScript:</p> + + <pre><code>tell application "Foo" + beep + end tell + </code></pre> + +A code block continues until it reaches a line that is not indented +(or the end of the article). + +Within a code block, ampersands (`&`) and angle brackets (`<` and `>`) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this: + + <div class="footer"> + © 2004 Foo Corporation + </div> + +will turn into: + + <pre><code><div class="footer"> + &copy; 2004 Foo Corporation + </div> + </code></pre> + +Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax. + + + +<h3 id="hr">Horizontal Rules</h3> + +You can produce a horizontal rule tag (`<hr />`) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule: + + * * * + + *** + + ***** + + - - - + + --------------------------------------- + + _ _ _ + + +* * * + +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +Markdown supports two style of links: *inline* and *reference*. + +In both styles, the link text is delimited by [square brackets]. + +To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an *optional* +title for the link, surrounded in quotes. For example: + + This is [an example](http://example.com/ "Title") inline link. + + [This link](http://example.net/) has no title attribute. + +Will produce: + + <p>This is <a href="http://example.com/" title="Title"> + an example</a> inline link.</p> + + <p><a href="http://example.net/">This link</a> has no + title attribute.</p> + +If you're referring to a local resource on the same server, you can +use relative paths: + + See my [About](/about/) page for details. + +Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link: + + This is [an example][id] reference-style link. + +You can optionally use a space to separate the sets of brackets: + + This is [an example] [id] reference-style link. + +Then, anywhere in the document, you define your link label like this, +on a line by itself: + + [id]: http://example.com/ "Optional Title Here" + +That is: + +* Square brackets containing the link identifier (optionally + indented from the left margin using up to three spaces); +* followed by a colon; +* followed by one or more spaces (or tabs); +* followed by the URL for the link; +* optionally followed by a title attribute for the link, enclosed + in double or single quotes. + +The link URL may, optionally, be surrounded by angle brackets: + + [id]: <http://example.com/> "Optional Title Here" + +You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs: + + [id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" + +Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output. + +Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links: + + [link text][a] + [link text][A] + +are equivalent. + +The *implicit link name* shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write: + + [Google][] + +And then define the link: + + [Google]: http://google.com/ + +Because link names may contain spaces, this shortcut even works for +multiple words in the link text: + + Visit [Daring Fireball][] for more information. + +And then define the link: + + [Daring Fireball]: http://daringfireball.net/ + +Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes. + +Here's an example of reference links in action: + + I get 10 times more traffic from [Google] [1] than from + [Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Using the implicit link name shortcut, you could instead write: + + I get 10 times more traffic from [Google][] than from + [Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" + +Both of the above examples will produce the following HTML output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from + <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> + or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> + +For comparison, here is the same paragraph written using +Markdown's inline link style: + + I get 10 times more traffic from [Google](http://google.com/ "Google") + than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or + [MSN](http://search.msn.com/ "MSN Search"). + +The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text. + +With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose. + + +<h3 id="em">Emphasis</h3> + +Markdown treats asterisks (`*`) and underscores (`_`) as indicators of +emphasis. Text wrapped with one `*` or `_` will be wrapped with an +HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML +`<strong>` tag. E.g., this input: + + *single asterisks* + + _single underscores_ + + **double asterisks** + + __double underscores__ + +will produce: + + <em>single asterisks</em> + + <em>single underscores</em> + + <strong>double asterisks</strong> + + <strong>double underscores</strong> + +You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span. + +Emphasis can be used in the middle of a word: + + un*fucking*believable + +But if you surround an `*` or `_` with spaces, it'll be treated as a +literal asterisk or underscore. + +To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it: + + \*this text is surrounded by literal asterisks\* + + + +<h3 id="code">Code</h3> + +To indicate a span of code, wrap it with backtick quotes (`` ` ``). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example: + + Use the `printf()` function. + +will produce: + + <p>Use the <code>printf()</code> function.</p> + +To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters: + + ``There is a literal backtick (`) here.`` + +which will produce this: + + <p><code>There is a literal backtick (`) here.</code></p> + +The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span: + + A single backtick in a code span: `` ` `` + + A backtick-delimited string in a code span: `` `foo` `` + +will produce: + + <p>A single backtick in a code span: <code>`</code></p> + + <p>A backtick-delimited string in a code span: <code>`foo`</code></p> + +With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this: + + Please don't use any `<blink>` tags. + +into: + + <p>Please don't use any <code><blink></code> tags.</p> + +You can write this: + + `—` is the decimal-encoded equivalent of `—`. + +to produce: + + <p><code>&#8212;</code> is the decimal-encoded + equivalent of <code>&mdash;</code>.</p> + + + +<h3 id="img">Images</h3> + +Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format. + +Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: *inline* and *reference*. + +Inline image syntax looks like this: + +  + +  + +That is: + +* An exclamation mark: `!`; +* followed by a set of square brackets, containing the `alt` + attribute text for the image; +* followed by a set of parentheses, containing the URL or path to + the image, and an optional `title` attribute enclosed in double + or single quotes. + +Reference-style image syntax looks like this: + + ![Alt text][id] + +Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references: + + [id]: url/to/image "Optional title attribute" + +As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML `<img>` tags. + + +* * * + + +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this: + + <http://example.com/> + +Markdown will turn this into: + + <a href="http://example.com/">http://example.com/</a> + +Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this: + + <address@example.com> + +into something like this: + + <a href="mailto:addre + ss@example.co + m">address@exa + mple.com</a> + +which will render in a browser as a clickable link to "address@example.com". + +(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.) + + + +<h3 id="backslash">Backslash Escapes</h3> + +Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML `<em>` tag), you can backslashes +before the asterisks, like this: + + \*literal asterisks\* + +Markdown provides backslash escapes for the following characters: + + \ backslash + ` backtick + * asterisk + _ underscore + {} curly braces + [] square brackets + () parentheses + # hash mark + + plus sign + - minus sign (hyphen) + . dot + ! exclamation mark + diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text-out b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text-out new file mode 100644 index 0000000..ecf2e70 --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text-out @@ -0,0 +1,957 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h1>Markdown: Syntax</h1> +<ul id="ProjectSubmenu"> +<li><a href="/projects/markdown/" title= +"Markdown Project Page">Main</a></li> +<li><a href="/projects/markdown/basics" title= +"Markdown Basics">Basics</a></li> +<li><a class="selected" title= +"Markdown Syntax Documentation">Syntax</a></li> +<li><a href="/projects/markdown/license" title= +"Pricing and License Information">License</a></li> +<li><a href="/projects/markdown/dingus" title= +"Online Markdown Web Form">Dingus</a></li> +</ul> +<ul> +<li><a href="#overview">Overview</a> +<ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#html">Inline HTML</a></li> +<li><a href="#autoescape">Automatic Escaping for Special +Characters</a></li> +</ul> +</li> +<li><a href="#block">Block Elements</a> +<ul> +<li><a href="#p">Paragraphs and Line Breaks</a></li> +<li><a href="#header">Headers</a></li> +<li><a href="#blockquote">Blockquotes</a></li> +<li><a href="#list">Lists</a></li> +<li><a href="#precode">Code Blocks</a></li> +<li><a href="#hr">Horizontal Rules</a></li> +</ul> +</li> +<li><a href="#span">Span Elements</a> +<ul> +<li><a href="#link">Links</a></li> +<li><a href="#em">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#img">Images</a></li> +</ul> +</li> +<li><a href="#misc">Miscellaneous</a> +<ul> +<li><a href="#backslash">Backslash Escapes</a></li> +<li><a href="#autolink">Automatic Links</a></li> +</ul> +</li> +</ul> +<p><strong>Note:</strong> This document is itself written using +Markdown; you can <a href="/projects/markdown/syntax.text">see the +source for it by adding '.text' to the URL</a>.</p> +<hr> +<h2 id="overview">Overview</h2> +<h3 id="philosophy">Philosophy</h3> +<p>Markdown is intended to be as easy-to-read and easy-to-write as +is feasible.</p> +<p>Readability, however, is emphasized above all else. A +Markdown-formatted document should be publishable as-is, as plain +text, without looking like it's been marked up with tags or +formatting instructions. While Markdown's syntax has been +influenced by several existing text-to-HTML filters -- including +<a href= +"http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, +<a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href= +"http://textism.com/tools/textile/">Textile</a>, <a href= +"http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href= +"http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and +<a href="http://ettext.taint.org/doc/">EtText</a> -- the single +biggest source of inspiration for Markdown's syntax is the format +of plain text email.</p> +<p>To this end, Markdown's syntax is comprised entirely of +punctuation characters, which punctuation characters have been +carefully chosen so as to look like what they mean. E.g., asterisks +around a word actually look like *emphasis*. Markdown lists look +like, well, lists. Even blockquotes look like quoted passages of +text, assuming you've ever used email.</p> +<h3 id="html">Inline HTML</h3> +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes +it easier to insert HTML tags. In my opinion, HTML tags are already +easy to insert. The idea for Markdown is to make it easy to read, +write, and edit prose. HTML is a <em>publishing</em> format; +Markdown is a <em>writing</em> format. Thus, Markdown's formatting +syntax only addresses issues that can be conveyed in plain +text.</p> +<p>For any markup that is not covered by Markdown's syntax, you +simply use HTML itself. There's no need to preface it or delimit it +to indicate that you're switching from Markdown to HTML; you just +use the tags.</p> +<p>The only restrictions are that block-level HTML elements -- e.g. +<code><div></code>, <code><table></code>, +<code><pre></code>, <code><p></code>, etc. -- must be +separated from surrounding content by blank lines, and the start +and end tags of the block should not be indented with tabs or +spaces. Markdown is smart enough not to add extra (unwanted) +<code><p></code> tags around HTML block-level tags.</p> +<p>For example, to add an HTML table to a Markdown article:</p> +<pre> +<code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code> +</pre> +<p>Note that Markdown formatting syntax is not processed within +block-level HTML tags. E.g., you can't use Markdown-style +<code>*emphasis*</code> inside an HTML block.</p> +<p>Span-level HTML tags -- e.g. <code><span></code>, +<code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; +e.g. if you'd prefer to use HTML <code><a></code> or +<code><img></code> tags instead of Markdown's link or image +syntax, go right ahead.</p> +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> +processed within span-level tags.</p> +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> +<p>In HTML, there are two characters that demand special treatment: +<code><</code> and <code>&</code>. Left angle brackets are +used to start tags; ampersands are used to denote HTML entities. If +you want to use them as literal characters, you must escape them as +entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> +<p>Ampersands in particular are bedeviling for web writers. If you +want to write about 'AT&T', you need to write +'<code>AT&amp;T</code>'. You even need to escape ampersands +within URLs. Thus, if you want to link to:</p> +<pre> +<code>http://images.google.com/images?num=30&q=larry+bird +</code> +</pre> +<p>you need to encode the URL as:</p> +<pre> +<code>http://images.google.com/images?num=30&amp;q=larry+bird +</code> +</pre> +<p>in your anchor tag <code>href</code> attribute. Needless to say, +this is easy to forget, and is probably the single most common +source of HTML validation errors in otherwise well-marked-up web +sites.</p> +<p>Markdown allows you to use these characters naturally, taking +care of all the necessary escaping for you. If you use an ampersand +as part of an HTML entity, it remains unchanged; otherwise it will +be translated into <code>&amp;</code>.</p> +<p>So, if you want to include a copyright symbol in your article, +you can write:</p> +<pre> +<code>&copy; +</code> +</pre> +<p>and Markdown will leave it alone. But if you write:</p> +<pre> +<code>AT&T +</code> +</pre> +<p>Markdown will translate it to:</p> +<pre> +<code>AT&amp;T +</code> +</pre> +<p>Similarly, because Markdown supports <a href="#html">inline +HTML</a>, if you use angle brackets as delimiters for HTML tags, +Markdown will treat them as such. But if you write:</p> +<pre> +<code>4 < 5 +</code> +</pre> +<p>Markdown will translate it to:</p> +<pre> +<code>4 &lt; 5 +</code> +</pre> +<p>However, inside Markdown code spans and blocks, angle brackets +and ampersands are <em>always</em> encoded automatically. This +makes it easy to use Markdown to write about HTML code. (As opposed +to raw HTML, which is a terrible format for writing about HTML +syntax, because every single <code><</code> and +<code>&</code> in your example code needs to be escaped.)</p> +<hr> +<h2 id="block">Block Elements</h2> +<h3 id="p">Paragraphs and Line Breaks</h3> +<p>A paragraph is simply one or more consecutive lines of text, +separated by one or more blank lines. (A blank line is any line +that looks like a blank line -- a line containing nothing but +spaces or tabs is considered blank.) Normal paragraphs should not +be intended with spaces or tabs.</p> +<p>The implication of the "one or more consecutive lines of text" +rule is that Markdown supports "hard-wrapped" text paragraphs. This +differs significantly from most other text-to-HTML formatters +(including Movable Type's "Convert Line Breaks" option) which +translate every line break character in a paragraph into a +<code><br /></code> tag.</p> +<p>When you <em>do</em> want to insert a <code><br /></code> +break tag using Markdown, you end a line with two or more spaces, +then type return.</p> +<p>Yes, this takes a tad more effort to create a <code><br +/></code>, but a simplistic "every line break is a <code><br +/></code>" rule wouldn't work for Markdown. Markdown's +email-style <a href="#blockquote">blockquoting</a> and +multi-paragraph <a href="#list">list items</a> work best -- and +look better -- when you format them with hard breaks.</p> +<h3 id="header">Headers</h3> +<p>Markdown supports two styles of headers, <a href= +"http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and +<a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> +<p>Setext-style headers are "underlined" using equal signs (for +first-level headers) and dashes (for second-level headers). For +example:</p> +<pre> +<code>This is an H1 +============= + +This is an H2 +------------- +</code> +</pre> +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s +will work.</p> +<p>Atx-style headers use 1-6 hash characters at the start of the +line, corresponding to header levels 1-6. For example:</p> +<pre> +<code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code> +</pre> +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes used +to open the header. (The number of opening hashes determines the +header level.) :</p> +<pre> +<code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code> +</pre> +<h3 id="blockquote">Blockquotes</h3> +<p>Markdown uses email-style <code>></code> characters for +blockquoting. If you're familiar with quoting passages of text in +an email message, then you know how to create a blockquote in +Markdown. It looks best if you hard wrap the text and put a +<code>></code> before every line:</p> +<pre> +<code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>Markdown allows you to be lazy and only put the +<code>></code> before the first line of a hard-wrapped +paragraph:</p> +<pre> +<code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> +<pre> +<code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code> +</pre> +<p>Blockquotes can contain other Markdown elements, including +headers, lists, and code blocks:</p> +<pre> +<code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code> +</pre> +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> +<h3 id="list">Lists</h3> +<p>Markdown supports ordered (numbered) and unordered (bulleted) +lists.</p> +<p>Unordered lists use asterisks, pluses, and hyphens -- +interchangably -- as list markers:</p> +<pre> +<code>* Red +* Green +* Blue +</code> +</pre> +<p>is equivalent to:</p> +<pre> +<code>+ Red ++ Green ++ Blue +</code> +</pre> +<p>and:</p> +<pre> +<code>- Red +- Green +- Blue +</code> +</pre> +<p>Ordered lists use numbers followed by periods:</p> +<pre> +<code>1. Bird +2. McHale +3. Parish +</code> +</pre> +<p>It's important to note that the actual numbers you use to mark +the list have no effect on the HTML output Markdown produces. The +HTML Markdown produces from the above list is:</p> +<pre> +<code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code> +</pre> +<p>If you instead wrote the list in Markdown like this:</p> +<pre> +<code>1. Bird +1. McHale +1. Parish +</code> +</pre> +<p>or even:</p> +<pre> +<code>3. Bird +1. McHale +8. Parish +</code> +</pre> +<p>you'd get the exact same HTML output. The point is, if you want +to, you can use ordinal numbers in your ordered Markdown lists, so +that the numbers in your source match the numbers in your published +HTML. But if you want to be lazy, you don't have to.</p> +<p>If you do use lazy list numbering, however, you should still +start the list with the number 1. At some point in the future, +Markdown may support starting ordered lists at an arbitrary +number.</p> +<p>List markers typically start at the left margin, but may be +indented by up to three spaces. List markers must be followed by +one or more spaces or a tab.</p> +<p>To make lists look nice, you can wrap items with hanging +indents:</p> +<pre> +<code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>But if you want to be lazy, you don't have to:</p> +<pre> +<code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>If list items are separated by blank lines, Markdown will wrap +the items in <code><p></code> tags in the HTML output. For +example, this input:</p> +<pre> +<code>* Bird +* Magic +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code> +</pre> +<p>But this:</p> +<pre> +<code>* Bird + +* Magic +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code> +</pre> +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces or one +tab:</p> +<pre> +<code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be lazy:</p> +<pre> +<code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code> +</pre> +<p>To put a blockquote within a list item, the blockquote's +<code>></code> delimiters need to be indented:</p> +<pre> +<code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code> +</pre> +<p>To put a code block within a list item, the code block needs to +be indented <em>twice</em> -- 8 spaces or two tabs:</p> +<pre> +<code>* A list item with a code block: + + <code goes here> +</code> +</pre> +<p>It's worth noting that it's possible to trigger an ordered list +by accident, by writing something like this:</p> +<pre> +<code>1986. What a great season. +</code> +</pre> +<p>In other words, a <em>number-period-space</em> sequence at the +beginning of a line. To avoid this, you can backslash-escape the +period:</p> +<pre> +<code>1986\. What a great season. +</code> +</pre> +<h3 id="precode">Code Blocks</h3> +<p>Pre-formatted code blocks are used for writing about programming +or markup source code. Rather than forming normal paragraphs, the +lines of a code block are interpreted literally. Markdown wraps a +code block in both <code><pre></code> and +<code><code></code> tags.</p> +<p>To produce a code block in Markdown, simply indent every line of +the block by at least 4 spaces or 1 tab. For example, given this +input:</p> +<pre> +<code>This is a normal paragraph: + + This is a code block. +</code> +</pre> +<p>Markdown will generate:</p> +<pre> +<code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code> +</pre> +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from +each line of the code block. For example, this:</p> +<pre> +<code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code> +</pre> +<p>A code block continues until it reaches a line that is not +indented (or the end of the article).</p> +<p>Within a code block, ampersands (<code>&</code>) and angle +brackets (<code><</code> and <code>></code>) are +automatically converted into HTML entities. This makes it very easy +to include example HTML source code using Markdown -- just paste it +and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> +<pre> +<code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code> +</pre> +<p>Regular Markdown syntax is not processed within code blocks. +E.g., asterisks are just literal asterisks within a code block. +This means it's also easy to use Markdown to write about Markdown's +own syntax.</p> +<h3 id="hr">Horizontal Rules</h3> +<p>You can produce a horizontal rule tag (<code><hr +/></code>) by placing three or more hyphens, asterisks, or +underscores on a line by themselves. If you wish, you may use +spaces between the hyphens or asterisks. Each of the following +lines will produce a horizontal rule:</p> +<pre> +<code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code> +</pre> +<hr> +<h2 id="span">Span Elements</h2> +<h3 id="link">Links</h3> +<p>Markdown supports two style of links: <em>inline</em> and +<em>reference</em>.</p> +<p>In both styles, the link text is delimited by [square +brackets].</p> +<p>To create an inline link, use a set of regular parentheses +immediately after the link text's closing square bracket. Inside +the parentheses, put the URL where you want the link to point, +along with an <em>optional</em> title for the link, surrounded in +quotes. For example:</p> +<pre> +<code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code> +</pre> +<p>Will produce:</p> +<pre> +<code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code> +</pre> +<p>If you're referring to a local resource on the same server, you +can use relative paths:</p> +<pre> +<code>See my [About](/about/) page for details. +</code> +</pre> +<p>Reference-style links use a second set of square brackets, +inside which you place a label of your choosing to identify the +link:</p> +<pre> +<code>This is [an example][id] reference-style link. +</code> +</pre> +<p>You can optionally use a space to separate the sets of +brackets:</p> +<pre> +<code>This is [an example] [id] reference-style link. +</code> +</pre> +<p>Then, anywhere in the document, you define your link label like +this, on a line by itself:</p> +<pre> +<code>[id]: http://example.com/ "Optional Title Here" +</code> +</pre> +<p>That is:</p> +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> +<p>The link URL may, optionally, be surrounded by angle +brackets:</p> +<pre> +<code>[id]: <http://example.com/> "Optional Title Here" +</code> +</pre> +<p>You can put the title attribute on the next line and use extra +spaces or tabs for padding, which tends to look better with longer +URLs:</p> +<pre> +<code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code> +</pre> +<p>Link definitions are only used for creating links during +Markdown processing, and are stripped from your document in the +HTML output.</p> +<p>Link definition names may constist of letters, numbers, spaces, +and punctuation -- but they are <em>not</em> case sensitive. E.g. +these two links:</p> +<pre> +<code>[link text][a] +[link text][A] +</code> +</pre> +<p>are equivalent.</p> +<p>The <em>implicit link name</em> shortcut allows you to omit the +name of the link, in which case the link text itself is used as the +name. Just use an empty set of square brackets -- e.g., to link the +word "Google" to the google.com web site, you could simply +write:</p> +<pre> +<code>[Google][] +</code> +</pre> +<p>And then define the link:</p> +<pre> +<code>[Google]: http://google.com/ +</code> +</pre> +<p>Because link names may contain spaces, this shortcut even works +for multiple words in the link text:</p> +<pre> +<code>Visit [Daring Fireball][] for more information. +</code> +</pre> +<p>And then define the link:</p> +<pre> +<code>[Daring Fireball]: http://daringfireball.net/ +</code> +</pre> +<p>Link definitions can be placed anywhere in your Markdown +document. I tend to put them immediately after each paragraph in +which they're used, but if you want, you can put them all at the +end of your document, sort of like footnotes.</p> +<p>Here's an example of reference links in action:</p> +<pre> +<code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code> +</pre> +<p>Using the implicit link name shortcut, you could instead +write:</p> +<pre> +<code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code> +</pre> +<p>Both of the above examples will produce the following HTML +output:</p> +<pre> +<code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code> +</pre> +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> +<pre> +<code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code> +</pre> +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw +HTML, it's 234 characters. In the raw HTML, there's more markup +than there is text.</p> +<p>With Markdown's reference-style links, a source document much +more closely resembles the final output, as rendered in a browser. +By allowing you to move the markup-related metadata out of the +paragraph, you can add links without interrupting the narrative +flow of your prose.</p> +<h3 id="em">Emphasis</h3> +<p>Markdown treats asterisks (<code>*</code>) and underscores +(<code>_</code>) as indicators of emphasis. Text wrapped with one +<code>*</code> or <code>_</code> will be wrapped with an HTML +<code><em></code> tag; double <code>*</code>'s or +<code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> +<pre> +<code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code> +</pre> +<p>will produce:</p> +<pre> +<code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code> +</pre> +<p>You can use whichever style you prefer; the lone restriction is +that the same character must be used to open and close an emphasis +span.</p> +<p>Emphasis can be used in the middle of a word:</p> +<pre> +<code>un*fucking*believable +</code> +</pre> +<p>But if you surround an <code>*</code> or <code>_</code> with +spaces, it'll be treated as a literal asterisk or underscore.</p> +<p>To produce a literal asterisk or underscore at a position where +it would otherwise be used as an emphasis delimiter, you can +backslash escape it:</p> +<pre> +<code>\*this text is surrounded by literal asterisks\* +</code> +</pre> +<h3 id="code">Code</h3> +<p>To indicate a span of code, wrap it with backtick quotes +(<code>`</code>). Unlike a pre-formatted code block, a code span +indicates code within a normal paragraph. For example:</p> +<pre> +<code>Use the `printf()` function. +</code> +</pre> +<p>will produce:</p> +<pre> +<code><p>Use the <code>printf()</code> function.</p> +</code> +</pre> +<p>To include a literal backtick character within a code span, you +can use multiple backticks as the opening and closing +delimiters:</p> +<pre> +<code>``There is a literal backtick (`) here.`` +</code> +</pre> +<p>which will produce this:</p> +<pre> +<code><p><code>There is a literal backtick (`) here.</code></p> +</code> +</pre> +<p>The backtick delimiters surrounding a code span may include +spaces -- one after the opening, one before the closing. This +allows you to place literal backtick characters at the beginning or +end of a code span:</p> +<pre> +<code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code> +</pre> +<p>will produce:</p> +<pre> +<code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code> +</pre> +<p>With a code span, ampersands and angle brackets are encoded as +HTML entities automatically, which makes it easy to include example +HTML tags. Markdown will turn this:</p> +<pre> +<code>Please don't use any `<blink>` tags. +</code> +</pre> +<p>into:</p> +<pre> +<code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code> +</pre> +<p>You can write this:</p> +<pre> +<code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code> +</pre> +<p>to produce:</p> +<pre> +<code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code> +</pre> +<h3 id="img">Images</h3> +<p>Admittedly, it's fairly difficult to devise a "natural" syntax +for placing images into a plain text document format.</p> +<p>Markdown uses an image syntax that is intended to resemble the +syntax for links, allowing for two styles: <em>inline</em> and +<em>reference</em>.</p> +<p>Inline image syntax looks like this:</p> +<pre> +<code> + + +</code> +</pre> +<p>That is:</p> +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the +<code>alt</code> attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in +double or single quotes.</li> +</ul> +<p>Reference-style image syntax looks like this:</p> +<pre> +<code>![Alt text][id] +</code> +</pre> +<p>Where "id" is the name of a defined image reference. Image +references are defined using syntax identical to link +references:</p> +<pre> +<code>[id]: url/to/image "Optional title attribute" +</code> +</pre> +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> +<hr> +<h2 id="misc">Miscellaneous</h2> +<h3 id="autolink">Automatic Links</h3> +<p>Markdown supports a shortcut style for creating "automatic" +links for URLs and email addresses: simply surround the URL or +email address with angle brackets. What this means is that if you +want to show the actual text of a URL or email address, and also +have it be a clickable link, you can do this:</p> +<pre> +<code><http://example.com/> +</code> +</pre> +<p>Markdown will turn this into:</p> +<pre> +<code><a href="http://example.com/">http://example.com/</a> +</code> +</pre> +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from +address-harvesting spambots. For example, Markdown will turn +this:</p> +<pre> +<code><address@example.com> +</code> +</pre> +<p>into something like this:</p> +<pre> +<code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code> +</pre> +<p>which will render in a browser as a clickable link to +"address@example.com".</p> +<p>(This sort of entity-encoding trick will indeed fool many, if +not most, address-harvesting bots, but it definitely won't fool all +of them. It's better than nothing, but an address published in this +way will probably eventually start receiving spam.)</p> +<h3 id="backslash">Backslash Escapes</h3> +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word +with literal asterisks (instead of an HTML <code><em></code> +tag), you can backslashes before the asterisks, like this:</p> +<pre> +<code>\*literal asterisks\* +</code> +</pre> +<p>Markdown provides backslash escapes for the following +characters:</p> +<pre> +<code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text-res b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text-res new file mode 100644 index 0000000..ecf2e70 --- /dev/null +++ b/MarkdownTest/Tests_2004/Markdown Documentation - Syntax.text-res @@ -0,0 +1,957 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h1>Markdown: Syntax</h1> +<ul id="ProjectSubmenu"> +<li><a href="/projects/markdown/" title= +"Markdown Project Page">Main</a></li> +<li><a href="/projects/markdown/basics" title= +"Markdown Basics">Basics</a></li> +<li><a class="selected" title= +"Markdown Syntax Documentation">Syntax</a></li> +<li><a href="/projects/markdown/license" title= +"Pricing and License Information">License</a></li> +<li><a href="/projects/markdown/dingus" title= +"Online Markdown Web Form">Dingus</a></li> +</ul> +<ul> +<li><a href="#overview">Overview</a> +<ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#html">Inline HTML</a></li> +<li><a href="#autoescape">Automatic Escaping for Special +Characters</a></li> +</ul> +</li> +<li><a href="#block">Block Elements</a> +<ul> +<li><a href="#p">Paragraphs and Line Breaks</a></li> +<li><a href="#header">Headers</a></li> +<li><a href="#blockquote">Blockquotes</a></li> +<li><a href="#list">Lists</a></li> +<li><a href="#precode">Code Blocks</a></li> +<li><a href="#hr">Horizontal Rules</a></li> +</ul> +</li> +<li><a href="#span">Span Elements</a> +<ul> +<li><a href="#link">Links</a></li> +<li><a href="#em">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#img">Images</a></li> +</ul> +</li> +<li><a href="#misc">Miscellaneous</a> +<ul> +<li><a href="#backslash">Backslash Escapes</a></li> +<li><a href="#autolink">Automatic Links</a></li> +</ul> +</li> +</ul> +<p><strong>Note:</strong> This document is itself written using +Markdown; you can <a href="/projects/markdown/syntax.text">see the +source for it by adding '.text' to the URL</a>.</p> +<hr> +<h2 id="overview">Overview</h2> +<h3 id="philosophy">Philosophy</h3> +<p>Markdown is intended to be as easy-to-read and easy-to-write as +is feasible.</p> +<p>Readability, however, is emphasized above all else. A +Markdown-formatted document should be publishable as-is, as plain +text, without looking like it's been marked up with tags or +formatting instructions. While Markdown's syntax has been +influenced by several existing text-to-HTML filters -- including +<a href= +"http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, +<a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href= +"http://textism.com/tools/textile/">Textile</a>, <a href= +"http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href= +"http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and +<a href="http://ettext.taint.org/doc/">EtText</a> -- the single +biggest source of inspiration for Markdown's syntax is the format +of plain text email.</p> +<p>To this end, Markdown's syntax is comprised entirely of +punctuation characters, which punctuation characters have been +carefully chosen so as to look like what they mean. E.g., asterisks +around a word actually look like *emphasis*. Markdown lists look +like, well, lists. Even blockquotes look like quoted passages of +text, assuming you've ever used email.</p> +<h3 id="html">Inline HTML</h3> +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes +it easier to insert HTML tags. In my opinion, HTML tags are already +easy to insert. The idea for Markdown is to make it easy to read, +write, and edit prose. HTML is a <em>publishing</em> format; +Markdown is a <em>writing</em> format. Thus, Markdown's formatting +syntax only addresses issues that can be conveyed in plain +text.</p> +<p>For any markup that is not covered by Markdown's syntax, you +simply use HTML itself. There's no need to preface it or delimit it +to indicate that you're switching from Markdown to HTML; you just +use the tags.</p> +<p>The only restrictions are that block-level HTML elements -- e.g. +<code><div></code>, <code><table></code>, +<code><pre></code>, <code><p></code>, etc. -- must be +separated from surrounding content by blank lines, and the start +and end tags of the block should not be indented with tabs or +spaces. Markdown is smart enough not to add extra (unwanted) +<code><p></code> tags around HTML block-level tags.</p> +<p>For example, to add an HTML table to a Markdown article:</p> +<pre> +<code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code> +</pre> +<p>Note that Markdown formatting syntax is not processed within +block-level HTML tags. E.g., you can't use Markdown-style +<code>*emphasis*</code> inside an HTML block.</p> +<p>Span-level HTML tags -- e.g. <code><span></code>, +<code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; +e.g. if you'd prefer to use HTML <code><a></code> or +<code><img></code> tags instead of Markdown's link or image +syntax, go right ahead.</p> +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> +processed within span-level tags.</p> +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> +<p>In HTML, there are two characters that demand special treatment: +<code><</code> and <code>&</code>. Left angle brackets are +used to start tags; ampersands are used to denote HTML entities. If +you want to use them as literal characters, you must escape them as +entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> +<p>Ampersands in particular are bedeviling for web writers. If you +want to write about 'AT&T', you need to write +'<code>AT&amp;T</code>'. You even need to escape ampersands +within URLs. Thus, if you want to link to:</p> +<pre> +<code>http://images.google.com/images?num=30&q=larry+bird +</code> +</pre> +<p>you need to encode the URL as:</p> +<pre> +<code>http://images.google.com/images?num=30&amp;q=larry+bird +</code> +</pre> +<p>in your anchor tag <code>href</code> attribute. Needless to say, +this is easy to forget, and is probably the single most common +source of HTML validation errors in otherwise well-marked-up web +sites.</p> +<p>Markdown allows you to use these characters naturally, taking +care of all the necessary escaping for you. If you use an ampersand +as part of an HTML entity, it remains unchanged; otherwise it will +be translated into <code>&amp;</code>.</p> +<p>So, if you want to include a copyright symbol in your article, +you can write:</p> +<pre> +<code>&copy; +</code> +</pre> +<p>and Markdown will leave it alone. But if you write:</p> +<pre> +<code>AT&T +</code> +</pre> +<p>Markdown will translate it to:</p> +<pre> +<code>AT&amp;T +</code> +</pre> +<p>Similarly, because Markdown supports <a href="#html">inline +HTML</a>, if you use angle brackets as delimiters for HTML tags, +Markdown will treat them as such. But if you write:</p> +<pre> +<code>4 < 5 +</code> +</pre> +<p>Markdown will translate it to:</p> +<pre> +<code>4 &lt; 5 +</code> +</pre> +<p>However, inside Markdown code spans and blocks, angle brackets +and ampersands are <em>always</em> encoded automatically. This +makes it easy to use Markdown to write about HTML code. (As opposed +to raw HTML, which is a terrible format for writing about HTML +syntax, because every single <code><</code> and +<code>&</code> in your example code needs to be escaped.)</p> +<hr> +<h2 id="block">Block Elements</h2> +<h3 id="p">Paragraphs and Line Breaks</h3> +<p>A paragraph is simply one or more consecutive lines of text, +separated by one or more blank lines. (A blank line is any line +that looks like a blank line -- a line containing nothing but +spaces or tabs is considered blank.) Normal paragraphs should not +be intended with spaces or tabs.</p> +<p>The implication of the "one or more consecutive lines of text" +rule is that Markdown supports "hard-wrapped" text paragraphs. This +differs significantly from most other text-to-HTML formatters +(including Movable Type's "Convert Line Breaks" option) which +translate every line break character in a paragraph into a +<code><br /></code> tag.</p> +<p>When you <em>do</em> want to insert a <code><br /></code> +break tag using Markdown, you end a line with two or more spaces, +then type return.</p> +<p>Yes, this takes a tad more effort to create a <code><br +/></code>, but a simplistic "every line break is a <code><br +/></code>" rule wouldn't work for Markdown. Markdown's +email-style <a href="#blockquote">blockquoting</a> and +multi-paragraph <a href="#list">list items</a> work best -- and +look better -- when you format them with hard breaks.</p> +<h3 id="header">Headers</h3> +<p>Markdown supports two styles of headers, <a href= +"http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and +<a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> +<p>Setext-style headers are "underlined" using equal signs (for +first-level headers) and dashes (for second-level headers). For +example:</p> +<pre> +<code>This is an H1 +============= + +This is an H2 +------------- +</code> +</pre> +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s +will work.</p> +<p>Atx-style headers use 1-6 hash characters at the start of the +line, corresponding to header levels 1-6. For example:</p> +<pre> +<code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code> +</pre> +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes used +to open the header. (The number of opening hashes determines the +header level.) :</p> +<pre> +<code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code> +</pre> +<h3 id="blockquote">Blockquotes</h3> +<p>Markdown uses email-style <code>></code> characters for +blockquoting. If you're familiar with quoting passages of text in +an email message, then you know how to create a blockquote in +Markdown. It looks best if you hard wrap the text and put a +<code>></code> before every line:</p> +<pre> +<code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>Markdown allows you to be lazy and only put the +<code>></code> before the first line of a hard-wrapped +paragraph:</p> +<pre> +<code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> +<pre> +<code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code> +</pre> +<p>Blockquotes can contain other Markdown elements, including +headers, lists, and code blocks:</p> +<pre> +<code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code> +</pre> +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> +<h3 id="list">Lists</h3> +<p>Markdown supports ordered (numbered) and unordered (bulleted) +lists.</p> +<p>Unordered lists use asterisks, pluses, and hyphens -- +interchangably -- as list markers:</p> +<pre> +<code>* Red +* Green +* Blue +</code> +</pre> +<p>is equivalent to:</p> +<pre> +<code>+ Red ++ Green ++ Blue +</code> +</pre> +<p>and:</p> +<pre> +<code>- Red +- Green +- Blue +</code> +</pre> +<p>Ordered lists use numbers followed by periods:</p> +<pre> +<code>1. Bird +2. McHale +3. Parish +</code> +</pre> +<p>It's important to note that the actual numbers you use to mark +the list have no effect on the HTML output Markdown produces. The +HTML Markdown produces from the above list is:</p> +<pre> +<code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code> +</pre> +<p>If you instead wrote the list in Markdown like this:</p> +<pre> +<code>1. Bird +1. McHale +1. Parish +</code> +</pre> +<p>or even:</p> +<pre> +<code>3. Bird +1. McHale +8. Parish +</code> +</pre> +<p>you'd get the exact same HTML output. The point is, if you want +to, you can use ordinal numbers in your ordered Markdown lists, so +that the numbers in your source match the numbers in your published +HTML. But if you want to be lazy, you don't have to.</p> +<p>If you do use lazy list numbering, however, you should still +start the list with the number 1. At some point in the future, +Markdown may support starting ordered lists at an arbitrary +number.</p> +<p>List markers typically start at the left margin, but may be +indented by up to three spaces. List markers must be followed by +one or more spaces or a tab.</p> +<p>To make lists look nice, you can wrap items with hanging +indents:</p> +<pre> +<code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>But if you want to be lazy, you don't have to:</p> +<pre> +<code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>If list items are separated by blank lines, Markdown will wrap +the items in <code><p></code> tags in the HTML output. For +example, this input:</p> +<pre> +<code>* Bird +* Magic +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code> +</pre> +<p>But this:</p> +<pre> +<code>* Bird + +* Magic +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code> +</pre> +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces or one +tab:</p> +<pre> +<code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code> +</pre> +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be lazy:</p> +<pre> +<code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code> +</pre> +<p>To put a blockquote within a list item, the blockquote's +<code>></code> delimiters need to be indented:</p> +<pre> +<code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code> +</pre> +<p>To put a code block within a list item, the code block needs to +be indented <em>twice</em> -- 8 spaces or two tabs:</p> +<pre> +<code>* A list item with a code block: + + <code goes here> +</code> +</pre> +<p>It's worth noting that it's possible to trigger an ordered list +by accident, by writing something like this:</p> +<pre> +<code>1986. What a great season. +</code> +</pre> +<p>In other words, a <em>number-period-space</em> sequence at the +beginning of a line. To avoid this, you can backslash-escape the +period:</p> +<pre> +<code>1986\. What a great season. +</code> +</pre> +<h3 id="precode">Code Blocks</h3> +<p>Pre-formatted code blocks are used for writing about programming +or markup source code. Rather than forming normal paragraphs, the +lines of a code block are interpreted literally. Markdown wraps a +code block in both <code><pre></code> and +<code><code></code> tags.</p> +<p>To produce a code block in Markdown, simply indent every line of +the block by at least 4 spaces or 1 tab. For example, given this +input:</p> +<pre> +<code>This is a normal paragraph: + + This is a code block. +</code> +</pre> +<p>Markdown will generate:</p> +<pre> +<code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code> +</pre> +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from +each line of the code block. For example, this:</p> +<pre> +<code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code> +</pre> +<p>A code block continues until it reaches a line that is not +indented (or the end of the article).</p> +<p>Within a code block, ampersands (<code>&</code>) and angle +brackets (<code><</code> and <code>></code>) are +automatically converted into HTML entities. This makes it very easy +to include example HTML source code using Markdown -- just paste it +and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> +<pre> +<code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code> +</pre> +<p>will turn into:</p> +<pre> +<code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code> +</pre> +<p>Regular Markdown syntax is not processed within code blocks. +E.g., asterisks are just literal asterisks within a code block. +This means it's also easy to use Markdown to write about Markdown's +own syntax.</p> +<h3 id="hr">Horizontal Rules</h3> +<p>You can produce a horizontal rule tag (<code><hr +/></code>) by placing three or more hyphens, asterisks, or +underscores on a line by themselves. If you wish, you may use +spaces between the hyphens or asterisks. Each of the following +lines will produce a horizontal rule:</p> +<pre> +<code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code> +</pre> +<hr> +<h2 id="span">Span Elements</h2> +<h3 id="link">Links</h3> +<p>Markdown supports two style of links: <em>inline</em> and +<em>reference</em>.</p> +<p>In both styles, the link text is delimited by [square +brackets].</p> +<p>To create an inline link, use a set of regular parentheses +immediately after the link text's closing square bracket. Inside +the parentheses, put the URL where you want the link to point, +along with an <em>optional</em> title for the link, surrounded in +quotes. For example:</p> +<pre> +<code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code> +</pre> +<p>Will produce:</p> +<pre> +<code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code> +</pre> +<p>If you're referring to a local resource on the same server, you +can use relative paths:</p> +<pre> +<code>See my [About](/about/) page for details. +</code> +</pre> +<p>Reference-style links use a second set of square brackets, +inside which you place a label of your choosing to identify the +link:</p> +<pre> +<code>This is [an example][id] reference-style link. +</code> +</pre> +<p>You can optionally use a space to separate the sets of +brackets:</p> +<pre> +<code>This is [an example] [id] reference-style link. +</code> +</pre> +<p>Then, anywhere in the document, you define your link label like +this, on a line by itself:</p> +<pre> +<code>[id]: http://example.com/ "Optional Title Here" +</code> +</pre> +<p>That is:</p> +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> +<p>The link URL may, optionally, be surrounded by angle +brackets:</p> +<pre> +<code>[id]: <http://example.com/> "Optional Title Here" +</code> +</pre> +<p>You can put the title attribute on the next line and use extra +spaces or tabs for padding, which tends to look better with longer +URLs:</p> +<pre> +<code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code> +</pre> +<p>Link definitions are only used for creating links during +Markdown processing, and are stripped from your document in the +HTML output.</p> +<p>Link definition names may constist of letters, numbers, spaces, +and punctuation -- but they are <em>not</em> case sensitive. E.g. +these two links:</p> +<pre> +<code>[link text][a] +[link text][A] +</code> +</pre> +<p>are equivalent.</p> +<p>The <em>implicit link name</em> shortcut allows you to omit the +name of the link, in which case the link text itself is used as the +name. Just use an empty set of square brackets -- e.g., to link the +word "Google" to the google.com web site, you could simply +write:</p> +<pre> +<code>[Google][] +</code> +</pre> +<p>And then define the link:</p> +<pre> +<code>[Google]: http://google.com/ +</code> +</pre> +<p>Because link names may contain spaces, this shortcut even works +for multiple words in the link text:</p> +<pre> +<code>Visit [Daring Fireball][] for more information. +</code> +</pre> +<p>And then define the link:</p> +<pre> +<code>[Daring Fireball]: http://daringfireball.net/ +</code> +</pre> +<p>Link definitions can be placed anywhere in your Markdown +document. I tend to put them immediately after each paragraph in +which they're used, but if you want, you can put them all at the +end of your document, sort of like footnotes.</p> +<p>Here's an example of reference links in action:</p> +<pre> +<code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code> +</pre> +<p>Using the implicit link name shortcut, you could instead +write:</p> +<pre> +<code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code> +</pre> +<p>Both of the above examples will produce the following HTML +output:</p> +<pre> +<code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code> +</pre> +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> +<pre> +<code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code> +</pre> +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw +HTML, it's 234 characters. In the raw HTML, there's more markup +than there is text.</p> +<p>With Markdown's reference-style links, a source document much +more closely resembles the final output, as rendered in a browser. +By allowing you to move the markup-related metadata out of the +paragraph, you can add links without interrupting the narrative +flow of your prose.</p> +<h3 id="em">Emphasis</h3> +<p>Markdown treats asterisks (<code>*</code>) and underscores +(<code>_</code>) as indicators of emphasis. Text wrapped with one +<code>*</code> or <code>_</code> will be wrapped with an HTML +<code><em></code> tag; double <code>*</code>'s or +<code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> +<pre> +<code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code> +</pre> +<p>will produce:</p> +<pre> +<code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code> +</pre> +<p>You can use whichever style you prefer; the lone restriction is +that the same character must be used to open and close an emphasis +span.</p> +<p>Emphasis can be used in the middle of a word:</p> +<pre> +<code>un*fucking*believable +</code> +</pre> +<p>But if you surround an <code>*</code> or <code>_</code> with +spaces, it'll be treated as a literal asterisk or underscore.</p> +<p>To produce a literal asterisk or underscore at a position where +it would otherwise be used as an emphasis delimiter, you can +backslash escape it:</p> +<pre> +<code>\*this text is surrounded by literal asterisks\* +</code> +</pre> +<h3 id="code">Code</h3> +<p>To indicate a span of code, wrap it with backtick quotes +(<code>`</code>). Unlike a pre-formatted code block, a code span +indicates code within a normal paragraph. For example:</p> +<pre> +<code>Use the `printf()` function. +</code> +</pre> +<p>will produce:</p> +<pre> +<code><p>Use the <code>printf()</code> function.</p> +</code> +</pre> +<p>To include a literal backtick character within a code span, you +can use multiple backticks as the opening and closing +delimiters:</p> +<pre> +<code>``There is a literal backtick (`) here.`` +</code> +</pre> +<p>which will produce this:</p> +<pre> +<code><p><code>There is a literal backtick (`) here.</code></p> +</code> +</pre> +<p>The backtick delimiters surrounding a code span may include +spaces -- one after the opening, one before the closing. This +allows you to place literal backtick characters at the beginning or +end of a code span:</p> +<pre> +<code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code> +</pre> +<p>will produce:</p> +<pre> +<code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code> +</pre> +<p>With a code span, ampersands and angle brackets are encoded as +HTML entities automatically, which makes it easy to include example +HTML tags. Markdown will turn this:</p> +<pre> +<code>Please don't use any `<blink>` tags. +</code> +</pre> +<p>into:</p> +<pre> +<code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code> +</pre> +<p>You can write this:</p> +<pre> +<code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code> +</pre> +<p>to produce:</p> +<pre> +<code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code> +</pre> +<h3 id="img">Images</h3> +<p>Admittedly, it's fairly difficult to devise a "natural" syntax +for placing images into a plain text document format.</p> +<p>Markdown uses an image syntax that is intended to resemble the +syntax for links, allowing for two styles: <em>inline</em> and +<em>reference</em>.</p> +<p>Inline image syntax looks like this:</p> +<pre> +<code> + + +</code> +</pre> +<p>That is:</p> +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the +<code>alt</code> attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in +double or single quotes.</li> +</ul> +<p>Reference-style image syntax looks like this:</p> +<pre> +<code>![Alt text][id] +</code> +</pre> +<p>Where "id" is the name of a defined image reference. Image +references are defined using syntax identical to link +references:</p> +<pre> +<code>[id]: url/to/image "Optional title attribute" +</code> +</pre> +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> +<hr> +<h2 id="misc">Miscellaneous</h2> +<h3 id="autolink">Automatic Links</h3> +<p>Markdown supports a shortcut style for creating "automatic" +links for URLs and email addresses: simply surround the URL or +email address with angle brackets. What this means is that if you +want to show the actual text of a URL or email address, and also +have it be a clickable link, you can do this:</p> +<pre> +<code><http://example.com/> +</code> +</pre> +<p>Markdown will turn this into:</p> +<pre> +<code><a href="http://example.com/">http://example.com/</a> +</code> +</pre> +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from +address-harvesting spambots. For example, Markdown will turn +this:</p> +<pre> +<code><address@example.com> +</code> +</pre> +<p>into something like this:</p> +<pre> +<code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code> +</pre> +<p>which will render in a browser as a clickable link to +"address@example.com".</p> +<p>(This sort of entity-encoding trick will indeed fool many, if +not most, address-harvesting bots, but it definitely won't fool all +of them. It's better than nothing, but an address published in this +way will probably eventually start receiving spam.)</p> +<h3 id="backslash">Backslash Escapes</h3> +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word +with literal asterisks (instead of an HTML <code><em></code> +tag), you can backslashes before the asterisks, like this:</p> +<pre> +<code>\*literal asterisks\* +</code> +</pre> +<p>Markdown provides backslash escapes for the following +characters:</p> +<pre> +<code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Nested blockquotes.html b/MarkdownTest/Tests_2004/Nested blockquotes.html new file mode 100644 index 0000000..d8ec7f8 --- /dev/null +++ b/MarkdownTest/Tests_2004/Nested blockquotes.html @@ -0,0 +1,9 @@ +<blockquote> + <p>foo</p> + + <blockquote> + <p>bar</p> + </blockquote> + + <p>foo</p> +</blockquote> diff --git a/MarkdownTest/Tests_2004/Nested blockquotes.text b/MarkdownTest/Tests_2004/Nested blockquotes.text new file mode 100644 index 0000000..ed3c624 --- /dev/null +++ b/MarkdownTest/Tests_2004/Nested blockquotes.text @@ -0,0 +1,5 @@ +> foo +> +> > bar +> +> foo diff --git a/MarkdownTest/Tests_2004/Nested blockquotes.text-out b/MarkdownTest/Tests_2004/Nested blockquotes.text-out new file mode 100644 index 0000000..291201e --- /dev/null +++ b/MarkdownTest/Tests_2004/Nested blockquotes.text-out @@ -0,0 +1,17 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<blockquote> +<p>foo</p> +<blockquote> +<p>bar</p> +</blockquote> +<p>foo</p> +</blockquote> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Nested blockquotes.text-res b/MarkdownTest/Tests_2004/Nested blockquotes.text-res new file mode 100644 index 0000000..291201e --- /dev/null +++ b/MarkdownTest/Tests_2004/Nested blockquotes.text-res @@ -0,0 +1,17 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<blockquote> +<p>foo</p> +<blockquote> +<p>bar</p> +</blockquote> +<p>foo</p> +</blockquote> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Ordered and unordered lists.html b/MarkdownTest/Tests_2004/Ordered and unordered lists.html new file mode 100644 index 0000000..ce85c3a --- /dev/null +++ b/MarkdownTest/Tests_2004/Ordered and unordered lists.html @@ -0,0 +1,137 @@ +<h2>Unordered</h2> + +<p>Asterisks tight:</p> + +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> + +<p>Asterisks loose:</p> + +<ul> +<li><p>asterisk 1</p></li> +<li><p>asterisk 2</p></li> +<li><p>asterisk 3</p></li> +</ul> + +<hr /> + +<p>Pluses tight:</p> + +<ul> +<li>Plus 1</li> +<li>Plus 2</li> +<li>Plus 3</li> +</ul> + +<p>Pluses loose:</p> + +<ul> +<li><p>Plus 1</p></li> +<li><p>Plus 2</p></li> +<li><p>Plus 3</p></li> +</ul> + +<hr /> + +<p>Minuses tight:</p> + +<ul> +<li>Minus 1</li> +<li>Minus 2</li> +<li>Minus 3</li> +</ul> + +<p>Minuses loose:</p> + +<ul> +<li><p>Minus 1</p></li> +<li><p>Minus 2</p></li> +<li><p>Minus 3</p></li> +</ul> + +<h2>Ordered</h2> + +<p>Tight:</p> + +<ol> +<li>First</li> +<li>Second</li> +<li>Third</li> +</ol> + +<p>and:</p> + +<ol> +<li>One</li> +<li>Two</li> +<li>Three</li> +</ol> + +<p>Loose using tabs:</p> + +<ol> +<li><p>First</p></li> +<li><p>Second</p></li> +<li><p>Third</p></li> +</ol> + +<p>and using spaces:</p> + +<ol> +<li><p>One</p></li> +<li><p>Two</p></li> +<li><p>Three</p></li> +</ol> + +<p>Multiple paragraphs:</p> + +<ol> +<li><p>Item 1, graf one.</p> + +<p>Item 2. graf two. The quick brown fox jumped over the lazy dog's +back.</p></li> +<li><p>Item 2.</p></li> +<li><p>Item 3.</p></li> +</ol> + +<h2>Nested</h2> + +<ul> +<li>Tab +<ul> +<li>Tab +<ul> +<li>Tab</li> +</ul></li> +</ul></li> +</ul> + +<p>Here's another:</p> + +<ol> +<li>First</li> +<li>Second: +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul></li> +<li>Third</li> +</ol> + +<p>Same thing but with paragraphs:</p> + +<ol> +<li><p>First</p></li> +<li><p>Second:</p> + +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul></li> +<li><p>Third</p></li> +</ol> diff --git a/MarkdownTest/Tests_2004/Ordered and unordered lists.text b/MarkdownTest/Tests_2004/Ordered and unordered lists.text new file mode 100644 index 0000000..621db58 --- /dev/null +++ b/MarkdownTest/Tests_2004/Ordered and unordered lists.text @@ -0,0 +1,122 @@ +## Unordered + +Asterisks tight: + +* asterisk 1 +* asterisk 2 +* asterisk 3 + + +Asterisks loose: + +* asterisk 1 + +* asterisk 2 + +* asterisk 3 + +* * * + +Pluses tight: + ++ Plus 1 ++ Plus 2 ++ Plus 3 + + +Pluses loose: + ++ Plus 1 + ++ Plus 2 + ++ Plus 3 + +* * * + + +Minuses tight: + +- Minus 1 +- Minus 2 +- Minus 3 + + +Minuses loose: + +- Minus 1 + +- Minus 2 + +- Minus 3 + + +## Ordered + +Tight: + +1. First +2. Second +3. Third + +and: + +1. One +2. Two +3. Three + + +Loose using tabs: + +1. First + +2. Second + +3. Third + +and using spaces: + +1. One + +2. Two + +3. Three + +Multiple paragraphs: + +1. Item 1, graf one. + + Item 2. graf two. The quick brown fox jumped over the lazy dog's + back. + +2. Item 2. + +3. Item 3. + + + +## Nested + +* Tab + * Tab + * Tab + +Here's another: + +1. First +2. Second: + * Fee + * Fie + * Foe +3. Third + +Same thing but with paragraphs: + +1. First + +2. Second: + * Fee + * Fie + * Foe + +3. Third diff --git a/MarkdownTest/Tests_2004/Ordered and unordered lists.text-out b/MarkdownTest/Tests_2004/Ordered and unordered lists.text-out new file mode 100644 index 0000000..5e19e71 --- /dev/null +++ b/MarkdownTest/Tests_2004/Ordered and unordered lists.text-out @@ -0,0 +1,159 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h2>Unordered</h2> +<p>Asterisks tight:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +<p>Asterisks loose:</p> +<ul> +<li> +<p>asterisk 1</p> +</li> +<li> +<p>asterisk 2</p> +</li> +<li> +<p>asterisk 3</p> +</li> +</ul> +<hr> +<p>Pluses tight:</p> +<ul> +<li>Plus 1</li> +<li>Plus 2</li> +<li>Plus 3</li> +</ul> +<p>Pluses loose:</p> +<ul> +<li> +<p>Plus 1</p> +</li> +<li> +<p>Plus 2</p> +</li> +<li> +<p>Plus 3</p> +</li> +</ul> +<hr> +<p>Minuses tight:</p> +<ul> +<li>Minus 1</li> +<li>Minus 2</li> +<li>Minus 3</li> +</ul> +<p>Minuses loose:</p> +<ul> +<li> +<p>Minus 1</p> +</li> +<li> +<p>Minus 2</p> +</li> +<li> +<p>Minus 3</p> +</li> +</ul> +<h2>Ordered</h2> +<p>Tight:</p> +<ol> +<li>First</li> +<li>Second</li> +<li>Third</li> +</ol> +<p>and:</p> +<ol> +<li>One</li> +<li>Two</li> +<li>Three</li> +</ol> +<p>Loose using tabs:</p> +<ol> +<li> +<p>First</p> +</li> +<li> +<p>Second</p> +</li> +<li> +<p>Third</p> +</li> +</ol> +<p>and using spaces:</p> +<ol> +<li> +<p>One</p> +</li> +<li> +<p>Two</p> +</li> +<li> +<p>Three</p> +</li> +</ol> +<p>Multiple paragraphs:</p> +<ol> +<li> +<p>Item 1, graf one.</p> +<p>Item 2. graf two. The quick brown fox jumped over the lazy dog's +back.</p> +</li> +<li> +<p>Item 2.</p> +</li> +<li> +<p>Item 3.</p> +</li> +</ol> +<h2>Nested</h2> +<ul> +<li>Tab +<ul> +<li>Tab +<ul> +<li>Tab</li> +</ul> +</li> +</ul> +</li> +</ul> +<p>Here's another:</p> +<ol> +<li>First</li> +<li>Second: +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul> +</li> +<li>Third</li> +</ol> +<p>Same thing but with paragraphs:</p> +<ol> +<li> +<p>First</p> +</li> +<li> +<p>Second:</p> +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul> +</li> +<li> +<p>Third</p> +</li> +</ol> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Ordered and unordered lists.text-res b/MarkdownTest/Tests_2004/Ordered and unordered lists.text-res new file mode 100644 index 0000000..5e19e71 --- /dev/null +++ b/MarkdownTest/Tests_2004/Ordered and unordered lists.text-res @@ -0,0 +1,159 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h2>Unordered</h2> +<p>Asterisks tight:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +<p>Asterisks loose:</p> +<ul> +<li> +<p>asterisk 1</p> +</li> +<li> +<p>asterisk 2</p> +</li> +<li> +<p>asterisk 3</p> +</li> +</ul> +<hr> +<p>Pluses tight:</p> +<ul> +<li>Plus 1</li> +<li>Plus 2</li> +<li>Plus 3</li> +</ul> +<p>Pluses loose:</p> +<ul> +<li> +<p>Plus 1</p> +</li> +<li> +<p>Plus 2</p> +</li> +<li> +<p>Plus 3</p> +</li> +</ul> +<hr> +<p>Minuses tight:</p> +<ul> +<li>Minus 1</li> +<li>Minus 2</li> +<li>Minus 3</li> +</ul> +<p>Minuses loose:</p> +<ul> +<li> +<p>Minus 1</p> +</li> +<li> +<p>Minus 2</p> +</li> +<li> +<p>Minus 3</p> +</li> +</ul> +<h2>Ordered</h2> +<p>Tight:</p> +<ol> +<li>First</li> +<li>Second</li> +<li>Third</li> +</ol> +<p>and:</p> +<ol> +<li>One</li> +<li>Two</li> +<li>Three</li> +</ol> +<p>Loose using tabs:</p> +<ol> +<li> +<p>First</p> +</li> +<li> +<p>Second</p> +</li> +<li> +<p>Third</p> +</li> +</ol> +<p>and using spaces:</p> +<ol> +<li> +<p>One</p> +</li> +<li> +<p>Two</p> +</li> +<li> +<p>Three</p> +</li> +</ol> +<p>Multiple paragraphs:</p> +<ol> +<li> +<p>Item 1, graf one.</p> +<p>Item 2. graf two. The quick brown fox jumped over the lazy dog's +back.</p> +</li> +<li> +<p>Item 2.</p> +</li> +<li> +<p>Item 3.</p> +</li> +</ol> +<h2>Nested</h2> +<ul> +<li>Tab +<ul> +<li>Tab +<ul> +<li>Tab</li> +</ul> +</li> +</ul> +</li> +</ul> +<p>Here's another:</p> +<ol> +<li>First</li> +<li>Second: +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul> +</li> +<li>Third</li> +</ol> +<p>Same thing but with paragraphs:</p> +<ol> +<li> +<p>First</p> +</li> +<li> +<p>Second:</p> +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul> +</li> +<li> +<p>Third</p> +</li> +</ol> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Strong and em together.html b/MarkdownTest/Tests_2004/Strong and em together.html new file mode 100644 index 0000000..71ec78c --- /dev/null +++ b/MarkdownTest/Tests_2004/Strong and em together.html @@ -0,0 +1,7 @@ +<p><strong><em>This is strong and em.</em></strong></p> + +<p>So is <strong><em>this</em></strong> word.</p> + +<p><strong><em>This is strong and em.</em></strong></p> + +<p>So is <strong><em>this</em></strong> word.</p> diff --git a/MarkdownTest/Tests_2004/Strong and em together.text b/MarkdownTest/Tests_2004/Strong and em together.text new file mode 100644 index 0000000..95ee690 --- /dev/null +++ b/MarkdownTest/Tests_2004/Strong and em together.text @@ -0,0 +1,7 @@ +***This is strong and em.*** + +So is ***this*** word. + +___This is strong and em.___ + +So is ___this___ word. diff --git a/MarkdownTest/Tests_2004/Strong and em together.text-out b/MarkdownTest/Tests_2004/Strong and em together.text-out new file mode 100644 index 0000000..b596c19 --- /dev/null +++ b/MarkdownTest/Tests_2004/Strong and em together.text-out @@ -0,0 +1,14 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Strong and em together.text-res b/MarkdownTest/Tests_2004/Strong and em together.text-res new file mode 100644 index 0000000..b596c19 --- /dev/null +++ b/MarkdownTest/Tests_2004/Strong and em together.text-res @@ -0,0 +1,14 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Tabs.html b/MarkdownTest/Tests_2004/Tabs.html new file mode 100644 index 0000000..3301ba8 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tabs.html @@ -0,0 +1,25 @@ +<ul> +<li><p>this is a list item +indented with tabs</p></li> +<li><p>this is a list item +indented with spaces</p></li> +</ul> + +<p>Code:</p> + +<pre><code>this code block is indented by one tab +</code></pre> + +<p>And:</p> + +<pre><code> this code block is indented by two tabs +</code></pre> + +<p>And:</p> + +<pre><code>+ this is an example list item + indented with tabs + ++ this is an example list item + indented with spaces +</code></pre> diff --git a/MarkdownTest/Tests_2004/Tabs.text b/MarkdownTest/Tests_2004/Tabs.text new file mode 100644 index 0000000..589d113 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tabs.text @@ -0,0 +1,21 @@ ++ this is a list item + indented with tabs + ++ this is a list item + indented with spaces + +Code: + + this code block is indented by one tab + +And: + + this code block is indented by two tabs + +And: + + + this is an example list item + indented with tabs + + + this is an example list item + indented with spaces diff --git a/MarkdownTest/Tests_2004/Tabs.text-out b/MarkdownTest/Tests_2004/Tabs.text-out new file mode 100644 index 0000000..0cd92b1 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tabs.text-out @@ -0,0 +1,37 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<ul> +<li> +<p>this is a list item indented with tabs</p> +</li> +<li> +<p>this is a list item indented with spaces</p> +</li> +</ul> +<p>Code:</p> +<pre> +<code>this code block is indented by one tab +</code> +</pre> +<p>And:</p> +<pre> +<code> this code block is indented by two tabs +</code> +</pre> +<p>And:</p> +<pre> +<code>+ this is an example list item + indented with tabs + ++ this is an example list item + indented with spaces +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Tabs.text-res b/MarkdownTest/Tests_2004/Tabs.text-res new file mode 100644 index 0000000..0cd92b1 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tabs.text-res @@ -0,0 +1,37 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<ul> +<li> +<p>this is a list item indented with tabs</p> +</li> +<li> +<p>this is a list item indented with spaces</p> +</li> +</ul> +<p>Code:</p> +<pre> +<code>this code block is indented by one tab +</code> +</pre> +<p>And:</p> +<pre> +<code> this code block is indented by two tabs +</code> +</pre> +<p>And:</p> +<pre> +<code>+ this is an example list item + indented with tabs + ++ this is an example list item + indented with spaces +</code> +</pre> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Tidyness.html b/MarkdownTest/Tests_2004/Tidyness.html new file mode 100644 index 0000000..f2a8ce7 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tidyness.html @@ -0,0 +1,8 @@ +<blockquote> +<p>A list within a blockquote:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +</blockquote> diff --git a/MarkdownTest/Tests_2004/Tidyness.text b/MarkdownTest/Tests_2004/Tidyness.text new file mode 100644 index 0000000..5f18b8d --- /dev/null +++ b/MarkdownTest/Tests_2004/Tidyness.text @@ -0,0 +1,5 @@ +> A list within a blockquote: +> +> * asterisk 1 +> * asterisk 2 +> * asterisk 3 diff --git a/MarkdownTest/Tests_2004/Tidyness.text-out b/MarkdownTest/Tests_2004/Tidyness.text-out new file mode 100644 index 0000000..ebae4c4 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tidyness.text-out @@ -0,0 +1,18 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<blockquote> +<p>A list within a blockquote:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +</blockquote> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Tidyness.text-res b/MarkdownTest/Tests_2004/Tidyness.text-res new file mode 100644 index 0000000..ebae4c4 --- /dev/null +++ b/MarkdownTest/Tests_2004/Tidyness.text-res @@ -0,0 +1,18 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<blockquote> +<p>A list within a blockquote:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +</blockquote> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Attributes.html b/MarkdownTest/Tests_2004/Yuri-Attributes.html new file mode 100644 index 0000000..057da2f --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Attributes.html @@ -0,0 +1,28 @@ + + +<h1 id="lorem"> Lorem ipsum </h1> +<p>Dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor + incididunt ut labore et dolore magna aliqua. +</p> +<ul> + <li><p class="first_item">Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris + nisi ut aliquip ex ea commodo consequat. +</p> + + </li> + + <li><p>Duis aute irure dolor in reprehenderit in voluptate velit esse + cillum dolore eu fugiat nulla pariatur2. Excepteur sint occaecat + cupidatat non proident, sunt in culpa qui officia deserunt mollit + anim id est laborum. +</p> + + </li> +</ul> +<p>Duis aute <strong type="term">irure</strong> dolor in reprehenderit in voluptate + velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint + occaecat cupidatat non proident, sunt in culpa qui officia deserunt + mollit anim id est laborum. +</p> + + diff --git a/MarkdownTest/Tests_2004/Yuri-Attributes.text b/MarkdownTest/Tests_2004/Yuri-Attributes.text new file mode 100644 index 0000000..8ee512d --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Attributes.text @@ -0,0 +1,19 @@ + +Lorem ipsum {@id=lorem} +================================= + +Dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor +incididunt ut labore et dolore magna aliqua. + +* Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris + nisi ut aliquip ex ea commodo consequat.{@class=first_item} + +* Duis aute irure dolor in reprehenderit in voluptate velit esse + cillum dolore eu fugiat nulla pariatur2. Excepteur sint occaecat + cupidatat non proident, sunt in culpa qui officia deserunt mollit + anim id est laborum. + +Duis aute **irure{@type=term}** dolor in reprehenderit in voluptate +velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint +occaecat cupidatat non proident, sunt in culpa qui officia deserunt +mollit anim id est laborum. diff --git a/MarkdownTest/Tests_2004/Yuri-Attributes.text-out b/MarkdownTest/Tests_2004/Yuri-Attributes.text-out new file mode 100644 index 0000000..38fd233 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Attributes.text-out @@ -0,0 +1,29 @@ +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h1 id="lorem">Lorem ipsum</h1> +<p>Dolor sit amet, consectetur adipisicing elit, sed do eiusmod +tempor incididunt ut labore et dolore magna aliqua.</p> +<ul> +<li> +<p class="first_item">Ut enim ad minim veniam, quis nostrud +exercitation ullamco laboris nisi ut aliquip ex ea commodo +consequat.</p> +</li> +<li> +<p>Duis aute irure dolor in reprehenderit in voluptate velit esse +cillum dolore eu fugiat nulla pariatur2. Excepteur sint occaecat +cupidatat non proident, sunt in culpa qui officia deserunt mollit +anim id est laborum.</p> +</li> +</ul> +<p>Duis aute <strong type="term">irure</strong> dolor in +reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla +pariatur. Excepteur sint occaecat cupidatat non proident, sunt in +culpa qui officia deserunt mollit anim id est laborum.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Attributes.text-res b/MarkdownTest/Tests_2004/Yuri-Attributes.text-res new file mode 100644 index 0000000..38fd233 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Attributes.text-res @@ -0,0 +1,29 @@ +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h1 id="lorem">Lorem ipsum</h1> +<p>Dolor sit amet, consectetur adipisicing elit, sed do eiusmod +tempor incididunt ut labore et dolore magna aliqua.</p> +<ul> +<li> +<p class="first_item">Ut enim ad minim veniam, quis nostrud +exercitation ullamco laboris nisi ut aliquip ex ea commodo +consequat.</p> +</li> +<li> +<p>Duis aute irure dolor in reprehenderit in voluptate velit esse +cillum dolore eu fugiat nulla pariatur2. Excepteur sint occaecat +cupidatat non proident, sunt in culpa qui officia deserunt mollit +anim id est laborum.</p> +</li> +</ul> +<p>Duis aute <strong type="term">irure</strong> dolor in +reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla +pariatur. Excepteur sint occaecat cupidatat non proident, sunt in +culpa qui officia deserunt mollit anim id est laborum.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Attributes.text~ b/MarkdownTest/Tests_2004/Yuri-Attributes.text~ new file mode 100644 index 0000000..ba8fecd --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Attributes.text~ @@ -0,0 +1,24 @@ + +Lorem ipsum {@id=lorem} +================================= + +Dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor +incididunt ut labore et dolore magna aliqua1. Ut enim ad minim veniam, +quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea +commodo consequat. Duis aute irure dolor in reprehenderit in voluptate +velit esse cillum dolore eu fugiat nulla pariatur2. Excepteur sint +occaecat cupidatat non proident, sunt in culpa qui officia deserunt +mollit anim id est laborum. + + + + * Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore3 magna aliqua. + +Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. + + 1. Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo.%Gâ©%@ + 2. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. + + Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. %Gâ©%@ + 3. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. %Gâ©%@ + diff --git a/MarkdownTest/Tests_2004/Yuri-Email.html b/MarkdownTest/Tests_2004/Yuri-Email.html new file mode 100644 index 0000000..bf1d149 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Email.html @@ -0,0 +1,18 @@ + +<p>Lorem ipsum <a href="mailto:yuri@domain.org">yuri@domain.org</a>, etc. +</p> +<ul> + <li> + An email address in a list + </li> + + <li> + <a href="mailto:yuri@domain.org">yuri@domain.org</a> + </li> + + <li> + Another item. + </li> +</ul> + + diff --git a/MarkdownTest/Tests_2004/Yuri-Email.text b/MarkdownTest/Tests_2004/Yuri-Email.text new file mode 100644 index 0000000..8f9c779 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Email.text @@ -0,0 +1,7 @@ +Lorem ipsum <yuri@domain.org>, etc. + +* An email address in a list +* <yuri@domain.org> +* Another item. + + diff --git a/MarkdownTest/Tests_2004/Yuri-Email.text-out b/MarkdownTest/Tests_2004/Yuri-Email.text-out new file mode 100644 index 0000000..2fc9c74 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Email.text-out @@ -0,0 +1,17 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Lorem ipsum <a href= +"mailto:yuri@domain.org">yuri@domain.org</a>, etc.</p> +<ul> +<li>An email address in a list</li> +<li><a href="mailto:yuri@domain.org">yuri@domain.org</a></li> +<li>Another item.</li> +</ul> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Email.text-res b/MarkdownTest/Tests_2004/Yuri-Email.text-res new file mode 100644 index 0000000..2fc9c74 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Email.text-res @@ -0,0 +1,17 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Lorem ipsum <a href= +"mailto:yuri@domain.org">yuri@domain.org</a>, etc.</p> +<ul> +<li>An email address in a list</li> +<li><a href="mailto:yuri@domain.org">yuri@domain.org</a></li> +<li>Another item.</li> +</ul> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Footnotes.html b/MarkdownTest/Tests_2004/Yuri-Footnotes.html new file mode 100644 index 0000000..cadb040 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Footnotes.html @@ -0,0 +1,46 @@ + +<p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod + tempor incididunt ut labore et dolore magna aliqua<sup><a href="#fn1-903162597" id="fnr1-903162597">1</a></sup>. Ut enim ad minim + veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea + commodo consequat. Duis aute irure dolor in reprehenderit in voluptate + velit esse cillum dolore eu fugiat nulla pariatur<sup><a href="#fn2-903162597" id="fnr2-903162597">2</a></sup>. Excepteur sint + occaecat cupidatat non proident, sunt in culpa qui officia deserunt + mollit anim id est laborum. +</p> +<ul> + <li> + Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do + eiusmod tempor incididunt ut labore et dolore<sup><a href="#fn3-903162597" id="fnr3-903162597">3</a></sup> magna aliqua. + </li> +</ul> +<p>Duis aute irure dolor in reprehenderit in voluptate + velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint + occaecat cupidatat non proident, sunt in culpa qui officia deserunt + mollit anim id est laborum. +</p> + +<div class="footnote"><hr/><ol> + <li id="fn1-903162597"> + Sed ut perspiciatis unde omnis iste natus error sit voluptatem + accusantium doloremque laudantium, totam rem aperiam, eaque ipsa + quae ab illo inventore veritatis et quasi architecto beatae vitae + dicta sunt explicabo.<a href="#fnr1-903162597" class="footnoteBackLink" title="Jump back to footnote 1 in the text">↩</a> + </li> + + <li id="fn2-903162597"> + Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit + aut fugit, sed quia consequuntur magni dolores eos qui ratione + voluptatem sequi nesciunt. <p> Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, + consectetur, adipisci velit, sed quia non numquam eius modi + tempora incidunt ut labore et dolore magnam aliquam quaerat + voluptatem. <a href="#fnr2-903162597" class="footnoteBackLink" title="Jump back to footnote 1 in the text">↩</a> +</p> + + </li> + + <li id="fn3-903162597"> + Ut enim ad minim veniam, quis nostrud exercitation ullamco + laboris nisi ut aliquip ex ea commodo consequat. <a href="#fnr3-903162597" class="footnoteBackLink" title="Jump back to footnote 1 in the text">↩</a> + </li> +</ol> +</div> diff --git a/MarkdownTest/Tests_2004/Yuri-Footnotes.text b/MarkdownTest/Tests_2004/Yuri-Footnotes.text new file mode 100644 index 0000000..16fe402 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Footnotes.text @@ -0,0 +1,32 @@ +Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod +tempor incididunt ut labore et dolore magna aliqua[^2]. Ut enim ad minim +veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea +commodo consequat. Duis aute irure dolor in reprehenderit in voluptate +velit esse cillum dolore eu fugiat nulla pariatur[^1]. Excepteur sint +occaecat cupidatat non proident, sunt in culpa qui officia deserunt +mollit anim id est laborum. + +[^1]: Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit + aut fugit, sed quia consequuntur magni dolores eos qui ratione + voluptatem sequi nesciunt. + + Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, + consectetur, adipisci velit, sed quia non numquam eius modi + tempora incidunt ut labore et dolore magnam aliquam quaerat + voluptatem. + +[^2]: Sed ut perspiciatis unde omnis iste natus error sit voluptatem + accusantium doloremque laudantium, totam rem aperiam, eaque ipsa + quae ab illo inventore veritatis et quasi architecto beatae vitae + dicta sunt explicabo. + +* Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do + eiusmod tempor incididunt ut labore et dolore[^foo] magna aliqua. + +[^foo]: Ut enim ad minim veniam, quis nostrud exercitation ullamco + laboris nisi ut aliquip ex ea commodo consequat. + +Duis aute irure dolor in reprehenderit in voluptate +velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint +occaecat cupidatat non proident, sunt in culpa qui officia deserunt +mollit anim id est laborum. diff --git a/MarkdownTest/Tests_2004/Yuri-Footnotes.text-out b/MarkdownTest/Tests_2004/Yuri-Footnotes.text-out new file mode 100644 index 0000000..b934c10 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Footnotes.text-out @@ -0,0 +1,42 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do +eiusmod tempor incididunt ut labore et dolore magna aliqua[^2]. Ut +enim ad minim veniam, quis nostrud exercitation ullamco laboris +nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in +reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla +pariatur[^1]. Excepteur sint occaecat cupidatat non proident, sunt +in culpa qui officia deserunt mollit anim id est laborum.</p> +<p>[^1]: Nemo enim ipsam voluptatem quia voluptas sit aspernatur +aut odit aut fugit, sed quia consequuntur magni dolores eos qui +ratione voluptatem sequi nesciunt.</p> +<pre> +<code> Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, + consectetur, adipisci velit, sed quia non numquam eius modi + tempora incidunt ut labore et dolore magnam aliquam quaerat + voluptatem. +</code> +</pre> +<p>[^2]: Sed ut perspiciatis unde omnis iste natus error sit +voluptatem accusantium doloremque laudantium, totam rem aperiam, +eaque ipsa quae ab illo inventore veritatis et quasi architecto +beatae vitae dicta sunt explicabo.</p> +<ul> +<li>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed +do eiusmod tempor incididunt ut labore et dolore[^foo] magna +aliqua.</li> +</ul> +<p>[^foo]: Ut enim ad minim veniam, quis nostrud exercitation +ullamco laboris nisi ut aliquip ex ea commodo consequat.</p> +<p>Duis aute irure dolor in reprehenderit in voluptate velit esse +cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat +cupidatat non proident, sunt in culpa qui officia deserunt mollit +anim id est laborum.</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Footnotes.text-res b/MarkdownTest/Tests_2004/Yuri-Footnotes.text-res new file mode 100644 index 0000000..5752e27 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Footnotes.text-res @@ -0,0 +1,55 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do +eiusmod tempor incididunt ut labore et dolore magna +aliqua<sup><a href="#fn1-903162597" id="fnr1-903162597" name= +"fnr1-903162597">1</a></sup>. Ut enim ad minim veniam, quis nostrud +exercitation ullamco laboris nisi ut aliquip ex ea commodo +consequat. Duis aute irure dolor in reprehenderit in voluptate +velit esse cillum dolore eu fugiat nulla pariatur<sup><a href= +"#fn2-903162597" id="fnr2-903162597" name= +"fnr2-903162597">2</a></sup>. Excepteur sint occaecat cupidatat non +proident, sunt in culpa qui officia deserunt mollit anim id est +laborum.</p> +<ul> +<li>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed +do eiusmod tempor incididunt ut labore et dolore<sup><a href= +"#fn3-903162597" id="fnr3-903162597" name= +"fnr3-903162597">3</a></sup> magna aliqua.</li> +</ul> +<p>Duis aute irure dolor in reprehenderit in voluptate velit esse +cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat +cupidatat non proident, sunt in culpa qui officia deserunt mollit +anim id est laborum.</p> +<div class="footnote"> +<hr> +<ol> +<li id="fn1-903162597">Sed ut perspiciatis unde omnis iste natus +error sit voluptatem accusantium doloremque laudantium, totam rem +aperiam, eaque ipsa quae ab illo inventore veritatis et quasi +architecto beatae vitae dicta sunt explicabo.<a href= +"#fnr1-903162597" class="footnoteBackLink" title= +"Jump back to footnote 1 in the text">↩</a></li> +<li id="fn2-903162597">Nemo enim ipsam voluptatem quia voluptas sit +aspernatur aut odit aut fugit, sed quia consequuntur magni dolores +eos qui ratione voluptatem sequi nesciunt. +<p>Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, +consectetur, adipisci velit, sed quia non numquam eius modi tempora +incidunt ut labore et dolore magnam aliquam quaerat voluptatem. +<a href="#fnr2-903162597" class="footnoteBackLink" title= +"Jump back to footnote 1 in the text">↩</a></p> +</li> +<li id="fn3-903162597">Ut enim ad minim veniam, quis nostrud +exercitation ullamco laboris nisi ut aliquip ex ea commodo +consequat. <a href="#fnr3-903162597" class="footnoteBackLink" +title="Jump back to footnote 1 in the text">↩</a></li> +</ol> +</div> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.html b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.html new file mode 100644 index 0000000..6afc56e --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.html @@ -0,0 +1,15 @@ +<h2>A plain header</h2> + +<p>Let's first have a plain header</p> + +<h1>An underlined header</h1> + +<p>(That's also useful)</p> + +<h1>A header with a <a href="http://www.link.com">link</a></h1> + +<p>First with a hash</p> + +<h2>Another with a <a href="http://www.link.com/">link</a></h2> + +<p>This time underlined</p> diff --git a/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text new file mode 100644 index 0000000..d06a9e1 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text @@ -0,0 +1,18 @@ +## A plain header + +Let's first have a plain header + +An underlined header +==================== + +(That's also useful) + +# A header with a [link](http://www.link.com) + +First with a hash + +Another with a [link][a] +------------------------ +This time underlined + +[a]: http://www.link.com/ diff --git a/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text-out b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text-out new file mode 100644 index 0000000..1c5cf77 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text-out @@ -0,0 +1,18 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h2>A plain header</h2> +<p>Let's first have a plain header</p> +<h1>An underlined header</h1> +<p>(That's also useful)</p> +<h1>A header with a <a href="http://www.link.com">link</a></h1> +<p>First with a hash</p> +<h2>Another with a <a href="http://www.link.com/">link</a></h2> +<p>This time underlined</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text-res b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text-res new file mode 100644 index 0000000..1c5cf77 --- /dev/null +++ b/MarkdownTest/Tests_2004/Yuri-Links-in-Headers.text-res @@ -0,0 +1,18 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<html> +<head> +<meta name="generator" content= +"HTML Tidy for Linux/x86 (vers 1 September 2005), see www.w3.org"> +<title></title> +</head> +<body> +<h2>A plain header</h2> +<p>Let's first have a plain header</p> +<h1>An underlined header</h1> +<p>(That's also useful)</p> +<h1>A header with a <a href="http://www.link.com">link</a></h1> +<p>First with a hash</p> +<h2>Another with a <a href="http://www.link.com/">link</a></h2> +<p>This time underlined</p> +</body> +</html> diff --git a/MarkdownTest/Tests_2007/Amps and angle encoding.html b/MarkdownTest/Tests_2007/Amps and angle encoding.html new file mode 100644 index 0000000..9606860 --- /dev/null +++ b/MarkdownTest/Tests_2007/Amps and angle encoding.html @@ -0,0 +1,17 @@ +<p>AT&T has an ampersand in their name.</p> + +<p>AT&T is another way to write it.</p> + +<p>This & that.</p> + +<p>4 < 5.</p> + +<p>6 > 5.</p> + +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link</a> with an ampersand in the URL.</p> + +<p>Here's a link with an amersand in the link text: <a href="http://att.com/" title="AT&T">AT&T</a>.</p> + +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> + +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> diff --git a/MarkdownTest/Tests_2007/Amps and angle encoding.text b/MarkdownTest/Tests_2007/Amps and angle encoding.text new file mode 100644 index 0000000..0e9527f --- /dev/null +++ b/MarkdownTest/Tests_2007/Amps and angle encoding.text @@ -0,0 +1,21 @@ +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Here's a [link] [1] with an ampersand in the URL. + +Here's a link with an amersand in the link text: [AT&T] [2]. + +Here's an inline [link](/script?foo=1&bar=2). + +Here's an inline [link](</script?foo=1&bar=2>). + + +[1]: http://example.com/?foo=1&bar=2 +[2]: http://att.com/ "AT&T"
\ No newline at end of file diff --git a/MarkdownTest/Tests_2007/Auto links.html b/MarkdownTest/Tests_2007/Auto links.html new file mode 100644 index 0000000..f8df985 --- /dev/null +++ b/MarkdownTest/Tests_2007/Auto links.html @@ -0,0 +1,18 @@ +<p>Link: <a href="http://example.com/">http://example.com/</a>.</p> + +<p>With an ampersand: <a href="http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</a></p> + +<ul> +<li>In a list?</li> +<li><a href="http://example.com/">http://example.com/</a></li> +<li>It should.</li> +</ul> + +<blockquote> + <p>Blockquoted: <a href="http://example.com/">http://example.com/</a></p> +</blockquote> + +<p>Auto-links should not occur here: <code><http://example.com/></code></p> + +<pre><code>or here: <http://example.com/> +</code></pre> diff --git a/MarkdownTest/Tests_2007/Auto links.text b/MarkdownTest/Tests_2007/Auto links.text new file mode 100644 index 0000000..abbc488 --- /dev/null +++ b/MarkdownTest/Tests_2007/Auto links.text @@ -0,0 +1,13 @@ +Link: <http://example.com/>. + +With an ampersand: <http://example.com/?foo=1&bar=2> + +* In a list? +* <http://example.com/> +* It should. + +> Blockquoted: <http://example.com/> + +Auto-links should not occur here: `<http://example.com/>` + + or here: <http://example.com/>
\ No newline at end of file diff --git a/MarkdownTest/Tests_2007/Backslash escapes.html b/MarkdownTest/Tests_2007/Backslash escapes.html new file mode 100644 index 0000000..29870da --- /dev/null +++ b/MarkdownTest/Tests_2007/Backslash escapes.html @@ -0,0 +1,118 @@ +<p>These should all get escaped:</p> + +<p>Backslash: \</p> + +<p>Backtick: `</p> + +<p>Asterisk: *</p> + +<p>Underscore: _</p> + +<p>Left brace: {</p> + +<p>Right brace: }</p> + +<p>Left bracket: [</p> + +<p>Right bracket: ]</p> + +<p>Left paren: (</p> + +<p>Right paren: )</p> + +<p>Greater-than: ></p> + +<p>Hash: #</p> + +<p>Period: .</p> + +<p>Bang: !</p> + +<p>Plus: +</p> + +<p>Minus: -</p> + +<p>These should not, because they occur within a code block:</p> + +<pre><code>Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- +</code></pre> + +<p>Nor should these, which occur in code spans:</p> + +<p>Backslash: <code>\\</code></p> + +<p>Backtick: <code>\`</code></p> + +<p>Asterisk: <code>\*</code></p> + +<p>Underscore: <code>\_</code></p> + +<p>Left brace: <code>\{</code></p> + +<p>Right brace: <code>\}</code></p> + +<p>Left bracket: <code>\[</code></p> + +<p>Right bracket: <code>\]</code></p> + +<p>Left paren: <code>\(</code></p> + +<p>Right paren: <code>\)</code></p> + +<p>Greater-than: <code>\></code></p> + +<p>Hash: <code>\#</code></p> + +<p>Period: <code>\.</code></p> + +<p>Bang: <code>\!</code></p> + +<p>Plus: <code>\+</code></p> + +<p>Minus: <code>\-</code></p> + + +<p>These should get escaped, even though they're matching pairs for +other Markdown constructs:</p> + +<p>*asterisks*</p> + +<p>_underscores_</p> + +<p>`backticks`</p> + +<p>This is a code span with a literal backslash-backtick sequence: <code>\`</code></p> + +<p>This is a tag with unescaped backticks <span attr='`ticks`'>bar</span>.</p> + +<p>This is a tag with backslashes <span attr='\\backslashes\\'>bar</span>.</p> diff --git a/MarkdownTest/Tests_2007/Backslash escapes.text b/MarkdownTest/Tests_2007/Backslash escapes.text new file mode 100644 index 0000000..5b014cb --- /dev/null +++ b/MarkdownTest/Tests_2007/Backslash escapes.text @@ -0,0 +1,120 @@ +These should all get escaped: + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- + + + +These should not, because they occur within a code block: + + Backslash: \\ + + Backtick: \` + + Asterisk: \* + + Underscore: \_ + + Left brace: \{ + + Right brace: \} + + Left bracket: \[ + + Right bracket: \] + + Left paren: \( + + Right paren: \) + + Greater-than: \> + + Hash: \# + + Period: \. + + Bang: \! + + Plus: \+ + + Minus: \- + + +Nor should these, which occur in code spans: + +Backslash: `\\` + +Backtick: `` \` `` + +Asterisk: `\*` + +Underscore: `\_` + +Left brace: `\{` + +Right brace: `\}` + +Left bracket: `\[` + +Right bracket: `\]` + +Left paren: `\(` + +Right paren: `\)` + +Greater-than: `\>` + +Hash: `\#` + +Period: `\.` + +Bang: `\!` + +Plus: `\+` + +Minus: `\-` + + +These should get escaped, even though they're matching pairs for +other Markdown constructs: + +\*asterisks\* + +\_underscores\_ + +\`backticks\` + +This is a code span with a literal backslash-backtick sequence: `` \` `` + +This is a tag with unescaped backticks <span attr='`ticks`'>bar</span>. + +This is a tag with backslashes <span attr='\\backslashes\\'>bar</span>. diff --git a/MarkdownTest/Tests_2007/Blockquotes with code blocks.html b/MarkdownTest/Tests_2007/Blockquotes with code blocks.html new file mode 100644 index 0000000..990202a --- /dev/null +++ b/MarkdownTest/Tests_2007/Blockquotes with code blocks.html @@ -0,0 +1,15 @@ +<blockquote> + <p>Example:</p> + +<pre><code>sub status { + print "working"; +} +</code></pre> + + <p>Or:</p> + +<pre><code>sub status { + return "working"; +} +</code></pre> +</blockquote> diff --git a/MarkdownTest/Tests_2007/Blockquotes with code blocks.text b/MarkdownTest/Tests_2007/Blockquotes with code blocks.text new file mode 100644 index 0000000..c31d171 --- /dev/null +++ b/MarkdownTest/Tests_2007/Blockquotes with code blocks.text @@ -0,0 +1,11 @@ +> Example: +> +> sub status { +> print "working"; +> } +> +> Or: +> +> sub status { +> return "working"; +> } diff --git a/MarkdownTest/Tests_2007/Code Blocks.html b/MarkdownTest/Tests_2007/Code Blocks.html new file mode 100644 index 0000000..32703f5 --- /dev/null +++ b/MarkdownTest/Tests_2007/Code Blocks.html @@ -0,0 +1,18 @@ +<pre><code>code block on the first line +</code></pre> + +<p>Regular text.</p> + +<pre><code>code block indented by spaces +</code></pre> + +<p>Regular text.</p> + +<pre><code>the lines in this block +all contain trailing spaces +</code></pre> + +<p>Regular Text.</p> + +<pre><code>code block on the last line +</code></pre> diff --git a/MarkdownTest/Tests_2007/Code Blocks.text b/MarkdownTest/Tests_2007/Code Blocks.text new file mode 100644 index 0000000..b54b092 --- /dev/null +++ b/MarkdownTest/Tests_2007/Code Blocks.text @@ -0,0 +1,14 @@ + code block on the first line + +Regular text. + + code block indented by spaces + +Regular text. + + the lines in this block + all contain trailing spaces + +Regular Text. + + code block on the last line
\ No newline at end of file diff --git a/MarkdownTest/Tests_2007/Code Spans.html b/MarkdownTest/Tests_2007/Code Spans.html new file mode 100644 index 0000000..b057457 --- /dev/null +++ b/MarkdownTest/Tests_2007/Code Spans.html @@ -0,0 +1,5 @@ +<p><code><test a="</code> content of attribute <code>"></code></p> + +<p>Fix for backticks within HTML tag: <span attr='`ticks`'>like this</span></p> + +<p>Here's how you put <code>`backticks`</code> in a code span.</p> diff --git a/MarkdownTest/Tests_2007/Code Spans.text b/MarkdownTest/Tests_2007/Code Spans.text new file mode 100644 index 0000000..5c229c7 --- /dev/null +++ b/MarkdownTest/Tests_2007/Code Spans.text @@ -0,0 +1,5 @@ +`<test a="` content of attribute `">` + +Fix for backticks within HTML tag: <span attr='`ticks`'>like this</span> + +Here's how you put `` `backticks` `` in a code span.
\ No newline at end of file diff --git a/MarkdownTest/Tests_2007/Hard-wrapped paragraphs with list-like lines.html b/MarkdownTest/Tests_2007/Hard-wrapped paragraphs with list-like lines.html new file mode 100644 index 0000000..e21ac79 --- /dev/null +++ b/MarkdownTest/Tests_2007/Hard-wrapped paragraphs with list-like lines.html @@ -0,0 +1,8 @@ +<p>In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item.</p> + +<p>Here's one with a bullet. +* criminey.</p> diff --git a/MarkdownTest/Tests_2007/Hard-wrapped paragraphs with list-like lines.text b/MarkdownTest/Tests_2007/Hard-wrapped paragraphs with list-like lines.text new file mode 100644 index 0000000..f8a5b27 --- /dev/null +++ b/MarkdownTest/Tests_2007/Hard-wrapped paragraphs with list-like lines.text @@ -0,0 +1,8 @@ +In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item. + +Here's one with a bullet. +* criminey. diff --git a/MarkdownTest/Tests_2007/Horizontal rules.html b/MarkdownTest/Tests_2007/Horizontal rules.html new file mode 100644 index 0000000..2dc2ab6 --- /dev/null +++ b/MarkdownTest/Tests_2007/Horizontal rules.html @@ -0,0 +1,71 @@ +<p>Dashes:</p> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>--- +</code></pre> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>- - - +</code></pre> + +<p>Asterisks:</p> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>*** +</code></pre> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>* * * +</code></pre> + +<p>Underscores:</p> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>___ +</code></pre> + +<hr /> + +<hr /> + +<hr /> + +<hr /> + +<pre><code>_ _ _ +</code></pre> diff --git a/MarkdownTest/Tests_2007/Horizontal rules.text b/MarkdownTest/Tests_2007/Horizontal rules.text new file mode 100644 index 0000000..1594bda --- /dev/null +++ b/MarkdownTest/Tests_2007/Horizontal rules.text @@ -0,0 +1,67 @@ +Dashes: + +--- + + --- + + --- + + --- + + --- + +- - - + + - - - + + - - - + + - - - + + - - - + + +Asterisks: + +*** + + *** + + *** + + *** + + *** + +* * * + + * * * + + * * * + + * * * + + * * * + + +Underscores: + +___ + + ___ + + ___ + + ___ + + ___ + +_ _ _ + + _ _ _ + + _ _ _ + + _ _ _ + + _ _ _ diff --git a/MarkdownTest/Tests_2007/Images.html b/MarkdownTest/Tests_2007/Images.html new file mode 100644 index 0000000..217f028 --- /dev/null +++ b/MarkdownTest/Tests_2007/Images.html @@ -0,0 +1,21 @@ +<p><img src="/path/to/img.jpg" alt="Alt text" title="" /></p> + +<p><img src="/path/to/img.jpg" alt="Alt text" title="Optional title" /></p> + +<p>Inline within a paragraph: <a href="/url/">alt text</a>.</p> + +<p><img src="/url/" alt="alt text" title="title preceded by two spaces" /></p> + +<p><img src="/url/" alt="alt text" title="title has spaces afterward" /></p> + +<p><img src="/url/" alt="alt text" title="" /></p> + +<p><img src="/url/" alt="alt text" title="with a title" />.</p> + +<p><img src="" alt="Empty" title="" /></p> + +<p><img src="http://example.com/(parens).jpg" alt="this is a stupid URL" title="" /></p> + +<p><img src="/url/" alt="alt text" /></p> + +<p><img src="/url/" alt="alt text" title="Title here" /></p> diff --git a/MarkdownTest/Tests_2007/Images.text b/MarkdownTest/Tests_2007/Images.text new file mode 100644 index 0000000..5707590 --- /dev/null +++ b/MarkdownTest/Tests_2007/Images.text @@ -0,0 +1,26 @@ + + + + +Inline within a paragraph: [alt text](/url/). + + + + + + + +. + +![Empty]() + +.jpg) + + +![alt text][foo] + + [foo]: /url/ + +![alt text][bar] + + [bar]: /url/ "Title here"
\ No newline at end of file diff --git a/MarkdownTest/Tests_2007/Inline HTML (Advanced).html b/MarkdownTest/Tests_2007/Inline HTML (Advanced).html new file mode 100644 index 0000000..884f14c --- /dev/null +++ b/MarkdownTest/Tests_2007/Inline HTML (Advanced).html @@ -0,0 +1,30 @@ +<p>Simple block on one line:</p> + +<div>foo</div> + +<p>And nested without indentation:</p> + +<div> +<div> +<div> +foo +</div> +<div style=">"/> +</div> +<div>bar</div> +</div> + +<p>And with attributes:</p> + +<div> + <div id="foo"> + </div> +</div> + +<p>This was broken in 1.0.2b7:</p> + +<div class="inlinepage"> +<div class="toggleableend"> +foo +</div> +</div> diff --git a/MarkdownTest/Tests_2007/Inline HTML (Advanced).text b/MarkdownTest/Tests_2007/Inline HTML (Advanced).text new file mode 100644 index 0000000..3633f81 --- /dev/null +++ b/MarkdownTest/Tests_2007/Inline HTML (Advanced).text @@ -0,0 +1,30 @@ +Simple block on one line: + +<div>foo</div> + +And nested without indentation: + +<div> +<div> +<div> +foo +</div> +<div style=">"/> +</div> +<div>bar</div> +</div> + +And with attributes: + +<div> + <div id="foo"> + </div> +</div> + +This was broken in 1.0.2b7: + +<div class="inlinepage"> +<div class="toggleableend"> +foo +</div> +</div> diff --git a/MarkdownTest/Tests_2007/Inline HTML (Simple).html b/MarkdownTest/Tests_2007/Inline HTML (Simple).html new file mode 100644 index 0000000..6bf78f8 --- /dev/null +++ b/MarkdownTest/Tests_2007/Inline HTML (Simple).html @@ -0,0 +1,72 @@ +<p>Here's a simple block:</p> + +<div> + foo +</div> + +<p>This should be a code block, though:</p> + +<pre><code><div> + foo +</div> +</code></pre> + +<p>As should this:</p> + +<pre><code><div>foo</div> +</code></pre> + +<p>Now, nested:</p> + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +<p>This should just be an HTML comment:</p> + +<!-- Comment --> + +<p>Multiline:</p> + +<!-- +Blah +Blah +--> + +<p>Code block:</p> + +<pre><code><!-- Comment --> +</code></pre> + +<p>Just plain comment, with trailing spaces on the line:</p> + +<!-- foo --> + +<p>Code:</p> + +<pre><code><hr /> +</code></pre> + +<p>Hr's:</p> + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > diff --git a/MarkdownTest/Tests_2007/Inline HTML (Simple).text b/MarkdownTest/Tests_2007/Inline HTML (Simple).text new file mode 100644 index 0000000..14aa2dc --- /dev/null +++ b/MarkdownTest/Tests_2007/Inline HTML (Simple).text @@ -0,0 +1,69 @@ +Here's a simple block: + +<div> + foo +</div> + +This should be a code block, though: + + <div> + foo + </div> + +As should this: + + <div>foo</div> + +Now, nested: + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +This should just be an HTML comment: + +<!-- Comment --> + +Multiline: + +<!-- +Blah +Blah +--> + +Code block: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +<!-- foo --> + +Code: + + <hr /> + +Hr's: + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > + diff --git a/MarkdownTest/Tests_2007/Inline HTML comments.html b/MarkdownTest/Tests_2007/Inline HTML comments.html new file mode 100644 index 0000000..3f167a1 --- /dev/null +++ b/MarkdownTest/Tests_2007/Inline HTML comments.html @@ -0,0 +1,13 @@ +<p>Paragraph one.</p> + +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +<p>Paragraph two.</p> + +<!-- one comment block -- -- with two comments --> + +<p>The end.</p> diff --git a/MarkdownTest/Tests_2007/Inline HTML comments.text b/MarkdownTest/Tests_2007/Inline HTML comments.text new file mode 100644 index 0000000..41d830d --- /dev/null +++ b/MarkdownTest/Tests_2007/Inline HTML comments.text @@ -0,0 +1,13 @@ +Paragraph one. + +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +Paragraph two. + +<!-- one comment block -- -- with two comments --> + +The end. diff --git a/MarkdownTest/Tests_2007/Links, inline style.html b/MarkdownTest/Tests_2007/Links, inline style.html new file mode 100644 index 0000000..9f351ef --- /dev/null +++ b/MarkdownTest/Tests_2007/Links, inline style.html @@ -0,0 +1,23 @@ +<p>Just a <a href="/url/">URL</a>.</p> + +<p><a href="/url/" title="title">URL and title</a>.</p> + +<p><a href="/url/" title="title preceded by two spaces">URL and title</a>.</p> + +<p><a href="/url/" title="title preceded by a tab">URL and title</a>.</p> + +<p><a href="/url/" title="title has spaces afterward">URL and title</a>.</p> + +<p><a href="/url/">URL wrapped in angle brackets</a>.</p> + +<p><a href="/url/" title="Here's the title">URL w/ angle brackets + title</a>.</p> + +<p><a href="">Empty</a>.</p> + +<p><a href="http://en.wikipedia.org/wiki/WIMP_(computing)">With parens in the URL</a></p> + +<p>(With outer parens and <a href="/foo(bar)">parens in url</a>)</p> + +<p><a href="/foo(bar)" title="and a title">With parens in the URL</a></p> + +<p>(With outer parens and <a href="/foo(bar)" title="and a title">parens in url</a>)</p> diff --git a/MarkdownTest/Tests_2007/Links, inline style.text b/MarkdownTest/Tests_2007/Links, inline style.text new file mode 100644 index 0000000..aba9658 --- /dev/null +++ b/MarkdownTest/Tests_2007/Links, inline style.text @@ -0,0 +1,24 @@ +Just a [URL](/url/). + +[URL and title](/url/ "title"). + +[URL and title](/url/ "title preceded by two spaces"). + +[URL and title](/url/ "title preceded by a tab"). + +[URL and title](/url/ "title has spaces afterward" ). + +[URL wrapped in angle brackets](</url/>). + +[URL w/ angle brackets + title](</url/> "Here's the title"). + +[Empty](). + +[With parens in the URL](http://en.wikipedia.org/wiki/WIMP_(computing)) + +(With outer parens and [parens in url](/foo(bar))) + + +[With parens in the URL](/foo(bar) "and a title") + +(With outer parens and [parens in url](/foo(bar) "and a title")) diff --git a/MarkdownTest/Tests_2007/Links, reference style.html b/MarkdownTest/Tests_2007/Links, reference style.html new file mode 100644 index 0000000..8e70c32 --- /dev/null +++ b/MarkdownTest/Tests_2007/Links, reference style.html @@ -0,0 +1,52 @@ +<p>Foo <a href="/url/" title="Title">bar</a>.</p> + +<p>Foo <a href="/url/" title="Title">bar</a>.</p> + +<p>Foo <a href="/url/" title="Title">bar</a>.</p> + +<p>With <a href="/url/">embedded [brackets]</a>.</p> + +<p>Indented <a href="/url">once</a>.</p> + +<p>Indented <a href="/url">twice</a>.</p> + +<p>Indented <a href="/url">thrice</a>.</p> + +<p>Indented [four][] times.</p> + +<pre><code>[four]: /url +</code></pre> + +<hr /> + +<p><a href="foo">this</a> should work</p> + +<p>So should <a href="foo">this</a>.</p> + +<p>And <a href="foo">this</a>.</p> + +<p>And <a href="foo">this</a>.</p> + +<p>And <a href="foo">this</a>.</p> + +<p>But not [that] [].</p> + +<p>Nor [that][].</p> + +<p>Nor [that].</p> + +<p>[Something in brackets like <a href="foo">this</a> should work]</p> + +<p>[Same with <a href="foo">this</a>.]</p> + +<p>In this case, <a href="/somethingelse/">this</a> points to something else.</p> + +<p>Backslashing should suppress [this] and [this].</p> + +<hr /> + +<p>Here's one where the <a href="/url/">link +breaks</a> across lines.</p> + +<p>Here's another where the <a href="/url/">link +breaks</a> across lines, but with a line-ending space.</p> diff --git a/MarkdownTest/Tests_2007/Links, reference style.text b/MarkdownTest/Tests_2007/Links, reference style.text new file mode 100644 index 0000000..341ec88 --- /dev/null +++ b/MarkdownTest/Tests_2007/Links, reference style.text @@ -0,0 +1,71 @@ +Foo [bar] [1]. + +Foo [bar][1]. + +Foo [bar] +[1]. + +[1]: /url/ "Title" + + +With [embedded [brackets]] [b]. + + +Indented [once][]. + +Indented [twice][]. + +Indented [thrice][]. + +Indented [four][] times. + + [once]: /url + + [twice]: /url + + [thrice]: /url + + [four]: /url + + +[b]: /url/ + +* * * + +[this] [this] should work + +So should [this][this]. + +And [this] []. + +And [this][]. + +And [this]. + +But not [that] []. + +Nor [that][]. + +Nor [that]. + +[Something in brackets like [this][] should work] + +[Same with [this].] + +In this case, [this](/somethingelse/) points to something else. + +Backslashing should suppress \[this] and [this\]. + +[this]: foo + + +* * * + +Here's one where the [link +breaks] across lines. + +Here's another where the [link +breaks] across lines, but with a line-ending space. + + +[link breaks]: /url/ diff --git a/MarkdownTest/Tests_2007/Links, shortcut references.html b/MarkdownTest/Tests_2007/Links, shortcut references.html new file mode 100755 index 0000000..bf81e93 --- /dev/null +++ b/MarkdownTest/Tests_2007/Links, shortcut references.html @@ -0,0 +1,9 @@ +<p>This is the <a href="/simple">simple case</a>.</p> + +<p>This one has a <a href="/foo">line +break</a>.</p> + +<p>This one has a <a href="/foo">line +break</a> with a line-ending space.</p> + +<p><a href="/that">this</a> and the <a href="/other">other</a></p> diff --git a/MarkdownTest/Tests_2007/Links, shortcut references.text b/MarkdownTest/Tests_2007/Links, shortcut references.text new file mode 100755 index 0000000..8c44c98 --- /dev/null +++ b/MarkdownTest/Tests_2007/Links, shortcut references.text @@ -0,0 +1,20 @@ +This is the [simple case]. + +[simple case]: /simple + + + +This one has a [line +break]. + +This one has a [line +break] with a line-ending space. + +[line break]: /foo + + +[this] [that] and the [other] + +[this]: /this +[that]: /that +[other]: /other diff --git a/MarkdownTest/Tests_2007/Literal quotes in titles.html b/MarkdownTest/Tests_2007/Literal quotes in titles.html new file mode 100644 index 0000000..611c1ac --- /dev/null +++ b/MarkdownTest/Tests_2007/Literal quotes in titles.html @@ -0,0 +1,3 @@ +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> + +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> diff --git a/MarkdownTest/Tests_2007/Literal quotes in titles.text b/MarkdownTest/Tests_2007/Literal quotes in titles.text new file mode 100644 index 0000000..29d0e42 --- /dev/null +++ b/MarkdownTest/Tests_2007/Literal quotes in titles.text @@ -0,0 +1,7 @@ +Foo [bar][]. + +Foo [bar](/url/ "Title with "quotes" inside"). + + + [bar]: /url/ "Title with "quotes" inside" + diff --git a/MarkdownTest/Tests_2007/Markdown Documentation - Basics.html b/MarkdownTest/Tests_2007/Markdown Documentation - Basics.html new file mode 100644 index 0000000..d5bdbb2 --- /dev/null +++ b/MarkdownTest/Tests_2007/Markdown Documentation - Basics.html @@ -0,0 +1,314 @@ +<h1>Markdown: Basics</h1> + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a class="selected" title="Markdown Basics">Basics</a></li> + <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<h2>Getting the Gist of Markdown's Formatting Syntax</h2> + +<p>This page offers a brief overview of what it's like to use Markdown. +The <a href="/projects/markdown/syntax" title="Markdown Syntax">syntax page</a> provides complete, detailed documentation for +every feature, but Markdown should be very easy to pick up simply by +looking at a few examples of it in action. The examples on this page +are written in a before/after style, showing example syntax and the +HTML output produced by Markdown.</p> + +<p>It's also helpful to simply try Markdown out; the <a href="/projects/markdown/dingus" title="Markdown Dingus">Dingus</a> is a +web application that allows you type your own Markdown-formatted text +and translate it to XHTML.</p> + +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/basics.text">see the source for it by adding '.text' to the URL</a>.</p> + +<h2>Paragraphs, Headers, Blockquotes</h2> + +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> + +<p>Markdown offers two styles of headers: <em>Setext</em> and <em>atx</em>. +Setext-style headers for <code><h1></code> and <code><h2></code> are created by +"underlining" with equal signs (<code>=</code>) and hyphens (<code>-</code>), respectively. +To create an atx-style header, you put 1-6 hash marks (<code>#</code>) at the +beginning of the line -- the number of hashes equals the resulting +HTML header level.</p> + +<p>Blockquotes are indicated using email-style '<code>></code>' angle brackets.</p> + +<p>Markdown:</p> + +<pre><code>A First Level Header +==================== + +A Second Level Header +--------------------- + +Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph. + +The quick brown fox jumped over the lazy +dog's back. + +### Header 3 + +> This is a blockquote. +> +> This is the second paragraph in the blockquote. +> +> ## This is an H2 in a blockquote +</code></pre> + +<p>Output:</p> + +<pre><code><h1>A First Level Header</h1> + +<h2>A Second Level Header</h2> + +<p>Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph.</p> + +<p>The quick brown fox jumped over the lazy +dog's back.</p> + +<h3>Header 3</h3> + +<blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> +</blockquote> +</code></pre> + +<h3>Phrase Emphasis</h3> + +<p>Markdown uses asterisks and underscores to indicate spans of emphasis.</p> + +<p>Markdown:</p> + +<pre><code>Some of these words *are emphasized*. +Some of these words _are emphasized also_. + +Use two asterisks for **strong emphasis**. +Or, if you prefer, __use two underscores instead__. +</code></pre> + +<p>Output:</p> + +<pre><code><p>Some of these words <em>are emphasized</em>. +Some of these words <em>are emphasized also</em>.</p> + +<p>Use two asterisks for <strong>strong emphasis</strong>. +Or, if you prefer, <strong>use two underscores instead</strong>.</p> +</code></pre> + +<h2>Lists</h2> + +<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens (<code>*</code>, +<code>+</code>, and <code>-</code>) as list markers. These three markers are +interchangable; this:</p> + +<pre><code>* Candy. +* Gum. +* Booze. +</code></pre> + +<p>this:</p> + +<pre><code>+ Candy. ++ Gum. ++ Booze. +</code></pre> + +<p>and this:</p> + +<pre><code>- Candy. +- Gum. +- Booze. +</code></pre> + +<p>all produce the same output:</p> + +<pre><code><ul> +<li>Candy.</li> +<li>Gum.</li> +<li>Booze.</li> +</ul> +</code></pre> + +<p>Ordered (numbered) lists use regular numbers, followed by periods, as +list markers:</p> + +<pre><code>1. Red +2. Green +3. Blue +</code></pre> + +<p>Output:</p> + +<pre><code><ol> +<li>Red</li> +<li>Green</li> +<li>Blue</li> +</ol> +</code></pre> + +<p>If you put blank lines between items, you'll get <code><p></code> tags for the +list item text. You can create multi-paragraph list items by indenting +the paragraphs by 4 spaces or 1 tab:</p> + +<pre><code>* A list item. + + With multiple paragraphs. + +* Another item in the list. +</code></pre> + +<p>Output:</p> + +<pre><code><ul> +<li><p>A list item.</p> +<p>With multiple paragraphs.</p></li> +<li><p>Another item in the list.</p></li> +</ul> +</code></pre> + +<h3>Links</h3> + +<p>Markdown supports two styles for creating links: <em>inline</em> and +<em>reference</em>. With both styles, you use square brackets to delimit the +text you want to turn into a link.</p> + +<p>Inline-style links use parentheses immediately after the link text. +For example:</p> + +<pre><code>This is an [example link](http://example.com/). +</code></pre> + +<p>Output:</p> + +<pre><code><p>This is an <a href="http://example.com/"> +example link</a>.</p> +</code></pre> + +<p>Optionally, you may include a title attribute in the parentheses:</p> + +<pre><code>This is an [example link](http://example.com/ "With a Title"). +</code></pre> + +<p>Output:</p> + +<pre><code><p>This is an <a href="http://example.com/" title="With a Title"> +example link</a>.</p> +</code></pre> + +<p>Reference-style links allow you to refer to your links by names, which +you define elsewhere in your document:</p> + +<pre><code>I get 10 times more traffic from [Google][1] than from +[Yahoo][2] or [MSN][3]. + +[1]: http://google.com/ "Google" +[2]: http://search.yahoo.com/ "Yahoo Search" +[3]: http://search.msn.com/ "MSN Search" +</code></pre> + +<p>Output:</p> + +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from <a href="http://search.yahoo.com/" +title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" +title="MSN Search">MSN</a>.</p> +</code></pre> + +<p>The title attribute is optional. Link names may contain letters, +numbers and spaces, but are <em>not</em> case sensitive:</p> + +<pre><code>I start my morning with a cup of coffee and +[The New York Times][NY Times]. + +[ny times]: http://www.nytimes.com/ +</code></pre> + +<p>Output:</p> + +<pre><code><p>I start my morning with a cup of coffee and +<a href="http://www.nytimes.com/">The New York Times</a>.</p> +</code></pre> + +<h3>Images</h3> + +<p>Image syntax is very much like link syntax.</p> + +<p>Inline (titles are optional):</p> + +<pre><code> +</code></pre> + +<p>Reference-style:</p> + +<pre><code>![alt text][id] + +[id]: /path/to/img.jpg "Title" +</code></pre> + +<p>Both of the above examples produce the same output:</p> + +<pre><code><img src="/path/to/img.jpg" alt="alt text" title="Title" /> +</code></pre> + +<h3>Code</h3> + +<p>In a regular paragraph, you can create code span by wrapping text in +backtick quotes. Any ampersands (<code>&</code>) and angle brackets (<code><</code> or +<code>></code>) will automatically be translated into HTML entities. This makes +it easy to use Markdown to write about HTML example code:</p> + +<pre><code>I strongly recommend against using any `<blink>` tags. + +I wish SmartyPants used named entities like `&mdash;` +instead of decimal-encoded entites like `&#8212;`. +</code></pre> + +<p>Output:</p> + +<pre><code><p>I strongly recommend against using any +<code>&lt;blink&gt;</code> tags.</p> + +<p>I wish SmartyPants used named entities like +<code>&amp;mdash;</code> instead of decimal-encoded +entites like <code>&amp;#8212;</code>.</p> +</code></pre> + +<p>To specify an entire block of pre-formatted code, indent every line of +the block by 4 spaces or 1 tab. Just like with code spans, <code>&</code>, <code><</code>, +and <code>></code> characters will be escaped automatically.</p> + +<p>Markdown:</p> + +<pre><code>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> +</code></pre> + +<p>Output:</p> + +<pre><code><p>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes:</p> + +<pre><code>&lt;blockquote&gt; + &lt;p&gt;For example.&lt;/p&gt; +&lt;/blockquote&gt; +</code></pre> +</code></pre> diff --git a/MarkdownTest/Tests_2007/Markdown Documentation - Basics.text b/MarkdownTest/Tests_2007/Markdown Documentation - Basics.text new file mode 100644 index 0000000..486055c --- /dev/null +++ b/MarkdownTest/Tests_2007/Markdown Documentation - Basics.text @@ -0,0 +1,306 @@ +Markdown: Basics +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a class="selected" title="Markdown Basics">Basics</a></li> + <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +Getting the Gist of Markdown's Formatting Syntax +------------------------------------------------ + +This page offers a brief overview of what it's like to use Markdown. +The [syntax page] [s] provides complete, detailed documentation for +every feature, but Markdown should be very easy to pick up simply by +looking at a few examples of it in action. The examples on this page +are written in a before/after style, showing example syntax and the +HTML output produced by Markdown. + +It's also helpful to simply try Markdown out; the [Dingus] [d] is a +web application that allows you type your own Markdown-formatted text +and translate it to XHTML. + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL] [src]. + + [s]: /projects/markdown/syntax "Markdown Syntax" + [d]: /projects/markdown/dingus "Markdown Dingus" + [src]: /projects/markdown/basics.text + + +## Paragraphs, Headers, Blockquotes ## + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +Markdown offers two styles of headers: *Setext* and *atx*. +Setext-style headers for `<h1>` and `<h2>` are created by +"underlining" with equal signs (`=`) and hyphens (`-`), respectively. +To create an atx-style header, you put 1-6 hash marks (`#`) at the +beginning of the line -- the number of hashes equals the resulting +HTML header level. + +Blockquotes are indicated using email-style '`>`' angle brackets. + +Markdown: + + A First Level Header + ==================== + + A Second Level Header + --------------------- + + Now is the time for all good men to come to + the aid of their country. This is just a + regular paragraph. + + The quick brown fox jumped over the lazy + dog's back. + + ### Header 3 + + > This is a blockquote. + > + > This is the second paragraph in the blockquote. + > + > ## This is an H2 in a blockquote + + +Output: + + <h1>A First Level Header</h1> + + <h2>A Second Level Header</h2> + + <p>Now is the time for all good men to come to + the aid of their country. This is just a + regular paragraph.</p> + + <p>The quick brown fox jumped over the lazy + dog's back.</p> + + <h3>Header 3</h3> + + <blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> + </blockquote> + + + +### Phrase Emphasis ### + +Markdown uses asterisks and underscores to indicate spans of emphasis. + +Markdown: + + Some of these words *are emphasized*. + Some of these words _are emphasized also_. + + Use two asterisks for **strong emphasis**. + Or, if you prefer, __use two underscores instead__. + +Output: + + <p>Some of these words <em>are emphasized</em>. + Some of these words <em>are emphasized also</em>.</p> + + <p>Use two asterisks for <strong>strong emphasis</strong>. + Or, if you prefer, <strong>use two underscores instead</strong>.</p> + + + +## Lists ## + +Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`, +`+`, and `-`) as list markers. These three markers are +interchangable; this: + + * Candy. + * Gum. + * Booze. + +this: + + + Candy. + + Gum. + + Booze. + +and this: + + - Candy. + - Gum. + - Booze. + +all produce the same output: + + <ul> + <li>Candy.</li> + <li>Gum.</li> + <li>Booze.</li> + </ul> + +Ordered (numbered) lists use regular numbers, followed by periods, as +list markers: + + 1. Red + 2. Green + 3. Blue + +Output: + + <ol> + <li>Red</li> + <li>Green</li> + <li>Blue</li> + </ol> + +If you put blank lines between items, you'll get `<p>` tags for the +list item text. You can create multi-paragraph list items by indenting +the paragraphs by 4 spaces or 1 tab: + + * A list item. + + With multiple paragraphs. + + * Another item in the list. + +Output: + + <ul> + <li><p>A list item.</p> + <p>With multiple paragraphs.</p></li> + <li><p>Another item in the list.</p></li> + </ul> + + + +### Links ### + +Markdown supports two styles for creating links: *inline* and +*reference*. With both styles, you use square brackets to delimit the +text you want to turn into a link. + +Inline-style links use parentheses immediately after the link text. +For example: + + This is an [example link](http://example.com/). + +Output: + + <p>This is an <a href="http://example.com/"> + example link</a>.</p> + +Optionally, you may include a title attribute in the parentheses: + + This is an [example link](http://example.com/ "With a Title"). + +Output: + + <p>This is an <a href="http://example.com/" title="With a Title"> + example link</a>.</p> + +Reference-style links allow you to refer to your links by names, which +you define elsewhere in your document: + + I get 10 times more traffic from [Google][1] than from + [Yahoo][2] or [MSN][3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from <a href="http://search.yahoo.com/" + title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" + title="MSN Search">MSN</a>.</p> + +The title attribute is optional. Link names may contain letters, +numbers and spaces, but are *not* case sensitive: + + I start my morning with a cup of coffee and + [The New York Times][NY Times]. + + [ny times]: http://www.nytimes.com/ + +Output: + + <p>I start my morning with a cup of coffee and + <a href="http://www.nytimes.com/">The New York Times</a>.</p> + + +### Images ### + +Image syntax is very much like link syntax. + +Inline (titles are optional): + +  + +Reference-style: + + ![alt text][id] + + [id]: /path/to/img.jpg "Title" + +Both of the above examples produce the same output: + + <img src="/path/to/img.jpg" alt="alt text" title="Title" /> + + + +### Code ### + +In a regular paragraph, you can create code span by wrapping text in +backtick quotes. Any ampersands (`&`) and angle brackets (`<` or +`>`) will automatically be translated into HTML entities. This makes +it easy to use Markdown to write about HTML example code: + + I strongly recommend against using any `<blink>` tags. + + I wish SmartyPants used named entities like `—` + instead of decimal-encoded entites like `—`. + +Output: + + <p>I strongly recommend against using any + <code><blink></code> tags.</p> + + <p>I wish SmartyPants used named entities like + <code>&mdash;</code> instead of decimal-encoded + entites like <code>&#8212;</code>.</p> + + +To specify an entire block of pre-formatted code, indent every line of +the block by 4 spaces or 1 tab. Just like with code spans, `&`, `<`, +and `>` characters will be escaped automatically. + +Markdown: + + If you want your page to validate under XHTML 1.0 Strict, + you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> + +Output: + + <p>If you want your page to validate under XHTML 1.0 Strict, + you've got to put paragraph tags in your blockquotes:</p> + + <pre><code><blockquote> + <p>For example.</p> + </blockquote> + </code></pre> diff --git a/MarkdownTest/Tests_2007/Markdown Documentation - Syntax.html b/MarkdownTest/Tests_2007/Markdown Documentation - Syntax.html new file mode 100644 index 0000000..5c01306 --- /dev/null +++ b/MarkdownTest/Tests_2007/Markdown Documentation - Syntax.html @@ -0,0 +1,942 @@ +<h1>Markdown: Syntax</h1> + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<ul> +<li><a href="#overview">Overview</a> +<ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#html">Inline HTML</a></li> +<li><a href="#autoescape">Automatic Escaping for Special Characters</a></li> +</ul></li> +<li><a href="#block">Block Elements</a> +<ul> +<li><a href="#p">Paragraphs and Line Breaks</a></li> +<li><a href="#header">Headers</a></li> +<li><a href="#blockquote">Blockquotes</a></li> +<li><a href="#list">Lists</a></li> +<li><a href="#precode">Code Blocks</a></li> +<li><a href="#hr">Horizontal Rules</a></li> +</ul></li> +<li><a href="#span">Span Elements</a> +<ul> +<li><a href="#link">Links</a></li> +<li><a href="#em">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#img">Images</a></li> +</ul></li> +<li><a href="#misc">Miscellaneous</a> +<ul> +<li><a href="#backslash">Backslash Escapes</a></li> +<li><a href="#autolink">Automatic Links</a></li> +</ul></li> +</ul> + +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/syntax.text">see the source for it by adding '.text' to the URL</a>.</p> + +<hr /> + +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +<p>Markdown is intended to be as easy-to-read and easy-to-write as is feasible.</p> + +<p>Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, <a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href="http://textism.com/tools/textile/">Textile</a>, <a href="http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href="http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and <a href="http://ettext.taint.org/doc/">EtText</a> -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email.</p> + +<p>To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like *emphasis*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email.</p> + +<h3 id="html">Inline HTML</h3> + +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> + +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a <em>publishing</em> format; Markdown is a <em>writing</em> +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text.</p> + +<p>For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags.</p> + +<p>The only restrictions are that block-level HTML elements -- e.g. <code><div></code>, +<code><table></code>, <code><pre></code>, <code><p></code>, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) <code><p></code> tags around HTML block-level tags.</p> + +<p>For example, to add an HTML table to a Markdown article:</p> + +<pre><code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code></pre> + +<p>Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style <code>*emphasis*</code> inside an +HTML block.</p> + +<p>Span-level HTML tags -- e.g. <code><span></code>, <code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML <code><a></code> or <code><img></code> tags instead of Markdown's +link or image syntax, go right ahead.</p> + +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> processed within +span-level tags.</p> + +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +<p>In HTML, there are two characters that demand special treatment: <code><</code> +and <code>&</code>. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> + +<p>Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '<code>AT&amp;T</code>'. You even need to +escape ampersands within URLs. Thus, if you want to link to:</p> + +<pre><code>http://images.google.com/images?num=30&q=larry+bird +</code></pre> + +<p>you need to encode the URL as:</p> + +<pre><code>http://images.google.com/images?num=30&amp;q=larry+bird +</code></pre> + +<p>in your anchor tag <code>href</code> attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites.</p> + +<p>Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into <code>&amp;</code>.</p> + +<p>So, if you want to include a copyright symbol in your article, you can write:</p> + +<pre><code>&copy; +</code></pre> + +<p>and Markdown will leave it alone. But if you write:</p> + +<pre><code>AT&T +</code></pre> + +<p>Markdown will translate it to:</p> + +<pre><code>AT&amp;T +</code></pre> + +<p>Similarly, because Markdown supports <a href="#html">inline HTML</a>, if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write:</p> + +<pre><code>4 < 5 +</code></pre> + +<p>Markdown will translate it to:</p> + +<pre><code>4 &lt; 5 +</code></pre> + +<p>However, inside Markdown code spans and blocks, angle brackets and +ampersands are <em>always</em> encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single <code><</code> +and <code>&</code> in your example code needs to be escaped.)</p> + +<hr /> + +<h2 id="block">Block Elements</h2> + +<h3 id="p">Paragraphs and Line Breaks</h3> + +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> + +<p>The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a <code><br /></code> tag.</p> + +<p>When you <em>do</em> want to insert a <code><br /></code> break tag using Markdown, you +end a line with two or more spaces, then type return.</p> + +<p>Yes, this takes a tad more effort to create a <code><br /></code>, but a simplistic +"every line break is a <code><br /></code>" rule wouldn't work for Markdown. +Markdown's email-style <a href="#blockquote">blockquoting</a> and multi-paragraph <a href="#list">list items</a> +work best -- and look better -- when you format them with hard breaks.</p> + +<h3 id="header">Headers</h3> + +<p>Markdown supports two styles of headers, <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and <a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> + +<p>Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example:</p> + +<pre><code>This is an H1 +============= + +This is an H2 +------------- +</code></pre> + +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s will work.</p> + +<p>Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example:</p> + +<pre><code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code></pre> + +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) :</p> + +<pre><code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code></pre> + +<h3 id="blockquote">Blockquotes</h3> + +<p>Markdown uses email-style <code>></code> characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a <code>></code> before every line:</p> + +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>Markdown allows you to be lazy and only put the <code>></code> before the first +line of a hard-wrapped paragraph:</p> + +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> + +<pre><code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code></pre> + +<p>Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks:</p> + +<pre><code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code></pre> + +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> + +<h3 id="list">Lists</h3> + +<p>Markdown supports ordered (numbered) and unordered (bulleted) lists.</p> + +<p>Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers:</p> + +<pre><code>* Red +* Green +* Blue +</code></pre> + +<p>is equivalent to:</p> + +<pre><code>+ Red ++ Green ++ Blue +</code></pre> + +<p>and:</p> + +<pre><code>- Red +- Green +- Blue +</code></pre> + +<p>Ordered lists use numbers followed by periods:</p> + +<pre><code>1. Bird +2. McHale +3. Parish +</code></pre> + +<p>It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is:</p> + +<pre><code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code></pre> + +<p>If you instead wrote the list in Markdown like this:</p> + +<pre><code>1. Bird +1. McHale +1. Parish +</code></pre> + +<p>or even:</p> + +<pre><code>3. Bird +1. McHale +8. Parish +</code></pre> + +<p>you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to.</p> + +<p>If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number.</p> + +<p>List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab.</p> + +<p>To make lists look nice, you can wrap items with hanging indents:</p> + +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>But if you want to be lazy, you don't have to:</p> + +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>If list items are separated by blank lines, Markdown will wrap the +items in <code><p></code> tags in the HTML output. For example, this input:</p> + +<pre><code>* Bird +* Magic +</code></pre> + +<p>will turn into:</p> + +<pre><code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code></pre> + +<p>But this:</p> + +<pre><code>* Bird + +* Magic +</code></pre> + +<p>will turn into:</p> + +<pre><code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code></pre> + +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab:</p> + +<pre><code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> + +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy:</p> + +<pre><code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code></pre> + +<p>To put a blockquote within a list item, the blockquote's <code>></code> +delimiters need to be indented:</p> + +<pre><code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code></pre> + +<p>To put a code block within a list item, the code block needs +to be indented <em>twice</em> -- 8 spaces or two tabs:</p> + +<pre><code>* A list item with a code block: + + <code goes here> +</code></pre> + +<p>It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this:</p> + +<pre><code>1986. What a great season. +</code></pre> + +<p>In other words, a <em>number-period-space</em> sequence at the beginning of a +line. To avoid this, you can backslash-escape the period:</p> + +<pre><code>1986\. What a great season. +</code></pre> + +<h3 id="precode">Code Blocks</h3> + +<p>Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both <code><pre></code> and <code><code></code> tags.</p> + +<p>To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input:</p> + +<pre><code>This is a normal paragraph: + + This is a code block. +</code></pre> + +<p>Markdown will generate:</p> + +<pre><code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code></pre> + +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this:</p> + +<pre><code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code></pre> + +<p>will turn into:</p> + +<pre><code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code></pre> + +<p>A code block continues until it reaches a line that is not indented +(or the end of the article).</p> + +<p>Within a code block, ampersands (<code>&</code>) and angle brackets (<code><</code> and <code>></code>) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> + +<pre><code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code></pre> + +<p>will turn into:</p> + +<pre><code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code></pre> + +<p>Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax.</p> + +<h3 id="hr">Horizontal Rules</h3> + +<p>You can produce a horizontal rule tag (<code><hr /></code>) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule:</p> + +<pre><code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code></pre> + +<hr /> + +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +<p>Markdown supports two style of links: <em>inline</em> and <em>reference</em>.</p> + +<p>In both styles, the link text is delimited by [square brackets].</p> + +<p>To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an <em>optional</em> +title for the link, surrounded in quotes. For example:</p> + +<pre><code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code></pre> + +<p>Will produce:</p> + +<pre><code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code></pre> + +<p>If you're referring to a local resource on the same server, you can +use relative paths:</p> + +<pre><code>See my [About](/about/) page for details. +</code></pre> + +<p>Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link:</p> + +<pre><code>This is [an example][id] reference-style link. +</code></pre> + +<p>You can optionally use a space to separate the sets of brackets:</p> + +<pre><code>This is [an example] [id] reference-style link. +</code></pre> + +<p>Then, anywhere in the document, you define your link label like this, +on a line by itself:</p> + +<pre><code>[id]: http://example.com/ "Optional Title Here" +</code></pre> + +<p>That is:</p> + +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> + +<p>The link URL may, optionally, be surrounded by angle brackets:</p> + +<pre><code>[id]: <http://example.com/> "Optional Title Here" +</code></pre> + +<p>You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs:</p> + +<pre><code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code></pre> + +<p>Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output.</p> + +<p>Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are <em>not</em> case sensitive. E.g. these two links:</p> + +<pre><code>[link text][a] +[link text][A] +</code></pre> + +<p>are equivalent.</p> + +<p>The <em>implicit link name</em> shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write:</p> + +<pre><code>[Google][] +</code></pre> + +<p>And then define the link:</p> + +<pre><code>[Google]: http://google.com/ +</code></pre> + +<p>Because link names may contain spaces, this shortcut even works for +multiple words in the link text:</p> + +<pre><code>Visit [Daring Fireball][] for more information. +</code></pre> + +<p>And then define the link:</p> + +<pre><code>[Daring Fireball]: http://daringfireball.net/ +</code></pre> + +<p>Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes.</p> + +<p>Here's an example of reference links in action:</p> + +<pre><code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code></pre> + +<p>Using the implicit link name shortcut, you could instead write:</p> + +<pre><code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code></pre> + +<p>Both of the above examples will produce the following HTML output:</p> + +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code></pre> + +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> + +<pre><code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code></pre> + +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text.</p> + +<p>With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose.</p> + +<h3 id="em">Emphasis</h3> + +<p>Markdown treats asterisks (<code>*</code>) and underscores (<code>_</code>) as indicators of +emphasis. Text wrapped with one <code>*</code> or <code>_</code> will be wrapped with an +HTML <code><em></code> tag; double <code>*</code>'s or <code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> + +<pre><code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code></pre> + +<p>will produce:</p> + +<pre><code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code></pre> + +<p>You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span.</p> + +<p>Emphasis can be used in the middle of a word:</p> + +<pre><code>un*fucking*believable +</code></pre> + +<p>But if you surround an <code>*</code> or <code>_</code> with spaces, it'll be treated as a +literal asterisk or underscore.</p> + +<p>To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it:</p> + +<pre><code>\*this text is surrounded by literal asterisks\* +</code></pre> + +<h3 id="code">Code</h3> + +<p>To indicate a span of code, wrap it with backtick quotes (<code>`</code>). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example:</p> + +<pre><code>Use the `printf()` function. +</code></pre> + +<p>will produce:</p> + +<pre><code><p>Use the <code>printf()</code> function.</p> +</code></pre> + +<p>To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters:</p> + +<pre><code>``There is a literal backtick (`) here.`` +</code></pre> + +<p>which will produce this:</p> + +<pre><code><p><code>There is a literal backtick (`) here.</code></p> +</code></pre> + +<p>The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span:</p> + +<pre><code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code></pre> + +<p>will produce:</p> + +<pre><code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code></pre> + +<p>With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this:</p> + +<pre><code>Please don't use any `<blink>` tags. +</code></pre> + +<p>into:</p> + +<pre><code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code></pre> + +<p>You can write this:</p> + +<pre><code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code></pre> + +<p>to produce:</p> + +<pre><code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code></pre> + +<h3 id="img">Images</h3> + +<p>Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format.</p> + +<p>Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: <em>inline</em> and <em>reference</em>.</p> + +<p>Inline image syntax looks like this:</p> + +<pre><code> + + +</code></pre> + +<p>That is:</p> + +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the <code>alt</code> +attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in double +or single quotes.</li> +</ul> + +<p>Reference-style image syntax looks like this:</p> + +<pre><code>![Alt text][id] +</code></pre> + +<p>Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references:</p> + +<pre><code>[id]: url/to/image "Optional title attribute" +</code></pre> + +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> + +<hr /> + +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +<p>Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:</p> + +<pre><code><http://example.com/> +</code></pre> + +<p>Markdown will turn this into:</p> + +<pre><code><a href="http://example.com/">http://example.com/</a> +</code></pre> + +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this:</p> + +<pre><code><address@example.com> +</code></pre> + +<p>into something like this:</p> + +<pre><code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code></pre> + +<p>which will render in a browser as a clickable link to "address@example.com".</p> + +<p>(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.)</p> + +<h3 id="backslash">Backslash Escapes</h3> + +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML <code><em></code> tag), you can backslashes +before the asterisks, like this:</p> + +<pre><code>\*literal asterisks\* +</code></pre> + +<p>Markdown provides backslash escapes for the following characters:</p> + +<pre><code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code></pre> diff --git a/MarkdownTest/Tests_2007/Markdown Documentation - Syntax.text b/MarkdownTest/Tests_2007/Markdown Documentation - Syntax.text new file mode 100644 index 0000000..57360a1 --- /dev/null +++ b/MarkdownTest/Tests_2007/Markdown Documentation - Syntax.text @@ -0,0 +1,888 @@ +Markdown: Syntax +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +* [Overview](#overview) + * [Philosophy](#philosophy) + * [Inline HTML](#html) + * [Automatic Escaping for Special Characters](#autoescape) +* [Block Elements](#block) + * [Paragraphs and Line Breaks](#p) + * [Headers](#header) + * [Blockquotes](#blockquote) + * [Lists](#list) + * [Code Blocks](#precode) + * [Horizontal Rules](#hr) +* [Span Elements](#span) + * [Links](#link) + * [Emphasis](#em) + * [Code](#code) + * [Images](#img) +* [Miscellaneous](#misc) + * [Backslash Escapes](#backslash) + * [Automatic Links](#autolink) + + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL][src]. + + [src]: /projects/markdown/syntax.text + +* * * + +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +Markdown is intended to be as easy-to-read and easy-to-write as is feasible. + +Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4], +[Grutatext] [5], and [EtText] [6] -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email. + + [1]: http://docutils.sourceforge.net/mirror/setext.html + [2]: http://www.aaronsw.com/2002/atx/ + [3]: http://textism.com/tools/textile/ + [4]: http://docutils.sourceforge.net/rst.html + [5]: http://www.triptico.com/software/grutatxt.html + [6]: http://ettext.taint.org/doc/ + +To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like \*emphasis\*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email. + + + +<h3 id="html">Inline HTML</h3> + +Markdown's syntax is intended for one purpose: to be used as a +format for *writing* for the web. + +Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is *not* to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a *publishing* format; Markdown is a *writing* +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text. + +For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags. + +The only restrictions are that block-level HTML elements -- e.g. `<div>`, +`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) `<p>` tags around HTML block-level tags. + +For example, to add an HTML table to a Markdown article: + + This is a regular paragraph. + + <table> + <tr> + <td>Foo</td> + </tr> + </table> + + This is another regular paragraph. + +Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an +HTML block. + +Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's +link or image syntax, go right ahead. + +Unlike block-level HTML tags, Markdown syntax *is* processed within +span-level tags. + + +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +In HTML, there are two characters that demand special treatment: `<` +and `&`. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. `<`, and +`&`. + +Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '`AT&T`'. You even need to +escape ampersands within URLs. Thus, if you want to link to: + + http://images.google.com/images?num=30&q=larry+bird + +you need to encode the URL as: + + http://images.google.com/images?num=30&q=larry+bird + +in your anchor tag `href` attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites. + +Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into `&`. + +So, if you want to include a copyright symbol in your article, you can write: + + © + +and Markdown will leave it alone. But if you write: + + AT&T + +Markdown will translate it to: + + AT&T + +Similarly, because Markdown supports [inline HTML](#html), if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write: + + 4 < 5 + +Markdown will translate it to: + + 4 < 5 + +However, inside Markdown code spans and blocks, angle brackets and +ampersands are *always* encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single `<` +and `&` in your example code needs to be escaped.) + + +* * * + + +<h2 id="block">Block Elements</h2> + + +<h3 id="p">Paragraphs and Line Breaks</h3> + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a `<br />` tag. + +When you *do* want to insert a `<br />` break tag using Markdown, you +end a line with two or more spaces, then type return. + +Yes, this takes a tad more effort to create a `<br />`, but a simplistic +"every line break is a `<br />`" rule wouldn't work for Markdown. +Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l] +work best -- and look better -- when you format them with hard breaks. + + [bq]: #blockquote + [l]: #list + + + +<h3 id="header">Headers</h3> + +Markdown supports two styles of headers, [Setext] [1] and [atx] [2]. + +Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example: + + This is an H1 + ============= + + This is an H2 + ------------- + +Any number of underlining `=`'s or `-`'s will work. + +Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example: + + # This is an H1 + + ## This is an H2 + + ###### This is an H6 + +Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) : + + # This is an H1 # + + ## This is an H2 ## + + ### This is an H3 ###### + + +<h3 id="blockquote">Blockquotes</h3> + +Markdown uses email-style `>` characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a `>` before every line: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + > + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + > id sem consectetuer libero luctus adipiscing. + +Markdown allows you to be lazy and only put the `>` before the first +line of a hard-wrapped paragraph: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + id sem consectetuer libero luctus adipiscing. + +Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of `>`: + + > This is the first level of quoting. + > + > > This is nested blockquote. + > + > Back to the first level. + +Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks: + + > ## This is a header. + > + > 1. This is the first list item. + > 2. This is the second list item. + > + > Here's some example code: + > + > return shell_exec("echo $input | $markdown_script"); + +Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu. + + +<h3 id="list">Lists</h3> + +Markdown supports ordered (numbered) and unordered (bulleted) lists. + +Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers: + + * Red + * Green + * Blue + +is equivalent to: + + + Red + + Green + + Blue + +and: + + - Red + - Green + - Blue + +Ordered lists use numbers followed by periods: + + 1. Bird + 2. McHale + 3. Parish + +It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is: + + <ol> + <li>Bird</li> + <li>McHale</li> + <li>Parish</li> + </ol> + +If you instead wrote the list in Markdown like this: + + 1. Bird + 1. McHale + 1. Parish + +or even: + + 3. Bird + 1. McHale + 8. Parish + +you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to. + +If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number. + +List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab. + +To make lists look nice, you can wrap items with hanging indents: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +But if you want to be lazy, you don't have to: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +If list items are separated by blank lines, Markdown will wrap the +items in `<p>` tags in the HTML output. For example, this input: + + * Bird + * Magic + +will turn into: + + <ul> + <li>Bird</li> + <li>Magic</li> + </ul> + +But this: + + * Bird + + * Magic + +will turn into: + + <ul> + <li><p>Bird</p></li> + <li><p>Magic</p></li> + </ul> + +List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab: + + 1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + + 2. Suspendisse id sem consectetuer libero luctus adipiscing. + +It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy: + + * This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're + only required to indent the first line. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. + + * Another item in the same list. + +To put a blockquote within a list item, the blockquote's `>` +delimiters need to be indented: + + * A list item with a blockquote: + + > This is a blockquote + > inside a list item. + +To put a code block within a list item, the code block needs +to be indented *twice* -- 8 spaces or two tabs: + + * A list item with a code block: + + <code goes here> + + +It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this: + + 1986. What a great season. + +In other words, a *number-period-space* sequence at the beginning of a +line. To avoid this, you can backslash-escape the period: + + 1986\. What a great season. + + + +<h3 id="precode">Code Blocks</h3> + +Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both `<pre>` and `<code>` tags. + +To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input: + + This is a normal paragraph: + + This is a code block. + +Markdown will generate: + + <p>This is a normal paragraph:</p> + + <pre><code>This is a code block. + </code></pre> + +One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this: + + Here is an example of AppleScript: + + tell application "Foo" + beep + end tell + +will turn into: + + <p>Here is an example of AppleScript:</p> + + <pre><code>tell application "Foo" + beep + end tell + </code></pre> + +A code block continues until it reaches a line that is not indented +(or the end of the article). + +Within a code block, ampersands (`&`) and angle brackets (`<` and `>`) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this: + + <div class="footer"> + © 2004 Foo Corporation + </div> + +will turn into: + + <pre><code><div class="footer"> + &copy; 2004 Foo Corporation + </div> + </code></pre> + +Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax. + + + +<h3 id="hr">Horizontal Rules</h3> + +You can produce a horizontal rule tag (`<hr />`) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule: + + * * * + + *** + + ***** + + - - - + + --------------------------------------- + + _ _ _ + + +* * * + +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +Markdown supports two style of links: *inline* and *reference*. + +In both styles, the link text is delimited by [square brackets]. + +To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an *optional* +title for the link, surrounded in quotes. For example: + + This is [an example](http://example.com/ "Title") inline link. + + [This link](http://example.net/) has no title attribute. + +Will produce: + + <p>This is <a href="http://example.com/" title="Title"> + an example</a> inline link.</p> + + <p><a href="http://example.net/">This link</a> has no + title attribute.</p> + +If you're referring to a local resource on the same server, you can +use relative paths: + + See my [About](/about/) page for details. + +Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link: + + This is [an example][id] reference-style link. + +You can optionally use a space to separate the sets of brackets: + + This is [an example] [id] reference-style link. + +Then, anywhere in the document, you define your link label like this, +on a line by itself: + + [id]: http://example.com/ "Optional Title Here" + +That is: + +* Square brackets containing the link identifier (optionally + indented from the left margin using up to three spaces); +* followed by a colon; +* followed by one or more spaces (or tabs); +* followed by the URL for the link; +* optionally followed by a title attribute for the link, enclosed + in double or single quotes. + +The link URL may, optionally, be surrounded by angle brackets: + + [id]: <http://example.com/> "Optional Title Here" + +You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs: + + [id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" + +Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output. + +Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links: + + [link text][a] + [link text][A] + +are equivalent. + +The *implicit link name* shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write: + + [Google][] + +And then define the link: + + [Google]: http://google.com/ + +Because link names may contain spaces, this shortcut even works for +multiple words in the link text: + + Visit [Daring Fireball][] for more information. + +And then define the link: + + [Daring Fireball]: http://daringfireball.net/ + +Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes. + +Here's an example of reference links in action: + + I get 10 times more traffic from [Google] [1] than from + [Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Using the implicit link name shortcut, you could instead write: + + I get 10 times more traffic from [Google][] than from + [Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" + +Both of the above examples will produce the following HTML output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from + <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> + or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> + +For comparison, here is the same paragraph written using +Markdown's inline link style: + + I get 10 times more traffic from [Google](http://google.com/ "Google") + than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or + [MSN](http://search.msn.com/ "MSN Search"). + +The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text. + +With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose. + + +<h3 id="em">Emphasis</h3> + +Markdown treats asterisks (`*`) and underscores (`_`) as indicators of +emphasis. Text wrapped with one `*` or `_` will be wrapped with an +HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML +`<strong>` tag. E.g., this input: + + *single asterisks* + + _single underscores_ + + **double asterisks** + + __double underscores__ + +will produce: + + <em>single asterisks</em> + + <em>single underscores</em> + + <strong>double asterisks</strong> + + <strong>double underscores</strong> + +You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span. + +Emphasis can be used in the middle of a word: + + un*fucking*believable + +But if you surround an `*` or `_` with spaces, it'll be treated as a +literal asterisk or underscore. + +To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it: + + \*this text is surrounded by literal asterisks\* + + + +<h3 id="code">Code</h3> + +To indicate a span of code, wrap it with backtick quotes (`` ` ``). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example: + + Use the `printf()` function. + +will produce: + + <p>Use the <code>printf()</code> function.</p> + +To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters: + + ``There is a literal backtick (`) here.`` + +which will produce this: + + <p><code>There is a literal backtick (`) here.</code></p> + +The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span: + + A single backtick in a code span: `` ` `` + + A backtick-delimited string in a code span: `` `foo` `` + +will produce: + + <p>A single backtick in a code span: <code>`</code></p> + + <p>A backtick-delimited string in a code span: <code>`foo`</code></p> + +With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this: + + Please don't use any `<blink>` tags. + +into: + + <p>Please don't use any <code><blink></code> tags.</p> + +You can write this: + + `—` is the decimal-encoded equivalent of `—`. + +to produce: + + <p><code>&#8212;</code> is the decimal-encoded + equivalent of <code>&mdash;</code>.</p> + + + +<h3 id="img">Images</h3> + +Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format. + +Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: *inline* and *reference*. + +Inline image syntax looks like this: + +  + +  + +That is: + +* An exclamation mark: `!`; +* followed by a set of square brackets, containing the `alt` + attribute text for the image; +* followed by a set of parentheses, containing the URL or path to + the image, and an optional `title` attribute enclosed in double + or single quotes. + +Reference-style image syntax looks like this: + + ![Alt text][id] + +Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references: + + [id]: url/to/image "Optional title attribute" + +As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML `<img>` tags. + + +* * * + + +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this: + + <http://example.com/> + +Markdown will turn this into: + + <a href="http://example.com/">http://example.com/</a> + +Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this: + + <address@example.com> + +into something like this: + + <a href="mailto:addre + ss@example.co + m">address@exa + mple.com</a> + +which will render in a browser as a clickable link to "address@example.com". + +(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.) + + + +<h3 id="backslash">Backslash Escapes</h3> + +Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML `<em>` tag), you can backslashes +before the asterisks, like this: + + \*literal asterisks\* + +Markdown provides backslash escapes for the following characters: + + \ backslash + ` backtick + * asterisk + _ underscore + {} curly braces + [] square brackets + () parentheses + # hash mark + + plus sign + - minus sign (hyphen) + . dot + ! exclamation mark + diff --git a/MarkdownTest/Tests_2007/Nested blockquotes.html b/MarkdownTest/Tests_2007/Nested blockquotes.html new file mode 100644 index 0000000..d8ec7f8 --- /dev/null +++ b/MarkdownTest/Tests_2007/Nested blockquotes.html @@ -0,0 +1,9 @@ +<blockquote> + <p>foo</p> + + <blockquote> + <p>bar</p> + </blockquote> + + <p>foo</p> +</blockquote> diff --git a/MarkdownTest/Tests_2007/Nested blockquotes.text b/MarkdownTest/Tests_2007/Nested blockquotes.text new file mode 100644 index 0000000..ed3c624 --- /dev/null +++ b/MarkdownTest/Tests_2007/Nested blockquotes.text @@ -0,0 +1,5 @@ +> foo +> +> > bar +> +> foo diff --git a/MarkdownTest/Tests_2007/Ordered and unordered lists.html b/MarkdownTest/Tests_2007/Ordered and unordered lists.html new file mode 100644 index 0000000..ba71eab --- /dev/null +++ b/MarkdownTest/Tests_2007/Ordered and unordered lists.html @@ -0,0 +1,148 @@ +<h2>Unordered</h2> + +<p>Asterisks tight:</p> + +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> + +<p>Asterisks loose:</p> + +<ul> +<li><p>asterisk 1</p></li> +<li><p>asterisk 2</p></li> +<li><p>asterisk 3</p></li> +</ul> + +<hr /> + +<p>Pluses tight:</p> + +<ul> +<li>Plus 1</li> +<li>Plus 2</li> +<li>Plus 3</li> +</ul> + +<p>Pluses loose:</p> + +<ul> +<li><p>Plus 1</p></li> +<li><p>Plus 2</p></li> +<li><p>Plus 3</p></li> +</ul> + +<hr /> + +<p>Minuses tight:</p> + +<ul> +<li>Minus 1</li> +<li>Minus 2</li> +<li>Minus 3</li> +</ul> + +<p>Minuses loose:</p> + +<ul> +<li><p>Minus 1</p></li> +<li><p>Minus 2</p></li> +<li><p>Minus 3</p></li> +</ul> + +<h2>Ordered</h2> + +<p>Tight:</p> + +<ol> +<li>First</li> +<li>Second</li> +<li>Third</li> +</ol> + +<p>and:</p> + +<ol> +<li>One</li> +<li>Two</li> +<li>Three</li> +</ol> + +<p>Loose using tabs:</p> + +<ol> +<li><p>First</p></li> +<li><p>Second</p></li> +<li><p>Third</p></li> +</ol> + +<p>and using spaces:</p> + +<ol> +<li><p>One</p></li> +<li><p>Two</p></li> +<li><p>Three</p></li> +</ol> + +<p>Multiple paragraphs:</p> + +<ol> +<li><p>Item 1, graf one.</p> + +<p>Item 2. graf two. The quick brown fox jumped over the lazy dog's +back.</p></li> +<li><p>Item 2.</p></li> +<li><p>Item 3.</p></li> +</ol> + +<h2>Nested</h2> + +<ul> +<li>Tab +<ul> +<li>Tab +<ul> +<li>Tab</li> +</ul></li> +</ul></li> +</ul> + +<p>Here's another:</p> + +<ol> +<li>First</li> +<li>Second: +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul></li> +<li>Third</li> +</ol> + +<p>Same thing but with paragraphs:</p> + +<ol> +<li><p>First</p></li> +<li><p>Second:</p> + +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul></li> +<li><p>Third</p></li> +</ol> + + +<p>This was an error in Markdown 1.0.1:</p> + +<ul> +<li><p>this</p> + +<ul><li>sub</li></ul> + +<p>that</p></li> +</ul> diff --git a/MarkdownTest/Tests_2007/Ordered and unordered lists.text b/MarkdownTest/Tests_2007/Ordered and unordered lists.text new file mode 100644 index 0000000..7f3b497 --- /dev/null +++ b/MarkdownTest/Tests_2007/Ordered and unordered lists.text @@ -0,0 +1,131 @@ +## Unordered + +Asterisks tight: + +* asterisk 1 +* asterisk 2 +* asterisk 3 + + +Asterisks loose: + +* asterisk 1 + +* asterisk 2 + +* asterisk 3 + +* * * + +Pluses tight: + ++ Plus 1 ++ Plus 2 ++ Plus 3 + + +Pluses loose: + ++ Plus 1 + ++ Plus 2 + ++ Plus 3 + +* * * + + +Minuses tight: + +- Minus 1 +- Minus 2 +- Minus 3 + + +Minuses loose: + +- Minus 1 + +- Minus 2 + +- Minus 3 + + +## Ordered + +Tight: + +1. First +2. Second +3. Third + +and: + +1. One +2. Two +3. Three + + +Loose using tabs: + +1. First + +2. Second + +3. Third + +and using spaces: + +1. One + +2. Two + +3. Three + +Multiple paragraphs: + +1. Item 1, graf one. + + Item 2. graf two. The quick brown fox jumped over the lazy dog's + back. + +2. Item 2. + +3. Item 3. + + + +## Nested + +* Tab + * Tab + * Tab + +Here's another: + +1. First +2. Second: + * Fee + * Fie + * Foe +3. Third + +Same thing but with paragraphs: + +1. First + +2. Second: + * Fee + * Fie + * Foe + +3. Third + + +This was an error in Markdown 1.0.1: + +* this + + * sub + + that diff --git a/MarkdownTest/Tests_2007/Strong and em together.html b/MarkdownTest/Tests_2007/Strong and em together.html new file mode 100644 index 0000000..71ec78c --- /dev/null +++ b/MarkdownTest/Tests_2007/Strong and em together.html @@ -0,0 +1,7 @@ +<p><strong><em>This is strong and em.</em></strong></p> + +<p>So is <strong><em>this</em></strong> word.</p> + +<p><strong><em>This is strong and em.</em></strong></p> + +<p>So is <strong><em>this</em></strong> word.</p> diff --git a/MarkdownTest/Tests_2007/Strong and em together.text b/MarkdownTest/Tests_2007/Strong and em together.text new file mode 100644 index 0000000..95ee690 --- /dev/null +++ b/MarkdownTest/Tests_2007/Strong and em together.text @@ -0,0 +1,7 @@ +***This is strong and em.*** + +So is ***this*** word. + +___This is strong and em.___ + +So is ___this___ word. diff --git a/MarkdownTest/Tests_2007/Tabs.html b/MarkdownTest/Tests_2007/Tabs.html new file mode 100644 index 0000000..3301ba8 --- /dev/null +++ b/MarkdownTest/Tests_2007/Tabs.html @@ -0,0 +1,25 @@ +<ul> +<li><p>this is a list item +indented with tabs</p></li> +<li><p>this is a list item +indented with spaces</p></li> +</ul> + +<p>Code:</p> + +<pre><code>this code block is indented by one tab +</code></pre> + +<p>And:</p> + +<pre><code> this code block is indented by two tabs +</code></pre> + +<p>And:</p> + +<pre><code>+ this is an example list item + indented with tabs + ++ this is an example list item + indented with spaces +</code></pre> diff --git a/MarkdownTest/Tests_2007/Tabs.text b/MarkdownTest/Tests_2007/Tabs.text new file mode 100644 index 0000000..589d113 --- /dev/null +++ b/MarkdownTest/Tests_2007/Tabs.text @@ -0,0 +1,21 @@ ++ this is a list item + indented with tabs + ++ this is a list item + indented with spaces + +Code: + + this code block is indented by one tab + +And: + + this code block is indented by two tabs + +And: + + + this is an example list item + indented with tabs + + + this is an example list item + indented with spaces diff --git a/MarkdownTest/Tests_2007/Tidyness.html b/MarkdownTest/Tests_2007/Tidyness.html new file mode 100644 index 0000000..f2a8ce7 --- /dev/null +++ b/MarkdownTest/Tests_2007/Tidyness.html @@ -0,0 +1,8 @@ +<blockquote> +<p>A list within a blockquote:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +</blockquote> diff --git a/MarkdownTest/Tests_2007/Tidyness.text b/MarkdownTest/Tests_2007/Tidyness.text new file mode 100644 index 0000000..5f18b8d --- /dev/null +++ b/MarkdownTest/Tests_2007/Tidyness.text @@ -0,0 +1,5 @@ +> A list within a blockquote: +> +> * asterisk 1 +> * asterisk 2 +> * asterisk 3 diff --git a/MarkdownTest/readme.txt b/MarkdownTest/readme.txt new file mode 100644 index 0000000..68047b5 --- /dev/null +++ b/MarkdownTest/readme.txt @@ -0,0 +1 @@ +MarkdownTest_1.0_2007-05-09 updated for the new version of tidy. diff --git a/bin/markdown b/bin/markdown new file mode 100755 index 0000000..8d04cc9 --- /dev/null +++ b/bin/markdown @@ -0,0 +1,42 @@ +#!/usr/bin/env python +""" +Python Markdown, the Command Line Script +======================================== + +This is the command line script for Python Markdown. + +Basic use from the command line: + + markdown source.txt > destination.html + +Run "markdown --help" to see more options. + +See markdown/__init__.py for information on using Python Markdown as a module. + +## Authors and License + +Started by [Manfred Stienstra](http://www.dwerg.net/). Continued and +maintained by [Yuri Takhteyev](http://www.freewisdom.org), [Waylan +Limberg](http://achinghead.com/) and [Artem Yunusov](http://blog.splyer.com). + +Contact: markdown@freewisdom.org + +Copyright 2007, 2008 The Python Markdown Project (v. 1.7 and later) +Copyright 200? Django Software Foundation (OrderedDict implementation) +Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b) +Copyright 2004 Manfred Stienstra (the original version) + +License: BSD (see docs/LICENSE for details). +""" + +import logging +from markdown import COMMAND_LINE_LOGGING_LEVEL +from markdown import commandline + +# Setup a logger manually for compatibility with Python 2.3 +logger = logging.getLogger('MARKDOWN') +logger.setLevel(COMMAND_LINE_LOGGING_LEVEL) +logger.addHandler(logging.StreamHandler()) + +if __name__ == '__main__': + commandline.run() diff --git a/docs/AUTHORS b/docs/AUTHORS new file mode 100644 index 0000000..2843b56 --- /dev/null +++ b/docs/AUTHORS @@ -0,0 +1,44 @@ +Primary Authors +=============== + +Yuri Takteyev <http://freewisdom.org/>, who has written much of the current code +while procrastingating his Ph.D. + +Waylan Limberg <http://achinghead.com/>, who has written most of the available +extensions and later was asked to join Yuri, fixing nummrious bugs, adding +documentation and making general improvements to the existing codebase, +included a complete refactor of the core. + +Artem Yunusov, who as part of a 2008 GSoC project, has refactored inline +patterns, replaced the NanoDOM with ElementTree support and made various other +improvements. + +Manfed Stienstra <http://www.dwerg.net/>, who wrote the original version of +the script and is responsible for various parts of the existing codebase. + +David Wolever, who refactored the extension API and made other improvements +as he helped to integrate Markdown into Dr.Project. + +Other Contributors +================== + +The incomplete list of individuals below have provided patches or otherwise +contributed to the project in various ways. We would like to thank everyone +who has contributed to the progect in any way. + +Eric Abrahamsen +Jeff Balogh +Sergej Chodarev +Chris Clark +Tiago Cogumbreiro +Kjell Magne Fauske +G. Clark Haynes +Daniel Krech +Steward Midwinter +Jack Miller +Neale Pickett +Paul Stansifer +John Szakmeister +Malcolm Tredinnick +Ben Wilson +and many others who helped by reporting bugs diff --git a/docs/CHANGE_LOG b/docs/CHANGE_LOG new file mode 100644 index 0000000..e005ff8 --- /dev/null +++ b/docs/CHANGE_LOG @@ -0,0 +1,180 @@ +PYTHON MARKDOWN CHANGELOG +========================= + +Sept 28, 2009: Released version 2.0.2-Final. + +May 20, 2009: Released version 2.0.1-Final. + +Mar 30, 2009: Released version 2.0-Final. + +Mar 8, 2009: Release Candidate 2.0-rc-1. + +Feb 2009: Added support for multi-level lists to new Blockprocessors. + +Jan 2009: Added HTML 4 output as an option (thanks Eric Abrahamsen) + +Nov 2008: Added Definistion List ext. Replaced old core with BlockProcessors. +Broken up into multiple files. + +Oct 2008: Changed logging behavior to work better with other systems. +Refactored tree tarversing. Added treap implementation, then replaced with +OrderedDEict. Renamed various processors to better reflect what they actually +do. Refactored footnote ext to match php Extra's output. + +Sept 2008: Moved prettifyTree to a Postprocessor, replaced wikilink ext +with wikilinks (note the s) ext (uses bracketed links instead of CamelCase) +and various bug fixes. + +August 18 2008: Reorganized directory structure. Added a 'docs' dir +and moved all extensions into a 'markdown-extensions' package. +Added additional documentation and a few bug fixes. (v2.0-beta) + +August 4 2008: Updated included extensions to ElementTree. Added a +seperate commanline script. (v2.0-alpha) + +July 2008: Switched from home-grown NanoDOM to ElementTree and +various related bugs (thanks Artem Yunusov). + +June 2008: Fixed issues with nested inline patterns and cleaned +up testing framework (thanks Artem Yunusov). + +May 2008: Added a number of additional extensions to the +distribution and other minor changes. Moved repo to git from svn. + +Mar 2008: Refactored extension api to accept either an +extension name (as a string) or an instance of an extension +(Thanks David Wolever). Fixed various bugs and added doc strings. + +Feb 2008: Various bugfixes mostly regarding extensions. + +Feb 18, 2008: Version 1.7. + +Feb 13, 2008: A little code cleanup and better documentation +and inheritance for pre/post proccessors. + +Feb 9, 2008: Doublequotes no longer html escaped and rawhtml +honors <?foo>, <@foo>, and <%foo> for those who run markdown on +template syntax. + +Dec 12, 2007: Updated docs. Removed encoding arg from Markdown +and markdown as per list discussion. Clean up in prep for 1.7. + +Nov 29, 2007: Added support for images inside links. Also fixed +a few bugs in the footnote extension. + +Nov 19, 2007: `message` now uses python's logging module. Also removed +limit imposed by recursion in _process_section(). You can now parse as +long of a document as your memory can handle. + +Nov 5, 2007: Moved safe_mode code to a textPostprocessor and added +escaping option. + +Nov 3, 2007: Fixed convert method to accept empty strings. + +Oct 30, 2007: Fixed BOM removal (thanks Malcolm Tredinnick). Fixed +infinite loop in bracket regex for inline links. + +Oct 11, 2007: LineBreaks is now an inlinePattern. Fixed HR in +blockquotes. Refactored _processSection method (see tracker #1793419). + +Oct 9, 2007: Added textPreprocessor (from 1.6b). + +Oct 8, 2008: Fixed Lazy Blockquote. Fixed code block on first line. +Fixed empty inline image link. + +Oct 7, 2007: Limit recursion on inlinePatterns. Added a 'safe' tag +to htmlStash. + +March 18, 2007: Fixed or merged a bunch of minor bugs, including +multi-line comments and markup inside links. (Tracker #s: 1683066, +1671153, 1661751, 1627935, 1544371, 1458139.) -> v. 1.6b + +Oct 10, 2006: Fixed a bug that caused some text to be lost after +comments. Added "safe mode" (user's html tags are removed). + +Sept 6, 2006: Added exception for PHP tags when handling html blocks. + +August 7, 2006: Incorporated Sergej Chodarev's patch to fix a problem +with ampersand normalization and html blocks. + +July 10, 2006: Switched to using optparse. Added proper support for +unicode. + +July 9, 2006: Fixed the <!--@address.com> problem (Tracker #1501354). + +May 18, 2006: Stopped catching unquoted titles in reference links. +Stopped creating blank headers. + +May 15, 2006: A bug with lists, recursion on block-level elements, +run-in headers, spaces before headers, unicode input (thanks to Aaron +Swartz). Sourceforge tracker #s: 1489313, 1489312, 1489311, 1488370, +1485178, 1485176. (v. 1.5) + +Mar. 24, 2006: Switched to a not-so-recursive algorithm with +_handleInline. (Version 1.4) + +Mar. 15, 2006: Replaced some instance variables with class variables +(a patch from Stelios Xanthakis). Chris Clark's new regexps that do +not trigger midword underlining. + +Feb. 28, 2006: Clean-up and command-line handling by Stewart +Midwinter. (Version 1.3) + +Feb. 24, 2006: Fixed a bug with the last line of the list appearing +again as a separate paragraph. Incorporated Chris Clark's "mailto" +patch. Added support for <br /> at the end of lines ending in two or +more spaces. Fixed a crashing bug when using ImageReferencePattern. +Added several utility methods to Nanodom. (Version 1.2) + +Jan. 31, 2006: Added "hr" and "hr/" to BLOCK_LEVEL_ELEMENTS and +changed <hr/> to <hr />. (Thanks to Sergej Chodarev.) + +Nov. 26, 2005: Fixed a bug with certain tabbed lines inside lists +getting wrapped in <pre><code>. (v. 1.1) + +Nov. 19, 2005: Made "<!...", "<?...", etc. behave like block-level +HTML tags. + +Nov. 14, 2005: Added entity code and email autolink fix by Tiago +Cogumbreiro. Fixed some small issues with backticks to get 100% +compliance with John's test suite. (v. 1.0) + +Nov. 7, 2005: Added an unlink method for documents to aid with memory +collection (per Doug Sauder's suggestion). + +Oct. 29, 2005: Restricted a set of html tags that get treated as +block-level elements. + +Sept. 18, 2005: Refactored the whole script to make it easier to +customize it and made footnote functionality into an extension. +(v. 0.9) + +Sept. 5, 2005: Fixed a bug with multi-paragraph footnotes. Added +attribute support. + +Sept. 1, 2005: Changed the way headers are handled to allow inline +syntax in headers (e.g. links) and got the lists to use p-tags +correctly (v. 0.8) + +Aug. 29, 2005: Added flexible tabs, fixed a few small issues, added +basic support for footnotes. Got rid of xml.dom.minidom and added +pretty-printing. (v. 0.7) + +Aug. 13, 2005: Fixed a number of small bugs in order to conform to the +test suite. (v. 0.6) + +Aug. 11, 2005: Added support for inline html and entities, inline +images, autolinks, underscore emphasis. Cleaned up and refactored the +code, added some more comments. + +Feb. 19, 2005: Rewrote the handling of high-level elements to allow +multi-line list items and all sorts of nesting. + +Feb. 3, 2005: Reference-style links, single-line lists, backticks, +escape, emphasis in the beginning of the paragraph. + +Nov. 2004: Added links, blockquotes, html blocks to Manfred +Stienstra's code + +Apr. 2004: Manfred's version at http://www.dwerg.net/projects/markdown/ + diff --git a/docs/INSTALL b/docs/INSTALL new file mode 100644 index 0000000..d8feade --- /dev/null +++ b/docs/INSTALL @@ -0,0 +1,73 @@ +Installing Python-Markdown +========================== + +Checking Dependencies +--------------------- + +Python-Markdown requires the ElementTree module to be installed. In Python2.5+ +ElementTree is included as part of the standard library. For earlier versions +of Python, open a Python shell and type the following: + + >>> import cElementTree + >>> import ElementTree + +If at least one of those does not generate any errors, then you have a working +copy of ElementTree installed on your system. As cElementTree is faster, you +may want to install that if you don't already have it and it's available for +your system. + +See <http://effbot.org/zone/element-index.htm> for more information or to +download the latest version of ElementTree. + +The East Way +------------ + +The simplest way to install Python-Markdown is by using SetupTools. As and +Admin/Root user on your system do: + + easy_install ElementTree + easy_install Markdown + +That's it, your done. + +Installing on Windows +--------------------- + +Download the Windows installer (.exe) from PyPI: +<http://pypi.python.org/pypi/Markdown> + +Double-click the file and follow the instructions. + +If you prefer to manually install Python-Markdown in Windows, download the +Zip file, unzip it, and on the command line in the directory you unzipped to: + + python setup.py install + +If you plan to use the provided command line script, you need to make sure your +script directory is on your system path. On a typical Python install of Windows +the Scripts directory is `C:\Python25\Scripts\`. Adjust according to your +system and add that to your system path. + +Installing on *nix Systems +-------------------------- + +From the command line do the following: + + wget http://pypi.python.org/packages/source/M/Markdown/Markdown-2.0.tar.gz + tar xvzf Markdown-2.0.tar.gz + cd markdown-2.0/ + sudo python setup.py install + +Using the Git Repository +------------------------ + +If your the type that like to live on the edge, you may want to keep up with +the latest additions and bug fixes in the repository between releases. +Python-Markdown is maintained in a Git repository on Gitorious.org. To +get a copy of Python-Markdown from the repository do the following from the +command line: + + git clone git://gitorious.org/python-markdown/mainline.git python-markdown + cd python-markdown + python setup.py install + diff --git a/docs/LICENSE b/docs/LICENSE new file mode 100644 index 0000000..4cd8b14 --- /dev/null +++ b/docs/LICENSE @@ -0,0 +1,30 @@ +Copyright 2007, 2008 The Python Markdown Project (v. 1.7 and later) +Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b) +Copyright 2004 Manfred Stienstra (the original version) + +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +* Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. +* Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. +* Neither the name of the <organization> nor the + names of its contributors may be used to endorse or promote products + derived from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE PYTHON MARKDOWN PROJECT ''AS IS'' AND ANY +EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED +WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL ANY CONTRIBUTORS TO THE PYTHON MARKDOWN PROJECT +BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. + diff --git a/docs/README b/docs/README new file mode 100644 index 0000000..d19a1ea --- /dev/null +++ b/docs/README @@ -0,0 +1,30 @@ +[Python-Markdown][] +=================== + +This is a Python implementation of John Gruber's [Markdown][]. +It is almost completely compliant with the reference implementation, +though there are a few known issues. See [Features][] for information +on what exactly is supported and what is not. Additional features are +supported by the [Available Extensions][]. + +[Python-Markdown]: http://freewisdom.org/projects/python-markdown +[Markdown]: http://daringfireball.net/projects/markdown/ +[Features]: http://www.freewisdom.org/projects/python-markdown/Features +[Available Extensions]: http://www.freewisdom.org/projects/python-markdown/Available_Extensions + + +Documentation +------------- + +Installation and usage documentation is available in the `docs/` directory +of the distribution and on the project website at +<http://freewisdom.org/projects/python-markdown>. + +Support +------- + +You may ask for help and discuss various other issues on the [mailing list][] and report bugs on the [bug tracker][]. + +[mailing list]: http://lists.sourceforge.net/lists/listinfo/python-markdown-discuss +[bug tracker]: http://www.freewisdom.org/projects/python-markdown/Tickets + diff --git a/docs/README.html b/docs/README.html new file mode 100644 index 0000000..49e3b07 --- /dev/null +++ b/docs/README.html @@ -0,0 +1,12 @@ +<h1><a href="http://freewisdom.org/projects/python-markdown">Python-Markdown</a></h1> +<p>This is a Python implementation of John Gruber's <a href="http://daringfireball.net/projects/markdown/">Markdown</a>. +It is almost completely compliant with the reference implementation, +though there are a few known issues. See <a href="http://www.freewisdom.org/projects/python-markdown/Features">Features</a> for information +on what exactly is supported and what is not. Additional features are +supported by the <a href="http://www.freewisdom.org/projects/python-markdown/Available_Extensions">Available Extensions</a>.</p> +<h2>Documentation</h2> +<p>Installation and usage documentation is available in the <code>docs/</code> directory +of the distribution and on the project website at +<a href="http://freewisdom.org/projects/python-markdown">http://freewisdom.org/projects/python-markdown</a>.</p> +<h2>Support</h2> +<p>You may ask for help and discuss various other issues on the <a href="http://lists.sourceforge.net/lists/listinfo/python-markdown-discuss">mailing list</a> and report bugs on the <a href="http://www.freewisdom.org/projects/python-markdown/Tickets">bug tracker</a>.</p>
\ No newline at end of file diff --git a/docs/command_line.txt b/docs/command_line.txt new file mode 100644 index 0000000..d0134ea --- /dev/null +++ b/docs/command_line.txt @@ -0,0 +1,98 @@ +Using Python-Markdown on the Command Line +========================================= + +While Python-Markdown is primarily a python library, a command line script is +included as well. While there are many other command line implementations +of Markdown, you may not have them installed, or you may prefer to use +Python-Markdown's various extensions. + +Setup +----- + +Generally, you may simply call the ``markdown`` file from the command +line. However, if you have fully installed Markdown (``setup.py install`` or +``easy_install``), then the ``markdown`` script will have been copied to +you Python "Scripts" directory. Different systems require different methods to +ensure that any files in the Python "Scripts" directory are on your system +path. + +* **Windows**: + + Assuming a default install on Windows, your "Scripts" directory is most + likely something like ``C:\\Python25\Scripts``. Verify the location of + your "Scripts" directory and add it to you system path. + + Calling ``markdown`` from th ecommand line will call the wrapper batch file + ``markdown.bat`` in the "Scripts" directory created during install. + +* **Linux**: + + As each Linux distribution is different and we can't possibly document all + of them here, we'll provide a few helpful pointers: + + * Some systems will automatically install the script on your path. Try it + and see if it works. Just run ``markdown`` from the command line. + + * Other systems may maintain a separate "Scripts" directory which you + need to add to your path. Find it (check with your distribution) and + either add it to your path or make a symbolic link to it from your path. + + * If you are sure ``markdown`` is on your path, but it still isn't being + found, check the permissions of the file and make sure it is executable. + + As an alternative, you could just ``cd`` into the directory which contains + the source distribution, and run it from there. However, remember that your + markdown text files will not likely be in that directory, so it is much more + convenient to have ``markdown`` on your path. + +The Basics +---------- + +To use ``markdown`` from the command line, run it as + + $ markdown input_file.txt + +or + + $ markdown input_file.txt > output_file.html + +More Options +------------ + +If you are using Python 2.3 or higher, you can also use advanced +command line options to specify encoding or to run extensions. + + $ markdown --help + Usage: markdown INPUTFILE [options] + + Options: + -h, --help show this help message and exit + -f OUTPUT_FILE, --file=OUTPUT_FILE + write output to OUTPUT_FILE + -e ENCODING, --encoding=ENCODING + encoding for input and output files + -q, --quiet suppress all messages + -v, --verbose print info messages + -s SAFE_MODE, --safe=SAFE_MODE + safe mode ('replace', 'remove' or 'escape' user's + HTML tag) + -o OUTPUT_FORMAT, --output_format=OUTPUT_FORMAT + Format of output. One of 'xhtml1' (default) or + 'html4'. + --noisy print debug messages + -x EXTENSION, --extension=EXTENSION + load extension EXTENSION + +Using Extensions +---------------- + +For an extension to be ran this way it must be provided in a module +which should be in your python path (see [[writing_extensions]] for details). +It can then be invoked by the name of that module: + + $ markdown -x footnotes text_with_footnotes.txt > output.html + +If the extension supports config options, you can pass them in as well: + + $ markdown -x "footnotes(PLACE_MARKER=~~~~~~~~)" input.txt + diff --git a/docs/extensions/Abbreviations.txt b/docs/extensions/Abbreviations.txt new file mode 100644 index 0000000..fa54d3c --- /dev/null +++ b/docs/extensions/Abbreviations.txt @@ -0,0 +1,53 @@ +Abbreviations +------------- + +Summary +------- + +The Markdown Abbreviation Extension adds the ability to define abbreviations. +Specifically, any defined abbreviation is wrapped in an `<abbr>` tag. + +The Abbreviation extension is included in the standard Markdown library. + +Syntax +------ + +Abbreviations are defined using the syntax established in +[PHP Markdown Extra][php]. + +[php]: http://www.michelf.com/projects/php-markdown/extra/#abbr + +Thus, the following text (taken from the above referenced PHP documentation): + + The HTML specification + is maintained by the W3C. + + *[HTML]: Hyper Text Markup Language + *[W3C]: World Wide Web Consortium + +will be rendered like so: + + <p>The <abbr title="Hyper Text Markup Language">HTML</abbr> specification + is maintained by the <abbr title="World Wide Web Consortium">W3C</abbr>.</p> + +Usage +----- + +From the Python interpreter: + + >>> import markdown + >>> text = """ + ... Some text with an ABBR. + ... + ... *[ABBR]: Abbreviation + ... """ + >>> html = markdown.markdown(text, ['abbr']) + +To use with other extensions, just add them to the list, like this: + + >>> html = markdown.markdown(text, ['abbr', 'footnotes']) + +Abbreviations can also be called from the command line using Markdown's `-x` +parameter, like so: + + markdown.py -x abbr source.txt > output.html diff --git a/docs/extensions/CodeHilite.txt b/docs/extensions/CodeHilite.txt new file mode 100644 index 0000000..482ad60 --- /dev/null +++ b/docs/extensions/CodeHilite.txt @@ -0,0 +1,113 @@ +CodeHilite +========== + +Summary +------- + +The CodeHilite Extension adds code/syntax highlighting to standard +Python-Markdown code blocks using [Pygments][]. + +[Python-Markdown]: http://www.freewisdom.org/projects/python-markdown/ +[Pygments]: http://pygments.org/ + +This extension is included in the Markdown library. + +Setup +----- + +You will also need to [download][dl] and install the Pygments package on your +`PYTHONPATH`. You will need to determine the appropriate CSS classes and create +appropriate rules for them, which are either defined in or linked from the +header of your HTML templates. See the excellent [documentation][] for more +details. If no language is defined, Pygments will attempt to guess the +language. When that fails, the code block will display as un-highlighted code. + +[dl]: http://pygments.org/download/ +[documentation]: http://pygments.org/docs + +**Note:** The css and/or javascript is not included as part of this extension +but shall always be provided by the end user. + +Syntax +------ + +The CodeHilite Extension follows the same [syntax][] as regular Markdown code +blocks, with one exception. The hiliter needs to know what language to use for +the code block. There are three ways to tell the hiliter what language the code +block contains and each one has a different result. + +[syntax]: http://daringfireball.net/projects/markdown/syntax#precode + +###SheBang (with path) + +If the first line of the codeblock contains a shebang, the language is derived +from that and line numbers are used. + + #!/usr/bin/python + # Code goes here ... + +Will result in: + + #!/usr/bin/python + # Code goes here ... + + +###SheBang (no path) + +If the first line contains a shebang, but the shebang line does not contain a +path (a single `/` or even a space), then that line is removed from the code +block before processing. Line numbers are used. + + #!python + # Code goes here ... + +Will result in: + + # Code goes here ... + +####Colons + +If the first line begins with three or more colons, the text following the +colons identifies the language. The first line is removed from the code block +before processing and line numbers are not used. + + :::python + # Code goes here ... + +Will result in: + + # Code goes here ... + +###When No Language is Defined + +CodeHilite is completely backward compatible so that if a code block is +encountered that does not define a language, the block is simple wrapped in +`<pre>` tags and output. Note: one exception would be that the Pygments +highlighting engine will try to guess the language. Upon failure, the same +behavior will happen as described here. + + # Code goes here ... + +Will result in: + + # Code goes here ... + +Lets see the source for that: + + <div class="codehilite" ><pre><code># Code goes here ... + </code></pre></div> + +Usage +----- + +From the Python interpreter: + + >>> html = markdown.markdown(text, ['codehilite']) + +If you want every code block to have line numbers, even when using colons +(`:::`) for language identification, the setting `force_linenos` is available +to do so. + + >>> html = markdown.markdown(text, + ... ['codehilite(force_linenos=True)'] + ... ) diff --git a/docs/extensions/Definition_Lists.txt b/docs/extensions/Definition_Lists.txt new file mode 100644 index 0000000..983070d --- /dev/null +++ b/docs/extensions/Definition_Lists.txt @@ -0,0 +1,55 @@ +Definition Lists +---------------- + +Summary +------- + +The Definition List Extension adds the ability to create definition list in +Markdown documents. + +This extension is included in the standard Markdown library. + +Syntax +------ + +Definition lists are defined using the syntax established in +[PHP Markdown Extra][php]. + +[php]: http://www.michelf.com/projects/php-markdown/extra/#def-list + +Thus, the following text (taken from the above referenced PHP documentation): + + Apple + : Pomaceous fruit of plants of the genus Malus in + the family Rosaceae. + + Orange + : The fruit of an evergreen tree of the genus Citrus. + +will be rendered like so: + + <dl> + <dt>Apple</dt> + <dd>Pomaceous fruit of plants of the genus Malus in + the family Rosaceae.</dd> + + <dt>Orange</dt> + <dd>The fruit of an evergreen tree of the genus Citrus.</dd> + </dl> + + +Usage +----- + +From the Python interpreter: + + >>> html = markdown.markdown(text, ['def_list']) + +To use with other extensions, just add them to the list, like this: + + >>> html = markdown.markdown(text, ['def_list', 'footnotes']) + +The extension can also be called from the command line using Markdown's `-x` +parameter: + + markdown.py -x def_list source.txt > output.html diff --git a/docs/extensions/Fenced_Code_Blocks.txt b/docs/extensions/Fenced_Code_Blocks.txt new file mode 100644 index 0000000..6b1ba76 --- /dev/null +++ b/docs/extensions/Fenced_Code_Blocks.txt @@ -0,0 +1,63 @@ +Fenced Code Blocks +================== + +Summary +------- + +This extension adds a secondary way to define code blocks which overcomes a few +limitations of the indented code blocks. + +This extension is included in the standard Markdown library. + +Syntax +------ + +Fenced Code Blocks are defined using the syntax established in +[PHP Markdown Extra][php]. + +[php]: http://www.michelf.com/projects/php-markdown/extra/#fenced-code-blocks + +Thus, the following text (taken from the above referenced PHP documentation): + + This is a paragraph introducing: + + ~~~~~~~~~~~~~~~~~~~~ + a one-line code block + ~~~~~~~~~~~~~~~~~~~~ + +Fenced code blocks can have a blank line as the first and/or last line of a +code block and they can also come immediately after a list item without becoming +part of the list. + +In addition to PHP Extra's syntax, you can define the language of the code +block for use by syntax highlighters etc. The language will be assigned as a +class attribute of the ``<code>`` element in the output. Therefore, you should +define the language as you would a css class - ``.language``. For consistency +with other markdown syntax, the language can *optionally* be wrapped in curly +brackets: + + ~~~~{.python} + # python code + ~~~~ + + ~~~~.html + <p>HTML Document</p> + ~~~~ + +The above will output: + + <pre><code class="python"># python code + </code></pre> + + <pre><code class="html"><p>HTML Document</p> + </code></pre> + +Usage +----- + +From the Python interpreter: + + >>> html = markdown.markdown(text, ['fenced_code']) + + + diff --git a/docs/extensions/HTML_Tidy.txt b/docs/extensions/HTML_Tidy.txt new file mode 100644 index 0000000..52f991f --- /dev/null +++ b/docs/extensions/HTML_Tidy.txt @@ -0,0 +1,27 @@ +HTML Tidy +========= + +Runs [HTML Tidy][] on the output of Python-Markdown using the [uTidylib][] +Python wrapper. Both libtidy and uTidylib must be installed on your system. + +This extension is available in the standard Markdown library since version 2.0. + +[HTML Tidy]: http://tidy.sourceforge.net/ +[uTidylib]: http://utidylib.berlios.de/ + +Note than any Tidy [options][] can be passed in as extension configs. So, +for example, to output HTML rather than XHTML, set ``output_xhtml=0``. To +indent the output, set ``indent=auto`` and to have Tidy wrap the output in +``<html>`` and ``<body>`` tags, set ``show_body_only=0``. See Tidy's +[options][] for a full list of the available options. The defaults are set to +most closely match Markdowns defaults with the exception that you get much +better pretty-printing. + +[options]: http://tidy.sourceforge.net/docs/quickref.html + +Note that options set in this extension will override most any other settings +passed on to Markdown (such as "output_format"). Unlike Markdown, this extension +will also treat raw HTML no different than that output by Markdown. In other +words, it may munge a document authors carefully crafted HTML. Of course, it +may also transform poorly formed raw HTML into nice, valid HTML. Take these +things into consideration when electing to use this extension. diff --git a/docs/extensions/HeaderId.txt b/docs/extensions/HeaderId.txt new file mode 100644 index 0000000..efd1eb8 --- /dev/null +++ b/docs/extensions/HeaderId.txt @@ -0,0 +1,104 @@ +HeaderId +======== + +Summary +------- + +An extension to Python-Markdown that adds an 'id' attribute to HTML header +elements (h1-h6) in markdown's output. + +This extension is included in the standard Markdown library. + +Syntax +------ + +The basic syntax follows [PHP Markdown Extra][]'s implementation: + +[PHP Markdown Extra]: http://michelf.com/projects/php-markdown/extra/#header-id + + Header 1 {#header1} + ======== + + ## Header 2 ## {#header2} + +will result in the following HTML: + + <h1 id="header1">Header 1</h1> + + <h2 id="header2">Header 2</h2> + +However, there is much more that this extension does. + +By default, all headers will automatically have unique "id" attributes +generated based upon the text of the header (See below to turn this off). +Note this example in which all three headers would have the same "id": + + #Header + #Another Header {#header} + #Header + +Results in: + + <h1 id="header">Header</h1> + <h1 id="header_1">Another Header</h1> + <h1 id="header_2">Third Header</h1> + +Configuring the Output +---------------------- + +The HeaderId extension has two configuration settings: + +* **level**: Base level for headers. + + Default: `1` + +* **forceid**: Force all headers to have an id. + + Default: `True` + +The `level` setting allows you to automatically adjust the header levels to fit +within the hierarchy of your html templates. For example, the markdown text for +this page should not contain any headers higher than level 3 (`<h3>`). +Therefore, do the following: + + >>> text = ''' + ... #Some Header + ... ## Next Level''' + >>> html = markdown.markdown(text, ['headerid(level=3)']) + >>> print html + <h3 id="some_header">Some Header</h3> + <h4 id="next_level">Next Level</h4>' + +The `forceid` setting turns on or off the automatically generated ids for +headers that do not have one explicitly defined. + + >>> text = ''' + ... # Some Header + ... # Header with ID # { #foo }''' + >>> html = markdown.markdown(text, ['headerid(forceid=False)']) + >>> print html + <h1>Some Header</h1> + <h1 id="foo">Header with ID</h1> + +Using with Meta-Data +-------------------- + +The HeaderId Extension also supports the [[Meta-Data]] Extension. Please see the documentation for that extension for specifics. The supported meta-data keywords are: + +* `header_level` +* `header_forceid` + +When used, the meta-data will override the settings provided through the +`extension_configs` interface. + +This document: + + header_level: 2 + header_forceid: Off + + # A Header + + +Will result in the following output: + + <h2>A Header</h2> diff --git a/docs/extensions/ImageLinks.txt b/docs/extensions/ImageLinks.txt new file mode 100644 index 0000000..db4f99f --- /dev/null +++ b/docs/extensions/ImageLinks.txt @@ -0,0 +1,27 @@ +ImageLinks +========== + +Summary +------- + +ImageLinks is a Python-Markdown extension that provides a mechanism for +defining mini-photo galleries within a markdown document. + +This extension is part of the Markdown library since 2.0. + +Syntax +------ + +Turns paragraphs like + + <~~~~~~~~~~~~~~~~~~~~~~~~ + dir/subdir + dir/subdir + dir/subdir + ~~~~~~~~~~~~~~ + dir/subdir + dir/subdir + dir/subdir + ~~~~~~~~~~~~~~~~~~~> + +Into mini-photo galleries. diff --git a/docs/extensions/Meta-Data.txt b/docs/extensions/Meta-Data.txt new file mode 100644 index 0000000..982ea67 --- /dev/null +++ b/docs/extensions/Meta-Data.txt @@ -0,0 +1,88 @@ +Meta-Data +========= + +Summary +------- + +An extension to Python-Markdown that adds a syntax for defining meta-data about +a document. The Meta-Data extension is inspired by and follows the syntax of +[MultiMarkdown][]. Currently, this extension does not use the meta-data in any +way, but simply provides it as a `Meta` attribute of a markdown instance for +use by other extensions or directly by your python code. + +[MultiMarkdown]: http://fletcherpenney.net/MultiMarkdown_Syntax_Guide#metadata + +This extension has been a part of the Markdown library since 2.0. + +Syntax +------ + +Meta-data consists of a series of keywords and values defined at the beginning +of a markdown document like this: + + Title: My Document + Summary: A brief description of my document. + Authors: Waylan Limberg + John Doe + Date: October 2, 2007 + blank-value: + base_url: http://example.com + + This is the first paragraph of the document. + +The keywords are case-insensitive and may consist of letters, numbers, +underscores and dashes and must end with a colon. The values consist of +anything following the colon on the line and may even be blank. If a line is +indented 4 or more spaces, that line is assumed to be an additional line of the +value for the previous keyword. A keyword may have as many lines as desired. +The first blank line ends all meta-data for the document. Therefore, the first +line of a document must not be blank. All meta-data is stripped from the +document prior to any further processing by markdown. + +Accessing the Meta-Data +----------------------- + +The meta-data is made available as a python Dict in the `Meta` attribute of an +instance of the Markdown class. For example, using the above document: + + >>> md = markdown.Markdown(extensions = ['meta']) + >>> html = md.convert(text) + >>> # Meta-data has been stripped from output + >>> print html + <p>This is the first paragraph of the document.</p> + + >>> # View meta-data + >>> print md.Meta + { + 'title' : ['My Document'], + 'summary' : ['A brief description of my document.'], + 'authors' : ['Waylan Limberg', 'John Doe'], + 'date' : ['October 2, 2007'], + 'blank-value' : [''], + 'base_url' : ['http://example.com'] + } + +Note that the keys are all lowercase and the values consist of a list of +strings where each item is one line for that key. This way, one could preserve +line breaks if desired. Or the items could be joined where appropriate. No +assumptions are made regarding the data. It is simply passed as found to the +`Meta` attribute. + +Perhaps the meta-data could be passed into a template system, or used by +various markdown extensions. The possibilities are left to the imagination of +the developer. + +Compatible Extensions +--------------------- + +The following are extensions currently known to work with the Meta-Data +Extension and the keywords they are known to support: + +* [[HeaderId]] + * `header_level` + * `header_forceid` +* [[WikiLinks]] + * `wiki_base_url` + * `wiki_end_url` + * `wiki_html_class` + diff --git a/docs/extensions/RSS.txt b/docs/extensions/RSS.txt new file mode 100644 index 0000000..f2ecf0c --- /dev/null +++ b/docs/extensions/RSS.txt @@ -0,0 +1,35 @@ +RSS +=== + +Summary +------- + +An extension to Python-Markdown that outputs a markdown document as RSS. This +extension has been included with Python-Markdown since 1.7 and should be +available to anyone who has a typical install of Python-Markdown. + +Usage +----- + +From the Python interpreter: + + >>> import markdown + >>> text = "Some markdown document." + >>> rss = markdown.markdown(text, ['rss']) + +Configuring the Output +---------------------- + +An RSS document includes some data about the document (URI, author, title) that +will likely need to be configured for your needs. Therefore, three configuration +options are available: + +* **URL** : The Main URL for the document. +* **CREATOR** : The Feed creator's name. +* **TITLE** : The title for the feed. + +An example: + + >>> rss = markdown.markdown(text, extensions = \ + ... ['rss(URL=http://example.com,CREATOR=JOHN DOE,TITLE=My Document)'] + ... ) diff --git a/docs/extensions/Tables.txt b/docs/extensions/Tables.txt new file mode 100644 index 0000000..63d6849 --- /dev/null +++ b/docs/extensions/Tables.txt @@ -0,0 +1,53 @@ +Tables +---------------- + +Summary +------- + +The Table Extension adds the ability to create tables in Markdown documents. + +This extension is included in the standard Markdown library. + +Syntax +------ + +Tables are defined using the syntax established in [PHP Markdown Extra][php]. + +[php]: http://www.michelf.com/projects/php-markdown/extra/#table + +Thus, the following text (taken from the above referenced PHP documentation): + +First Header | Second Header +------------- | ------------- +Content Cell | Content Cell +Content Cell | Content Cell + +will be rendered as: + +<table> +<thead> +<tr> +<th>First Header</th> +<th>Second Header</th> +</tr> +</thead> +<tbody> +<tr> +<td>Content Cell</td> +<td>Content Cell</td> + +</tr> +<tr> +<td>Content Cell</td> +<td>Content Cell</td> +</tr> +</tbody> +</table> + +Usage +----- + +From the Python interpreter: + + >>> html = markdown.markdown(text, ['tables']) + diff --git a/docs/extensions/Tables_of_Contents.txt b/docs/extensions/Tables_of_Contents.txt new file mode 100644 index 0000000..032c25c --- /dev/null +++ b/docs/extensions/Tables_of_Contents.txt @@ -0,0 +1,50 @@ +Table of Contents +================= + +Summary +------- + +Adds a Table of Contents to a Markdown document. + +This extension is included with the Markdown library since version 2.0. + +Syntax +------ + +Place a marker in the document where you would like the table of contents to +appear. Then, a nested list of all the headers in the document will replace the +marker. The marker defaults to ``[TOC]`` so the following document: + + [TOC] + + # Header 1 + + ## Header 2 + +would generate the following output: + + <div class="toc"> + <ul> + <li><a href="#header-1">Header 1</a></li> + <ul> + <li><a href="#header-2">Header 2</a></li> + </ul> + </ul> + </div> + <h1 id="header-1">Header 1</h1> + <h1 id="header-2">Header 2</h1> + +Configuration Options +--------------------- + +The following options are provided to configure the output: + +* **marker**: Text to find and replace with the Table of Contents. Defaults + to ``[TOC]``. +* **slugify**: Callable to generate anchors based on header text. Defaults to a + built in ``slugify`` method. The callable must accept one argument which + contains the text content of the header and return a string which will be + used as the anchor text. +* **title**: Title to insert in TOC ``<div>``. Defaults to ``None``. +* **anchorlink**: Set to ``True`` to have the headers link to themselves. + Default is ``False``. diff --git a/docs/extensions/WikiLinks.txt b/docs/extensions/WikiLinks.txt new file mode 100644 index 0000000..8bbead5 --- /dev/null +++ b/docs/extensions/WikiLinks.txt @@ -0,0 +1,144 @@ +WikiLinks +========= + +Summary +------- + +An extension to Python-Markdown that adds [WikiLinks][]. Specifically, any +``[[bracketed]]`` word is converted to a link. + +[WikiLinks]: http://en.wikipedia.org/wiki/Wikilink + +This extension has been included in the Markdown library since 2.0. + +Syntax +------ + +A ``[[bracketed]]`` word is any combination of upper or lower case letters, +number, dashes, underscores and spaces surrounded by double brackets. Therefore + + [[Bracketed]] + +Would produce the following html: + + <a href="/Bracketed/" class="wikilink">Bracketed</a> + +Note that wikilinks are automatically assigned `class="wikilink"` making it +easy to style wikilinks differently from other links on a page if one so +desires. See below for ways to alter the class. + +You should also note that when a space is used, the space is converted to an +underscore in the link but left as-is in the label. Perhaps an example +would illustrate this best: + + [[Wiki Link]] + +Becomes + + <a href="/Wiki_Link/" class="wikilink">Wiki Link</a> + +Usage +----- + +From the Python interpreter: + + >>> text = "Some text with a [[WikiLink]]." + >>> html = markdown.markdown(text, ['wikilink']) + +The default behavior is to point each link to the document root of the current +domain and close with a trailing slash. Additionally, each link is assigned to +the html class `wikilink`. This may not always be desirable. Therefore, one can +customize that behavior within Python code. Three settings are provided to +change the default behavior: + +1. **base_url**: String to append to beginning of URL. + + Default: `'/'` + +2. **end_url**: String to append to end of URL. + + Default: `'/'` + +3. **html_class**: CSS hook. Leave blank for none. + + Default: `'wikilink'` + +4. **build_url**: Callable which formats the URL from it's parts. + +For an example, let us suppose links should always point to the subdirectory +`/wiki/` and end with `.html` + + >>> html = markdown.markdown(text, + ... ['wikilink(base_url=/wiki/,end_url=.html)'] + ... ) + +The above would result in the following link for `[[WikiLink]]`. + + <a href="/wiki/WikiLink.html" class="wikilink">WikiLink</a> + +If you want to do more that just alter the base and/or end of the URL, you +could also pass in a callable which must accept three arguments (``label``, +``base``, and ``end``). The callable must return the URL in it's entirety. + + def my_url_builder(label, base, end): + # do stuff + return url + + md = markdown.Markdown( + extensions=['wikilinks], + extension_configs={'wikilinks' : [('build_url', my_url_builder)]} + ) + + +The option is also provided to change or remove the class attribute. + + >>> html = markdown.markdown(text, + ... ['wikilink(base_url=myclass)'] + ... ) + +Would cause all wikilinks to be assigned to the class `myclass`. + + <a href="/WikiLink/" class="myclass">WikiLink</a> + +The same options can be used on the command line as well: + + python markdown.py -x wikilink(base_url=http://example.com/,end_url=.html,html_class=foo) src.txt + +Some may prefer the more complex format when calling the `Markdown` class directly: + + >>> md = markdown.Markdown( + ... extensions = ['wikilink'], + ... extension_configs = {'wikilink': [ + ... ('base_url', 'http://example.com/'), + ... ('end_url', '.html'), + ... ('html_class', '') ]}, + ... safe_mode = True + ... ) + >>> html = md.convert(text) + +Using with Meta-Data +-------------------- + +The WikiLink Extension also supports the [[Meta-Data]] Extension. Please see +the documentation for that extension for specifics. The supported meta-data +keywords are: + +* `wiki_base_url` +* `wiki_end_url` +* `wiki_html_class` + +When used, the meta-data will override the settings provided through the +`extension_configs` interface. + +This document: + + wiki_base_url: http://example.com/ + wiki_end_url: .html + wiki_html_class: + + A [[WikiLink]] in the first paragraph. + +would result in the following output (notice the blank `wiki_html_class`): + + <p>A <a href="http://example.com/WikiLink.html">WikiLink</a> in the first paragraph.</p> + diff --git a/docs/extensions/extra.txt b/docs/extensions/extra.txt new file mode 100644 index 0000000..817d58f --- /dev/null +++ b/docs/extensions/extra.txt @@ -0,0 +1,43 @@ +Python-Markdown Extra +===================== + +Summary +------- + +A compilation of various Python-Markdown extensions that (mostly) imitates +[PHP Markdown Extra](http://michelf.com/projects/php-markdown/extra/). + +The supported extensions include: + +* [[Abbreviations]] +* [[Definition_Lists]] +* [[Fenced_Code_Blocks]] +* [[Footnotes]] +* [[HeaderId]] +* [[Tables]] + +See each individual extension for syntax documentation. Extra and all it's +supported extensions are included in the standard Markdown library. + +Usage +----- + +From the Python interpreter: + + >>> import markdown + >>> html = markdown.markdown(text, ['extra']) + +In the unlikely event that one or more of the supported extensions are not +available for import, Markdown will simply continue without that +extension. If you would like to be notified of such failures, +you may set Python-Markdown's logger level to "WARN". + +There may be additional extensions that are distributed with +Python-Markdown that are not included here in Extra. Those extensions +are not part of PHP Markdown Extra, and therefore, not part of +Python-Markdown Extra. If you really would like Extra to include +additional extensions, we suggest creating your own clone of Extra +under a different name (see [[Writing Extensions]]). You could also +edit the `extensions` global variable defined in the source, but be +aware that such changes may be lost when you upgrade to any future +version of Python-Markdown. diff --git a/docs/extensions/footnotes.txt b/docs/extensions/footnotes.txt new file mode 100644 index 0000000..7188f44 --- /dev/null +++ b/docs/extensions/footnotes.txt @@ -0,0 +1,62 @@ +Footnotes +========= + +Summary +------- + +An extension to Python-Markdown that adds footnote syntax. This extension has +been included with Python-Markdown since 1.7 and should be available to anyone +who has a typical install of Python-Markdown. + +Syntax +------ + +Python-Markdown's Footnote syntax follows the generally accepted syntax of the +Markdown community at large and almost exactly matches [PHP Markdown Extra][]'s +implementation of footnotes. The only differences involve a few subtleties in +the output. + +[PHP Markdown Extra]: http://michelf.com/projects/php-markdown/extra/#footnotes + +Example: + + Footnotes[^1] have a label[^label] and a definition[^!DEF]. + + [^1]: This is a footnote + [^label]: A footnote on "label" + [^!DEF]: The definition of a footnote. + +A footnote definition may contain multiple lines, paragraphs, code blocks, +blockquotes and most any other markdown syntax. The additional line simply +must be indented at least an additional four spaces. + + [^1]: The first paragraph of the definition. + + Paragraph two of the definition. + + > A blockquote with + > multiple lines. + + a code block + + A final paragraph. + +By default, the footnote definitions are placed at the end of the resulting +HTML document. However, you may want the footnotes in another location within +the document. Simply place the following text at that location within your +markdown document (See how to configure this text below): + + ///Footnotes Go Here/// + +Usage +----- + +From the Python interpreter: + + >>> html = markdown.markdown(text, ['footnotes']) + +To configure the place marker for footnote definitions (just be sure not to +use any existing markdown syntax): + + >>> html = markdown.markdown(text, ['footnotes(PLACE_MARKER=+++my marker+++)']) + diff --git a/docs/extensions/index.txt b/docs/extensions/index.txt new file mode 100644 index 0000000..71d857c --- /dev/null +++ b/docs/extensions/index.txt @@ -0,0 +1,44 @@ +Available Extensions +==================== + +Officially Supported Extensions +------------------------------- + +These extensions are included with (at least) the most recent release and are +officially supported by the Python-Markdown developers. Any documentation is +maintained here and all bug reports should be made to the project. If you +have a typical install of Python-Markdown, these extensions are already +available to you. + +* [[Extra]] + * [[Abbreviations]] + * [[Definition_Lists]] + * [[Fenced_Code_Blocks]] + * [[Footnotes]] + * [[HeaderId]] + * [[Tables]] +* [[CodeHilite]] +* [[HTML_Tidy]] +* [[ImageLinks]] +* [[Meta-Data]] +* [[RSS]] +* [[Table_of_Contents]] +* [[WikiLinks]] + +Unofficially Supported Extensions +--------------------------------- + +These extensions have not yet been included in any official Python-Markdown +release. However, the code is maintained in the projects +[mainline git repository](http://gitorious.org/projects/python-markdown/repos/mainline) +by the Python-Markdown developers and the official documentation is maintained +here. All bug reports should be made to the project. It is anticipated that +these extensions will be included with some future official release, at which +time they will be moved to the above list of official extensions. + +* [[Legacy]] + + + + + diff --git a/docs/release-2.0.1.txt b/docs/release-2.0.1.txt new file mode 100644 index 0000000..e5946b2 --- /dev/null +++ b/docs/release-2.0.1.txt @@ -0,0 +1,16 @@ +Python-Markdown 2.0.1 Release Notes +=================================== + +Python-Markdown 2.0.1 is a bug-fix release. No new features have been added. +Most notably, various issues with the command line script have been fixed. +There have also been a few fixes for minor parsing bugs in some edge cases. +For a full list of changes, see the git log. + +Backwards-incompatible Changes +------------------------------ + +Due to various complications in how Python handles command line scripts in +differance systems and with differant installation tools, we were forced to +rename the commandline script to ``markdown`` (no ".py"). A matching batch +script will get installed on Windows. Any shell scripts which call +``markdown.py`` will need to be altered to call ``markdown`` instead. diff --git a/docs/release-2.0.2.txt b/docs/release-2.0.2.txt new file mode 100644 index 0000000..8ae9a3d --- /dev/null +++ b/docs/release-2.0.2.txt @@ -0,0 +1,9 @@ +Python-Markdown 2.0.2 Release Notes +=================================== + +Python-Markdown 2.0.2 is a bug-fix release. No new features have been added. +Most notably, the setup script has been updated to include a dependency on +ElementTree on older versions of Python (< 2.5). There have also been a few +fixes for minor parsing bugs in some edge cases. For a full list of changes, +see the git log. + diff --git a/docs/release-2.0.txt b/docs/release-2.0.txt new file mode 100644 index 0000000..b1f71ad --- /dev/null +++ b/docs/release-2.0.txt @@ -0,0 +1,67 @@ +Python-Markdown 2.0 Release Notes +================================= + +We are happy to release Python-Markdown 2.0, which has been over a year in the +making. We have rewritten significant portions of the code, dramatically +extending the extension API, increased performance, and added numerous +extensions to the distribution (including an extension that mimics PHP Markdown +Extra), all while maintaining backward compatibility with the end user API in +version 1.7. + +Python-Markdown supports Python versions 2.3, 2.4, 2.5, and 2.6. We've even +released a version converted to Python 3.0! + +Backwards-incompatible Changes +------------------------------ + +While Python-Markdown has experienced numerous internal changes, those changes +should only affect extension authors. If you have not written your own +extensions, then you should not need to make any changes to your code. +However, you may want to ensure that any third party extensions you are using +are compatible with the new API. + +The new extension API is fully documented in [[writing_extensions]]. Below is a +summary of the significant changes: + +* The old home-grown NanoDOM has been replaced with ElementTree. Therefore all + extensions must use ElementTree rather than the old NanoDOM. +* The various processors and patterns are now stored with OrderedDicts rather + than lists. Any code adding processors and/or patterns into Python-Markdown + will need to be adjusted to use the new API using OrderedDicts. +* The various types of processors available have been either combined, added, + or removed. Ensure that your processors match the currently supported types. + +What's New in Python-Markdown 2.0 +--------------------------------- + +Thanks to the work of Artem Yunusov as part of GSoC 2008, Python-Markdown uses +ElementTree internally to build the (X)HTML document from markdown source text. +This has resolved various issues with the older home-grown NanoDOM and made +notable increases in performance. + +Artem also refactored the Inline Patterns to better support nested patterns +which has resolved many inconsistencies in Python-Markdown's parsing of the +markdown syntax. + +The core parser had been completely rewritten, increasing performance and, for +the first time, making it possible to override/add/change the way block level +content is parsed. + +Python-Markdown now parses markdown source text more closely to the other +popular implementations (Perl, PHP, etc.) than it ever has before. With the +exception of a few minor insignificant differences, any difference should be +considered a bug, rather than a limitation of the parser. + +The option to return HTML4 output as apposed to XHTML has been added. In +addition, extensions should be able to easily add additional output formats. + +As part of implementing markdown in the Dr. Project project (a Trac fork), among +other things, David Wolever refactored the "extension" keyword so that it +accepts either the extension names as strings or instances of extensions. This +makes it possible to include multiple extensions in a single module. + +Numerous extensions are included in the distribution by default. See +[[available_extensions]] for a complete list. + +See the [[change_log]] for a full list of changes. + diff --git a/docs/using_as_module.txt b/docs/using_as_module.txt new file mode 100644 index 0000000..130d0a7 --- /dev/null +++ b/docs/using_as_module.txt @@ -0,0 +1,150 @@ +Using Markdown as Python Library +================================ + +First and foremost, Python-Markdown is intended to be a python library module +used by various projects to convert Markdown syntax into HTML. + +The Basics +---------- + +To use markdown as a module: + + import markdown + html = markdown.markdown(your_text_string) + +Encoded Text +------------ + +Note that ``markdown()`` expects **Unicode** as input (although a simple ASCII +string should work) and returns output as Unicode. Do not pass encoded strings to it! +If your input is encoded, e.g. as UTF-8, it is your responsibility to decode +it. E.g.: + + input_file = codecs.open("some_file.txt", mode="r", encoding="utf-8") + text = input_file.read() + html = markdown.markdown(text, extensions) + +If you later want to write it to disk, you should encode it yourself: + + output_file = codecs.open("some_file.html", "w", encoding="utf-8") + output_file.write(html) + +More Options +------------ + +If you want to pass more options, you can create an instance of the ``Markdown`` +class yourself and then use ``convert()`` to generate HTML: + + import markdown + md = markdown.Markdown( + extensions=['footnotes'], + extension_configs= {'footnotes' : ('PLACE_MARKER','~~~~~~~~')}, + safe_mode=True, + output_format='html4' + ) + return md.convert(some_text) + +You should also use this method if you want to process multiple strings: + + md = markdown.Markdown() + html1 = md.convert(text1) + html2 = md.convert(text2) + +Working with Files +------------------ + +While the Markdown class is only intended to work with Unicode text, some +encoding/decoding is required for the command line features. These functions +and methods are only intended to fit the common use case. + +The ``Markdown`` class has the method ``convertFile`` which reads in a file and +writes out to a file-like-object: + + md = markdown.Markdown() + md.convertFile(input="in.txt", output="out.html", encoding="utf-8") + +The markdown module also includes a shortcut function ``markdownFromFile`` that +wraps the above method. + + markdown.markdownFromFile(input="in.txt", + output="out.html", + extensions=[], + encoding="utf-8", + safe=False) + +In either case, if the ``output`` keyword is passed a file name (i.e.: +``output="out.html"``), it will try to write to a file by that name. If +``output`` is passed a file-like-object (i.e. ``output=StringIO.StringIO()``), +it will attempt to write out to that object. Finally, if ``output`` is +set to ``None``, it will write to ``stdout``. + +Using Extensions +---------------- + +One of the parameters that you can pass is a list of Extensions. Extensions +must be available as python modules either within the ``markdown.extensions`` +package or on your PYTHONPATH with names starting with `mdx_`, followed by the +name of the extension. Thus, ``extensions=['footnotes']`` will first look for +the module ``markdown.extensions.footnotes``, then a module named +``mdx_footnotes``. See the documentation specific to the extension you are +using for help in specifying configuration settings for that extension. + +Note that some extensions may need their state reset between each call to +``convert``: + + html1 = md.convert(text1) + md.reset() + html2 = md.convert(text2) + +Safe Mode +--------- + +If you are using Markdown on a web system which will transform text provided +by untrusted users, you may want to use the "safe_mode" option which ensures +that the user's HTML tags are either replaced, removed or escaped. (They can +still create links using Markdown syntax.) + +* To replace HTML, set ``safe_mode="replace"`` (``safe_mode=True`` still works + for backward compatibility with older versions). The HTML will be replaced + with the text defined in ``markdown.HTML_REMOVED_TEXT`` which defaults to + ``[HTML_REMOVED]``. To replace the HTML with something else: + + markdown.HTML_REMOVED_TEXT = "--RAW HTML IS NOT ALLOWED--" + md = markdown.Markdown(safe_mode="replace") + + **Note**: You could edit the value of ``HTML_REMOVED_TEXT`` directly in + markdown/__init__.py but you will need to remember to do so every time you + upgrade to a newer version of Markdown. Therefore, this is not recommended. + +* To remove HTML, set ``safe_mode="remove"``. Any raw HTML will be completely + stripped from the text with no warning to the author. + +* To escape HTML, set ``safe_mode="escape"``. The HTML will be escaped and + included in the document. + +Output Formats +-------------- + +If Markdown is outputing (X)HTML as part of a web page, most likely you will +want the output to match the (X)HTML version used by the rest of your page/site. +Currently, Markdown offers two output formats out of the box; "HTML4" and +"XHTML1" (the default) . Markdown will also accept the formats "HTML" and +"XHTML" which currently map to "HTML4" and "XHTML" respectively. However, +you should use the more explicit keys as the general keys may change in the +future if it makes sense at that time. The keys can either be lowercase or +uppercase. + +To set the output format do: + + html = markdown.markdown(text, output_format='html4') + +Or, when using the Markdown class: + + md = markdown.Markdown(output_format='html4') + html = md.convert(text) + +Note that the output format is only set once for the class and cannot be +specified each time ``convert()`` is called. If you really must change the +output format for the class, you can use the ``set_output_format`` method: + + md.set_output_format('xhtml1') diff --git a/docs/writing_extensions.txt b/docs/writing_extensions.txt new file mode 100644 index 0000000..3aad74a --- /dev/null +++ b/docs/writing_extensions.txt @@ -0,0 +1,594 @@ +Writing Extensions for Python-Markdown +====================================== + +Overview +-------- + +Python-Markdown includes an API for extension writers to plug their own +custom functionality and/or syntax into the parser. There are preprocessors +which allow you to alter the source before it is passed to the parser, +inline patterns which allow you to add, remove or override the syntax of +any inline elements, and postprocessors which allow munging of the +output of the parser before it is returned. If you really want to dive in, +there are also blockprocessors which are part of the core BlockParser. + +As the parser builds an [ElementTree][] object which is later rendered +as Unicode text, there are also some helpers provided to ease manipulation of +the tree. Each part of the API is discussed in its respective section below. +Additionaly, reading the source of some [[Available Extensions]] may be helpful. +For example, the [[Footnotes]] extension uses most of the features documented +here. + +* [Preprocessors][] +* [InlinePatterns][] +* [Treeprocessors][] +* [Postprocessors][] +* [BlockParser][] +* [Working with the ElementTree][] +* [Integrating your code into Markdown][] + * [extendMarkdown][] + * [OrderedDict][] + * [registerExtension][] + * [Config Settings][] + * [makeExtension][] + +<h3 id="preprocessors">Preprocessors</h3> + +Preprocessors munge the source text before it is passed into the Markdown +core. This is an excellent place to clean up bad syntax, extract things the +parser may otherwise choke on and perhaps even store it for later retrieval. + +Preprocessors should inherit from ``markdown.preprocessors.Preprocessor`` and +implement a ``run`` method with one argument ``lines``. The ``run`` method of +each Preprocessor will be passed the entire source text as a list of Unicode +strings. Each string will contain one line of text. The ``run`` method should +return either that list, or an altered list of Unicode strings. + +A pseudo example: + + class MyPreprocessor(markdown.preprocessors.Preprocessor): + def run(self, lines): + new_lines = [] + for line in lines: + m = MYREGEX.match(line) + if m: + # do stuff + else: + new_lines.append(line) + return new_lines + +<h3 id="inlinepatterns">Inline Patterns</h3> + +Inline Patterns implement the inline HTML element syntax for Markdown such as +``*emphasis*`` or ``[links](http://example.com)``. Pattern objects should be +instances of classes that inherit from ``markdown.inlinepatterns.Pattern`` or +one of its children. Each pattern object uses a single regular expression and +must have the following methods: + +* **``getCompiledRegExp()``**: + + Returns a compiled regular expression. + +* **``handleMatch(m)``**: + + Accepts a match object and returns an ElementTree element of a plain + Unicode string. + +Note that any regular expression returned by ``getCompiledRegExp`` must capture +the whole block. Therefore, they should all start with ``r'^(.*?)'`` and end +with ``r'(.*?)!'``. When using the default ``getCompiledRegExp()`` method +provided in the ``Pattern`` you can pass in a regular expression without that +and ``getCompiledRegExp`` will wrap your expression for you. This means that +the first group of your match will be ``m.group(2)`` as ``m.group(1)`` will +match everything before the pattern. + +For an example, consider this simplified emphasis pattern: + + class EmphasisPattern(markdown.inlinepatterns.Pattern): + def handleMatch(self, m): + el = markdown.etree.Element('em') + el.text = m.group(3) + return el + +As discussed in [Integrating Your Code Into Markdown][], an instance of this +class will need to be provided to Markdown. That instance would be created +like so: + + # an oversimplified regex + MYPATTERN = r'\*([^*]+)\*' + # pass in pattern and create instance + emphasis = EmphasisPattern(MYPATTERN) + +Actually it would not be necessary to create that pattern (and not just because +a more sophisticated emphasis pattern already exists in Markdown). The fact is, +that example pattern is not very DRY. A pattern for `**strong**` text would +be almost identical, with the exception that it would create a 'strong' element. +Therefore, Markdown provides a number of generic pattern classes that can +provide some common functionality. For example, both emphasis and strong are +implemented with separate instances of the ``SimpleTagPettern`` listed below. +Feel free to use or extend any of these Pattern classes. + +**Generic Pattern Classes** + +* **``SimpleTextPattern(pattern)``**: + + Returns simple text of ``group(2)`` of a ``pattern``. + +* **``SimpleTagPattern(pattern, tag)``**: + + Returns an element of type "`tag`" with a text attribute of ``group(3)`` + of a ``pattern``. ``tag`` should be a string of a HTML element (i.e.: 'em'). + +* **``SubstituteTagPattern(pattern, tag)``**: + + Returns an element of type "`tag`" with no children or text (i.e.: 'br'). + +There may be other Pattern classes in the Markdown source that you could extend +or use as well. Read through the source and see if there is anything you can +use. You might even get a few ideas for different approaches to your specific +situation. + +<h3 id="treeprocessors">Treeprocessors</h3> + +Treeprocessors manipulate an ElemenTree object after it has passed through the +core BlockParser. This is where additional manipulation of the tree takes +place. Additionally, the InlineProcessor is a Treeprocessor which steps through +the tree and runs the InlinePatterns on the text of each Element in the tree. + +A Treeprocessor should inherit from ``markdown.treeprocessors.Treeprocessor``, +over-ride the ``run`` method which takes one argument ``root`` (an Elementree +object) and returns either that root element or a modified root element. + +A pseudo example: + + class MyTreeprocessor(markdown.treeprocessors.Treeprocessor): + def run(self, root): + #do stuff + return my_modified_root + +For specifics on manipulating the ElementTree, see +[Working with the ElementTree][] below. + +<h3 id="postprocessors">Postprocessors</h3> + +Postprocessors manipulate the document after the ElementTree has been +serialized into a string. Postprocessors should be used to work with the +text just before output. + +A Postprocessor should inherit from ``markdown.postprocessors.Postprocessor`` +and over-ride the ``run`` method which takes one argument ``text`` and returns +a Unicode string. + +Postprocessors are run after the ElementTree has been serialized back into +Unicode text. For example, this may be an appropriate place to add a table of +contents to a document: + + class TocPostprocessor(markdown.postprocessors.Postprocessor): + def run(self, text): + return MYMARKERRE.sub(MyToc, text) + +<h3 id="blockparser">BlockParser</h3> + +Sometimes, pre/tree/postprocessors and Inline Patterns aren't going to do what +you need. Perhaps you want a new type of block type that needs to be integrated +into the core parsing. In such a situation, you can add/change/remove +functionality of the core ``BlockParser``. The BlockParser is composed of a +number of Blockproccessors. The BlockParser steps through each block of text +(split by blank lines) and passes each block to the appropriate Blockprocessor. +That Blockprocessor parses the block and adds it to the ElementTree. The +[[Definition Lists]] extension would be a good example of an extension that +adds/modifies Blockprocessors. + +A Blockprocessor should inherit from ``markdown.blockprocessors.BlockProcessor`` +and implement both the ``test`` and ``run`` methods. + +The ``test`` method is used by BlockParser to identify the type of block. +Therefore the ``test`` method must return a boolean value. If the test returns +``True``, then the BlockParser will call that Blockprocessor's ``run`` method. +If it returns ``False``, the BlockParser will move on to the next +BlockProcessor. + +The **``test``** method takes two arguments: + +* **``parent``**: The parent etree Element of the block. This can be useful as + the block may need to be treated differently if it is inside a list, for + example. + +* **``block``**: A string of the current block of text. The test may be a + simple string method (such as ``block.startswith(some_text)``) or a complex + regular expression. + +The **``run``** method takes two arguments: + +* **``parent``**: A pointer to the parent etree Element of the block. The run + method will most likely attach additional nodes to this parent. Note that + nothing is returned by the method. The Elementree object is altered in place. + +* **``blocks``**: A list of all remaining blocks of the document. Your run + method must remove (pop) the first block from the list (which it altered in + place - not returned) and parse that block. You may find that a block of text + legitimately contains multiple block types. Therefore, after processing the + first type, your processor can insert the remaining text into the beginning + of the ``blocks`` list for future parsing. + +Please be aware that a single block can span multiple text blocks. For example, +The official Markdown syntax rules state that a blank line does not end a +Code Block. If the next block of text is also indented, then it is part of +the previous block. Therefore, the BlockParser was specifically designed to +address these types of situations. If you notice the ``CodeBlockProcessor``, +in the core, you will note that it checks the last child of the ``parent``. +If the last child is a code block (``<pre><code>...</code></pre>``), then it +appends that block to the previous code block rather than creating a new +code block. + +Each BlockProcessor has the following utility methods available: + +* **``lastChild(parent)``**: + + Returns the last child of the given etree Element or ``None`` if it had no + children. + +* **``detab(text)``**: + + Removes one level of indent (four spaces by default) from the front of each + line of the given text string. + +* **``looseDetab(text, level)``**: + + Removes "level" levels of indent (defaults to 1) from the front of each line + of the given text string. However, this methods allows secondary lines to + not be indented as does some parts of the Markdown syntax. + +Each BlockProcessor also has a pointer to the containing BlockParser instance at +``self.parser``, which can be used to check or alter the state of the parser. +The BlockParser tracks it's state in a stack at ``parser.state``. The state +stack is an instance of the ``State`` class. + +**``State``** is a subclass of ``list`` and has the additional methods: + +* **``set(state)``**: + + Set a new state to string ``state``. The new state is appended to the end + of the stack. + +* **``reset()``**: + + Step back one step in the stack. The last state at the end is removed from + the stack. + +* **``isstate(state)``**: + + Test that the top (current) level of the stack is of the given string + ``state``. + +Note that to ensure that the state stack doesn't become corrupted, each time a +state is set for a block, that state *must* be reset when the parser finishes +parsing that block. + +An instance of the **``BlockParser``** is found at ``Markdown.parser``. +``BlockParser`` has the following methods: + +* **``parseDocument(lines)``**: + + Given a list of lines, an ElementTree object is returned. This should be + passed an entire document and is the only method the ``Markdown`` class + calls directly. + +* **``parseChunk(parent, text)``**: + + Parses a chunk of markdown text composed of multiple blocks and attaches + those blocks to the ``parent`` Element. The ``parent`` is altered in place + and nothing is returned. Extensions would most likely use this method for + block parsing. + +* **``parseBlocks(parent, blocks)``**: + + Parses a list of blocks of text and attaches those blocks to the ``parent`` + Element. The ``parent`` is altered in place and nothing is returned. This + method will generally only be used internally to recursively parse nested + blocks of text. + +While is is not recommended, an extension could subclass or completely replace +the ``BlockParser``. The new class would have to provide the same public API. +However, be aware that other extensions may expect the core parser provided +and will not work with such a drastically different parser. + +<h3 id="working_with_et">Working with the ElementTree</h3> + +As mentioned, the Markdown parser converts a source document to an +[ElementTree][] object before serializing that back to Unicode text. +Markdown has provided some helpers to ease that manipulation within the context +of the Markdown module. + +First, to get access to the ElementTree module import ElementTree from +``markdown`` rather than importing it directly. This will ensure you are using +the same version of ElementTree as markdown. The module is named ``etree`` +within Markdown. + + from markdown import etree + +``markdown.etree`` tries to import ElementTree from any known location, first +as a standard library module (from ``xml.etree`` in Python 2.5), then as a third +party package (``Elementree``). In each instance, ``cElementTree`` is tried +first, then ``ElementTree`` if the faster C implementation is not available on +your system. + +Sometimes you may want text inserted into an element to be parsed by +[InlinePatterns][]. In such a situation, simply insert the text as you normally +would and the text will be automatically run through the InlinePatterns. +However, if you do *not* want some text to be parsed by InlinePatterns, +then insert the text as an ``AtomicString``. + + some_element.text = markdown.AtomicString(some_text) + +Here's a basic example which creates an HTML table (note that the contents of +the second cell (``td2``) will be run through InlinePatterns latter): + + table = etree.Element("table") + table.set("cellpadding", "2") # Set cellpadding to 2 + tr = etree.SubElement(table, "tr") # Add child tr to table + td1 = etree.SubElement(tr, "td") # Add child td1 to tr + td1.text = markdown.AtomicString("Cell content") # Add plain text content + td2 = etree.SubElement(tr, "td") # Add second td to tr + td2.text = "*text* with **inline** formatting." # Add markup text + table.tail = "Text after table" # Add text after table + +You can also manipulate an existing tree. Consider the following example which +adds a ``class`` attribute to ``<a>`` elements: + + def set_link_class(self, element): + for child in element: + if child.tag == "a": + child.set("class", "myclass") #set the class attribute + set_link_class(child) # run recursively on children + +For more information about working with ElementTree see the ElementTree +[Documentation](http://effbot.org/zone/element-index.htm) +([Python Docs](http://docs.python.org/lib/module-xml.etree.ElementTree.html)). + +<h3 id="integrating_into_markdown">Integrating Your Code Into Markdown</h3> + +Once you have the various pieces of your extension built, you need to tell +Markdown about them and ensure that they are run in the proper sequence. +Markdown accepts a ``Extension`` instance for each extension. Therefore, you +will need to define a class that extends ``markdown.Extension`` and over-rides +the ``extendMarkdown`` method. Within this class you will manage configuration +options for your extension and attach the various processors and patterns to +the Markdown instance. + +It is important to note that the order of the various processors and patterns +matters. For example, if we replace ``http://...`` links with <a> elements, and +*then* try to deal with inline html, we will end up with a mess. Therefore, +the various types of processors and patterns are stored within an instance of +the Markdown class in [OrderedDict][]s. Your ``Extension`` class will need to +manipulate those OrderedDicts appropriately. You may insert instances of your +processors and patterns into the appropriate location in an OrderedDict, remove +a built-in instance, or replace a built-in instance with your own. + +<h4 id="extendmarkdown">extendMarkdown</h4> + +The ``extendMarkdown`` method of a ``markdown.Extension`` class accepts two +arguments: + +* **``md``**: + + A pointer to the instance of the Markdown class. You should use this to + access the [OrderedDict][]s of processors and patterns. They are found + under the following attributes: + + * ``md.preprocessors`` + * ``md.inlinePatterns`` + * ``md.parser.blockprocessors`` + * ``md.treepreprocessors`` + * ``md.postprocessors`` + + Some other things you may want to access in the markdown instance are: + + * ``md.htmlStash`` + * ``md.output_formats`` + * ``md.set_output_format()`` + * ``md.registerExtension()`` + +* **``md_globals``**: + + Contains all the various global variables within the markdown module. + +Of course, with access to those items, theoretically you have the option to +changing anything through various [monkey_patching][] techniques. However, you +should be aware that the various undocumented or private parts of markdown +may change without notice and your monkey_patches may break with a new release. +Therefore, what you really should be doing is inserting processors and patterns +into the markdown pipeline. Consider yourself warned. + +[monkey_patching]: http://en.wikipedia.org/wiki/Monkey_patch + +A simple example: + + class MyExtension(markdown.Extension): + def extendMarkdown(self, md, md_globals): + # Insert instance of 'mypattern' before 'references' pattern + md.inlinePatterns.add('mypattern', MyPattern(md), '<references') + +<h4 id="ordereddict">OrderedDict</h4> + +An OrderedDict is a dictionary like object that retains the order of it's +items. The items are ordered in the order in which they were appended to +the OrderedDict. However, an item can also be inserted into the OrderedDict +in a specific location in relation to the existing items. + +Think of OrderedDict as a combination of a list and a dictionary as it has +methods common to both. For example, you can get and set items using the +``od[key] = value`` syntax and the methods ``keys()``, ``values()``, and +``items()`` work as expected with the keys, values and items returned in the +proper order. At the same time, you can use ``insert()``, ``append()``, and +``index()`` as you would with a list. + +Generally speaking, within Markdown extensions you will be using the special +helper method ``add()`` to add additional items to an existing OrderedDict. + +The ``add()`` method accepts three arguments: + +* **``key``**: A string. The key is used for later reference to the item. + +* **``value``**: The object instance stored in this item. + +* **``location``**: Optional. The items location in relation to other items. + + Note that the location can consist of a few different values: + + * The special strings ``"_begin"`` and ``"_end"`` insert that item at the + beginning or end of the OrderedDict respectively. + + * A less-than sign (``<``) followed by an existing key (i.e.: + ``"<somekey"``) inserts that item before the existing key. + + * A greater-than sign (``>``) followed by an existing key (i.e.: + ``">somekey"``) inserts that item after the existing key. + +Consider the following example: + + >>> import markdown + >>> od = markdown.OrderedDict() + >>> od['one'] = 1 # The same as: od.add('one', 1, '_begin') + >>> od['three'] = 3 # The same as: od.add('three', 3, '>one') + >>> od['four'] = 4 # The same as: od.add('four', 4, '_end') + >>> od.items() + [("one", 1), ("three", 3), ("four", 4)] + +Note that when building an OrderedDict in order, the extra features of the +``add`` method offer no real value and are not necessary. However, when +manipulating an existing OrderedDict, ``add`` can be very helpful. So let's +insert another item into the OrderedDict. + + >>> od.add('two', 2, '>one') # Insert after 'one' + >>> od.values() + [1, 2, 3, 4] + +Now let's insert another item. + + >>> od.add('twohalf', 2.5, '<three') # Insert before 'three' + >>> od.keys() + ["one", "two", "twohalf", "three", "four"] + +Note that we also could have set the location of "twohalf" to be 'after two' +(i.e.: ``'>two'``). However, it's unlikely that you will have control over the +order in which extensions will be loaded, and this could affect the final +sorted order of an OrderedDict. For example, suppose an extension adding +'twohalf' in the above examples was loaded before a separate extension which +adds 'two'. You may need to take this into consideration when adding your +extension components to the various markdown OrderedDicts. + +Once an OrderedDict is created, the items are available via key: + + MyNode = od['somekey'] + +Therefore, to delete an existing item: + + del od['somekey'] + +To change the value of an existing item (leaving location unchanged): + + od['somekey'] = MyNewObject() + +To change the location of an existing item: + + t.link('somekey', '<otherkey') + +<h4 id="registerextension">registerExtension</h4> + +Some extensions may need to have their state reset between multiple runs of the +Markdown class. For example, consider the following use of the [[Footnotes]] +extension: + + md = markdown.Markdown(extensions=['footnotes']) + html1 = md.convert(text_with_footnote) + md.reset() + html2 = md.convert(text_without_footnote) + +Without calling ``reset``, the footnote definitions from the first document will +be inserted into the second document as they are still stored within the class +instance. Therefore the ``Extension`` class needs to define a ``reset`` method +that will reset the state of the extension (i.e.: ``self.footnotes = {}``). +However, as many extensions do not have a need for ``reset``, ``reset`` is only +called on extensions that are registered. + +To register an extension, call ``md.registerExtension`` from within your +``extendMarkdown`` method: + + + def extendMarkdown(self, md, md_globals): + md.registerExtension(self) + # insert processors and patterns here + +Then, each time ``reset`` is called on the Markdown instance, the ``reset`` +method of each registered extension will be called as well. You should also +note that ``reset`` will be called on each registered extension after it is +initialized the first time. Keep that in mind when over-riding the extension's +``reset`` method. + +<h4 id="configsettings">Config Settings</h4> + +If an extension uses any parameters that the user may want to change, +those parameters should be stored in ``self.config`` of your +``markdown.Extension`` class in the following format: + + self.config = {parameter_1_name : [value1, description1], + parameter_2_name : [value2, description2] } + +When stored this way the config parameters can be over-ridden from the +command line or at the time Markdown is initiated: + + markdown.py -x myextension(SOME_PARAM=2) inputfile.txt > output.txt + +Note that parameters should always be assumed to be set to string +values, and should be converted at run time. For example: + + i = int(self.getConfig("SOME_PARAM")) + +<h4 id="makeextension">makeExtension</h4> + +Each extension should ideally be placed in its own module starting +with the ``mdx_`` prefix (e.g. ``mdx_footnotes.py``). The module must +provide a module-level function called ``makeExtension`` that takes +an optional parameter consisting of a dictionary of configuration over-rides +and returns an instance of the extension. An example from the footnote +extension: + + def makeExtension(configs=None) : + return FootnoteExtension(configs=configs) + +By following the above example, when Markdown is passed the name of your +extension as a string (i.e.: ``'footnotes'``), it will automatically import +the module and call the ``makeExtension`` function initiating your extension. + +You may have noted that the extensions packaged with Python-Markdown do not +use the ``mdx_`` prefix in their module names. This is because they are all +part of the ``markdown.extensions`` package. Markdown will first try to import +from ``markdown.extensions.extname`` and upon failure, ``mdx_extname``. If both +fail, Markdown will continue without the extension. + +However, Markdown will also accept an already existing instance of an extension. +For example: + + import markdown + import myextension + configs = {...} + myext = myextension.MyExtension(configs=configs) + md = markdown.Markdown(extensions=[myext]) + +This is useful if you need to implement a large number of extensions with more +than one residing in a module. + +[Preprocessors]: #preprocessors +[InlinePatterns]: #inlinepatterns +[Treeprocessors]: #treeprocessors +[Postprocessors]: #postprocessors +[BlockParser]: #blockparser +[Working with the ElementTree]: #working_with_et +[Integrating your code into Markdown]: #integrating_into_markdown +[extendMarkdown]: #extendmarkdown +[OrderedDict]: #ordereddict +[registerExtension]: #registerextension +[Config Settings]: #configsettings +[makeExtension]: #makeextension +[ElementTree]: http://effbot.org/zone/element-index.htm diff --git a/markdown/__init__.py b/markdown/__init__.py new file mode 100644 index 0000000..bd52113 --- /dev/null +++ b/markdown/__init__.py @@ -0,0 +1,614 @@ +""" +Python Markdown +=============== + +Python Markdown converts Markdown to HTML and can be used as a library or +called from the command line. + +## Basic usage as a module: + + import markdown + md = Markdown() + html = md.convert(your_text_string) + +## Basic use from the command line: + + markdown source.txt > destination.html + +Run "markdown --help" to see more options. + +## Extensions + +See <http://www.freewisdom.org/projects/python-markdown/> for more +information and instructions on how to extend the functionality of +Python Markdown. Read that before you try modifying this file. + +## Authors and License + +Started by [Manfred Stienstra](http://www.dwerg.net/). Continued and +maintained by [Yuri Takhteyev](http://www.freewisdom.org), [Waylan +Limberg](http://achinghead.com/) and [Artem Yunusov](http://blog.splyer.com). + +Contact: markdown@freewisdom.org + +Copyright 2007, 2008 The Python Markdown Project (v. 1.7 and later) +Copyright 200? Django Software Foundation (OrderedDict implementation) +Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b) +Copyright 2004 Manfred Stienstra (the original version) + +License: BSD (see docs/LICENSE for details). +""" + +version = "2.0.3" +version_info = (2,0,3, "Final") + +import re +import codecs +import sys +import warnings +import logging +from logging import DEBUG, INFO, WARN, ERROR, CRITICAL + + +""" +CONSTANTS +============================================================================= +""" + +""" +Constants you might want to modify +----------------------------------------------------------------------------- +""" + +# default logging level for command-line use +COMMAND_LINE_LOGGING_LEVEL = CRITICAL +TAB_LENGTH = 4 # expand tabs to this many spaces +ENABLE_ATTRIBUTES = True # @id = xyz -> <... id="xyz"> +SMART_EMPHASIS = True # this_or_that does not become this<i>or</i>that +DEFAULT_OUTPUT_FORMAT = 'xhtml1' # xhtml or html4 output +HTML_REMOVED_TEXT = "[HTML_REMOVED]" # text used instead of HTML in safe mode +BLOCK_LEVEL_ELEMENTS = re.compile("p|div|h[1-6]|blockquote|pre|table|dl|ol|ul" + "|script|noscript|form|fieldset|iframe|math" + "|ins|del|hr|hr/|style|li|dt|dd|thead|tbody" + "|tr|th|td") +DOC_TAG = "div" # Element used to wrap document - later removed + +# Placeholders +STX = u'\u0002' # Use STX ("Start of text") for start-of-placeholder +ETX = u'\u0003' # Use ETX ("End of text") for end-of-placeholder +INLINE_PLACEHOLDER_PREFIX = STX+"klzzwxh:" +INLINE_PLACEHOLDER = INLINE_PLACEHOLDER_PREFIX + "%s" + ETX +AMP_SUBSTITUTE = STX+"amp"+ETX + + +""" +Constants you probably do not need to change +----------------------------------------------------------------------------- +""" + +RTL_BIDI_RANGES = ( (u'\u0590', u'\u07FF'), + # Hebrew (0590-05FF), Arabic (0600-06FF), + # Syriac (0700-074F), Arabic supplement (0750-077F), + # Thaana (0780-07BF), Nko (07C0-07FF). + (u'\u2D30', u'\u2D7F'), # Tifinagh + ) + + +""" +AUXILIARY GLOBAL FUNCTIONS +============================================================================= +""" + + +def message(level, text): + """ A wrapper method for logging debug messages. """ + logger = logging.getLogger('MARKDOWN') + if logger.handlers: + # The logger is configured + logger.log(level, text) + if level > WARN: + sys.exit(0) + elif level > WARN: + raise MarkdownException, text + else: + warnings.warn(text, MarkdownWarning) + + +def isBlockLevel(tag): + """Check if the tag is a block level HTML tag.""" + return BLOCK_LEVEL_ELEMENTS.match(tag) + +""" +MISC AUXILIARY CLASSES +============================================================================= +""" + +class AtomicString(unicode): + """A string which should not be further processed.""" + pass + + +class MarkdownException(Exception): + """ A Markdown Exception. """ + pass + + +class MarkdownWarning(Warning): + """ A Markdown Warning. """ + pass + + +""" +OVERALL DESIGN +============================================================================= + +Markdown processing takes place in four steps: + +1. A bunch of "preprocessors" munge the input text. +2. BlockParser() parses the high-level structural elements of the + pre-processed text into an ElementTree. +3. A bunch of "treeprocessors" are run against the ElementTree. One such + treeprocessor runs InlinePatterns against the ElementTree, detecting inline + markup. +4. Some post-processors are run against the text after the ElementTree has + been serialized into text. +5. The output is written to a string. + +Those steps are put together by the Markdown() class. + +""" + +import preprocessors +import blockprocessors +import treeprocessors +import inlinepatterns +import postprocessors +import blockparser +import etree_loader +import odict + +# Extensions should use "markdown.etree" instead of "etree" (or do `from +# markdown import etree`). Do not import it by yourself. + +etree = etree_loader.importETree() + +# Adds the ability to output html4 +import html4 + + +class Markdown: + """Convert Markdown to HTML.""" + + def __init__(self, + extensions=[], + extension_configs={}, + safe_mode = False, + output_format=DEFAULT_OUTPUT_FORMAT): + """ + Creates a new Markdown instance. + + Keyword arguments: + + * extensions: A list of extensions. + If they are of type string, the module mdx_name.py will be loaded. + If they are a subclass of markdown.Extension, they will be used + as-is. + * extension-configs: Configuration setting for extensions. + * safe_mode: Disallow raw html. One of "remove", "replace" or "escape". + * output_format: Format of output. Supported formats are: + * "xhtml1": Outputs XHTML 1.x. Default. + * "xhtml": Outputs latest supported version of XHTML (currently XHTML 1.1). + * "html4": Outputs HTML 4 + * "html": Outputs latest supported version of HTML (currently HTML 4). + Note that it is suggested that the more specific formats ("xhtml1" + and "html4") be used as "xhtml" or "html" may change in the future + if it makes sense at that time. + + """ + + self.safeMode = safe_mode + self.registeredExtensions = [] + self.docType = "" + self.stripTopLevelTags = True + + # Preprocessors + self.preprocessors = odict.OrderedDict() + self.preprocessors["html_block"] = \ + preprocessors.HtmlBlockPreprocessor(self) + self.preprocessors["reference"] = \ + preprocessors.ReferencePreprocessor(self) + # footnote preprocessor will be inserted with "<reference" + + # Block processors - ran by the parser + self.parser = blockparser.BlockParser() + self.parser.blockprocessors['empty'] = \ + blockprocessors.EmptyBlockProcessor(self.parser) + self.parser.blockprocessors['indent'] = \ + blockprocessors.ListIndentProcessor(self.parser) + self.parser.blockprocessors['code'] = \ + blockprocessors.CodeBlockProcessor(self.parser) + self.parser.blockprocessors['hashheader'] = \ + blockprocessors.HashHeaderProcessor(self.parser) + self.parser.blockprocessors['setextheader'] = \ + blockprocessors.SetextHeaderProcessor(self.parser) + self.parser.blockprocessors['hr'] = \ + blockprocessors.HRProcessor(self.parser) + self.parser.blockprocessors['olist'] = \ + blockprocessors.OListProcessor(self.parser) + self.parser.blockprocessors['ulist'] = \ + blockprocessors.UListProcessor(self.parser) + self.parser.blockprocessors['quote'] = \ + blockprocessors.BlockQuoteProcessor(self.parser) + self.parser.blockprocessors['paragraph'] = \ + blockprocessors.ParagraphProcessor(self.parser) + + + #self.prePatterns = [] + + # Inline patterns - Run on the tree + self.inlinePatterns = odict.OrderedDict() + self.inlinePatterns["backtick"] = \ + inlinepatterns.BacktickPattern(inlinepatterns.BACKTICK_RE) + self.inlinePatterns["escape"] = \ + inlinepatterns.SimpleTextPattern(inlinepatterns.ESCAPE_RE) + self.inlinePatterns["reference"] = \ + inlinepatterns.ReferencePattern(inlinepatterns.REFERENCE_RE, self) + self.inlinePatterns["link"] = \ + inlinepatterns.LinkPattern(inlinepatterns.LINK_RE, self) + self.inlinePatterns["image_link"] = \ + inlinepatterns.ImagePattern(inlinepatterns.IMAGE_LINK_RE, self) + self.inlinePatterns["image_reference"] = \ + inlinepatterns.ImageReferencePattern(inlinepatterns.IMAGE_REFERENCE_RE, self) + self.inlinePatterns["autolink"] = \ + inlinepatterns.AutolinkPattern(inlinepatterns.AUTOLINK_RE, self) + self.inlinePatterns["automail"] = \ + inlinepatterns.AutomailPattern(inlinepatterns.AUTOMAIL_RE, self) + self.inlinePatterns["linebreak2"] = \ + inlinepatterns.SubstituteTagPattern(inlinepatterns.LINE_BREAK_2_RE, 'br') + self.inlinePatterns["linebreak"] = \ + inlinepatterns.SubstituteTagPattern(inlinepatterns.LINE_BREAK_RE, 'br') + self.inlinePatterns["html"] = \ + inlinepatterns.HtmlPattern(inlinepatterns.HTML_RE, self) + self.inlinePatterns["entity"] = \ + inlinepatterns.HtmlPattern(inlinepatterns.ENTITY_RE, self) + self.inlinePatterns["not_strong"] = \ + inlinepatterns.SimpleTextPattern(inlinepatterns.NOT_STRONG_RE) + self.inlinePatterns["strong_em"] = \ + inlinepatterns.DoubleTagPattern(inlinepatterns.STRONG_EM_RE, 'strong,em') + self.inlinePatterns["strong"] = \ + inlinepatterns.SimpleTagPattern(inlinepatterns.STRONG_RE, 'strong') + self.inlinePatterns["emphasis"] = \ + inlinepatterns.SimpleTagPattern(inlinepatterns.EMPHASIS_RE, 'em') + self.inlinePatterns["emphasis2"] = \ + inlinepatterns.SimpleTagPattern(inlinepatterns.EMPHASIS_2_RE, 'em') + # The order of the handlers matters!!! + + + # Tree processors - run once we have a basic parse. + self.treeprocessors = odict.OrderedDict() + self.treeprocessors["inline"] = treeprocessors.InlineProcessor(self) + self.treeprocessors["prettify"] = \ + treeprocessors.PrettifyTreeprocessor(self) + + # Postprocessors - finishing touches. + self.postprocessors = odict.OrderedDict() + self.postprocessors["raw_html"] = \ + postprocessors.RawHtmlPostprocessor(self) + self.postprocessors["amp_substitute"] = \ + postprocessors.AndSubstitutePostprocessor() + # footnote postprocessor will be inserted with ">amp_substitute" + + # Map format keys to serializers + self.output_formats = { + 'html' : html4.to_html_string, + 'html4' : html4.to_html_string, + 'xhtml' : etree.tostring, + 'xhtml1': etree.tostring, + } + + self.references = {} + self.htmlStash = preprocessors.HtmlStash() + self.registerExtensions(extensions = extensions, + configs = extension_configs) + self.set_output_format(output_format) + self.reset() + + def registerExtensions(self, extensions, configs): + """ + Register extensions with this instance of Markdown. + + Keyword aurguments: + + * extensions: A list of extensions, which can either + be strings or objects. See the docstring on Markdown. + * configs: A dictionary mapping module names to config options. + + """ + for ext in extensions: + if isinstance(ext, basestring): + ext = load_extension(ext, configs.get(ext, [])) + if isinstance(ext, Extension): + try: + ext.extendMarkdown(self, globals()) + except NotImplementedError, e: + message(ERROR, e) + else: + message(ERROR, 'Extension "%s.%s" must be of type: "markdown.Extension".' \ + % (ext.__class__.__module__, ext.__class__.__name__)) + + def registerExtension(self, extension): + """ This gets called by the extension """ + self.registeredExtensions.append(extension) + + def reset(self): + """ + Resets all state variables so that we can start with a new text. + """ + self.htmlStash.reset() + self.references.clear() + + for extension in self.registeredExtensions: + extension.reset() + + def set_output_format(self, format): + """ Set the output format for the class instance. """ + try: + self.serializer = self.output_formats[format.lower()] + except KeyError: + message(CRITICAL, 'Invalid Output Format: "%s". Use one of %s.' \ + % (format, self.output_formats.keys())) + + def convert(self, source): + """ + Convert markdown to serialized XHTML or HTML. + + Keyword arguments: + + * source: Source text as a Unicode string. + + """ + + # Fixup the source text + if not source.strip(): + return u"" # a blank unicode string + try: + source = unicode(source) + except UnicodeDecodeError: + message(CRITICAL, 'UnicodeDecodeError: Markdown only accepts unicode or ascii input.') + return u"" + + source = source.replace(STX, "").replace(ETX, "") + source = source.replace("\r\n", "\n").replace("\r", "\n") + "\n\n" + source = re.sub(r'\n\s+\n', '\n\n', source) + source = source.expandtabs(TAB_LENGTH) + + # Split into lines and run the line preprocessors. + self.lines = source.split("\n") + for prep in self.preprocessors.values(): + self.lines = prep.run(self.lines) + + # Parse the high-level elements. + root = self.parser.parseDocument(self.lines).getroot() + + # Run the tree-processors + for treeprocessor in self.treeprocessors.values(): + newRoot = treeprocessor.run(root) + if newRoot: + root = newRoot + + # Serialize _properly_. Strip top-level tags. + output, length = codecs.utf_8_decode(self.serializer(root, encoding="utf-8")) + if self.stripTopLevelTags: + try: + start = output.index('<%s>'%DOC_TAG)+len(DOC_TAG)+2 + end = output.rindex('</%s>'%DOC_TAG) + output = output[start:end].strip() + except ValueError: + if output.strip().endswith('<%s />'%DOC_TAG): + # We have an empty document + output = '' + else: + # We have a serious problem + message(CRITICAL, 'Failed to strip top level tags.') + + # Run the text post-processors + for pp in self.postprocessors.values(): + output = pp.run(output) + + return output.strip() + + def convertFile(self, input=None, output=None, encoding=None): + """Converts a markdown file and returns the HTML as a unicode string. + + Decodes the file using the provided encoding (defaults to utf-8), + passes the file content to markdown, and outputs the html to either + the provided stream or the file with provided name, using the same + encoding as the source file. + + **Note:** This is the only place that decoding and encoding of unicode + takes place in Python-Markdown. (All other code is unicode-in / + unicode-out.) + + Keyword arguments: + + * input: Name of source text file. + * output: Name of output file. Writes to stdout if `None`. + * encoding: Encoding of input and output files. Defaults to utf-8. + + """ + + encoding = encoding or "utf-8" + + # Read the source + input_file = codecs.open(input, mode="r", encoding=encoding) + text = input_file.read() + input_file.close() + text = text.lstrip(u'\ufeff') # remove the byte-order mark + + # Convert + html = self.convert(text) + + # Write to file or stdout + if isinstance(output, (str, unicode)): + output_file = codecs.open(output, "w", encoding=encoding) + output_file.write(html) + output_file.close() + else: + output.write(html.encode(encoding)) + + +""" +Extensions +----------------------------------------------------------------------------- +""" + +class Extension: + """ Base class for extensions to subclass. """ + def __init__(self, configs = {}): + """Create an instance of an Extention. + + Keyword arguments: + + * configs: A dict of configuration setting used by an Extension. + """ + self.config = configs + + def getConfig(self, key): + """ Return a setting for the given key or an empty string. """ + if key in self.config: + return self.config[key][0] + else: + return "" + + def getConfigInfo(self): + """ Return all config settings as a list of tuples. """ + return [(key, self.config[key][1]) for key in self.config.keys()] + + def setConfig(self, key, value): + """ Set a config setting for `key` with the given `value`. """ + self.config[key][0] = value + + def extendMarkdown(self, md, md_globals): + """ + Add the various proccesors and patterns to the Markdown Instance. + + This method must be overriden by every extension. + + Keyword arguments: + + * md: The Markdown instance. + + * md_globals: Global variables in the markdown module namespace. + + """ + raise NotImplementedError, 'Extension "%s.%s" must define an "extendMarkdown"' \ + 'method.' % (self.__class__.__module__, self.__class__.__name__) + + +def load_extension(ext_name, configs = []): + """Load extension by name, then return the module. + + The extension name may contain arguments as part of the string in the + following format: "extname(key1=value1,key2=value2)" + + """ + + # Parse extensions config params (ignore the order) + configs = dict(configs) + pos = ext_name.find("(") # find the first "(" + if pos > 0: + ext_args = ext_name[pos+1:-1] + ext_name = ext_name[:pos] + pairs = [x.split("=") for x in ext_args.split(",")] + configs.update([(x.strip(), y.strip()) for (x, y) in pairs]) + + # Setup the module names + ext_module = 'markdown.extensions' + module_name_new_style = '.'.join([ext_module, ext_name]) + module_name_old_style = '_'.join(['mdx', ext_name]) + + # Try loading the extention first from one place, then another + try: # New style (markdown.extensons.<extension>) + module = __import__(module_name_new_style, {}, {}, [ext_module]) + except ImportError: + try: # Old style (mdx.<extension>) + module = __import__(module_name_old_style) + except ImportError: + message(WARN, "Failed loading extension '%s' from '%s' or '%s'" + % (ext_name, module_name_new_style, module_name_old_style)) + # Return None so we don't try to initiate none-existant extension + return None + + # If the module is loaded successfully, we expect it to define a + # function called makeExtension() + try: + return module.makeExtension(configs.items()) + except AttributeError: + message(CRITICAL, "Failed to initiate extension '%s'" % ext_name) + + +def load_extensions(ext_names): + """Loads multiple extensions""" + extensions = [] + for ext_name in ext_names: + extension = load_extension(ext_name) + if extension: + extensions.append(extension) + return extensions + + +""" +EXPORTED FUNCTIONS +============================================================================= + +Those are the two functions we really mean to export: markdown() and +markdownFromFile(). +""" + +def markdown(text, + extensions = [], + safe_mode = False, + output_format = DEFAULT_OUTPUT_FORMAT): + """Convert a markdown string to HTML and return HTML as a unicode string. + + This is a shortcut function for `Markdown` class to cover the most + basic use case. It initializes an instance of Markdown, loads the + necessary extensions and runs the parser on the given text. + + Keyword arguments: + + * text: Markdown formatted text as Unicode or ASCII string. + * extensions: A list of extensions or extension names (may contain config args). + * safe_mode: Disallow raw html. One of "remove", "replace" or "escape". + * output_format: Format of output. Supported formats are: + * "xhtml1": Outputs XHTML 1.x. Default. + * "xhtml": Outputs latest supported version of XHTML (currently XHTML 1.1). + * "html4": Outputs HTML 4 + * "html": Outputs latest supported version of HTML (currently HTML 4). + Note that it is suggested that the more specific formats ("xhtml1" + and "html4") be used as "xhtml" or "html" may change in the future + if it makes sense at that time. + + Returns: An HTML document as a string. + + """ + md = Markdown(extensions=load_extensions(extensions), + safe_mode=safe_mode, + output_format=output_format) + return md.convert(text) + + +def markdownFromFile(input = None, + output = None, + extensions = [], + encoding = None, + safe_mode = False, + output_format = DEFAULT_OUTPUT_FORMAT): + """Read markdown code from a file and write it to a file or a stream.""" + md = Markdown(extensions=load_extensions(extensions), + safe_mode=safe_mode, + output_format=output_format) + md.convertFile(input, output, encoding) + + + diff --git a/markdown/blockparser.py b/markdown/blockparser.py new file mode 100644 index 0000000..e18b338 --- /dev/null +++ b/markdown/blockparser.py @@ -0,0 +1,95 @@ + +import markdown + +class State(list): + """ Track the current and nested state of the parser. + + This utility class is used to track the state of the BlockParser and + support multiple levels if nesting. It's just a simple API wrapped around + a list. Each time a state is set, that state is appended to the end of the + list. Each time a state is reset, that state is removed from the end of + the list. + + Therefore, each time a state is set for a nested block, that state must be + reset when we back out of that level of nesting or the state could be + corrupted. + + While all the methods of a list object are available, only the three + defined below need be used. + + """ + + def set(self, state): + """ Set a new state. """ + self.append(state) + + def reset(self): + """ Step back one step in nested state. """ + self.pop() + + def isstate(self, state): + """ Test that top (current) level is of given state. """ + if len(self): + return self[-1] == state + else: + return False + +class BlockParser: + """ Parse Markdown blocks into an ElementTree object. + + A wrapper class that stitches the various BlockProcessors together, + looping through them and creating an ElementTree object. + """ + + def __init__(self): + self.blockprocessors = markdown.odict.OrderedDict() + self.state = State() + + def parseDocument(self, lines): + """ Parse a markdown document into an ElementTree. + + Given a list of lines, an ElementTree object (not just a parent Element) + is created and the root element is passed to the parser as the parent. + The ElementTree object is returned. + + This should only be called on an entire document, not pieces. + + """ + # Create a ElementTree from the lines + self.root = markdown.etree.Element(markdown.DOC_TAG) + self.parseChunk(self.root, '\n'.join(lines)) + return markdown.etree.ElementTree(self.root) + + def parseChunk(self, parent, text): + """ Parse a chunk of markdown text and attach to given etree node. + + While the ``text`` argument is generally assumed to contain multiple + blocks which will be split on blank lines, it could contain only one + block. Generally, this method would be called by extensions when + block parsing is required. + + The ``parent`` etree Element passed in is altered in place. + Nothing is returned. + + """ + self.parseBlocks(parent, text.split('\n\n')) + + def parseBlocks(self, parent, blocks): + """ Process blocks of markdown text and attach to given etree node. + + Given a list of ``blocks``, each blockprocessor is stepped through + until there are no blocks left. While an extension could potentially + call this method directly, it's generally expected to be used internally. + + This is a public method as an extension may need to add/alter additional + BlockProcessors which call this method to recursively parse a nested + block. + + """ + while blocks: + for processor in self.blockprocessors.values(): + if processor.test(parent, blocks[0]): + processor.run(parent, blocks) + break + + diff --git a/markdown/blockprocessors.py b/markdown/blockprocessors.py new file mode 100644 index 0000000..7d3b137 --- /dev/null +++ b/markdown/blockprocessors.py @@ -0,0 +1,460 @@ +""" +CORE MARKDOWN BLOCKPARSER +============================================================================= + +This parser handles basic parsing of Markdown blocks. It doesn't concern itself +with inline elements such as **bold** or *italics*, but rather just catches +blocks, lists, quotes, etc. + +The BlockParser is made up of a bunch of BlockProssors, each handling a +different type of block. Extensions may add/replace/remove BlockProcessors +as they need to alter how markdown blocks are parsed. + +""" + +import re +import markdown + +class BlockProcessor: + """ Base class for block processors. + + Each subclass will provide the methods below to work with the source and + tree. Each processor will need to define it's own ``test`` and ``run`` + methods. The ``test`` method should return True or False, to indicate + whether the current block should be processed by this processor. If the + test passes, the parser will call the processors ``run`` method. + + """ + + def __init__(self, parser=None): + self.parser = parser + + def lastChild(self, parent): + """ Return the last child of an etree element. """ + if len(parent): + return parent[-1] + else: + return None + + def detab(self, text): + """ Remove a tab from the front of each line of the given text. """ + newtext = [] + lines = text.split('\n') + for line in lines: + if line.startswith(' '*markdown.TAB_LENGTH): + newtext.append(line[markdown.TAB_LENGTH:]) + elif not line.strip(): + newtext.append('') + else: + break + return '\n'.join(newtext), '\n'.join(lines[len(newtext):]) + + def looseDetab(self, text, level=1): + """ Remove a tab from front of lines but allowing dedented lines. """ + lines = text.split('\n') + for i in range(len(lines)): + if lines[i].startswith(' '*markdown.TAB_LENGTH*level): + lines[i] = lines[i][markdown.TAB_LENGTH*level:] + return '\n'.join(lines) + + def test(self, parent, block): + """ Test for block type. Must be overridden by subclasses. + + As the parser loops through processors, it will call the ``test`` method + on each to determine if the given block of text is of that type. This + method must return a boolean ``True`` or ``False``. The actual method of + testing is left to the needs of that particular block type. It could + be as simple as ``block.startswith(some_string)`` or a complex regular + expression. As the block type may be different depending on the parent + of the block (i.e. inside a list), the parent etree element is also + provided and may be used as part of the test. + + Keywords: + + * ``parent``: A etree element which will be the parent of the block. + * ``block``: A block of text from the source which has been split at + blank lines. + """ + pass + + def run(self, parent, blocks): + """ Run processor. Must be overridden by subclasses. + + When the parser determines the appropriate type of a block, the parser + will call the corresponding processor's ``run`` method. This method + should parse the individual lines of the block and append them to + the etree. + + Note that both the ``parent`` and ``etree`` keywords are pointers + to instances of the objects which should be edited in place. Each + processor must make changes to the existing objects as there is no + mechanism to return new/different objects to replace them. + + This means that this method should be adding SubElements or adding text + to the parent, and should remove (``pop``) or add (``insert``) items to + the list of blocks. + + Keywords: + + * ``parent``: A etree element which is the parent of the current block. + * ``blocks``: A list of all remaining blocks of the document. + """ + pass + + +class ListIndentProcessor(BlockProcessor): + """ Process children of list items. + + Example: + * a list item + process this part + + or this part + + """ + + INDENT_RE = re.compile(r'^(([ ]{%s})+)'% markdown.TAB_LENGTH) + ITEM_TYPES = ['li'] + LIST_TYPES = ['ul', 'ol'] + + def test(self, parent, block): + return block.startswith(' '*markdown.TAB_LENGTH) and \ + not self.parser.state.isstate('detabbed') and \ + (parent.tag in self.ITEM_TYPES or \ + (len(parent) and parent[-1] and \ + (parent[-1].tag in self.LIST_TYPES) + ) + ) + + def run(self, parent, blocks): + block = blocks.pop(0) + level, sibling = self.get_level(parent, block) + block = self.looseDetab(block, level) + + self.parser.state.set('detabbed') + if parent.tag in self.ITEM_TYPES: + # The parent is already a li. Just parse the child block. + self.parser.parseBlocks(parent, [block]) + elif sibling.tag in self.ITEM_TYPES: + # The sibling is a li. Use it as parent. + self.parser.parseBlocks(sibling, [block]) + elif len(sibling) and sibling[-1].tag in self.ITEM_TYPES: + # The parent is a list (``ol`` or ``ul``) which has children. + # Assume the last child li is the parent of this block. + if sibling[-1].text: + # If the parent li has text, that text needs to be moved to a p + block = '%s\n\n%s' % (sibling[-1].text, block) + sibling[-1].text = '' + self.parser.parseChunk(sibling[-1], block) + else: + self.create_item(sibling, block) + self.parser.state.reset() + + def create_item(self, parent, block): + """ Create a new li and parse the block with it as the parent. """ + li = markdown.etree.SubElement(parent, 'li') + self.parser.parseBlocks(li, [block]) + + def get_level(self, parent, block): + """ Get level of indent based on list level. """ + # Get indent level + m = self.INDENT_RE.match(block) + if m: + indent_level = len(m.group(1))/markdown.TAB_LENGTH + else: + indent_level = 0 + if self.parser.state.isstate('list'): + # We're in a tightlist - so we already are at correct parent. + level = 1 + else: + # We're in a looselist - so we need to find parent. + level = 0 + # Step through children of tree to find matching indent level. + while indent_level > level: + child = self.lastChild(parent) + if child and (child.tag in self.LIST_TYPES or child.tag in self.ITEM_TYPES): + if child.tag in self.LIST_TYPES: + level += 1 + parent = child + else: + # No more child levels. If we're short of indent_level, + # we have a code block. So we stop here. + break + return level, parent + + +class CodeBlockProcessor(BlockProcessor): + """ Process code blocks. """ + + def test(self, parent, block): + return block.startswith(' '*markdown.TAB_LENGTH) + + def run(self, parent, blocks): + sibling = self.lastChild(parent) + block = blocks.pop(0) + theRest = '' + if sibling and sibling.tag == "pre" and len(sibling) \ + and sibling[0].tag == "code": + # The previous block was a code block. As blank lines do not start + # new code blocks, append this block to the previous, adding back + # linebreaks removed from the split into a list. + code = sibling[0] + block, theRest = self.detab(block) + code.text = markdown.AtomicString('%s\n%s\n' % (code.text, block.rstrip())) + else: + # This is a new codeblock. Create the elements and insert text. + pre = markdown.etree.SubElement(parent, 'pre') + code = markdown.etree.SubElement(pre, 'code') + block, theRest = self.detab(block) + code.text = markdown.AtomicString('%s\n' % block.rstrip()) + if theRest: + # This block contained unindented line(s) after the first indented + # line. Insert these lines as the first block of the master blocks + # list for future processing. + blocks.insert(0, theRest) + + +class BlockQuoteProcessor(BlockProcessor): + + RE = re.compile(r'(^|\n)[ ]{0,3}>[ ]?(.*)') + + def test(self, parent, block): + return bool(self.RE.search(block)) + + def run(self, parent, blocks): + block = blocks.pop(0) + m = self.RE.search(block) + if m: + before = block[:m.start()] # Lines before blockquote + # Pass lines before blockquote in recursively for parsing forst. + self.parser.parseBlocks(parent, [before]) + # Remove ``> `` from begining of each line. + block = '\n'.join([self.clean(line) for line in + block[m.start():].split('\n')]) + sibling = self.lastChild(parent) + if sibling and sibling.tag == "blockquote": + # Previous block was a blockquote so set that as this blocks parent + quote = sibling + else: + # This is a new blockquote. Create a new parent element. + quote = markdown.etree.SubElement(parent, 'blockquote') + # Recursively parse block with blockquote as parent. + self.parser.parseChunk(quote, block) + + def clean(self, line): + """ Remove ``>`` from beginning of a line. """ + m = self.RE.match(line) + if line.strip() == ">": + return "" + elif m: + return m.group(2) + else: + return line + +class OListProcessor(BlockProcessor): + """ Process ordered list blocks. """ + + TAG = 'ol' + # Detect an item (``1. item``). ``group(1)`` contains contents of item. + RE = re.compile(r'^[ ]{0,3}\d+\.[ ]+(.*)') + # Detect items on secondary lines. they can be of either list type. + CHILD_RE = re.compile(r'^[ ]{0,3}((\d+\.)|[*+-])[ ]+(.*)') + # Detect indented (nested) items of either type + INDENT_RE = re.compile(r'^[ ]{4,7}((\d+\.)|[*+-])[ ]+.*') + + def test(self, parent, block): + return bool(self.RE.match(block)) + + def run(self, parent, blocks): + # Check fr multiple items in one block. + items = self.get_items(blocks.pop(0)) + sibling = self.lastChild(parent) + if sibling and sibling.tag in ['ol', 'ul']: + # Previous block was a list item, so set that as parent + lst = sibling + # make sure previous item is in a p. + if len(lst) and lst[-1].text and not len(lst[-1]): + p = markdown.etree.SubElement(lst[-1], 'p') + p.text = lst[-1].text + lst[-1].text = '' + # parse first block differently as it gets wrapped in a p. + li = markdown.etree.SubElement(lst, 'li') + self.parser.state.set('looselist') + firstitem = items.pop(0) + self.parser.parseBlocks(li, [firstitem]) + self.parser.state.reset() + else: + # This is a new list so create parent with appropriate tag. + lst = markdown.etree.SubElement(parent, self.TAG) + self.parser.state.set('list') + # Loop through items in block, recursively parsing each with the + # appropriate parent. + for item in items: + if item.startswith(' '*markdown.TAB_LENGTH): + # Item is indented. Parse with last item as parent + self.parser.parseBlocks(lst[-1], [item]) + else: + # New item. Create li and parse with it as parent + li = markdown.etree.SubElement(lst, 'li') + self.parser.parseBlocks(li, [item]) + self.parser.state.reset() + + def get_items(self, block): + """ Break a block into list items. """ + items = [] + for line in block.split('\n'): + m = self.CHILD_RE.match(line) + if m: + # This is a new item. Append + items.append(m.group(3)) + elif self.INDENT_RE.match(line): + # This is an indented (possibly nested) item. + if items[-1].startswith(' '*markdown.TAB_LENGTH): + # Previous item was indented. Append to that item. + items[-1] = '%s\n%s' % (items[-1], line) + else: + items.append(line) + else: + # This is another line of previous item. Append to that item. + items[-1] = '%s\n%s' % (items[-1], line) + return items + + +class UListProcessor(OListProcessor): + """ Process unordered list blocks. """ + + TAG = 'ul' + RE = re.compile(r'^[ ]{0,3}[*+-][ ]+(.*)') + + +class HashHeaderProcessor(BlockProcessor): + """ Process Hash Headers. """ + + # Detect a header at start of any line in block + RE = re.compile(r'(^|\n)(?P<level>#{1,6})(?P<header>.*?)#*(\n|$)') + + def test(self, parent, block): + return bool(self.RE.search(block)) + + def run(self, parent, blocks): + block = blocks.pop(0) + m = self.RE.search(block) + if m: + before = block[:m.start()] # All lines before header + after = block[m.end():] # All lines after header + if before: + # As the header was not the first line of the block and the + # lines before the header must be parsed first, + # recursively parse this lines as a block. + self.parser.parseBlocks(parent, [before]) + # Create header using named groups from RE + h = markdown.etree.SubElement(parent, 'h%d' % len(m.group('level'))) + h.text = m.group('header').strip() + if after: + # Insert remaining lines as first block for future parsing. + blocks.insert(0, after) + else: + # This should never happen, but just in case... + message(CRITICAL, "We've got a problem header!") + + +class SetextHeaderProcessor(BlockProcessor): + """ Process Setext-style Headers. """ + + # Detect Setext-style header. Must be first 2 lines of block. + RE = re.compile(r'^.*?\n[=-]{3,}', re.MULTILINE) + + def test(self, parent, block): + return bool(self.RE.match(block)) + + def run(self, parent, blocks): + lines = blocks.pop(0).split('\n') + # Determine level. ``=`` is 1 and ``-`` is 2. + if lines[1].startswith('='): + level = 1 + else: + level = 2 + h = markdown.etree.SubElement(parent, 'h%d' % level) + h.text = lines[0].strip() + if len(lines) > 2: + # Block contains additional lines. Add to master blocks for later. + blocks.insert(0, '\n'.join(lines[2:])) + + +class HRProcessor(BlockProcessor): + """ Process Horizontal Rules. """ + + RE = r'[ ]{0,3}(?P<ch>[*_-])[ ]?((?P=ch)[ ]?){2,}[ ]*' + # Detect hr on any line of a block. + SEARCH_RE = re.compile(r'(^|\n)%s(\n|$)' % RE) + # Match a hr on a single line of text. + MATCH_RE = re.compile(r'^%s$' % RE) + + def test(self, parent, block): + return bool(self.SEARCH_RE.search(block)) + + def run(self, parent, blocks): + lines = blocks.pop(0).split('\n') + prelines = [] + # Check for lines in block before hr. + for line in lines: + m = self.MATCH_RE.match(line) + if m: + break + else: + prelines.append(line) + if len(prelines): + # Recursively parse lines before hr so they get parsed first. + self.parser.parseBlocks(parent, ['\n'.join(prelines)]) + # create hr + hr = markdown.etree.SubElement(parent, 'hr') + # check for lines in block after hr. + lines = lines[len(prelines)+1:] + if len(lines): + # Add lines after hr to master blocks for later parsing. + blocks.insert(0, '\n'.join(lines)) + + +class EmptyBlockProcessor(BlockProcessor): + """ Process blocks and start with an empty line. """ + + # Detect a block that only contains whitespace + # or only whitespace on the first line. + RE = re.compile(r'^\s*\n') + + def test(self, parent, block): + return bool(self.RE.match(block)) + + def run(self, parent, blocks): + block = blocks.pop(0) + m = self.RE.match(block) + if m: + # Add remaining line to master blocks for later. + blocks.insert(0, block[m.end():]) + sibling = self.lastChild(parent) + if sibling and sibling.tag == 'pre' and sibling[0] and \ + sibling[0].tag == 'code': + # Last block is a codeblock. Append to preserve whitespace. + sibling[0].text = markdown.AtomicString('%s/n/n/n' % sibling[0].text ) + + +class ParagraphProcessor(BlockProcessor): + """ Process Paragraph blocks. """ + + def test(self, parent, block): + return True + + def run(self, parent, blocks): + block = blocks.pop(0) + if block.strip(): + # Not a blank block. Add to parent, otherwise throw it away. + if self.parser.state.isstate('list'): + # The parent is a tight-list. Append to parent.text + if parent.text: + parent.text = '%s\n%s' % (parent.text, block) + else: + parent.text = block.lstrip() + else: + # Create a regular paragraph + p = markdown.etree.SubElement(parent, 'p') + p.text = block.lstrip() diff --git a/markdown/commandline.py b/markdown/commandline.py new file mode 100644 index 0000000..1eedc6d --- /dev/null +++ b/markdown/commandline.py @@ -0,0 +1,96 @@ +""" +COMMAND-LINE SPECIFIC STUFF +============================================================================= + +The rest of the code is specifically for handling the case where Python +Markdown is called from the command line. +""" + +import markdown +import sys +import logging +from logging import DEBUG, INFO, WARN, ERROR, CRITICAL + +EXECUTABLE_NAME_FOR_USAGE = "python markdown.py" +""" The name used in the usage statement displayed for python versions < 2.3. +(With python 2.3 and higher the usage statement is generated by optparse +and uses the actual name of the executable called.) """ + +OPTPARSE_WARNING = """ +Python 2.3 or higher required for advanced command line options. +For lower versions of Python use: + + %s INPUT_FILE > OUTPUT_FILE + +""" % EXECUTABLE_NAME_FOR_USAGE + +def parse_options(): + """ + Define and parse `optparse` options for command-line usage. + """ + + try: + optparse = __import__("optparse") + except: + if len(sys.argv) == 2: + return {'input': sys.argv[1], + 'output': None, + 'safe': False, + 'extensions': [], + 'encoding': None }, CRITICAL + else: + print OPTPARSE_WARNING + return None, None + + parser = optparse.OptionParser(usage="%prog INPUTFILE [options]") + parser.add_option("-f", "--file", dest="filename", default=sys.stdout, + help="write output to OUTPUT_FILE", + metavar="OUTPUT_FILE") + parser.add_option("-e", "--encoding", dest="encoding", + help="encoding for input and output files",) + parser.add_option("-q", "--quiet", default = CRITICAL, + action="store_const", const=CRITICAL+10, dest="verbose", + help="suppress all messages") + parser.add_option("-v", "--verbose", + action="store_const", const=INFO, dest="verbose", + help="print info messages") + parser.add_option("-s", "--safe", dest="safe", default=False, + metavar="SAFE_MODE", + help="safe mode ('replace', 'remove' or 'escape' user's HTML tag)") + parser.add_option("-o", "--output_format", dest="output_format", + default='xhtml1', metavar="OUTPUT_FORMAT", + help="Format of output. One of 'xhtml1' (default) or 'html4'.") + parser.add_option("--noisy", + action="store_const", const=DEBUG, dest="verbose", + help="print debug messages") + parser.add_option("-x", "--extension", action="append", dest="extensions", + help = "load extension EXTENSION", metavar="EXTENSION") + + (options, args) = parser.parse_args() + + if not len(args) == 1: + parser.print_help() + return None, None + else: + input_file = args[0] + + if not options.extensions: + options.extensions = [] + + return {'input': input_file, + 'output': options.filename, + 'safe_mode': options.safe, + 'extensions': options.extensions, + 'encoding': options.encoding, + 'output_format': options.output_format}, options.verbose + +def run(): + """Run Markdown from the command line.""" + + # Parse options and adjust logging level if necessary + options, logging_level = parse_options() + if not options: sys.exit(0) + if logging_level: logging.getLogger('MARKDOWN').setLevel(logging_level) + + # Run + markdown.markdownFromFile(**options) diff --git a/markdown/etree_loader.py b/markdown/etree_loader.py new file mode 100644 index 0000000..e2599b2 --- /dev/null +++ b/markdown/etree_loader.py @@ -0,0 +1,33 @@ + +from markdown import message, CRITICAL +import sys + +## Import +def importETree(): + """Import the best implementation of ElementTree, return a module object.""" + etree_in_c = None + try: # Is it Python 2.5+ with C implemenation of ElementTree installed? + import xml.etree.cElementTree as etree_in_c + except ImportError: + try: # Is it Python 2.5+ with Python implementation of ElementTree? + import xml.etree.ElementTree as etree + except ImportError: + try: # An earlier version of Python with cElementTree installed? + import cElementTree as etree_in_c + except ImportError: + try: # An earlier version of Python with Python ElementTree? + import elementtree.ElementTree as etree + except ImportError: + message(CRITICAL, "Failed to import ElementTree") + sys.exit(1) + if etree_in_c and etree_in_c.VERSION < "1.0": + message(CRITICAL, "For cElementTree version 1.0 or higher is required.") + sys.exit(1) + elif etree_in_c : + return etree_in_c + elif etree.VERSION < "1.1": + message(CRITICAL, "For ElementTree version 1.1 or higher is required") + sys.exit(1) + else : + return etree + diff --git a/markdown/extensions/__init__.py b/markdown/extensions/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/markdown/extensions/__init__.py diff --git a/markdown/extensions/abbr.py b/markdown/extensions/abbr.py new file mode 100644 index 0000000..783220e --- /dev/null +++ b/markdown/extensions/abbr.py @@ -0,0 +1,95 @@ +''' +Abbreviation Extension for Python-Markdown +========================================== + +This extension adds abbreviation handling to Python-Markdown. + +Simple Usage: + + >>> import markdown + >>> text = """ + ... Some text with an ABBR and a REF. Ignore REFERENCE and ref. + ... + ... *[ABBR]: Abbreviation + ... *[REF]: Abbreviation Reference + ... """ + >>> markdown.markdown(text, ['abbr']) + u'<p>Some text with an <abbr title="Abbreviation">ABBR</abbr> and a <abbr title="Abbreviation Reference">REF</abbr>. Ignore REFERENCE and ref.</p>' + +Copyright 2007-2008 +* [Waylan Limberg](http://achinghead.com/) +* [Seemant Kulleen](http://www.kulleen.org/) + + +''' + +import markdown, re +from markdown import etree + +# Global Vars +ABBR_REF_RE = re.compile(r'[*]\[(?P<abbr>[^\]]*)\][ ]?:\s*(?P<title>.*)') + +class AbbrExtension(markdown.Extension): + """ Abbreviation Extension for Python-Markdown. """ + + def extendMarkdown(self, md, md_globals): + """ Insert AbbrPreprocessor before ReferencePreprocessor. """ + md.preprocessors.add('abbr', AbbrPreprocessor(md), '<reference') + + +class AbbrPreprocessor(markdown.preprocessors.Preprocessor): + """ Abbreviation Preprocessor - parse text for abbr references. """ + + def run(self, lines): + ''' + Find and remove all Abbreviation references from the text. + Each reference is set as a new AbbrPattern in the markdown instance. + + ''' + new_text = [] + for line in lines: + m = ABBR_REF_RE.match(line) + if m: + abbr = m.group('abbr').strip() + title = m.group('title').strip() + self.markdown.inlinePatterns['abbr-%s'%abbr] = \ + AbbrPattern(self._generate_pattern(abbr), title) + else: + new_text.append(line) + return new_text + + def _generate_pattern(self, text): + ''' + Given a string, returns an regex pattern to match that string. + + 'HTML' -> r'(?P<abbr>[H][T][M][L])' + + Note: we force each char as a literal match (in brackets) as we don't + know what they will be beforehand. + + ''' + chars = list(text) + for i in range(len(chars)): + chars[i] = r'[%s]' % chars[i] + return r'(?P<abbr>\b%s\b)' % (r''.join(chars)) + + +class AbbrPattern(markdown.inlinepatterns.Pattern): + """ Abbreviation inline pattern. """ + + def __init__(self, pattern, title): + markdown.inlinepatterns.Pattern.__init__(self, pattern) + self.title = title + + def handleMatch(self, m): + abbr = etree.Element('abbr') + abbr.text = m.group('abbr') + abbr.set('title', self.title) + return abbr + +def makeExtension(configs=None): + return AbbrExtension(configs=configs) + +if __name__ == "__main__": + import doctest + doctest.testmod() diff --git a/markdown/extensions/codehilite.py b/markdown/extensions/codehilite.py new file mode 100644 index 0000000..c5d496b --- /dev/null +++ b/markdown/extensions/codehilite.py @@ -0,0 +1,224 @@ +#!/usr/bin/python + +""" +CodeHilite Extension for Python-Markdown +======================================== + +Adds code/syntax highlighting to standard Python-Markdown code blocks. + +Copyright 2006-2008 [Waylan Limberg](http://achinghead.com/). + +Project website: <http://www.freewisdom.org/project/python-markdown/CodeHilite> +Contact: markdown@freewisdom.org + +License: BSD (see ../docs/LICENSE for details) + +Dependencies: +* [Python 2.3+](http://python.org/) +* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/) +* [Pygments](http://pygments.org/) + +""" + +import markdown + +# --------------- CONSTANTS YOU MIGHT WANT TO MODIFY ----------------- + +try: + TAB_LENGTH = markdown.TAB_LENGTH +except AttributeError: + TAB_LENGTH = 4 + + +# ------------------ The Main CodeHilite Class ---------------------- +class CodeHilite: + """ + Determine language of source code, and pass it into the pygments hilighter. + + Basic Usage: + >>> code = CodeHilite(src = 'some text') + >>> html = code.hilite() + + * src: Source string or any object with a .readline attribute. + + * linenos: (Boolen) Turn line numbering 'on' or 'off' (off by default). + + * css_class: Set class name of wrapper div ('codehilite' by default). + + Low Level Usage: + >>> code = CodeHilite() + >>> code.src = 'some text' # String or anything with a .readline attr. + >>> code.linenos = True # True or False; Turns line numbering on or of. + >>> html = code.hilite() + + """ + + def __init__(self, src=None, linenos=False, css_class="codehilite"): + self.src = src + self.lang = None + self.linenos = linenos + self.css_class = css_class + + def hilite(self): + """ + Pass code to the [Pygments](http://pygments.pocoo.org/) highliter with + optional line numbers. The output should then be styled with css to + your liking. No styles are applied by default - only styling hooks + (i.e.: <span class="k">). + + returns : A string of html. + + """ + + self.src = self.src.strip('\n') + + self._getLang() + + try: + from pygments import highlight + from pygments.lexers import get_lexer_by_name, guess_lexer, \ + TextLexer + from pygments.formatters import HtmlFormatter + except ImportError: + # just escape and pass through + txt = self._escape(self.src) + if self.linenos: + txt = self._number(txt) + else : + txt = '<div class="%s"><pre>%s</pre></div>\n'% \ + (self.css_class, txt) + return txt + else: + try: + lexer = get_lexer_by_name(self.lang) + except ValueError: + try: + lexer = guess_lexer(self.src) + except ValueError: + lexer = TextLexer() + formatter = HtmlFormatter(linenos=self.linenos, + cssclass=self.css_class) + return highlight(self.src, lexer, formatter) + + def _escape(self, txt): + """ basic html escaping """ + txt = txt.replace('&', '&') + txt = txt.replace('<', '<') + txt = txt.replace('>', '>') + txt = txt.replace('"', '"') + return txt + + def _number(self, txt): + """ Use <ol> for line numbering """ + # Fix Whitespace + txt = txt.replace('\t', ' '*TAB_LENGTH) + txt = txt.replace(" "*4, " ") + txt = txt.replace(" "*3, " ") + txt = txt.replace(" "*2, " ") + + # Add line numbers + lines = txt.splitlines() + txt = '<div class="codehilite"><pre><ol>\n' + for line in lines: + txt += '\t<li>%s</li>\n'% line + txt += '</ol></pre></div>\n' + return txt + + + def _getLang(self): + """ + Determines language of a code block from shebang lines and whether said + line should be removed or left in place. If the sheband line contains a + path (even a single /) then it is assumed to be a real shebang lines and + left alone. However, if no path is given (e.i.: #!python or :::python) + then it is assumed to be a mock shebang for language identifitation of a + code fragment and removed from the code block prior to processing for + code highlighting. When a mock shebang (e.i: #!python) is found, line + numbering is turned on. When colons are found in place of a shebang + (e.i.: :::python), line numbering is left in the current state - off + by default. + + """ + + import re + + #split text into lines + lines = self.src.split("\n") + #pull first line to examine + fl = lines.pop(0) + + c = re.compile(r''' + (?:(?:::+)|(?P<shebang>[#]!)) # Shebang or 2 or more colons. + (?P<path>(?:/\w+)*[/ ])? # Zero or 1 path + (?P<lang>[\w+-]*) # The language + ''', re.VERBOSE) + # search first line for shebang + m = c.search(fl) + if m: + # we have a match + try: + self.lang = m.group('lang').lower() + except IndexError: + self.lang = None + if m.group('path'): + # path exists - restore first line + lines.insert(0, fl) + if m.group('shebang'): + # shebang exists - use line numbers + self.linenos = True + else: + # No match + lines.insert(0, fl) + + self.src = "\n".join(lines).strip("\n") + + + +# ------------------ The Markdown Extension ------------------------------- +class HiliteTreeprocessor(markdown.treeprocessors.Treeprocessor): + """ Hilight source code in code blocks. """ + + def run(self, root): + """ Find code blocks and store in htmlStash. """ + blocks = root.getiterator('pre') + for block in blocks: + children = block.getchildren() + if len(children) == 1 and children[0].tag == 'code': + code = CodeHilite(children[0].text, + linenos=self.config['force_linenos'][0], + css_class=self.config['css_class'][0]) + placeholder = self.markdown.htmlStash.store(code.hilite(), + safe=True) + # Clear codeblock in etree instance + block.clear() + # Change to p element which will later + # be removed when inserting raw html + block.tag = 'p' + block.text = placeholder + + +class CodeHiliteExtension(markdown.Extension): + """ Add source code hilighting to markdown codeblocks. """ + + def __init__(self, configs): + # define default configs + self.config = { + 'force_linenos' : [False, "Force line numbers - Default: False"], + 'css_class' : ["codehilite", + "Set class name for wrapper <div> - Default: codehilite"], + } + + # Override defaults with user settings + for key, value in configs: + self.setConfig(key, value) + + def extendMarkdown(self, md, md_globals): + """ Add HilitePostprocessor to Markdown instance. """ + hiliter = HiliteTreeprocessor(md) + hiliter.config = self.config + md.treeprocessors.add("hilite", hiliter, "_begin") + + +def makeExtension(configs={}): + return CodeHiliteExtension(configs=configs) + diff --git a/markdown/extensions/def_list.py b/markdown/extensions/def_list.py new file mode 100644 index 0000000..73a1c85 --- /dev/null +++ b/markdown/extensions/def_list.py @@ -0,0 +1,104 @@ +#!/usr/bin/env Python +""" +Definition List Extension for Python-Markdown +============================================= + +Added parsing of Definition Lists to Python-Markdown. + +A simple example: + + Apple + : Pomaceous fruit of plants of the genus Malus in + the family Rosaceae. + : An american computer company. + + Orange + : The fruit of an evergreen tree of the genus Citrus. + +Copyright 2008 - [Waylan Limberg](http://achinghead.com) + +""" + +import markdown, re +from markdown import etree + + +class DefListProcessor(markdown.blockprocessors.BlockProcessor): + """ Process Definition Lists. """ + + RE = re.compile(r'(^|\n)[ ]{0,3}:[ ]{1,3}(.*?)(\n|$)') + + def test(self, parent, block): + return bool(self.RE.search(block)) + + def run(self, parent, blocks): + block = blocks.pop(0) + m = self.RE.search(block) + terms = [l.strip() for l in block[:m.start()].split('\n') if l.strip()] + d, theRest = self.detab(block[m.end():]) + if d: + d = '%s\n%s' % (m.group(2), d) + else: + d = m.group(2) + #import ipdb; ipdb.set_trace() + sibling = self.lastChild(parent) + if not terms and sibling.tag == 'p': + # The previous paragraph contains the terms + state = 'looselist' + terms = sibling.text.split('\n') + parent.remove(sibling) + # Aquire new sibling + sibling = self.lastChild(parent) + else: + state = 'list' + + if sibling and sibling.tag == 'dl': + # This is another item on an existing list + dl = sibling + if len(dl) and dl[-1].tag == 'dd' and len(dl[-1]): + state = 'looselist' + else: + # This is a new list + dl = etree.SubElement(parent, 'dl') + # Add terms + for term in terms: + dt = etree.SubElement(dl, 'dt') + dt.text = term + # Add definition + self.parser.state.set(state) + dd = etree.SubElement(dl, 'dd') + self.parser.parseBlocks(dd, [d]) + self.parser.state.reset() + + if theRest: + blocks.insert(0, theRest) + +class DefListIndentProcessor(markdown.blockprocessors.ListIndentProcessor): + """ Process indented children of definition list items. """ + + ITEM_TYPES = ['dd'] + LIST_TYPES = ['dl'] + + def create_item(parent, block): + """ Create a new dd and parse the block with it as the parent. """ + dd = markdown.etree.SubElement(parent, 'dd') + self.parser.parseBlocks(dd, [block]) + + + +class DefListExtension(markdown.Extension): + """ Add definition lists to Markdown. """ + + def extendMarkdown(self, md, md_globals): + """ Add an instance of DefListProcessor to BlockParser. """ + md.parser.blockprocessors.add('defindent', + DefListIndentProcessor(md.parser), + '>indent') + md.parser.blockprocessors.add('deflist', + DefListProcessor(md.parser), + '>ulist') + + +def makeExtension(configs={}): + return DefListExtension(configs=configs) + diff --git a/markdown/extensions/extra.py b/markdown/extensions/extra.py new file mode 100644 index 0000000..4a2ffbf --- /dev/null +++ b/markdown/extensions/extra.py @@ -0,0 +1,49 @@ +#!/usr/bin/env python +""" +Python-Markdown Extra Extension +=============================== + +A compilation of various Python-Markdown extensions that imitates +[PHP Markdown Extra](http://michelf.com/projects/php-markdown/extra/). + +Note that each of the individual extensions still need to be available +on your PYTHONPATH. This extension simply wraps them all up as a +convenience so that only one extension needs to be listed when +initiating Markdown. See the documentation for each individual +extension for specifics about that extension. + +In the event that one or more of the supported extensions are not +available for import, Markdown will issue a warning and simply continue +without that extension. + +There may be additional extensions that are distributed with +Python-Markdown that are not included here in Extra. Those extensions +are not part of PHP Markdown Extra, and therefore, not part of +Python-Markdown Extra. If you really would like Extra to include +additional extensions, we suggest creating your own clone of Extra +under a differant name. You could also edit the `extensions` global +variable defined below, but be aware that such changes may be lost +when you upgrade to any future version of Python-Markdown. + +""" + +import markdown + +extensions = ['fenced_code', + 'footnotes', + 'headerid', + 'def_list', + 'tables', + 'abbr', + ] + + +class ExtraExtension(markdown.Extension): + """ Add various extensions to Markdown class.""" + + def extendMarkdown(self, md, md_globals): + """ Register extension instances. """ + md.registerExtensions(extensions, self.config) + +def makeExtension(configs={}): + return ExtraExtension(configs=dict(configs)) diff --git a/markdown/extensions/fenced_code.py b/markdown/extensions/fenced_code.py new file mode 100644 index 0000000..307b1dc --- /dev/null +++ b/markdown/extensions/fenced_code.py @@ -0,0 +1,117 @@ +#!/usr/bin/env python + +""" +Fenced Code Extension for Python Markdown +========================================= + +This extension adds Fenced Code Blocks to Python-Markdown. + + >>> import markdown + >>> text = ''' + ... A paragraph before a fenced code block: + ... + ... ~~~ + ... Fenced code block + ... ~~~ + ... ''' + >>> html = markdown.markdown(text, extensions=['fenced_code']) + >>> html + u'<p>A paragraph before a fenced code block:</p>\\n<pre><code>Fenced code block\\n</code></pre>' + +Works with safe_mode also (we check this because we are using the HtmlStash): + + >>> markdown.markdown(text, extensions=['fenced_code'], safe_mode='replace') + u'<p>A paragraph before a fenced code block:</p>\\n<pre><code>Fenced code block\\n</code></pre>' + +Include tilde's in a code block and wrap with blank lines: + + >>> text = ''' + ... ~~~~~~~~ + ... + ... ~~~~ + ... + ... ~~~~~~~~''' + >>> markdown.markdown(text, extensions=['fenced_code']) + u'<pre><code>\\n~~~~\\n\\n</code></pre>' + +Multiple blocks and language tags: + + >>> text = ''' + ... ~~~~{.python} + ... block one + ... ~~~~ + ... + ... ~~~~.html + ... <p>block two</p> + ... ~~~~''' + >>> markdown.markdown(text, extensions=['fenced_code']) + u'<pre><code class="python">block one\\n</code></pre>\\n\\n<pre><code class="html"><p>block two</p>\\n</code></pre>' + +Copyright 2007-2008 [Waylan Limberg](http://achinghead.com/). + +Project website: <http://www.freewisdom.org/project/python-markdown/Fenced__Code__Blocks> +Contact: markdown@freewisdom.org + +License: BSD (see ../docs/LICENSE for details) + +Dependencies: +* [Python 2.3+](http://python.org) +* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/) + +""" + +import markdown, re + +# Global vars +FENCED_BLOCK_RE = re.compile( \ + r'(?P<fence>^~{3,})[ ]*(\{?\.(?P<lang>[a-zA-Z0-9_-]*)\}?)?[ ]*\n(?P<code>.*?)(?P=fence)[ ]*$', + re.MULTILINE|re.DOTALL + ) +CODE_WRAP = '<pre><code%s>%s</code></pre>' +LANG_TAG = ' class="%s"' + + +class FencedCodeExtension(markdown.Extension): + + def extendMarkdown(self, md, md_globals): + """ Add FencedBlockPreprocessor to the Markdown instance. """ + + md.preprocessors.add('fenced_code_block', + FencedBlockPreprocessor(md), + "_begin") + + +class FencedBlockPreprocessor(markdown.preprocessors.Preprocessor): + + def run(self, lines): + """ Match and store Fenced Code Blocks in the HtmlStash. """ + text = "\n".join(lines) + while 1: + m = FENCED_BLOCK_RE.search(text) + if m: + lang = '' + if m.group('lang'): + lang = LANG_TAG % m.group('lang') + code = CODE_WRAP % (lang, self._escape(m.group('code'))) + placeholder = self.markdown.htmlStash.store(code, safe=True) + text = '%s\n%s\n%s'% (text[:m.start()], placeholder, text[m.end():]) + else: + break + return text.split("\n") + + def _escape(self, txt): + """ basic html escaping """ + txt = txt.replace('&', '&') + txt = txt.replace('<', '<') + txt = txt.replace('>', '>') + txt = txt.replace('"', '"') + return txt + + +def makeExtension(configs=None): + return FencedCodeExtension() + + +if __name__ == "__main__": + import doctest + doctest.testmod() diff --git a/markdown/extensions/footnotes.py b/markdown/extensions/footnotes.py new file mode 100644 index 0000000..e1a9cda --- /dev/null +++ b/markdown/extensions/footnotes.py @@ -0,0 +1,307 @@ +""" +========================= FOOTNOTES ================================= + +This section adds footnote handling to markdown. It can be used as +an example for extending python-markdown with relatively complex +functionality. While in this case the extension is included inside +the module itself, it could just as easily be added from outside the +module. Not that all markdown classes above are ignorant about +footnotes. All footnote functionality is provided separately and +then added to the markdown instance at the run time. + +Footnote functionality is attached by calling extendMarkdown() +method of FootnoteExtension. The method also registers the +extension to allow it's state to be reset by a call to reset() +method. + +Example: + Footnotes[^1] have a label[^label] and a definition[^!DEF]. + + [^1]: This is a footnote + [^label]: A footnote on "label" + [^!DEF]: The footnote for definition + +""" + +import re, markdown +from markdown import etree + +FN_BACKLINK_TEXT = "zz1337820767766393qq" +NBSP_PLACEHOLDER = "qq3936677670287331zz" +DEF_RE = re.compile(r'(\ ?\ ?\ ?)\[\^([^\]]*)\]:\s*(.*)') +TABBED_RE = re.compile(r'((\t)|( ))(.*)') + +class FootnoteExtension(markdown.Extension): + """ Footnote Extension. """ + + def __init__ (self, configs): + """ Setup configs. """ + self.config = {'PLACE_MARKER': + ["///Footnotes Go Here///", + "The text string that marks where the footnotes go"], + 'UNIQUE_IDS': + [False, + "Avoid name collisions across " + "multiple calls to reset()."]} + + for key, value in configs: + self.config[key][0] = value + + # In multiple invocations, emit links that don't get tangled. + self.unique_prefix = 0 + + self.reset() + + def extendMarkdown(self, md, md_globals): + """ Add pieces to Markdown. """ + md.registerExtension(self) + self.parser = md.parser + # Insert a preprocessor before ReferencePreprocessor + md.preprocessors.add("footnote", FootnotePreprocessor(self), + "<reference") + # Insert an inline pattern before ImageReferencePattern + FOOTNOTE_RE = r'\[\^([^\]]*)\]' # blah blah [^1] blah + md.inlinePatterns.add("footnote", FootnotePattern(FOOTNOTE_RE, self), + "<reference") + # Insert a tree-processor that would actually add the footnote div + # This must be before the inline treeprocessor so inline patterns + # run on the contents of the div. + md.treeprocessors.add("footnote", FootnoteTreeprocessor(self), + "<inline") + # Insert a postprocessor after amp_substitute oricessor + md.postprocessors.add("footnote", FootnotePostprocessor(self), + ">amp_substitute") + + def reset(self): + """ Clear the footnotes on reset, and prepare for a distinct document. """ + self.footnotes = markdown.odict.OrderedDict() + self.unique_prefix += 1 + + def findFootnotesPlaceholder(self, root): + """ Return ElementTree Element that contains Footnote placeholder. """ + def finder(element): + for child in element: + if child.text: + if child.text.find(self.getConfig("PLACE_MARKER")) > -1: + return child, True + if child.tail: + if child.tail.find(self.getConfig("PLACE_MARKER")) > -1: + return (child, element), False + finder(child) + return None + + res = finder(root) + return res + + def setFootnote(self, id, text): + """ Store a footnote for later retrieval. """ + self.footnotes[id] = text + + def makeFootnoteId(self, id): + """ Return footnote link id. """ + if self.getConfig("UNIQUE_IDS"): + return 'fn:%d-%s' % (self.unique_prefix, id) + else: + return 'fn:%s' % id + + def makeFootnoteRefId(self, id): + """ Return footnote back-link id. """ + if self.getConfig("UNIQUE_IDS"): + return 'fnref:%d-%s' % (self.unique_prefix, id) + else: + return 'fnref:%s' % id + + def makeFootnotesDiv(self, root): + """ Return div of footnotes as et Element. """ + + if not self.footnotes.keys(): + return None + + div = etree.Element("div") + div.set('class', 'footnote') + hr = etree.SubElement(div, "hr") + ol = etree.SubElement(div, "ol") + + for id in self.footnotes.keys(): + li = etree.SubElement(ol, "li") + li.set("id", self.makeFootnoteId(id)) + self.parser.parseChunk(li, self.footnotes[id]) + backlink = etree.Element("a") + backlink.set("href", "#" + self.makeFootnoteRefId(id)) + backlink.set("rev", "footnote") + backlink.set("title", "Jump back to footnote %d in the text" % \ + (self.footnotes.index(id)+1)) + backlink.text = FN_BACKLINK_TEXT + + if li.getchildren(): + node = li[-1] + if node.tag == "p": + node.text = node.text + NBSP_PLACEHOLDER + node.append(backlink) + else: + p = etree.SubElement(li, "p") + p.append(backlink) + return div + + +class FootnotePreprocessor(markdown.preprocessors.Preprocessor): + """ Find all footnote references and store for later use. """ + + def __init__ (self, footnotes): + self.footnotes = footnotes + + def run(self, lines): + lines = self._handleFootnoteDefinitions(lines) + text = "\n".join(lines) + return text.split("\n") + + def _handleFootnoteDefinitions(self, lines): + """ + Recursively find all footnote definitions in lines. + + Keywords: + + * lines: A list of lines of text + + Return: A list of lines with footnote definitions removed. + + """ + i, id, footnote = self._findFootnoteDefinition(lines) + + if id : + plain = lines[:i] + detabbed, theRest = self.detectTabbed(lines[i+1:]) + self.footnotes.setFootnote(id, + footnote + "\n" + + "\n".join(detabbed)) + more_plain = self._handleFootnoteDefinitions(theRest) + return plain + [""] + more_plain + else : + return lines + + def _findFootnoteDefinition(self, lines): + """ + Find the parts of a footnote definition. + + Keywords: + + * lines: A list of lines of text. + + Return: A three item tuple containing the index of the first line of a + footnote definition, the id of the definition and the body of the + definition. + + """ + counter = 0 + for line in lines: + m = DEF_RE.match(line) + if m: + return counter, m.group(2), m.group(3) + counter += 1 + return counter, None, None + + def detectTabbed(self, lines): + """ Find indented text and remove indent before further proccesing. + + Keyword arguments: + + * lines: an array of strings + + Returns: a list of post processed items and the unused + remainder of the original list + + """ + items = [] + item = -1 + i = 0 # to keep track of where we are + + def detab(line): + match = TABBED_RE.match(line) + if match: + return match.group(4) + + for line in lines: + if line.strip(): # Non-blank line + line = detab(line) + if line: + items.append(line) + i += 1 + continue + else: + return items, lines[i:] + + else: # Blank line: _maybe_ we are done. + i += 1 # advance + + # Find the next non-blank line + for j in range(i, len(lines)): + if lines[j].strip(): + next_line = lines[j]; break + else: + break # There is no more text; we are done. + + # Check if the next non-blank line is tabbed + if detab(next_line): # Yes, more work to do. + items.append("") + continue + else: + break # No, we are done. + else: + i += 1 + + return items, lines[i:] + + +class FootnotePattern(markdown.inlinepatterns.Pattern): + """ InlinePattern for footnote markers in a document's body text. """ + + def __init__(self, pattern, footnotes): + markdown.inlinepatterns.Pattern.__init__(self, pattern) + self.footnotes = footnotes + + def handleMatch(self, m): + sup = etree.Element("sup") + a = etree.SubElement(sup, "a") + id = m.group(2) + sup.set('id', self.footnotes.makeFootnoteRefId(id)) + a.set('href', '#' + self.footnotes.makeFootnoteId(id)) + a.set('rel', 'footnote') + a.text = str(self.footnotes.footnotes.index(id) + 1) + return sup + + +class FootnoteTreeprocessor(markdown.treeprocessors.Treeprocessor): + """ Build and append footnote div to end of document. """ + + def __init__ (self, footnotes): + self.footnotes = footnotes + + def run(self, root): + footnotesDiv = self.footnotes.makeFootnotesDiv(root) + if footnotesDiv: + result = self.footnotes.findFootnotesPlaceholder(root) + if result: + node, isText = result + if isText: + node.text = None + node.getchildren().insert(0, footnotesDiv) + else: + child, element = node + ind = element.getchildren().find(child) + element.getchildren().insert(ind + 1, footnotesDiv) + child.tail = None + fnPlaceholder.parent.replaceChild(fnPlaceholder, footnotesDiv) + else: + root.append(footnotesDiv) + +class FootnotePostprocessor(markdown.postprocessors.Postprocessor): + """ Replace placeholders with html entities. """ + + def run(self, text): + text = text.replace(FN_BACKLINK_TEXT, "↩") + return text.replace(NBSP_PLACEHOLDER, " ") + +def makeExtension(configs=[]): + """ Return an instance of the FootnoteExtension """ + return FootnoteExtension(configs=configs) + diff --git a/markdown/extensions/headerid.py b/markdown/extensions/headerid.py new file mode 100644 index 0000000..f70a7a9 --- /dev/null +++ b/markdown/extensions/headerid.py @@ -0,0 +1,195 @@ +#!/usr/bin/python + +""" +HeaderID Extension for Python-Markdown +====================================== + +Adds ability to set HTML IDs for headers. + +Basic usage: + + >>> import markdown + >>> text = "# Some Header # {#some_id}" + >>> md = markdown.markdown(text, ['headerid']) + >>> md + u'<h1 id="some_id">Some Header</h1>' + +All header IDs are unique: + + >>> text = ''' + ... #Header + ... #Another Header {#header} + ... #Third Header {#header}''' + >>> md = markdown.markdown(text, ['headerid']) + >>> md + u'<h1 id="header">Header</h1>\\n<h1 id="header_1">Another Header</h1>\\n<h1 id="header_2">Third Header</h1>' + +To fit within a html template's hierarchy, set the header base level: + + >>> text = ''' + ... #Some Header + ... ## Next Level''' + >>> md = markdown.markdown(text, ['headerid(level=3)']) + >>> md + u'<h3 id="some_header">Some Header</h3>\\n<h4 id="next_level">Next Level</h4>' + +Turn off auto generated IDs: + + >>> text = ''' + ... # Some Header + ... # Header with ID # { #foo }''' + >>> md = markdown.markdown(text, ['headerid(forceid=False)']) + >>> md + u'<h1>Some Header</h1>\\n<h1 id="foo">Header with ID</h1>' + +Use with MetaData extension: + + >>> text = '''header_level: 2 + ... header_forceid: Off + ... + ... # A Header''' + >>> md = markdown.markdown(text, ['headerid', 'meta']) + >>> md + u'<h2>A Header</h2>' + +Copyright 2007-2008 [Waylan Limberg](http://achinghead.com/). + +Project website: <http://www.freewisdom.org/project/python-markdown/HeaderId> +Contact: markdown@freewisdom.org + +License: BSD (see ../docs/LICENSE for details) + +Dependencies: +* [Python 2.3+](http://python.org) +* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/) + +""" + +import markdown +from markdown import etree +import re +from string import ascii_lowercase, digits, punctuation + +ID_CHARS = ascii_lowercase + digits + '-_' +IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$') + + +class HeaderIdProcessor(markdown.blockprocessors.BlockProcessor): + """ Replacement BlockProcessor for Header IDs. """ + + # Detect a header at start of any line in block + RE = re.compile(r"""(^|\n) + (?P<level>\#{1,6}) # group('level') = string of hashes + (?P<header>.*?) # group('header') = Header text + \#* # optional closing hashes + (?:[ \t]*\{[ \t]*\#(?P<id>[-_:a-zA-Z0-9]+)[ \t]*\})? + (\n|$) # ^^ group('id') = id attribute + """, + re.VERBOSE) + + IDs = [] + + def test(self, parent, block): + return bool(self.RE.search(block)) + + def run(self, parent, blocks): + block = blocks.pop(0) + m = self.RE.search(block) + if m: + before = block[:m.start()] # All lines before header + after = block[m.end():] # All lines after header + if before: + # As the header was not the first line of the block and the + # lines before the header must be parsed first, + # recursively parse this lines as a block. + self.parser.parseBlocks(parent, [before]) + # Create header using named groups from RE + start_level, force_id = self._get_meta() + level = len(m.group('level')) + start_level + if level > 6: + level = 6 + h = markdown.etree.SubElement(parent, 'h%d' % level) + h.text = m.group('header').strip() + if m.group('id'): + h.set('id', self._unique_id(m.group('id'))) + elif force_id: + h.set('id', self._create_id(m.group('header').strip())) + if after: + # Insert remaining lines as first block for future parsing. + blocks.insert(0, after) + else: + # This should never happen, but just in case... + message(CRITICAL, "We've got a problem header!") + + def _get_meta(self): + """ Return meta data suported by this ext as a tuple """ + level = int(self.config['level'][0]) - 1 + force = self._str2bool(self.config['forceid'][0]) + if hasattr(self.md, 'Meta'): + if self.md.Meta.has_key('header_level'): + level = int(self.md.Meta['header_level'][0]) - 1 + if self.md.Meta.has_key('header_forceid'): + force = self._str2bool(self.md.Meta['header_forceid'][0]) + return level, force + + def _str2bool(self, s, default=False): + """ Convert a string to a booleen value. """ + s = str(s) + if s.lower() in ['0', 'f', 'false', 'off', 'no', 'n']: + return False + elif s.lower() in ['1', 't', 'true', 'on', 'yes', 'y']: + return True + return default + + def _unique_id(self, id): + """ Ensure ID is unique. Append '_1', '_2'... if not """ + while id in self.IDs: + m = IDCOUNT_RE.match(id) + if m: + id = '%s_%d'% (m.group(1), int(m.group(2))+1) + else: + id = '%s_%d'% (id, 1) + self.IDs.append(id) + return id + + def _create_id(self, header): + """ Return ID from Header text. """ + h = '' + for c in header.lower().replace(' ', '_'): + if c in ID_CHARS: + h += c + elif c not in punctuation: + h += '+' + return self._unique_id(h) + + +class HeaderIdExtension (markdown.Extension): + def __init__(self, configs): + # set defaults + self.config = { + 'level' : ['1', 'Base level for headers.'], + 'forceid' : ['True', 'Force all headers to have an id.'] + } + + for key, value in configs: + self.setConfig(key, value) + + def extendMarkdown(self, md, md_globals): + md.registerExtension(self) + self.processor = HeaderIdProcessor(md.parser) + self.processor.md = md + self.processor.config = self.config + # Replace existing hasheader in place. + md.parser.blockprocessors['hashheader'] = self.processor + + def reset(self): + self.processor.IDs = [] + + +def makeExtension(configs=None): + return HeaderIdExtension(configs=configs) + +if __name__ == "__main__": + import doctest + doctest.testmod() + diff --git a/markdown/extensions/html_tidy.py b/markdown/extensions/html_tidy.py new file mode 100644 index 0000000..5105e33 --- /dev/null +++ b/markdown/extensions/html_tidy.py @@ -0,0 +1,62 @@ +#!/usr/bin/env python + +""" +HTML Tidy Extension for Python-Markdown +======================================= + +Runs [HTML Tidy][] on the output of Python-Markdown using the [uTidylib][] +Python wrapper. Both libtidy and uTidylib must be installed on your system. + +Note than any Tidy [options][] can be passed in as extension configs. So, +for example, to output HTML rather than XHTML, set ``output_xhtml=0``. To +indent the output, set ``indent=auto`` and to have Tidy wrap the output in +``<html>`` and ``<body>`` tags, set ``show_body_only=0``. + +[HTML Tidy]: http://tidy.sourceforge.net/ +[uTidylib]: http://utidylib.berlios.de/ +[options]: http://tidy.sourceforge.net/docs/quickref.html + +Copyright (c)2008 [Waylan Limberg](http://achinghead.com) + +License: [BSD](http://www.opensource.org/licenses/bsd-license.php) + +Dependencies: +* [Python2.3+](http://python.org) +* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/) +* [HTML Tidy](http://utidylib.berlios.de/) +* [uTidylib](http://utidylib.berlios.de/) + +""" + +import markdown +import tidy + +class TidyExtension(markdown.Extension): + + def __init__(self, configs): + # Set defaults to match typical markdown behavior. + self.config = dict(output_xhtml=1, + show_body_only=1, + ) + # Merge in user defined configs overriding any present if nessecary. + for c in configs: + self.config[c[0]] = c[1] + + def extendMarkdown(self, md, md_globals): + # Save options to markdown instance + md.tidy_options = self.config + # Add TidyProcessor to postprocessors + md.postprocessors['tidy'] = TidyProcessor(md) + + +class TidyProcessor(markdown.postprocessors.Postprocessor): + + def run(self, text): + # Pass text to Tidy. As Tidy does not accept unicode we need to encode + # it and decode its return value. + return unicode(tidy.parseString(text.encode('utf-8'), + **self.markdown.tidy_options)) + + +def makeExtension(configs=None): + return TidyExtension(configs=configs) diff --git a/markdown/extensions/imagelinks.py b/markdown/extensions/imagelinks.py new file mode 100644 index 0000000..ee0b708 --- /dev/null +++ b/markdown/extensions/imagelinks.py @@ -0,0 +1,119 @@ +""" +========================= IMAGE LINKS ================================= + + +Turns paragraphs like + +<~~~~~~~~~~~~~~~~~~~~~~~~ +dir/subdir +dir/subdir +dir/subdir +~~~~~~~~~~~~~~ +dir/subdir +dir/subdir +dir/subdir +~~~~~~~~~~~~~~~~~~~> + +Into mini-photo galleries. + +""" + +import re, markdown +import url_manager + + +IMAGE_LINK = """<a href="%s"><img src="%s" title="%s"/></a>""" +SLIDESHOW_LINK = """<a href="%s" target="_blank">[slideshow]</a>""" +ALBUM_LINK = """ <a href="%s">[%s]</a>""" + + +class ImageLinksExtension(markdown.Extension): + + def extendMarkdown(self, md, md_globals): + + md.preprocessors.add("imagelink", ImageLinkPreprocessor(md), "_begin") + + +class ImageLinkPreprocessor(markdown.preprocessors.Preprocessor): + + def run(self, lines): + + url = url_manager.BlogEntryUrl(url_manager.BlogUrl("all"), + "2006/08/29/the_rest_of_our") + + + all_images = [] + blocks = [] + in_image_block = False + + new_lines = [] + + for line in lines: + + if line.startswith("<~~~~~~~"): + albums = [] + rows = [] + in_image_block = True + + if not in_image_block: + + new_lines.append(line) + + else: + + line = line.strip() + + if line.endswith("~~~~~~>") or not line: + in_image_block = False + new_block = "<div><br/><center><span class='image-links'>\n" + + album_url_hash = {} + + for row in rows: + for photo_url, title in row: + new_block += " " + new_block += IMAGE_LINK % (photo_url, + photo_url.get_thumbnail(), + title) + + album_url_hash[str(photo_url.get_album())] = 1 + + new_block += "<br/>" + + new_block += "</span>" + new_block += SLIDESHOW_LINK % url.get_slideshow() + + album_urls = album_url_hash.keys() + album_urls.sort() + + if len(album_urls) == 1: + new_block += ALBUM_LINK % (album_urls[0], "complete album") + else : + for i in range(len(album_urls)) : + new_block += ALBUM_LINK % (album_urls[i], + "album %d" % (i + 1) ) + + new_lines.append(new_block + "</center><br/></div>") + + elif line[1:6] == "~~~~~" : + rows.append([]) # start a new row + else : + parts = line.split() + line = parts[0] + title = " ".join(parts[1:]) + + album, photo = line.split("/") + photo_url = url.get_photo(album, photo, + len(all_images)+1) + all_images.append(photo_url) + rows[-1].append((photo_url, title)) + + if not album in albums : + albums.append(album) + + return new_lines + + +def makeExtension(configs): + return ImageLinksExtension(configs) + diff --git a/markdown/extensions/meta.py b/markdown/extensions/meta.py new file mode 100644 index 0000000..1b555b2 --- /dev/null +++ b/markdown/extensions/meta.py @@ -0,0 +1,90 @@ +#!usr/bin/python + +""" +Meta Data Extension for Python-Markdown +======================================= + +This extension adds Meta Data handling to markdown. + +Basic Usage: + + >>> import markdown + >>> text = '''Title: A Test Doc. + ... Author: Waylan Limberg + ... John Doe + ... Blank_Data: + ... + ... The body. This is paragraph one. + ... ''' + >>> md = markdown.Markdown(['meta']) + >>> md.convert(text) + u'<p>The body. This is paragraph one.</p>' + >>> md.Meta + {u'blank_data': [u''], u'author': [u'Waylan Limberg', u'John Doe'], u'title': [u'A Test Doc.']} + +Make sure text without Meta Data still works (markdown < 1.6b returns a <p>). + + >>> text = ' Some Code - not extra lines of meta data.' + >>> md = markdown.Markdown(['meta']) + >>> md.convert(text) + u'<pre><code>Some Code - not extra lines of meta data.\\n</code></pre>' + >>> md.Meta + {} + +Copyright 2007-2008 [Waylan Limberg](http://achinghead.com). + +Project website: <http://www.freewisdom.org/project/python-markdown/Meta-Data> +Contact: markdown@freewisdom.org + +License: BSD (see ../docs/LICENSE for details) + +""" + +import markdown, re + +# Global Vars +META_RE = re.compile(r'^[ ]{0,3}(?P<key>[A-Za-z0-9_-]+):\s*(?P<value>.*)') +META_MORE_RE = re.compile(r'^[ ]{4,}(?P<value>.*)') + +class MetaExtension (markdown.Extension): + """ Meta-Data extension for Python-Markdown. """ + + def extendMarkdown(self, md, md_globals): + """ Add MetaPreprocessor to Markdown instance. """ + + md.preprocessors.add("meta", MetaPreprocessor(md), "_begin") + + +class MetaPreprocessor(markdown.preprocessors.Preprocessor): + """ Get Meta-Data. """ + + def run(self, lines): + """ Parse Meta-Data and store in Markdown.Meta. """ + meta = {} + key = None + while 1: + line = lines.pop(0) + if line.strip() == '': + break # blank line - done + m1 = META_RE.match(line) + if m1: + key = m1.group('key').lower().strip() + meta[key] = [m1.group('value').strip()] + else: + m2 = META_MORE_RE.match(line) + if m2 and key: + # Add another line to existing key + meta[key].append(m2.group('value').strip()) + else: + lines.insert(0, line) + break # no meta data - done + self.markdown.Meta = meta + return lines + + +def makeExtension(configs={}): + return MetaExtension(configs=configs) + +if __name__ == "__main__": + import doctest + doctest.testmod() diff --git a/markdown/extensions/rss.py b/markdown/extensions/rss.py new file mode 100644 index 0000000..1274da2 --- /dev/null +++ b/markdown/extensions/rss.py @@ -0,0 +1,114 @@ +import markdown +from markdown import etree + +DEFAULT_URL = "http://www.freewisdom.org/projects/python-markdown/" +DEFAULT_CREATOR = "Yuri Takhteyev" +DEFAULT_TITLE = "Markdown in Python" +GENERATOR = "http://www.freewisdom.org/projects/python-markdown/markdown2rss" + +month_map = { "Jan" : "01", + "Feb" : "02", + "March" : "03", + "April" : "04", + "May" : "05", + "June" : "06", + "July" : "07", + "August" : "08", + "September" : "09", + "October" : "10", + "November" : "11", + "December" : "12" } + +def get_time(heading): + + heading = heading.split("-")[0] + heading = heading.strip().replace(",", " ").replace(".", " ") + + month, date, year = heading.split() + month = month_map[month] + + return rdftime(" ".join((month, date, year, "12:00:00 AM"))) + +def rdftime(time): + + time = time.replace(":", " ") + time = time.replace("/", " ") + time = time.split() + return "%s-%s-%sT%s:%s:%s-08:00" % (time[0], time[1], time[2], + time[3], time[4], time[5]) + + +def get_date(text): + return "date" + +class RssExtension (markdown.Extension): + + def extendMarkdown(self, md, md_globals): + + self.config = { 'URL' : [DEFAULT_URL, "Main URL"], + 'CREATOR' : [DEFAULT_CREATOR, "Feed creator's name"], + 'TITLE' : [DEFAULT_TITLE, "Feed title"] } + + md.xml_mode = True + + # Insert a tree-processor that would actually add the title tag + treeprocessor = RssTreeProcessor(md) + treeprocessor.ext = self + md.treeprocessors['rss'] = treeprocessor + md.stripTopLevelTags = 0 + md.docType = '<?xml version="1.0" encoding="utf-8"?>\n' + +class RssTreeProcessor(markdown.treeprocessors.Treeprocessor): + + def run (self, root): + + rss = etree.Element("rss") + rss.set("version", "2.0") + + channel = etree.SubElement(rss, "channel") + + for tag, text in (("title", self.ext.getConfig("TITLE")), + ("link", self.ext.getConfig("URL")), + ("description", None)): + + element = etree.SubElement(channel, tag) + element.text = text + + for child in root: + + if child.tag in ["h1", "h2", "h3", "h4", "h5"]: + + heading = child.text.strip() + item = etree.SubElement(channel, "item") + link = etree.SubElement(item, "link") + link.text = self.ext.getConfig("URL") + title = etree.SubElement(item, "title") + title.text = heading + + guid = ''.join([x for x in heading if x.isalnum()]) + guidElem = etree.SubElement(item, "guid") + guidElem.text = guid + guidElem.set("isPermaLink", "false") + + elif child.tag in ["p"]: + try: + description = etree.SubElement(item, "description") + except UnboundLocalError: + # Item not defined - moving on + pass + else: + if len(child): + content = "\n".join([etree.tostring(node) + for node in child]) + else: + content = child.text + pholder = self.markdown.htmlStash.store( + "<![CDATA[ %s]]>" % content) + description.text = pholder + + return rss + + +def makeExtension(configs): + + return RssExtension(configs) diff --git a/markdown/extensions/tables.py b/markdown/extensions/tables.py new file mode 100644 index 0000000..1d3c920 --- /dev/null +++ b/markdown/extensions/tables.py @@ -0,0 +1,97 @@ +#!/usr/bin/env Python +""" +Tables Extension for Python-Markdown +==================================== + +Added parsing of tables to Python-Markdown. + +A simple example: + + First Header | Second Header + ------------- | ------------- + Content Cell | Content Cell + Content Cell | Content Cell + +Copyright 2009 - [Waylan Limberg](http://achinghead.com) +""" +import markdown +from markdown import etree + + +class TableProcessor(markdown.blockprocessors.BlockProcessor): + """ Process Tables. """ + + def test(self, parent, block): + rows = block.split('\n') + return (len(rows) > 2 and '|' in rows[0] and + '|' in rows[1] and '-' in rows[1] and + rows[1][0] in ['|', ':', '-']) + + def run(self, parent, blocks): + """ Parse a table block and build table. """ + block = blocks.pop(0).split('\n') + header = block[:2] + rows = block[2:] + # Get format type (bordered by pipes or not) + border = False + if header[0].startswith('|'): + border = True + # Get alignment of columns + align = [] + for c in self._split_row(header[1], border): + if c.startswith(':') and c.endswith(':'): + align.append('center') + elif c.startswith(':'): + align.append('left') + elif c.endswith(':'): + align.append('right') + else: + align.append(None) + # Build table + table = etree.SubElement(parent, 'table') + thead = etree.SubElement(table, 'thead') + self._build_row(header[0], thead, align, border) + tbody = etree.SubElement(table, 'tbody') + for row in rows: + self._build_row(row, tbody, align, border) + + def _build_row(self, row, parent, align, border): + """ Given a row of text, build table cells. """ + tr = etree.SubElement(parent, 'tr') + tag = 'td' + if parent.tag == 'thead': + tag = 'th' + cells = self._split_row(row, border) + # We use align here rather than cells to ensure every row + # contains the same number of columns. + for i, a in enumerate(align): + c = etree.SubElement(tr, tag) + try: + c.text = cells[i].strip() + except IndexError: + c.text = "" + if a: + c.set('align', a) + + def _split_row(self, row, border): + """ split a row of text into list of cells. """ + if border: + if row.startswith('|'): + row = row[1:] + if row.endswith('|'): + row = row[:-1] + return row.split('|') + + +class TableExtension(markdown.Extension): + """ Add tables to Markdown. """ + + def extendMarkdown(self, md, md_globals): + """ Add an instance of TableProcessor to BlockParser. """ + md.parser.blockprocessors.add('table', + TableProcessor(md.parser), + '<hashheader') + + +def makeExtension(configs={}): + return TableExtension(configs=configs) diff --git a/markdown/extensions/toc.py b/markdown/extensions/toc.py new file mode 100644 index 0000000..1d9489c --- /dev/null +++ b/markdown/extensions/toc.py @@ -0,0 +1,136 @@ +""" +Table of Contents Extension for Python-Markdown +* * * + +(c) 2008 [Jack Miller](http://codezen.org) + +Dependencies: +* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/) + +""" +import markdown +from markdown import etree +import re + +class TocTreeprocessor(markdown.treeprocessors.Treeprocessor): + # Iterator wrapper to get parent and child all at once + def iterparent(self, root): + for parent in root.getiterator(): + for child in parent: + yield parent, child + + def run(self, doc): + div = etree.Element("div") + div.attrib["class"] = "toc" + last_li = None + + # Add title to the div + if self.config["title"][0]: + header = etree.SubElement(div, "span") + header.attrib["class"] = "toctitle" + header.text = self.config["title"][0] + + level = 0 + list_stack=[div] + header_rgx = re.compile("[Hh][123456]") + + # Get a list of id attributes + used_ids = [] + for c in doc.getiterator(): + if "id" in c.attrib: + used_ids.append(c.attrib["id"]) + + for (p, c) in self.iterparent(doc): + if not c.text: + continue + + # To keep the output from screwing up the + # validation by putting a <div> inside of a <p> + # we actually replace the <p> in its entirety. + # We do not allow the marker inside a header as that + # would causes an enless loop of placing a new TOC + # inside previously generated TOC. + + if c.text.find(self.config["marker"][0]) > -1 and not header_rgx.match(c.tag): + for i in range(len(p)): + if p[i] == c: + p[i] = div + break + + if header_rgx.match(c.tag): + tag_level = int(c.tag[-1]) + + while tag_level < level: + list_stack.pop() + level -= 1 + + if tag_level > level: + newlist = etree.Element("ul") + if last_li: + last_li.append(newlist) + else: + list_stack[-1].append(newlist) + list_stack.append(newlist) + level += 1 + + # Do not override pre-existing ids + if not "id" in c.attrib: + id = self.config["slugify"][0](c.text) + if id in used_ids: + ctr = 1 + while "%s_%d" % (id, ctr) in used_ids: + ctr += 1 + id = "%s_%d" % (id, ctr) + used_ids.append(id) + c.attrib["id"] = id + else: + id = c.attrib["id"] + + # List item link, to be inserted into the toc div + last_li = etree.Element("li") + link = etree.SubElement(last_li, "a") + link.text = c.text + link.attrib["href"] = '#' + id + + if int(self.config["anchorlink"][0]): + anchor = etree.SubElement(c, "a") + anchor.text = c.text + anchor.attrib["href"] = "#" + id + anchor.attrib["class"] = "toclink" + c.text = "" + + list_stack[-1].append(last_li) + +class TocExtension(markdown.Extension): + def __init__(self, configs): + self.config = { "marker" : ["[TOC]", + "Text to find and replace with Table of Contents -" + "Defaults to \"[TOC]\""], + "slugify" : [self.slugify, + "Function to generate anchors based on header text-" + "Defaults to a built in slugify function."], + "title" : [None, + "Title to insert into TOC <div> - " + "Defaults to None"], + "anchorlink" : [0, + "1 if header should be a self link" + "Defaults to 0"]} + + for key, value in configs: + self.setConfig(key, value) + + # This is exactly the same as Django's slugify + def slugify(self, value): + """ Slugify a string, to make it URL friendly. """ + import unicodedata + value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore') + value = unicode(re.sub('[^\w\s-]', '', value).strip().lower()) + return re.sub('[-\s]+','-',value) + + def extendMarkdown(self, md, md_globals): + tocext = TocTreeprocessor(md) + tocext.config = self.config + md.treeprocessors.add("toc", tocext, "_begin") + +def makeExtension(configs={}): + return TocExtension(configs=configs) diff --git a/markdown/extensions/wikilinks.py b/markdown/extensions/wikilinks.py new file mode 100644 index 0000000..df44e1c --- /dev/null +++ b/markdown/extensions/wikilinks.py @@ -0,0 +1,155 @@ +#!/usr/bin/env python + +''' +WikiLinks Extension for Python-Markdown +====================================== + +Converts [[WikiLinks]] to relative links. Requires Python-Markdown 2.0+ + +Basic usage: + + >>> import markdown + >>> text = "Some text with a [[WikiLink]]." + >>> html = markdown.markdown(text, ['wikilinks']) + >>> html + u'<p>Some text with a <a class="wikilink" href="/WikiLink/">WikiLink</a>.</p>' + +Whitespace behavior: + + >>> markdown.markdown('[[ foo bar_baz ]]', ['wikilinks']) + u'<p><a class="wikilink" href="/foo_bar_baz/">foo bar_baz</a></p>' + >>> markdown.markdown('foo [[ ]] bar', ['wikilinks']) + u'<p>foo bar</p>' + +To define custom settings the simple way: + + >>> markdown.markdown(text, + ... ['wikilinks(base_url=/wiki/,end_url=.html,html_class=foo)'] + ... ) + u'<p>Some text with a <a class="foo" href="/wiki/WikiLink.html">WikiLink</a>.</p>' + +Custom settings the complex way: + + >>> md = markdown.Markdown( + ... extensions = ['wikilinks'], + ... extension_configs = {'wikilinks': [ + ... ('base_url', 'http://example.com/'), + ... ('end_url', '.html'), + ... ('html_class', '') ]}, + ... safe_mode = True) + >>> md.convert(text) + u'<p>Some text with a <a href="http://example.com/WikiLink.html">WikiLink</a>.</p>' + +Use MetaData with mdx_meta.py (Note the blank html_class in MetaData): + + >>> text = """wiki_base_url: http://example.com/ + ... wiki_end_url: .html + ... wiki_html_class: + ... + ... Some text with a [[WikiLink]].""" + >>> md = markdown.Markdown(extensions=['meta', 'wikilinks']) + >>> md.convert(text) + u'<p>Some text with a <a href="http://example.com/WikiLink.html">WikiLink</a>.</p>' + +MetaData should not carry over to next document: + + >>> md.convert("No [[MetaData]] here.") + u'<p>No <a class="wikilink" href="/MetaData/">MetaData</a> here.</p>' + +Define a custom URL builder: + + >>> def my_url_builder(label, base, end): + ... return '/bar/' + >>> md = markdown.Markdown(extensions=['wikilinks'], + ... extension_configs={'wikilinks' : [('build_url', my_url_builder)]}) + >>> md.convert('[[foo]]') + u'<p><a class="wikilink" href="/bar/">foo</a></p>' + +From the command line: + + python markdown.py -x wikilinks(base_url=http://example.com/,end_url=.html,html_class=foo) src.txt + +By [Waylan Limberg](http://achinghead.com/). + +License: [BSD](http://www.opensource.org/licenses/bsd-license.php) + +Dependencies: +* [Python 2.3+](http://python.org) +* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/) +''' + +import markdown +import re + +def build_url(label, base, end): + """ Build a url from the label, a base, and an end. """ + clean_label = re.sub(r'([ ]+_)|(_[ ]+)|([ ]+)', '_', label) + return '%s%s%s'% (base, clean_label, end) + + +class WikiLinkExtension(markdown.Extension): + def __init__(self, configs): + # set extension defaults + self.config = { + 'base_url' : ['/', 'String to append to beginning or URL.'], + 'end_url' : ['/', 'String to append to end of URL.'], + 'html_class' : ['wikilink', 'CSS hook. Leave blank for none.'], + 'build_url' : [build_url, 'Callable formats URL from label.'], + } + + # Override defaults with user settings + for key, value in configs : + self.setConfig(key, value) + + def extendMarkdown(self, md, md_globals): + self.md = md + + # append to end of inline patterns + WIKILINK_RE = r'\[\[([A-Za-z0-9_ -]+)\]\]' + wikilinkPattern = WikiLinks(WIKILINK_RE, self.config) + wikilinkPattern.md = md + md.inlinePatterns.add('wikilink', wikilinkPattern, "<not_strong") + + +class WikiLinks(markdown.inlinepatterns.Pattern): + def __init__(self, pattern, config): + markdown.inlinepatterns.Pattern.__init__(self, pattern) + self.config = config + + def handleMatch(self, m): + if m.group(2).strip(): + base_url, end_url, html_class = self._getMeta() + label = m.group(2).strip() + url = self.config['build_url'][0](label, base_url, end_url) + a = markdown.etree.Element('a') + a.text = label + a.set('href', url) + if html_class: + a.set('class', html_class) + else: + a = '' + return a + + def _getMeta(self): + """ Return meta data or config data. """ + base_url = self.config['base_url'][0] + end_url = self.config['end_url'][0] + html_class = self.config['html_class'][0] + if hasattr(self.md, 'Meta'): + if self.md.Meta.has_key('wiki_base_url'): + base_url = self.md.Meta['wiki_base_url'][0] + if self.md.Meta.has_key('wiki_end_url'): + end_url = self.md.Meta['wiki_end_url'][0] + if self.md.Meta.has_key('wiki_html_class'): + html_class = self.md.Meta['wiki_html_class'][0] + return base_url, end_url, html_class + + +def makeExtension(configs=None) : + return WikiLinkExtension(configs=configs) + + +if __name__ == "__main__": + import doctest + doctest.testmod() + diff --git a/markdown/html4.py b/markdown/html4.py new file mode 100644 index 0000000..08f241d --- /dev/null +++ b/markdown/html4.py @@ -0,0 +1,274 @@ +# markdown/html4.py +# +# Add html4 serialization to older versions of Elementree +# Taken from ElementTree 1.3 preview with slight modifications +# +# Copyright (c) 1999-2007 by Fredrik Lundh. All rights reserved. +# +# fredrik@pythonware.com +# http://www.pythonware.com +# +# -------------------------------------------------------------------- +# The ElementTree toolkit is +# +# Copyright (c) 1999-2007 by Fredrik Lundh +# +# By obtaining, using, and/or copying this software and/or its +# associated documentation, you agree that you have read, understood, +# and will comply with the following terms and conditions: +# +# Permission to use, copy, modify, and distribute this software and +# its associated documentation for any purpose and without fee is +# hereby granted, provided that the above copyright notice appears in +# all copies, and that both that copyright notice and this permission +# notice appear in supporting documentation, and that the name of +# Secret Labs AB or the author not be used in advertising or publicity +# pertaining to distribution of the software without specific, written +# prior permission. +# +# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD +# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT- +# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR +# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY +# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, +# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS +# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE +# OF THIS SOFTWARE. +# -------------------------------------------------------------------- + + +import markdown +ElementTree = markdown.etree.ElementTree +QName = markdown.etree.QName +Comment = markdown.etree.Comment +PI = markdown.etree.PI +ProcessingInstruction = markdown.etree.ProcessingInstruction + +HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr", + "img", "input", "isindex", "link", "meta" "param") + +try: + HTML_EMPTY = set(HTML_EMPTY) +except NameError: + pass + +_namespace_map = { + # "well-known" namespace prefixes + "http://www.w3.org/XML/1998/namespace": "xml", + "http://www.w3.org/1999/xhtml": "html", + "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf", + "http://schemas.xmlsoap.org/wsdl/": "wsdl", + # xml schema + "http://www.w3.org/2001/XMLSchema": "xs", + "http://www.w3.org/2001/XMLSchema-instance": "xsi", + # dublic core + "http://purl.org/dc/elements/1.1/": "dc", +} + + +def _raise_serialization_error(text): + raise TypeError( + "cannot serialize %r (type %s)" % (text, type(text).__name__) + ) + +def _encode(text, encoding): + try: + return text.encode(encoding, "xmlcharrefreplace") + except (TypeError, AttributeError): + _raise_serialization_error(text) + +def _escape_cdata(text, encoding): + # escape character data + try: + # it's worth avoiding do-nothing calls for strings that are + # shorter than 500 character, or so. assume that's, by far, + # the most common case in most applications. + if "&" in text: + text = text.replace("&", "&") + if "<" in text: + text = text.replace("<", "<") + if ">" in text: + text = text.replace(">", ">") + return text.encode(encoding, "xmlcharrefreplace") + except (TypeError, AttributeError): + _raise_serialization_error(text) + + +def _escape_attrib(text, encoding): + # escape attribute value + try: + if "&" in text: + text = text.replace("&", "&") + if "<" in text: + text = text.replace("<", "<") + if ">" in text: + text = text.replace(">", ">") + if "\"" in text: + text = text.replace("\"", """) + if "\n" in text: + text = text.replace("\n", " ") + return text.encode(encoding, "xmlcharrefreplace") + except (TypeError, AttributeError): + _raise_serialization_error(text) + +def _escape_attrib_html(text, encoding): + # escape attribute value + try: + if "&" in text: + text = text.replace("&", "&") + if ">" in text: + text = text.replace(">", ">") + if "\"" in text: + text = text.replace("\"", """) + return text.encode(encoding, "xmlcharrefreplace") + except (TypeError, AttributeError): + _raise_serialization_error(text) + + +def _serialize_html(write, elem, encoding, qnames, namespaces): + tag = elem.tag + text = elem.text + if tag is Comment: + write("<!--%s-->" % _escape_cdata(text, encoding)) + elif tag is ProcessingInstruction: + write("<?%s?>" % _escape_cdata(text, encoding)) + else: + tag = qnames[tag] + if tag is None: + if text: + write(_escape_cdata(text, encoding)) + for e in elem: + _serialize_html(write, e, encoding, qnames, None) + else: + write("<" + tag) + items = elem.items() + if items or namespaces: + items.sort() # lexical order + for k, v in items: + if isinstance(k, QName): + k = k.text + if isinstance(v, QName): + v = qnames[v.text] + else: + v = _escape_attrib_html(v, encoding) + # FIXME: handle boolean attributes + write(" %s=\"%s\"" % (qnames[k], v)) + if namespaces: + items = namespaces.items() + items.sort(key=lambda x: x[1]) # sort on prefix + for v, k in items: + if k: + k = ":" + k + write(" xmlns%s=\"%s\"" % ( + k.encode(encoding), + _escape_attrib(v, encoding) + )) + write(">") + tag = tag.lower() + if text: + if tag == "script" or tag == "style": + write(_encode(text, encoding)) + else: + write(_escape_cdata(text, encoding)) + for e in elem: + _serialize_html(write, e, encoding, qnames, None) + if tag not in HTML_EMPTY: + write("</" + tag + ">") + if elem.tail: + write(_escape_cdata(elem.tail, encoding)) + +def write_html(root, f, + # keyword arguments + encoding="us-ascii", + default_namespace=None): + assert root is not None + if not hasattr(f, "write"): + f = open(f, "wb") + write = f.write + if not encoding: + encoding = "us-ascii" + qnames, namespaces = _namespaces( + root, encoding, default_namespace + ) + _serialize_html( + write, root, encoding, qnames, namespaces + ) + +# -------------------------------------------------------------------- +# serialization support + +def _namespaces(elem, encoding, default_namespace=None): + # identify namespaces used in this tree + + # maps qnames to *encoded* prefix:local names + qnames = {None: None} + + # maps uri:s to prefixes + namespaces = {} + if default_namespace: + namespaces[default_namespace] = "" + + def encode(text): + return text.encode(encoding) + + def add_qname(qname): + # calculate serialized qname representation + try: + if qname[:1] == "{": + uri, tag = qname[1:].split("}", 1) + prefix = namespaces.get(uri) + if prefix is None: + prefix = _namespace_map.get(uri) + if prefix is None: + prefix = "ns%d" % len(namespaces) + if prefix != "xml": + namespaces[uri] = prefix + if prefix: + qnames[qname] = encode("%s:%s" % (prefix, tag)) + else: + qnames[qname] = encode(tag) # default element + else: + if default_namespace: + # FIXME: can this be handled in XML 1.0? + raise ValueError( + "cannot use non-qualified names with " + "default_namespace option" + ) + qnames[qname] = encode(qname) + except TypeError: + _raise_serialization_error(qname) + + # populate qname and namespaces table + try: + iterate = elem.iter + except AttributeError: + iterate = elem.getiterator # cET compatibility + for elem in iterate(): + tag = elem.tag + if isinstance(tag, QName) and tag.text not in qnames: + add_qname(tag.text) + elif isinstance(tag, basestring): + if tag not in qnames: + add_qname(tag) + elif tag is not None and tag is not Comment and tag is not PI: + _raise_serialization_error(tag) + for key, value in elem.items(): + if isinstance(key, QName): + key = key.text + if key not in qnames: + add_qname(key) + if isinstance(value, QName) and value.text not in qnames: + add_qname(value.text) + text = elem.text + if isinstance(text, QName) and text.text not in qnames: + add_qname(text.text) + return qnames, namespaces + +def to_html_string(element, encoding=None): + class dummy: + pass + data = [] + file = dummy() + file.write = data.append + write_html(ElementTree(element).getroot(),file,encoding) + return "".join(data) diff --git a/markdown/inlinepatterns.py b/markdown/inlinepatterns.py new file mode 100644 index 0000000..917a9d3 --- /dev/null +++ b/markdown/inlinepatterns.py @@ -0,0 +1,371 @@ +""" +INLINE PATTERNS +============================================================================= + +Inline patterns such as *emphasis* are handled by means of auxiliary +objects, one per pattern. Pattern objects must be instances of classes +that extend markdown.Pattern. Each pattern object uses a single regular +expression and needs support the following methods: + + pattern.getCompiledRegExp() # returns a regular expression + + pattern.handleMatch(m) # takes a match object and returns + # an ElementTree element or just plain text + +All of python markdown's built-in patterns subclass from Pattern, +but you can add additional patterns that don't. + +Also note that all the regular expressions used by inline must +capture the whole block. For this reason, they all start with +'^(.*)' and end with '(.*)!'. In case with built-in expression +Pattern takes care of adding the "^(.*)" and "(.*)!". + +Finally, the order in which regular expressions are applied is very +important - e.g. if we first replace http://.../ links with <a> tags +and _then_ try to replace inline html, we would end up with a mess. +So, we apply the expressions in the following order: + +* escape and backticks have to go before everything else, so + that we can preempt any markdown patterns by escaping them. + +* then we handle auto-links (must be done before inline html) + +* then we handle inline HTML. At this point we will simply + replace all inline HTML strings with a placeholder and add + the actual HTML to a hash. + +* then inline images (must be done before links) + +* then bracketed links, first regular then reference-style + +* finally we apply strong and emphasis +""" + +import markdown +import re +from urlparse import urlparse, urlunparse +import sys +if sys.version >= "3.0": + from html import entities as htmlentitydefs +else: + import htmlentitydefs + +""" +The actual regular expressions for patterns +----------------------------------------------------------------------------- +""" + +NOBRACKET = r'[^\]\[]*' +BRK = ( r'\[(' + + (NOBRACKET + r'(\[')*6 + + (NOBRACKET+ r'\])*')*6 + + NOBRACKET + r')\]' ) +NOIMG = r'(?<!\!)' + +BACKTICK_RE = r'(?<!\\)(`+)(.+?)(?<!`)\2(?!`)' # `e=f()` or ``e=f("`")`` +ESCAPE_RE = r'\\(.)' # \< +EMPHASIS_RE = r'(\*)([^\*]+)\2' # *emphasis* +STRONG_RE = r'(\*{2}|_{2})(.+?)\2' # **strong** +STRONG_EM_RE = r'(\*{3}|_{3})(.+?)\2' # ***strong*** + +if markdown.SMART_EMPHASIS: + EMPHASIS_2_RE = r'(?<!\w)(_)(\S.+?)\2(?!\w)' # _emphasis_ +else: + EMPHASIS_2_RE = r'(_)(.+?)\2' # _emphasis_ + +LINK_RE = NOIMG + BRK + \ +r'''\(\s*(<.*?>|((?:(?:\(.*?\))|[^\(\)]))*?)\s*((['"])(.*?)\12)?\)''' +# [text](url) or [text](<url>) + +IMAGE_LINK_RE = r'\!' + BRK + r'\s*\((<.*?>|([^\)]*))\)' +#  or  +REFERENCE_RE = NOIMG + BRK+ r'\s*\[([^\]]*)\]' # [Google][3] +IMAGE_REFERENCE_RE = r'\!' + BRK + '\s*\[([^\]]*)\]' # ![alt text][2] +NOT_STRONG_RE = r'((^| )(\*|_)( |$))' # stand-alone * or _ +AUTOLINK_RE = r'<((?:f|ht)tps?://[^>]*)>' # <http://www.123.com> +AUTOMAIL_RE = r'<([^> \!]*@[^> ]*)>' # <me@example.com> + +HTML_RE = r'(\<([a-zA-Z/][^\>]*?|\!--.*?--)\>)' # <...> +ENTITY_RE = r'(&[\#a-zA-Z0-9]*;)' # & +LINE_BREAK_RE = r' \n' # two spaces at end of line +LINE_BREAK_2_RE = r' $' # two spaces at end of text + + +def dequote(string): + """Remove quotes from around a string.""" + if ( ( string.startswith('"') and string.endswith('"')) + or (string.startswith("'") and string.endswith("'")) ): + return string[1:-1] + else: + return string + +ATTR_RE = re.compile("\{@([^\}]*)=([^\}]*)}") # {@id=123} + +def handleAttributes(text, parent): + """Set values of an element based on attribute definitions ({@id=123}).""" + def attributeCallback(match): + parent.set(match.group(1), match.group(2).replace('\n', ' ')) + return ATTR_RE.sub(attributeCallback, text) + + +""" +The pattern classes +----------------------------------------------------------------------------- +""" + +class Pattern: + """Base class that inline patterns subclass. """ + + def __init__ (self, pattern, markdown_instance=None): + """ + Create an instant of an inline pattern. + + Keyword arguments: + + * pattern: A regular expression that matches a pattern + + """ + self.pattern = pattern + self.compiled_re = re.compile("^(.*?)%s(.*?)$" % pattern, re.DOTALL) + + # Api for Markdown to pass safe_mode into instance + self.safe_mode = False + if markdown_instance: + self.markdown = markdown_instance + + def getCompiledRegExp (self): + """ Return a compiled regular expression. """ + return self.compiled_re + + def handleMatch(self, m): + """Return a ElementTree element from the given match. + + Subclasses should override this method. + + Keyword arguments: + + * m: A re match object containing a match of the pattern. + + """ + pass + + def type(self): + """ Return class name, to define pattern type """ + return self.__class__.__name__ + +BasePattern = Pattern # for backward compatibility + +class SimpleTextPattern (Pattern): + """ Return a simple text of group(2) of a Pattern. """ + def handleMatch(self, m): + text = m.group(2) + if text == markdown.INLINE_PLACEHOLDER_PREFIX: + return None + return text + +class SimpleTagPattern (Pattern): + """ + Return element of type `tag` with a text attribute of group(3) + of a Pattern. + + """ + def __init__ (self, pattern, tag): + Pattern.__init__(self, pattern) + self.tag = tag + + def handleMatch(self, m): + el = markdown.etree.Element(self.tag) + el.text = m.group(3) + return el + + +class SubstituteTagPattern (SimpleTagPattern): + """ Return a eLement of type `tag` with no children. """ + def handleMatch (self, m): + return markdown.etree.Element(self.tag) + + +class BacktickPattern (Pattern): + """ Return a `<code>` element containing the matching text. """ + def __init__ (self, pattern): + Pattern.__init__(self, pattern) + self.tag = "code" + + def handleMatch(self, m): + el = markdown.etree.Element(self.tag) + el.text = markdown.AtomicString(m.group(3).strip()) + return el + + +class DoubleTagPattern (SimpleTagPattern): + """Return a ElementTree element nested in tag2 nested in tag1. + + Useful for strong emphasis etc. + + """ + def handleMatch(self, m): + tag1, tag2 = self.tag.split(",") + el1 = markdown.etree.Element(tag1) + el2 = markdown.etree.SubElement(el1, tag2) + el2.text = m.group(3) + return el1 + + +class HtmlPattern (Pattern): + """ Store raw inline html and return a placeholder. """ + def handleMatch (self, m): + rawhtml = m.group(2) + inline = True + place_holder = self.markdown.htmlStash.store(rawhtml) + return place_holder + + +class LinkPattern (Pattern): + """ Return a link element from the given match. """ + def handleMatch(self, m): + el = markdown.etree.Element("a") + el.text = m.group(2) + title = m.group(11) + href = m.group(9) + + if href: + if href[0] == "<": + href = href[1:-1] + el.set("href", self.sanitize_url(href.strip())) + else: + el.set("href", "") + + if title: + title = dequote(title) #.replace('"', """) + el.set("title", title) + return el + + def sanitize_url(self, url): + """ + Sanitize a url against xss attacks in "safe_mode". + + Rather than specifically blacklisting `javascript:alert("XSS")` and all + its aliases (see <http://ha.ckers.org/xss.html>), we whitelist known + safe url formats. Most urls contain a network location, however some + are known not to (i.e.: mailto links). Script urls do not contain a + location. Additionally, for `javascript:...`, the scheme would be + "javascript" but some aliases will appear to `urlparse()` to have no + scheme. On top of that relative links (i.e.: "foo/bar.html") have no + scheme. Therefore we must check "path", "parameters", "query" and + "fragment" for any literal colons. We don't check "scheme" for colons + because it *should* never have any and "netloc" must allow the form: + `username:password@host:port`. + + """ + locless_schemes = ['', 'mailto', 'news'] + scheme, netloc, path, params, query, fragment = url = urlparse(url) + safe_url = False + if netloc != '' or scheme in locless_schemes: + safe_url = True + + for part in url[2:]: + if ":" in part: + safe_url = False + + if self.markdown.safeMode and not safe_url: + return '' + else: + return urlunparse(url) + +class ImagePattern(LinkPattern): + """ Return a img element from the given match. """ + def handleMatch(self, m): + el = markdown.etree.Element("img") + src_parts = m.group(9).split() + if src_parts: + src = src_parts[0] + if src[0] == "<" and src[-1] == ">": + src = src[1:-1] + el.set('src', self.sanitize_url(src)) + else: + el.set('src', "") + if len(src_parts) > 1: + el.set('title', dequote(" ".join(src_parts[1:]))) + + if markdown.ENABLE_ATTRIBUTES: + truealt = handleAttributes(m.group(2), el) + else: + truealt = m.group(2) + + el.set('alt', truealt) + return el + +class ReferencePattern(LinkPattern): + """ Match to a stored reference and return link element. """ + def handleMatch(self, m): + if m.group(9): + id = m.group(9).lower() + else: + # if we got something like "[Google][]" + # we'll use "google" as the id + id = m.group(2).lower() + + if not id in self.markdown.references: # ignore undefined refs + return None + href, title = self.markdown.references[id] + + text = m.group(2) + return self.makeTag(href, title, text) + + def makeTag(self, href, title, text): + el = markdown.etree.Element('a') + + el.set('href', self.sanitize_url(href)) + if title: + el.set('title', title) + + el.text = text + return el + + +class ImageReferencePattern (ReferencePattern): + """ Match to a stored reference and return img element. """ + def makeTag(self, href, title, text): + el = markdown.etree.Element("img") + el.set("src", self.sanitize_url(href)) + if title: + el.set("title", title) + el.set("alt", text) + return el + + +class AutolinkPattern (Pattern): + """ Return a link Element given an autolink (`<http://example/com>`). """ + def handleMatch(self, m): + el = markdown.etree.Element("a") + el.set('href', m.group(2)) + el.text = markdown.AtomicString(m.group(2)) + return el + +class AutomailPattern (Pattern): + """ + Return a mailto link Element given an automail link (`<foo@example.com>`). + """ + def handleMatch(self, m): + el = markdown.etree.Element('a') + email = m.group(2) + if email.startswith("mailto:"): + email = email[len("mailto:"):] + + def codepoint2name(code): + """Return entity definition by code, or the code if not defined.""" + entity = htmlentitydefs.codepoint2name.get(code) + if entity: + return "%s%s;" % (markdown.AMP_SUBSTITUTE, entity) + else: + return "%s#%d;" % (markdown.AMP_SUBSTITUTE, code) + + letters = [codepoint2name(ord(letter)) for letter in email] + el.text = markdown.AtomicString(''.join(letters)) + + mailto = "mailto:" + email + mailto = "".join([markdown.AMP_SUBSTITUTE + '#%d;' % + ord(letter) for letter in mailto]) + el.set('href', mailto) + return el + diff --git a/markdown/odict.py b/markdown/odict.py new file mode 100644 index 0000000..bf3ef07 --- /dev/null +++ b/markdown/odict.py @@ -0,0 +1,162 @@ +class OrderedDict(dict): + """ + A dictionary that keeps its keys in the order in which they're inserted. + + Copied from Django's SortedDict with some modifications. + + """ + def __new__(cls, *args, **kwargs): + instance = super(OrderedDict, cls).__new__(cls, *args, **kwargs) + instance.keyOrder = [] + return instance + + def __init__(self, data=None): + if data is None: + data = {} + super(OrderedDict, self).__init__(data) + if isinstance(data, dict): + self.keyOrder = data.keys() + else: + self.keyOrder = [] + for key, value in data: + if key not in self.keyOrder: + self.keyOrder.append(key) + + def __deepcopy__(self, memo): + from copy import deepcopy + return self.__class__([(key, deepcopy(value, memo)) + for key, value in self.iteritems()]) + + def __setitem__(self, key, value): + super(OrderedDict, self).__setitem__(key, value) + if key not in self.keyOrder: + self.keyOrder.append(key) + + def __delitem__(self, key): + super(OrderedDict, self).__delitem__(key) + self.keyOrder.remove(key) + + def __iter__(self): + for k in self.keyOrder: + yield k + + def pop(self, k, *args): + result = super(OrderedDict, self).pop(k, *args) + try: + self.keyOrder.remove(k) + except ValueError: + # Key wasn't in the dictionary in the first place. No problem. + pass + return result + + def popitem(self): + result = super(OrderedDict, self).popitem() + self.keyOrder.remove(result[0]) + return result + + def items(self): + return zip(self.keyOrder, self.values()) + + def iteritems(self): + for key in self.keyOrder: + yield key, super(OrderedDict, self).__getitem__(key) + + def keys(self): + return self.keyOrder[:] + + def iterkeys(self): + return iter(self.keyOrder) + + def values(self): + return [super(OrderedDict, self).__getitem__(k) for k in self.keyOrder] + + def itervalues(self): + for key in self.keyOrder: + yield super(OrderedDict, self).__getitem__(key) + + def update(self, dict_): + for k, v in dict_.items(): + self.__setitem__(k, v) + + def setdefault(self, key, default): + if key not in self.keyOrder: + self.keyOrder.append(key) + return super(OrderedDict, self).setdefault(key, default) + + def value_for_index(self, index): + """Return the value of the item at the given zero-based index.""" + return self[self.keyOrder[index]] + + def insert(self, index, key, value): + """Insert the key, value pair before the item with the given index.""" + if key in self.keyOrder: + n = self.keyOrder.index(key) + del self.keyOrder[n] + if n < index: + index -= 1 + self.keyOrder.insert(index, key) + super(OrderedDict, self).__setitem__(key, value) + + def copy(self): + """Return a copy of this object.""" + # This way of initializing the copy means it works for subclasses, too. + obj = self.__class__(self) + obj.keyOrder = self.keyOrder[:] + return obj + + def __repr__(self): + """ + Replace the normal dict.__repr__ with a version that returns the keys + in their sorted order. + """ + return '{%s}' % ', '.join(['%r: %r' % (k, v) for k, v in self.items()]) + + def clear(self): + super(OrderedDict, self).clear() + self.keyOrder = [] + + def index(self, key): + """ Return the index of a given key. """ + return self.keyOrder.index(key) + + def index_for_location(self, location): + """ Return index or None for a given location. """ + if location == '_begin': + i = 0 + elif location == '_end': + i = None + elif location.startswith('<') or location.startswith('>'): + i = self.index(location[1:]) + if location.startswith('>'): + if i >= len(self): + # last item + i = None + else: + i += 1 + else: + raise ValueError('Not a valid location: "%s". Location key ' + 'must start with a ">" or "<".' % location) + return i + + def add(self, key, value, location): + """ Insert by key location. """ + i = self.index_for_location(location) + if i is not None: + self.insert(i, key, value) + else: + self.__setitem__(key, value) + + def link(self, key, location): + """ Change location of an existing item. """ + n = self.keyOrder.index(key) + del self.keyOrder[n] + i = self.index_for_location(location) + try: + if i is not None: + self.keyOrder.insert(i, key) + else: + self.keyOrder.append(key) + except Error: + # restore to prevent data loss and reraise + self.keyOrder.insert(n, key) + raise Error diff --git a/markdown/postprocessors.py b/markdown/postprocessors.py new file mode 100644 index 0000000..80227bb --- /dev/null +++ b/markdown/postprocessors.py @@ -0,0 +1,77 @@ +""" +POST-PROCESSORS +============================================================================= + +Markdown also allows post-processors, which are similar to preprocessors in +that they need to implement a "run" method. However, they are run after core +processing. + +""" + + +import markdown + +class Processor: + def __init__(self, markdown_instance=None): + if markdown_instance: + self.markdown = markdown_instance + +class Postprocessor(Processor): + """ + Postprocessors are run after the ElementTree it converted back into text. + + Each Postprocessor implements a "run" method that takes a pointer to a + text string, modifies it as necessary and returns a text string. + + Postprocessors must extend markdown.Postprocessor. + + """ + + def run(self, text): + """ + Subclasses of Postprocessor should implement a `run` method, which + takes the html document as a single text string and returns a + (possibly modified) string. + + """ + pass + + +class RawHtmlPostprocessor(Postprocessor): + """ Restore raw html to the document. """ + + def run(self, text): + """ Iterate over html stash and restore "safe" html. """ + for i in range(self.markdown.htmlStash.html_counter): + html, safe = self.markdown.htmlStash.rawHtmlBlocks[i] + if self.markdown.safeMode and not safe: + if str(self.markdown.safeMode).lower() == 'escape': + html = self.escape(html) + elif str(self.markdown.safeMode).lower() == 'remove': + html = '' + else: + html = markdown.HTML_REMOVED_TEXT + if safe or not self.markdown.safeMode: + text = text.replace("<p>%s</p>" % + (markdown.preprocessors.HTML_PLACEHOLDER % i), + html + "\n") + text = text.replace(markdown.preprocessors.HTML_PLACEHOLDER % i, + html) + return text + + def escape(self, html): + """ Basic html escaping """ + html = html.replace('&', '&') + html = html.replace('<', '<') + html = html.replace('>', '>') + return html.replace('"', '"') + + +class AndSubstitutePostprocessor(Postprocessor): + """ Restore valid entities """ + def __init__(self): + pass + + def run(self, text): + text = text.replace(markdown.AMP_SUBSTITUTE, "&") + return text diff --git a/markdown/preprocessors.py b/markdown/preprocessors.py new file mode 100644 index 0000000..ef04cab --- /dev/null +++ b/markdown/preprocessors.py @@ -0,0 +1,215 @@ + +""" +PRE-PROCESSORS +============================================================================= + +Preprocessors work on source text before we start doing anything too +complicated. +""" + +import re +import markdown + +HTML_PLACEHOLDER_PREFIX = markdown.STX+"wzxhzdk:" +HTML_PLACEHOLDER = HTML_PLACEHOLDER_PREFIX + "%d" + markdown.ETX + +class Processor: + def __init__(self, markdown_instance=None): + if markdown_instance: + self.markdown = markdown_instance + +class Preprocessor (Processor): + """ + Preprocessors are run after the text is broken into lines. + + Each preprocessor implements a "run" method that takes a pointer to a + list of lines of the document, modifies it as necessary and returns + either the same pointer or a pointer to a new list. + + Preprocessors must extend markdown.Preprocessor. + + """ + def run(self, lines): + """ + Each subclass of Preprocessor should override the `run` method, which + takes the document as a list of strings split by newlines and returns + the (possibly modified) list of lines. + + """ + pass + +class HtmlStash: + """ + This class is used for stashing HTML objects that we extract + in the beginning and replace with place-holders. + """ + + def __init__ (self): + """ Create a HtmlStash. """ + self.html_counter = 0 # for counting inline html segments + self.rawHtmlBlocks=[] + + def store(self, html, safe=False): + """ + Saves an HTML segment for later reinsertion. Returns a + placeholder string that needs to be inserted into the + document. + + Keyword arguments: + + * html: an html segment + * safe: label an html segment as safe for safemode + + Returns : a placeholder string + + """ + self.rawHtmlBlocks.append((html, safe)) + placeholder = HTML_PLACEHOLDER % self.html_counter + self.html_counter += 1 + return placeholder + + def reset(self): + self.html_counter = 0 + self.rawHtmlBlocks = [] + + +class HtmlBlockPreprocessor(Preprocessor): + """Remove html blocks from the text and store them for later retrieval.""" + + right_tag_patterns = ["</%s>", "%s>"] + + def _get_left_tag(self, block): + return block[1:].replace(">", " ", 1).split()[0].lower() + + def _get_right_tag(self, left_tag, block): + for p in self.right_tag_patterns: + tag = p % left_tag + i = block.rfind(tag) + if i > 2: + return tag.lstrip("<").rstrip(">"), i + len(p)-2 + len(left_tag) + return block.rstrip()[-len(left_tag)-2:-1].lower(), len(block) + + def _equal_tags(self, left_tag, right_tag): + if left_tag == 'div' or left_tag[0] in ['?', '@', '%']: # handle PHP, etc. + return True + if ("/" + left_tag) == right_tag: + return True + if (right_tag == "--" and left_tag == "--"): + return True + elif left_tag == right_tag[1:] \ + and right_tag[0] != "<": + return True + else: + return False + + def _is_oneliner(self, tag): + return (tag in ['hr', 'hr/']) + + def run(self, lines): + text = "\n".join(lines) + new_blocks = [] + text = text.split("\n\n") + items = [] + left_tag = '' + right_tag = '' + in_tag = False # flag + + while text: + block = text[0] + if block.startswith("\n"): + block = block[1:] + text = text[1:] + + if block.startswith("\n"): + block = block[1:] + + if not in_tag: + if block.startswith("<"): + left_tag = self._get_left_tag(block) + right_tag, data_index = self._get_right_tag(left_tag, block) + + if block[1] == "!": + # is a comment block + left_tag = "--" + right_tag, data_index = self._get_right_tag(left_tag, block) + # keep checking conditions below and maybe just append + + if data_index < len(block) \ + and markdown.isBlockLevel(left_tag): + text.insert(0, block[data_index:]) + block = block[:data_index] + + if not (markdown.isBlockLevel(left_tag) \ + or block[1] in ["!", "?", "@", "%"]): + new_blocks.append(block) + continue + + if self._is_oneliner(left_tag): + new_blocks.append(block.strip()) + continue + + if block.rstrip().endswith(">") \ + and self._equal_tags(left_tag, right_tag): + new_blocks.append( + self.markdown.htmlStash.store(block.strip())) + continue + else: #if not block[1] == "!": + # if is block level tag and is not complete + + if markdown.isBlockLevel(left_tag) or left_tag == "--" \ + and not block.rstrip().endswith(">"): + items.append(block.strip()) + in_tag = True + else: + new_blocks.append( + self.markdown.htmlStash.store(block.strip())) + + continue + + new_blocks.append(block) + + else: + items.append(block.strip()) + + right_tag, data_index = self._get_right_tag(left_tag, block) + + if self._equal_tags(left_tag, right_tag): + # if find closing tag + in_tag = False + new_blocks.append( + self.markdown.htmlStash.store('\n\n'.join(items))) + items = [] + + if items: + new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items))) + new_blocks.append('\n') + + new_text = "\n\n".join(new_blocks) + return new_text.split("\n") + + +class ReferencePreprocessor(Preprocessor): + """ Remove reference definitions from text and store for later use. """ + + RE = re.compile(r'^(\ ?\ ?\ ?)\[([^\]]*)\]:\s*([^ ]*)(.*)$', re.DOTALL) + + def run (self, lines): + new_text = []; + for line in lines: + m = self.RE.match(line) + if m: + id = m.group(2).strip().lower() + t = m.group(4).strip() # potential title + if not t: + self.markdown.references[id] = (m.group(3), t) + elif (len(t) >= 2 + and (t[0] == t[-1] == "\"" + or t[0] == t[-1] == "\'" + or (t[0] == "(" and t[-1] == ")") ) ): + self.markdown.references[id] = (m.group(3), t[1:-1]) + else: + new_text.append(line) + else: + new_text.append(line) + + return new_text #+ "\n" diff --git a/markdown/treeprocessors.py b/markdown/treeprocessors.py new file mode 100644 index 0000000..1dc612a --- /dev/null +++ b/markdown/treeprocessors.py @@ -0,0 +1,329 @@ +import markdown +import re + +def isString(s): + """ Check if it's string """ + return isinstance(s, unicode) or isinstance(s, str) + +class Processor: + def __init__(self, markdown_instance=None): + if markdown_instance: + self.markdown = markdown_instance + +class Treeprocessor(Processor): + """ + Treeprocessors are run on the ElementTree object before serialization. + + Each Treeprocessor implements a "run" method that takes a pointer to an + ElementTree, modifies it as necessary and returns an ElementTree + object. + + Treeprocessors must extend markdown.Treeprocessor. + + """ + def run(self, root): + """ + Subclasses of Treeprocessor should implement a `run` method, which + takes a root ElementTree. This method can return another ElementTree + object, and the existing root ElementTree will be replaced, or it can + modify the current tree and return None. + """ + pass + + +class InlineProcessor(Treeprocessor): + """ + A Treeprocessor that traverses a tree, applying inline patterns. + """ + + def __init__ (self, md): + self.__placeholder_prefix = markdown.INLINE_PLACEHOLDER_PREFIX + self.__placeholder_suffix = markdown.ETX + self.__placeholder_length = 4 + len(self.__placeholder_prefix) \ + + len(self.__placeholder_suffix) + self.__placeholder_re = re.compile(markdown.INLINE_PLACEHOLDER % r'([0-9]{4})') + self.markdown = md + + def __makePlaceholder(self, type): + """ Generate a placeholder """ + id = "%04d" % len(self.stashed_nodes) + hash = markdown.INLINE_PLACEHOLDER % id + return hash, id + + def __findPlaceholder(self, data, index): + """ + Extract id from data string, start from index + + Keyword arguments: + + * data: string + * index: index, from which we start search + + Returns: placeholder id and string index, after the found placeholder. + """ + + m = self.__placeholder_re.search(data, index) + if m: + return m.group(1), m.end() + else: + return None, index + 1 + + def __stashNode(self, node, type): + """ Add node to stash """ + placeholder, id = self.__makePlaceholder(type) + self.stashed_nodes[id] = node + return placeholder + + def __handleInline(self, data, patternIndex=0): + """ + Process string with inline patterns and replace it + with placeholders + + Keyword arguments: + + * data: A line of Markdown text + * patternIndex: The index of the inlinePattern to start with + + Returns: String with placeholders. + + """ + if not isinstance(data, markdown.AtomicString): + startIndex = 0 + while patternIndex < len(self.markdown.inlinePatterns): + data, matched, startIndex = self.__applyPattern( + self.markdown.inlinePatterns.value_for_index(patternIndex), + data, patternIndex, startIndex) + if not matched: + patternIndex += 1 + return data + + def __processElementText(self, node, subnode, isText=True): + """ + Process placeholders in Element.text or Element.tail + of Elements popped from self.stashed_nodes. + + Keywords arguments: + + * node: parent node + * subnode: processing node + * isText: bool variable, True - it's text, False - it's tail + + Returns: None + + """ + if isText: + text = subnode.text + subnode.text = None + else: + text = subnode.tail + subnode.tail = None + + childResult = self.__processPlaceholders(text, subnode) + + if not isText and node is not subnode: + pos = node.getchildren().index(subnode) + node.remove(subnode) + else: + pos = 0 + + childResult.reverse() + for newChild in childResult: + node.insert(pos, newChild) + + def __processPlaceholders(self, data, parent): + """ + Process string with placeholders and generate ElementTree tree. + + Keyword arguments: + + * data: string with placeholders instead of ElementTree elements. + * parent: Element, which contains processing inline data + + Returns: list with ElementTree elements with applied inline patterns. + """ + def linkText(text): + if text: + if result: + if result[-1].tail: + result[-1].tail += text + else: + result[-1].tail = text + else: + if parent.text: + parent.text += text + else: + parent.text = text + + result = [] + strartIndex = 0 + while data: + index = data.find(self.__placeholder_prefix, strartIndex) + if index != -1: + id, phEndIndex = self.__findPlaceholder(data, index) + + if id in self.stashed_nodes: + node = self.stashed_nodes.get(id) + + if index > 0: + text = data[strartIndex:index] + linkText(text) + + if not isString(node): # it's Element + for child in [node] + node.getchildren(): + if child.tail: + if child.tail.strip(): + self.__processElementText(node, child, False) + if child.text: + if child.text.strip(): + self.__processElementText(child, child) + else: # it's just a string + linkText(node) + strartIndex = phEndIndex + continue + + strartIndex = phEndIndex + result.append(node) + + else: # wrong placeholder + end = index + len(prefix) + linkText(data[strartIndex:end]) + strartIndex = end + else: + text = data[strartIndex:] + linkText(text) + data = "" + + return result + + def __applyPattern(self, pattern, data, patternIndex, startIndex=0): + """ + Check if the line fits the pattern, create the necessary + elements, add it to stashed_nodes. + + Keyword arguments: + + * data: the text to be processed + * pattern: the pattern to be checked + * patternIndex: index of current pattern + * startIndex: string index, from which we starting search + + Returns: String with placeholders instead of ElementTree elements. + + """ + match = pattern.getCompiledRegExp().match(data[startIndex:]) + leftData = data[:startIndex] + + if not match: + return data, False, 0 + + node = pattern.handleMatch(match) + + if node is None: + return data, True, len(leftData) + match.span(len(match.groups()))[0] + + if not isString(node): + if not isinstance(node.text, markdown.AtomicString): + # We need to process current node too + for child in [node] + node.getchildren(): + if not isString(node): + if child.text: + child.text = self.__handleInline(child.text, + patternIndex + 1) + if child.tail: + child.tail = self.__handleInline(child.tail, + patternIndex) + + placeholder = self.__stashNode(node, pattern.type()) + + return "%s%s%s%s" % (leftData, + match.group(1), + placeholder, match.groups()[-1]), True, 0 + + def run(self, tree): + """Apply inline patterns to a parsed Markdown tree. + + Iterate over ElementTree, find elements with inline tag, apply inline + patterns and append newly created Elements to tree. If you don't + want process your data with inline paterns, instead of normal string, + use subclass AtomicString: + + node.text = markdown.AtomicString("data won't be processed with inline patterns") + + Arguments: + + * markdownTree: ElementTree object, representing Markdown tree. + + Returns: ElementTree object with applied inline patterns. + + """ + self.stashed_nodes = {} + + stack = [tree] + + while stack: + currElement = stack.pop() + insertQueue = [] + for child in currElement.getchildren(): + if child.text and not isinstance(child.text, markdown.AtomicString): + text = child.text + child.text = None + lst = self.__processPlaceholders(self.__handleInline( + text), child) + stack += lst + insertQueue.append((child, lst)) + + if child.getchildren(): + stack.append(child) + + for element, lst in insertQueue: + if element.text: + element.text = \ + markdown.inlinepatterns.handleAttributes(element.text, + element) + i = 0 + for newChild in lst: + # Processing attributes + if newChild.tail: + newChild.tail = \ + markdown.inlinepatterns.handleAttributes(newChild.tail, + element) + if newChild.text: + newChild.text = \ + markdown.inlinepatterns.handleAttributes(newChild.text, + newChild) + element.insert(i, newChild) + i += 1 + return tree + + +class PrettifyTreeprocessor(Treeprocessor): + """ Add linebreaks to the html document. """ + + def _prettifyETree(self, elem): + """ Recursively add linebreaks to ElementTree children. """ + + i = "\n" + if markdown.isBlockLevel(elem.tag) and elem.tag not in ['code', 'pre']: + if (not elem.text or not elem.text.strip()) \ + and len(elem) and markdown.isBlockLevel(elem[0].tag): + elem.text = i + for e in elem: + if markdown.isBlockLevel(e.tag): + self._prettifyETree(e) + if not elem.tail or not elem.tail.strip(): + elem.tail = i + if not elem.tail or not elem.tail.strip(): + elem.tail = i + + def run(self, root): + """ Add linebreaks to ElementTree root object. """ + + self._prettifyETree(root) + # Do <br />'s seperately as they are often in the middle of + # inline content and missed by _prettifyETree. + brs = root.getiterator('br') + for br in brs: + if not br.tail or not br.tail.strip(): + br.tail = '\n' + else: + br.tail = '\n%s' % br.tail diff --git a/regression-tests.py b/regression-tests.py new file mode 100755 index 0000000..7601061 --- /dev/null +++ b/regression-tests.py @@ -0,0 +1,234 @@ +#!/usr/bin/python +""" +Python-Markdown Regression Tests +================================ + +Tests of the various APIs with the python markdown lib. + +""" + +import unittest +from doctest import DocTestSuite +import os +import markdown + +class TestMarkdown(unittest.TestCase): + """ Tests basics of the Markdown class. """ + + def setUp(self): + """ Create instance of Markdown. """ + self.md = markdown.Markdown() + + def testBlankInput(self): + """ Test blank input. """ + self.assertEqual(self.md.convert(''), '') + + def testWhitespaceOnly(self): + """ Test input of only whitespace. """ + self.assertEqual(self.md.convert(' '), '') + + def testSimpleInput(self): + """ Test simple input. """ + self.assertEqual(self.md.convert('foo'), '<p>foo</p>') + +class TestBlockParser(unittest.TestCase): + """ Tests of the BlockParser class. """ + + def setUp(self): + """ Create instance of BlockParser. """ + self.parser = markdown.Markdown().parser + + def testParseChunk(self): + """ Test BlockParser.parseChunk. """ + root = markdown.etree.Element("div") + text = 'foo' + self.parser.parseChunk(root, text) + self.assertEqual(markdown.etree.tostring(root), "<div><p>foo</p></div>") + + def testParseDocument(self): + """ Test BlockParser.parseDocument. """ + lines = ['#foo', '', 'bar', '', ' baz'] + tree = self.parser.parseDocument(lines) + self.assert_(isinstance(tree, markdown.etree.ElementTree)) + self.assert_(markdown.etree.iselement(tree.getroot())) + self.assertEqual(markdown.etree.tostring(tree.getroot()), + "<div><h1>foo</h1><p>bar</p><pre><code>baz\n</code></pre></div>") + + +class TestBlockParserState(unittest.TestCase): + """ Tests of the State class for BlockParser. """ + + def setUp(self): + self.state = markdown.blockparser.State() + + def testBlankState(self): + """ Test State when empty. """ + self.assertEqual(self.state, []) + + def testSetSate(self): + """ Test State.set(). """ + self.state.set('a_state') + self.assertEqual(self.state, ['a_state']) + self.state.set('state2') + self.assertEqual(self.state, ['a_state', 'state2']) + + def testIsSate(self): + """ Test State.isstate(). """ + self.assertEqual(self.state.isstate('anything'), False) + self.state.set('a_state') + self.assertEqual(self.state.isstate('a_state'), True) + self.state.set('state2') + self.assertEqual(self.state.isstate('state2'), True) + self.assertEqual(self.state.isstate('a_state'), False) + self.assertEqual(self.state.isstate('missing'), False) + + def testReset(self): + """ Test State.reset(). """ + self.state.set('a_state') + self.state.reset() + self.assertEqual(self.state, []) + self.state.set('state1') + self.state.set('state2') + self.state.reset() + self.assertEqual(self.state, ['state1']) + +class TestHtmlStash(unittest.TestCase): + """ Test Markdown's HtmlStash. """ + + def setUp(self): + self.stash = markdown.preprocessors.HtmlStash() + self.placeholder = self.stash.store('foo') + + def testSimpleStore(self): + """ Test HtmlStash.store. """ + self.assertEqual(self.placeholder, + markdown.preprocessors.HTML_PLACEHOLDER % 0) + self.assertEqual(self.stash.html_counter, 1) + self.assertEqual(self.stash.rawHtmlBlocks, [('foo', False)]) + + def testStoreMore(self): + """ Test HtmlStash.store with additional blocks. """ + placeholder = self.stash.store('bar') + self.assertEqual(placeholder, + markdown.preprocessors.HTML_PLACEHOLDER % 1) + self.assertEqual(self.stash.html_counter, 2) + self.assertEqual(self.stash.rawHtmlBlocks, + [('foo', False), ('bar', False)]) + + def testSafeStore(self): + """ Test HtmlStash.store with 'safe' html. """ + self.stash.store('bar', True) + self.assertEqual(self.stash.rawHtmlBlocks, + [('foo', False), ('bar', True)]) + + def testReset(self): + """ Test HtmlStash.reset. """ + self.stash.reset() + self.assertEqual(self.stash.html_counter, 0) + self.assertEqual(self.stash.rawHtmlBlocks, []) + +class TestOrderedDict(unittest.TestCase): + """ Test OrderedDict storage class. """ + + def setUp(self): + self.odict = markdown.odict.OrderedDict() + self.odict['first'] = 'This' + self.odict['third'] = 'a' + self.odict['fourth'] = 'self' + self.odict['fifth'] = 'test' + + def testValues(self): + """ Test output of OrderedDict.values(). """ + self.assertEqual(self.odict.values(), ['This', 'a', 'self', 'test']) + + def testKeys(self): + """ Test output of OrderedDict.keys(). """ + self.assertEqual(self.odict.keys(), + ['first', 'third', 'fourth', 'fifth']) + + def testItems(self): + """ Test output of OrderedDict.items(). """ + self.assertEqual(self.odict.items(), + [('first', 'This'), ('third', 'a'), + ('fourth', 'self'), ('fifth', 'test')]) + + def testAddBefore(self): + """ Test adding an OrderedDict item before a given key. """ + self.odict.add('second', 'is', '<third') + self.assertEqual(self.odict.items(), + [('first', 'This'), ('second', 'is'), ('third', 'a'), + ('fourth', 'self'), ('fifth', 'test')]) + + def testAddAfter(self): + """ Test adding an OrderDict item after a given key. """ + self.odict.add('second', 'is', '>first') + self.assertEqual(self.odict.items(), + [('first', 'This'), ('second', 'is'), ('third', 'a'), + ('fourth', 'self'), ('fifth', 'test')]) + + def testAddAfterEnd(self): + """ Test adding an OrderedDict item after the last key. """ + self.odict.add('sixth', '.', '>fifth') + self.assertEqual(self.odict.items(), + [('first', 'This'), ('third', 'a'), + ('fourth', 'self'), ('fifth', 'test'), ('sixth', '.')]) + + def testAdd_begin(self): + """ Test adding an OrderedDict item using "_begin". """ + self.odict.add('zero', 'CRAZY', '_begin') + self.assertEqual(self.odict.items(), + [('zero', 'CRAZY'), ('first', 'This'), ('third', 'a'), + ('fourth', 'self'), ('fifth', 'test')]) + + def testAdd_end(self): + """ Test adding an OrderedDict item using "_end". """ + self.odict.add('sixth', '.', '_end') + self.assertEqual(self.odict.items(), + [('first', 'This'), ('third', 'a'), + ('fourth', 'self'), ('fifth', 'test'), ('sixth', '.')]) + + def testAddBadLocation(self): + """ Test Error on bad location in OrderedDict.add(). """ + self.assertRaises(ValueError, self.odict.add, 'sixth', '.', '<seventh') + self.assertRaises(ValueError, self.odict.add, 'second', 'is', 'third') + + def testDeleteItem(self): + """ Test deletion of an OrderedDict item. """ + del self.odict['fourth'] + self.assertEqual(self.odict.items(), + [('first', 'This'), ('third', 'a'), ('fifth', 'test')]) + + def testChangeValue(self): + """ Test OrderedDict change value. """ + self.odict['fourth'] = 'CRAZY' + self.assertEqual(self.odict.items(), + [('first', 'This'), ('third', 'a'), + ('fourth', 'CRAZY'), ('fifth', 'test')]) + + def testChangeOrder(self): + """ Test OrderedDict change order. """ + self.odict.link('fourth', '<third') + self.assertEqual(self.odict.items(), + [('first', 'This'), ('fourth', 'self'), + ('third', 'a'), ('fifth', 'test')]) + +def suite(): + """ Build a test suite of the above tests and extension doctests. """ + suite = unittest.TestSuite() + suite.addTest(unittest.makeSuite(TestMarkdown)) + suite.addTest(unittest.makeSuite(TestBlockParser)) + suite.addTest(unittest.makeSuite(TestBlockParserState)) + suite.addTest(unittest.makeSuite(TestHtmlStash)) + suite.addTest(unittest.makeSuite(TestOrderedDict)) + + for filename in os.listdir('markdown/extensions'): + if filename.endswith('.py'): + module = 'markdown.extensions.%s' % filename[:-3] + try: + suite.addTest(DocTestSuite(module)) + except: ValueError + # No tests + return suite + +if __name__ == '__main__': + unittest.TextTestRunner(verbosity=2).run(suite()) diff --git a/setup.py b/setup.py new file mode 100755 index 0000000..42939d3 --- /dev/null +++ b/setup.py @@ -0,0 +1,65 @@ +#!/usr/bin/env python + +import sys, os +from distutils.core import setup +from distutils.command.install_scripts import install_scripts + +version = '2.0.3' + +class md_install_scripts(install_scripts): + """ Customized install_scripts. Create markdown.bat for win32. """ + def run(self): + install_scripts.run(self) + + if sys.platform == 'win32': + try: + script_dir = os.path.join(sys.prefix, 'Scripts') + script_path = os.path.join(script_dir, 'markdown') + bat_str = '@"%s" "%s" %%*' % (sys.executable, script_path) + bat_path = os.path.join(self.install_dir, 'markdown.bat') + f = file(bat_path, 'w') + f.write(bat_str) + f.close() + print 'Created:', bat_path + except Exception, e: + print 'ERROR: Unable to create %s: %s' % (bat_path, e) + +data = dict( + name = 'Markdown', + version = version, + url = 'http://www.freewisdom.org/projects/python-markdown', + download_url = 'http://pypi.python.org/packages/source/M/Markdown/Markdown-%s.tar.gz' % version, + description = 'Python implementation of Markdown.', + author = 'Manfred Stienstra and Yuri takhteyev', + author_email = 'yuri [at] freewisdom.org', + maintainer = 'Waylan Limberg', + maintainer_email = 'waylan [at] gmail.com', + license = 'BSD License', + packages = ['markdown', 'markdown.extensions'], + scripts = ['bin/markdown'], + cmdclass = {'install_scripts': md_install_scripts}, + classifiers = ['Development Status :: 5 - Production/Stable', + 'License :: OSI Approved :: BSD License', + 'Operating System :: OS Independent', + 'Programming Language :: Python', + 'Programming Language :: Python :: 2', + 'Programming Language :: Python :: 2.3', + 'Programming Language :: Python :: 2.4', + 'Programming Language :: Python :: 2.5', + 'Programming Language :: Python :: 2.6', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.0', + 'Topic :: Communications :: Email :: Filters', + 'Topic :: Internet :: WWW/HTTP :: Dynamic Content :: CGI Tools/Libraries', + 'Topic :: Internet :: WWW/HTTP :: Site Management', + 'Topic :: Software Development :: Documentation', + 'Topic :: Software Development :: Libraries :: Python Modules', + 'Topic :: Text Processing :: Filters', + 'Topic :: Text Processing :: Markup :: HTML', + ], + ) + +if sys.version[:3] < '2.5': + data['install_requires'] = ['elementtree'] + +setup(**data) diff --git a/test-markdown.py b/test-markdown.py new file mode 100755 index 0000000..e5dd870 --- /dev/null +++ b/test-markdown.py @@ -0,0 +1,347 @@ +#!/usr/bin/env python + +import os, difflib, time, gc, codecs, platform, sys +from pprint import pprint +import textwrap + +# Setup a logger manually for compatibility with Python 2.3 +import logging +logging.getLogger('MARKDOWN').addHandler(logging.StreamHandler()) +import markdown + +TEST_DIR = "tests" +TMP_DIR = "./tmp/" +WRITE_BENCHMARK = True +WRITE_BENCHMARK = False +ACTUALLY_MEASURE_MEMORY = True + +###################################################################### + +if platform.system().lower() == "darwin": # Darwin + _proc_status = '/proc/%d/stat' % os.getpid() +else: # Linux + _proc_status = '/proc/%d/status' % os.getpid() + +_scale = {'kB': 1024.0, 'mB': 1024.0*1024.0, + 'KB': 1024.0, 'MB': 1024.0*1024.0} + +def _VmB(VmKey): + '''Private. + ''' + global _proc_status, _scale + # get pseudo file /proc/<pid>/status + try: + t = open(_proc_status) + v = t.read() + t.close() + except: + return 0.0 # non-Linux? + # get VmKey line e.g. 'VmRSS: 9999 kB\n ...' + i = v.index(VmKey) + v = v[i:].split(None, 3) # whitespace + if len(v) < 3: + return 0.0 # invalid format? + # convert Vm value to bytes + return float(v[1]) * _scale[v[2]] + + +def memory(since=0.0): + '''Return memory usage in bytes. + ''' + if ACTUALLY_MEASURE_MEMORY : + return _VmB('VmSize:') - since + + +def resident(since=0.0): + '''Return resident memory usage in bytes. + ''' + return _VmB('VmRSS:') - since + + +def stacksize(since=0.0): + '''Return stack size in bytes. + ''' + return _VmB('VmStk:') - since + + +############################################################ + +DIFF_FILE_TEMPLATE = """ +<html> + <head> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> + <style> + td { + padding-left: 10px; + padding-right: 10px; + } + colgroup { + margin: 10px; + } + .diff_header { + color: gray; + } + .ok { + color: green; + } + .gray { + color: gray; + } + .failed a { + color: red; + } + .failed { + color: red; + } + </style> +</head> +<body> +<h1>Results Summary</h1> +<table rules="groups" > + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <th> + <td></td> + <td>Seconds</td> + <td></td> + <td>Memory</td> + </th> + <tbody> + """ + +FOOTER = """ +</body> +</html> +""" + +DIFF_TABLE_TEMPLATE = """ + <table class="diff" rules="groups" > + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <colgroup></colgroup> + <th> + <td></td> + <td>Expected</td> + <td></td> + <td></td> + <td>Actual</td> + </th> + <tbody> + %s + </tbody> + </table> +""" + + +def smart_split(text) : + result = [] + for x in text.splitlines() : + for y in textwrap.wrap(textwrap.dedent(x), 40): + result.append(y) + return result + + +differ = difflib.Differ() +try : + htmldiff = difflib.HtmlDiff() +except: + htmldiff = None + +class TestRunner : + + def __init__ (self) : + self.failedTests = [] + if not os.path.exists(TMP_DIR): + os.mkdir(TMP_DIR) + + def test_directory(self, dir, measure_time=False, safe_mode=False, encoding="utf-8", output_format='xhtml1') : + self.encoding = encoding + benchmark_file_name = os.path.join(dir, "benchmark.dat") + self.saved_benchmarks = {} + + if measure_time : + if os.path.exists(benchmark_file_name) : + file = open(benchmark_file_name) + for line in file.readlines() : + test, str_time, str_mem = line.strip().split(":") + self.saved_benchmarks[test] = (float(str_time), float(str_mem)) + repeat = range(10) + else : + repeat = (0,) + + # First, determine from the name of the directory if any extensions + # need to be loaded. + + parts = os.path.split(dir)[-1].split("-x-") + if len(parts) > 1 : + extensions = parts[1].split("-") + print extensions + else : + extensions = [] + + mem = memory() + start = time.clock() + self.md = markdown.Markdown(extensions=extensions, safe_mode = safe_mode, output_format=output_format) + construction_time = time.clock() - start + construction_mem = memory(mem) + + self.benchmark_buffer = "construction:%f:%f\n" % (construction_time, + construction_mem) + + html_diff_file_path = os.path.join(TMP_DIR, os.path.split(dir)[-1]) + ".html" + self.html_diff_file = codecs.open(html_diff_file_path, "w", encoding=encoding) + self.html_diff_file.write(DIFF_FILE_TEMPLATE) + + self.diffs_buffer = "" + + tests = [x.replace(".txt", "") + for x in os.listdir(dir) if x.endswith(".txt")] + tests.sort() + for test in tests : + self.run_test(dir, test, repeat) + + self.html_diff_file.write("</table>") + + if sys.version < "3.0": + self.html_diff_file.write(self.diffs_buffer.decode("utf-8")) + + self.html_diff_file.write(FOOTER) + self.html_diff_file.close() + print "Diff written to %s" % html_diff_file_path + + benchmark_output_file_name = benchmark_file_name + + if not WRITE_BENCHMARK: + benchmark_output_file_name += ".tmp" + + self.benchmark_file = open(benchmark_output_file_name, "w") + self.benchmark_file.write(self.benchmark_buffer) + self.benchmark_file.close() + + +#################### + + + def run_test(self, dir, test, repeat): + + print "--- %s ---" % test + self.html_diff_file.write("<tr><td>%s</td>" % test) + input_file = os.path.join(dir, test + ".txt") + output_file = os.path.join(dir, test + ".html") + + expected_output = codecs.open(output_file, encoding=self.encoding).read() + input = codecs.open(input_file, encoding=self.encoding).read() + actual_output = "" + actual_lines = [] + self.md.source = "" + gc.collect() + mem = memory() + start = time.clock() + for x in repeat: + actual_output = self.md.convert(input) + conversion_time = time.clock() - start + conversion_mem = memory(mem) + self.md.reset() + + expected_lines = [x.encode("utf-8") for x in smart_split(expected_output)] + actual_lines = [x.encode("utf-8") for x in smart_split(actual_output)] + + #diff = difflib.ndiff(expected_output.split("\n"), + # actual_output.split("\n")) + + diff = [x for x in differ.compare(expected_lines, + actual_lines) + if not x.startswith(" ")] + + if not diff: + self.html_diff_file.write("<td class='ok'>OK</td>") + else : + self.failedTests.append(test) + self.html_diff_file.write("<td class='failed'>" + + "<a href='#diff-%s'>FAILED</a></td>" % test) + print "MISMATCH on %s/%s.txt" % (dir, test) + print + for line in diff : + print line + if htmldiff!=None : + htmlDiff = htmldiff.make_table(expected_lines, actual_lines, + context=True) + htmlDiff = "\n".join( [x for x in htmlDiff.splitlines() + if x.strip().startswith("<tr>")] ) + self.diffs_buffer += "<a name='diff-%s'/><h2>%s</h2>" % (test, test) + self.diffs_buffer += DIFF_TABLE_TEMPLATE % htmlDiff + + expected_time, expected_mem = self.saved_benchmarks.get(test, ("na", "na")) + + self.html_diff_file.write(get_benchmark_html(conversion_time, expected_time)) + self.html_diff_file.write(get_benchmark_html(conversion_mem, expected_mem)) + self.html_diff_file.write("</tr>\n") + + self.benchmark_buffer += "%s:%f:%f\n" % (test, + conversion_time, conversion_mem) + + + + + +def get_benchmark_html (actual, expected) : + buffer = "" + if not expected == "na": + if actual > expected * 1.5: + tdiff = "failed" + elif actual * 1.5 < expected : + tdiff = "ok" + else : + tdiff = "same" + if ( (actual <= 0 and expected < 0.015) or + (expected <= 0 and actual < 0.015)) : + tdiff = "same" + else : + tdiff = "same" + buffer += "<td class='%s'>%.2f</td>" % (tdiff, actual) + if not expected == "na": + buffer += "<td class='gray'>%.2f</td>" % (expected) + return buffer + + +def run_tests() : + + tester = TestRunner() + #test.test_directory("tests/basic") + tester.test_directory("tests/markdown-test", measure_time=True) + tester.test_directory("tests/misc", measure_time=True) + tester.test_directory("tests/extensions-x-tables") + tester.test_directory("tests/extensions-x-footnotes") + #tester.test_directory("tests/extensions-x-ext1-ext2") + tester.test_directory("tests/safe_mode", measure_time=True, safe_mode="escape") + tester.test_directory("tests/extensions-x-wikilinks") + tester.test_directory("tests/extensions-x-toc") + tester.test_directory("tests/extensions-x-def_list") + tester.test_directory("tests/extensions-x-abbr") + tester.test_directory("tests/html4", output_format='html4') + + try: + import pygments + except ImportError: + # Dependancy not avalable - skip test + pass + else: + tester.test_directory("tests/extensions-x-codehilite") + + print "\n### Final result ###" + if len(tester.failedTests): + print "%d failed tests: %s" % (len(tester.failedTests), str(tester.failedTests)) + else: + print "All tests passed, no errors!" + +run_tests() + + + + diff --git a/tests/extensions-x-abbr/abbr.html b/tests/extensions-x-abbr/abbr.html new file mode 100644 index 0000000..456524e --- /dev/null +++ b/tests/extensions-x-abbr/abbr.html @@ -0,0 +1,4 @@ +<p>An <abbr title="Abbreviation">ABBR</abbr>: "<abbr title="Reference">REF</abbr>". +ref and REFERENCE should be ignored.</p> +<p>The <abbr title="Hyper Text Markup Language">HTML</abbr> specification +is maintained by the <abbr title="World Wide Web Consortium">W3C</abbr>.</p>
\ No newline at end of file diff --git a/tests/extensions-x-abbr/abbr.txt b/tests/extensions-x-abbr/abbr.txt new file mode 100644 index 0000000..991bf15 --- /dev/null +++ b/tests/extensions-x-abbr/abbr.txt @@ -0,0 +1,13 @@ +An ABBR: "REF". +ref and REFERENCE should be ignored. + +*[REF]: Reference +*[ABBR]: This gets overriden by the next one. +*[ABBR]: Abbreviation + +The HTML specification +is maintained by the W3C. + +*[HTML]: Hyper Text Markup Language +*[W3C]: World Wide Web Consortium + diff --git a/tests/extensions-x-codehilite/code.html b/tests/extensions-x-codehilite/code.html new file mode 100644 index 0000000..6a8ee91 --- /dev/null +++ b/tests/extensions-x-codehilite/code.html @@ -0,0 +1,16 @@ +<p>Some text</p> +<table class="codehilitetable"><tr><td class="linenos"><pre>1 +2 +3 +4 +5 +6</pre></td><td class="code"><div class="codehilite"><pre><span class="k">def</span> <span class="nf">__init__</span> <span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pattern</span><span class="p">)</span> <span class="p">:</span> + <span class="bp">self</span><span class="o">.</span><span class="n">pattern</span> <span class="o">=</span> <span class="n">pattern</span> + <span class="bp">self</span><span class="o">.</span><span class="n">compiled_re</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="s">"^(.*)</span><span class="si">%s</span><span class="s">(.*)$"</span> <span class="o">%</span> <span class="n">pattern</span><span class="p">,</span> <span class="n">re</span><span class="o">.</span><span class="n">DOTALL</span><span class="p">)</span> + +<span class="k">def</span> <span class="nf">getCompiledRegExp</span> <span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="p">:</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">compiled_re</span> +</pre></div> +</td></tr></table> + +<p>More text</p>
\ No newline at end of file diff --git a/tests/extensions-x-codehilite/code.txt b/tests/extensions-x-codehilite/code.txt new file mode 100644 index 0000000..6c62e6a --- /dev/null +++ b/tests/extensions-x-codehilite/code.txt @@ -0,0 +1,12 @@ + +Some text + + #!python + def __init__ (self, pattern) : + self.pattern = pattern + self.compiled_re = re.compile("^(.*)%s(.*)$" % pattern, re.DOTALL) + + def getCompiledRegExp (self) : + return self.compiled_re + +More text
\ No newline at end of file diff --git a/tests/extensions-x-def_list/loose_def_list.html b/tests/extensions-x-def_list/loose_def_list.html new file mode 100644 index 0000000..98fdec8 --- /dev/null +++ b/tests/extensions-x-def_list/loose_def_list.html @@ -0,0 +1,21 @@ +<p>some text</p> +<dl> +<dt>term 1</dt> +<dd> +<p>def 1-1</p> +</dd> +<dd> +<p>def 2-2</p> +</dd> +<dt>term 2</dt> +<dt>term 3</dt> +<dd> +<p>def 2-1 +line 2 of def 2-1</p> +</dd> +<dd> +<p>def 2-2</p> +<p>par 2 of def2-2</p> +</dd> +</dl> +<p>more text</p>
\ No newline at end of file diff --git a/tests/extensions-x-def_list/loose_def_list.txt b/tests/extensions-x-def_list/loose_def_list.txt new file mode 100644 index 0000000..24cd6a4 --- /dev/null +++ b/tests/extensions-x-def_list/loose_def_list.txt @@ -0,0 +1,20 @@ +some text + +term 1 + +: def 1-1 + +: def 2-2 + +term 2 +term 3 + +: def 2-1 + line 2 of def 2-1 + +: def 2-2 + + par 2 of def2-2 + +more text + diff --git a/tests/extensions-x-def_list/markdown-syntax.html b/tests/extensions-x-def_list/markdown-syntax.html new file mode 100644 index 0000000..2f63b4b --- /dev/null +++ b/tests/extensions-x-def_list/markdown-syntax.html @@ -0,0 +1,728 @@ +<h1>Markdown: Syntax</h1> +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<ul> +<li><a href="#overview">Overview</a><ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#html">Inline HTML</a></li> +<li><a href="#autoescape">Automatic Escaping for Special Characters</a></li> +</ul> +</li> +<li><a href="#block">Block Elements</a><ul> +<li><a href="#p">Paragraphs and Line Breaks</a></li> +<li><a href="#header">Headers</a></li> +<li><a href="#blockquote">Blockquotes</a></li> +<li><a href="#list">Lists</a></li> +<li><a href="#precode">Code Blocks</a></li> +<li><a href="#hr">Horizontal Rules</a></li> +</ul> +</li> +<li><a href="#span">Span Elements</a><ul> +<li><a href="#link">Links</a></li> +<li><a href="#em">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#img">Images</a></li> +</ul> +</li> +<li><a href="#misc">Miscellaneous</a><ul> +<li><a href="#backslash">Backslash Escapes</a></li> +<li><a href="#autolink">Automatic Links</a></li> +</ul> +</li> +</ul> +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/syntax.text">see the source for it by adding '.text' to the URL</a>.</p> +<hr /> +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +<p>Markdown is intended to be as easy-to-read and easy-to-write as is feasible.</p> +<p>Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, <a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href="http://textism.com/tools/textile/">Textile</a>, <a href="http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href="http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and <a href="http://ettext.taint.org/doc/">EtText</a> -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email.</p> +<p>To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like *emphasis*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email.</p> +<h3 id="html">Inline HTML</h3> + +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a <em>publishing</em> format; Markdown is a <em>writing</em> +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text.</p> +<p>For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags.</p> +<p>The only restrictions are that block-level HTML elements -- e.g. <code><div></code>, +<code><table></code>, <code><pre></code>, <code><p></code>, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) <code><p></code> tags around HTML block-level tags.</p> +<p>For example, to add an HTML table to a Markdown article:</p> +<pre><code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code></pre> +<p>Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style <code>*emphasis*</code> inside an +HTML block.</p> +<p>Span-level HTML tags -- e.g. <code><span></code>, <code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML <code><a></code> or <code><img></code> tags instead of Markdown's +link or image syntax, go right ahead.</p> +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> processed within +span-level tags.</p> +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +<p>In HTML, there are two characters that demand special treatment: <code><</code> +and <code>&</code>. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> +<p>Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '<code>AT&amp;T</code>'. You even need to +escape ampersands within URLs. Thus, if you want to link to:</p> +<pre><code>http://images.google.com/images?num=30&q=larry+bird +</code></pre> +<p>you need to encode the URL as:</p> +<pre><code>http://images.google.com/images?num=30&amp;q=larry+bird +</code></pre> +<p>in your anchor tag <code>href</code> attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites.</p> +<p>Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into <code>&amp;</code>.</p> +<p>So, if you want to include a copyright symbol in your article, you can write:</p> +<pre><code>&copy; +</code></pre> +<p>and Markdown will leave it alone. But if you write:</p> +<pre><code>AT&T +</code></pre> +<p>Markdown will translate it to:</p> +<pre><code>AT&amp;T +</code></pre> +<p>Similarly, because Markdown supports <a href="#html">inline HTML</a>, if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write:</p> +<pre><code>4 < 5 +</code></pre> +<p>Markdown will translate it to:</p> +<pre><code>4 &lt; 5 +</code></pre> +<p>However, inside Markdown code spans and blocks, angle brackets and +ampersands are <em>always</em> encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single <code><</code> +and <code>&</code> in your example code needs to be escaped.)</p> +<hr /> +<h2 id="block">Block Elements</h2> + +<h3 id="p">Paragraphs and Line Breaks</h3> + +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> +<p>The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a <code><br /></code> tag.</p> +<p>When you <em>do</em> want to insert a <code><br /></code> break tag using Markdown, you +end a line with two or more spaces, then type return.</p> +<p>Yes, this takes a tad more effort to create a <code><br /></code>, but a simplistic +"every line break is a <code><br /></code>" rule wouldn't work for Markdown. +Markdown's email-style <a href="#blockquote">blockquoting</a> and multi-paragraph <a href="#list">list items</a> +work best -- and look better -- when you format them with hard breaks.</p> +<h3 id="header">Headers</h3> + +<p>Markdown supports two styles of headers, <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and <a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> +<p>Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example:</p> +<pre><code>This is an H1 +============= + +This is an H2 +------------- +</code></pre> +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s will work.</p> +<p>Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example:</p> +<pre><code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code></pre> +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) :</p> +<pre><code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code></pre> +<h3 id="blockquote">Blockquotes</h3> + +<p>Markdown uses email-style <code>></code> characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a <code>></code> before every line:</p> +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>Markdown allows you to be lazy and only put the <code>></code> before the first +line of a hard-wrapped paragraph:</p> +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> +<pre><code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code></pre> +<p>Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks:</p> +<pre><code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code></pre> +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> +<h3 id="list">Lists</h3> + +<p>Markdown supports ordered (numbered) and unordered (bulleted) lists.</p> +<p>Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers:</p> +<pre><code>* Red +* Green +* Blue +</code></pre> +<p>is equivalent to:</p> +<pre><code>+ Red ++ Green ++ Blue +</code></pre> +<p>and:</p> +<pre><code>- Red +- Green +- Blue +</code></pre> +<p>Ordered lists use numbers followed by periods:</p> +<pre><code>1. Bird +2. McHale +3. Parish +</code></pre> +<p>It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is:</p> +<pre><code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code></pre> +<p>If you instead wrote the list in Markdown like this:</p> +<pre><code>1. Bird +1. McHale +1. Parish +</code></pre> +<p>or even:</p> +<pre><code>3. Bird +1. McHale +8. Parish +</code></pre> +<p>you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to.</p> +<p>If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number.</p> +<p>List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab.</p> +<p>To make lists look nice, you can wrap items with hanging indents:</p> +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>But if you want to be lazy, you don't have to:</p> +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>If list items are separated by blank lines, Markdown will wrap the +items in <code><p></code> tags in the HTML output. For example, this input:</p> +<pre><code>* Bird +* Magic +</code></pre> +<p>will turn into:</p> +<pre><code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code></pre> +<p>But this:</p> +<pre><code>* Bird + +* Magic +</code></pre> +<p>will turn into:</p> +<pre><code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code></pre> +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab:</p> +<pre><code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy:</p> +<pre><code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code></pre> +<p>To put a blockquote within a list item, the blockquote's <code>></code> +delimiters need to be indented:</p> +<pre><code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code></pre> +<p>To put a code block within a list item, the code block needs +to be indented <em>twice</em> -- 8 spaces or two tabs:</p> +<pre><code>* A list item with a code block: + + <code goes here> +</code></pre> +<p>It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this:</p> +<pre><code>1986. What a great season. +</code></pre> +<p>In other words, a <em>number-period-space</em> sequence at the beginning of a +line. To avoid this, you can backslash-escape the period:</p> +<pre><code>1986\. What a great season. +</code></pre> +<h3 id="precode">Code Blocks</h3> + +<p>Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both <code><pre></code> and <code><code></code> tags.</p> +<p>To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input:</p> +<pre><code>This is a normal paragraph: + + This is a code block. +</code></pre> +<p>Markdown will generate:</p> +<pre><code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code></pre> +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this:</p> +<pre><code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code></pre> +<p>will turn into:</p> +<pre><code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code></pre> +<p>A code block continues until it reaches a line that is not indented +(or the end of the article).</p> +<p>Within a code block, ampersands (<code>&</code>) and angle brackets (<code><</code> and <code>></code>) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> +<pre><code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code></pre> +<p>will turn into:</p> +<pre><code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code></pre> +<p>Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax.</p> +<h3 id="hr">Horizontal Rules</h3> + +<p>You can produce a horizontal rule tag (<code><hr /></code>) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule:</p> +<pre><code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code></pre> +<hr /> +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +<p>Markdown supports two style of links: <em>inline</em> and <em>reference</em>.</p> +<p>In both styles, the link text is delimited by [square brackets].</p> +<p>To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an <em>optional</em> +title for the link, surrounded in quotes. For example:</p> +<pre><code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code></pre> +<p>Will produce:</p> +<pre><code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code></pre> +<p>If you're referring to a local resource on the same server, you can +use relative paths:</p> +<pre><code>See my [About](/about/) page for details. +</code></pre> +<p>Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link:</p> +<pre><code>This is [an example][id] reference-style link. +</code></pre> +<p>You can optionally use a space to separate the sets of brackets:</p> +<pre><code>This is [an example] [id] reference-style link. +</code></pre> +<p>Then, anywhere in the document, you define your link label like this, +on a line by itself:</p> +<pre><code>[id]: http://example.com/ "Optional Title Here" +</code></pre> +<p>That is:</p> +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> +<p>The link URL may, optionally, be surrounded by angle brackets:</p> +<pre><code>[id]: <http://example.com/> "Optional Title Here" +</code></pre> +<p>You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs:</p> +<pre><code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code></pre> +<p>Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output.</p> +<p>Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are <em>not</em> case sensitive. E.g. these two links:</p> +<pre><code>[link text][a] +[link text][A] +</code></pre> +<p>are equivalent.</p> +<p>The <em>implicit link name</em> shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write:</p> +<pre><code>[Google][] +</code></pre> +<p>And then define the link:</p> +<pre><code>[Google]: http://google.com/ +</code></pre> +<p>Because link names may contain spaces, this shortcut even works for +multiple words in the link text:</p> +<pre><code>Visit [Daring Fireball][] for more information. +</code></pre> +<p>And then define the link:</p> +<pre><code>[Daring Fireball]: http://daringfireball.net/ +</code></pre> +<p>Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes.</p> +<p>Here's an example of reference links in action:</p> +<pre><code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Using the implicit link name shortcut, you could instead write:</p> +<pre><code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Both of the above examples will produce the following HTML output:</p> +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code></pre> +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> +<pre><code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code></pre> +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text.</p> +<p>With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose.</p> +<h3 id="em">Emphasis</h3> + +<p>Markdown treats asterisks (<code>*</code>) and underscores (<code>_</code>) as indicators of +emphasis. Text wrapped with one <code>*</code> or <code>_</code> will be wrapped with an +HTML <code><em></code> tag; double <code>*</code>'s or <code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> +<pre><code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code></pre> +<p>will produce:</p> +<pre><code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code></pre> +<p>You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span.</p> +<p>Emphasis can be used in the middle of a word:</p> +<pre><code>un*fucking*believable +</code></pre> +<p>But if you surround an <code>*</code> or <code>_</code> with spaces, it'll be treated as a +literal asterisk or underscore.</p> +<p>To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it:</p> +<pre><code>\*this text is surrounded by literal asterisks\* +</code></pre> +<h3 id="code">Code</h3> + +<p>To indicate a span of code, wrap it with backtick quotes (<code>`</code>). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example:</p> +<pre><code>Use the `printf()` function. +</code></pre> +<p>will produce:</p> +<pre><code><p>Use the <code>printf()</code> function.</p> +</code></pre> +<p>To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters:</p> +<pre><code>``There is a literal backtick (`) here.`` +</code></pre> +<p>which will produce this:</p> +<pre><code><p><code>There is a literal backtick (`) here.</code></p> +</code></pre> +<p>The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span:</p> +<pre><code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code></pre> +<p>will produce:</p> +<pre><code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code></pre> +<p>With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this:</p> +<pre><code>Please don't use any `<blink>` tags. +</code></pre> +<p>into:</p> +<pre><code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code></pre> +<p>You can write this:</p> +<pre><code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code></pre> +<p>to produce:</p> +<pre><code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code></pre> +<h3 id="img">Images</h3> + +<p>Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format.</p> +<p>Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: <em>inline</em> and <em>reference</em>.</p> +<p>Inline image syntax looks like this:</p> +<pre><code> + + +</code></pre> +<p>That is:</p> +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the <code>alt</code> +attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in double +or single quotes.</li> +</ul> +<p>Reference-style image syntax looks like this:</p> +<pre><code>![Alt text][id] +</code></pre> +<p>Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references:</p> +<pre><code>[id]: url/to/image "Optional title attribute" +</code></pre> +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> +<hr /> +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +<p>Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:</p> +<pre><code><http://example.com/> +</code></pre> +<p>Markdown will turn this into:</p> +<pre><code><a href="http://example.com/">http://example.com/</a> +</code></pre> +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this:</p> +<pre><code><address@example.com> +</code></pre> +<p>into something like this:</p> +<pre><code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code></pre> +<p>which will render in a browser as a clickable link to "address@example.com".</p> +<p>(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.)</p> +<h3 id="backslash">Backslash Escapes</h3> + +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML <code><em></code> tag), you can backslashes +before the asterisks, like this:</p> +<pre><code>\*literal asterisks\* +</code></pre> +<p>Markdown provides backslash escapes for the following characters:</p> +<pre><code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code></pre>
\ No newline at end of file diff --git a/tests/extensions-x-def_list/markdown-syntax.txt b/tests/extensions-x-def_list/markdown-syntax.txt new file mode 100644 index 0000000..dabd75c --- /dev/null +++ b/tests/extensions-x-def_list/markdown-syntax.txt @@ -0,0 +1,888 @@ +Markdown: Syntax +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +* [Overview](#overview) + * [Philosophy](#philosophy) + * [Inline HTML](#html) + * [Automatic Escaping for Special Characters](#autoescape) +* [Block Elements](#block) + * [Paragraphs and Line Breaks](#p) + * [Headers](#header) + * [Blockquotes](#blockquote) + * [Lists](#list) + * [Code Blocks](#precode) + * [Horizontal Rules](#hr) +* [Span Elements](#span) + * [Links](#link) + * [Emphasis](#em) + * [Code](#code) + * [Images](#img) +* [Miscellaneous](#misc) + * [Backslash Escapes](#backslash) + * [Automatic Links](#autolink) + + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL][src]. + + [src]: /projects/markdown/syntax.text + +* * * + +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +Markdown is intended to be as easy-to-read and easy-to-write as is feasible. + +Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4], +[Grutatext] [5], and [EtText] [6] -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email. + + [1]: http://docutils.sourceforge.net/mirror/setext.html + [2]: http://www.aaronsw.com/2002/atx/ + [3]: http://textism.com/tools/textile/ + [4]: http://docutils.sourceforge.net/rst.html + [5]: http://www.triptico.com/software/grutatxt.html + [6]: http://ettext.taint.org/doc/ + +To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like \*emphasis\*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email. + + + +<h3 id="html">Inline HTML</h3> + +Markdown's syntax is intended for one purpose: to be used as a +format for *writing* for the web. + +Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is *not* to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a *publishing* format; Markdown is a *writing* +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text. + +For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags. + +The only restrictions are that block-level HTML elements -- e.g. `<div>`, +`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) `<p>` tags around HTML block-level tags. + +For example, to add an HTML table to a Markdown article: + + This is a regular paragraph. + + <table> + <tr> + <td>Foo</td> + </tr> + </table> + + This is another regular paragraph. + +Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an +HTML block. + +Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's +link or image syntax, go right ahead. + +Unlike block-level HTML tags, Markdown syntax *is* processed within +span-level tags. + + +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +In HTML, there are two characters that demand special treatment: `<` +and `&`. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. `<`, and +`&`. + +Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '`AT&T`'. You even need to +escape ampersands within URLs. Thus, if you want to link to: + + http://images.google.com/images?num=30&q=larry+bird + +you need to encode the URL as: + + http://images.google.com/images?num=30&q=larry+bird + +in your anchor tag `href` attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites. + +Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into `&`. + +So, if you want to include a copyright symbol in your article, you can write: + + © + +and Markdown will leave it alone. But if you write: + + AT&T + +Markdown will translate it to: + + AT&T + +Similarly, because Markdown supports [inline HTML](#html), if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write: + + 4 < 5 + +Markdown will translate it to: + + 4 < 5 + +However, inside Markdown code spans and blocks, angle brackets and +ampersands are *always* encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single `<` +and `&` in your example code needs to be escaped.) + + +* * * + + +<h2 id="block">Block Elements</h2> + + +<h3 id="p">Paragraphs and Line Breaks</h3> + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a `<br />` tag. + +When you *do* want to insert a `<br />` break tag using Markdown, you +end a line with two or more spaces, then type return. + +Yes, this takes a tad more effort to create a `<br />`, but a simplistic +"every line break is a `<br />`" rule wouldn't work for Markdown. +Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l] +work best -- and look better -- when you format them with hard breaks. + + [bq]: #blockquote + [l]: #list + + + +<h3 id="header">Headers</h3> + +Markdown supports two styles of headers, [Setext] [1] and [atx] [2]. + +Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example: + + This is an H1 + ============= + + This is an H2 + ------------- + +Any number of underlining `=`'s or `-`'s will work. + +Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example: + + # This is an H1 + + ## This is an H2 + + ###### This is an H6 + +Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) : + + # This is an H1 # + + ## This is an H2 ## + + ### This is an H3 ###### + + +<h3 id="blockquote">Blockquotes</h3> + +Markdown uses email-style `>` characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a `>` before every line: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + > + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + > id sem consectetuer libero luctus adipiscing. + +Markdown allows you to be lazy and only put the `>` before the first +line of a hard-wrapped paragraph: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + id sem consectetuer libero luctus adipiscing. + +Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of `>`: + + > This is the first level of quoting. + > + > > This is nested blockquote. + > + > Back to the first level. + +Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks: + + > ## This is a header. + > + > 1. This is the first list item. + > 2. This is the second list item. + > + > Here's some example code: + > + > return shell_exec("echo $input | $markdown_script"); + +Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu. + + +<h3 id="list">Lists</h3> + +Markdown supports ordered (numbered) and unordered (bulleted) lists. + +Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers: + + * Red + * Green + * Blue + +is equivalent to: + + + Red + + Green + + Blue + +and: + + - Red + - Green + - Blue + +Ordered lists use numbers followed by periods: + + 1. Bird + 2. McHale + 3. Parish + +It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is: + + <ol> + <li>Bird</li> + <li>McHale</li> + <li>Parish</li> + </ol> + +If you instead wrote the list in Markdown like this: + + 1. Bird + 1. McHale + 1. Parish + +or even: + + 3. Bird + 1. McHale + 8. Parish + +you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to. + +If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number. + +List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab. + +To make lists look nice, you can wrap items with hanging indents: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +But if you want to be lazy, you don't have to: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +If list items are separated by blank lines, Markdown will wrap the +items in `<p>` tags in the HTML output. For example, this input: + + * Bird + * Magic + +will turn into: + + <ul> + <li>Bird</li> + <li>Magic</li> + </ul> + +But this: + + * Bird + + * Magic + +will turn into: + + <ul> + <li><p>Bird</p></li> + <li><p>Magic</p></li> + </ul> + +List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab: + + 1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + + 2. Suspendisse id sem consectetuer libero luctus adipiscing. + +It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy: + + * This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're + only required to indent the first line. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. + + * Another item in the same list. + +To put a blockquote within a list item, the blockquote's `>` +delimiters need to be indented: + + * A list item with a blockquote: + + > This is a blockquote + > inside a list item. + +To put a code block within a list item, the code block needs +to be indented *twice* -- 8 spaces or two tabs: + + * A list item with a code block: + + <code goes here> + + +It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this: + + 1986. What a great season. + +In other words, a *number-period-space* sequence at the beginning of a +line. To avoid this, you can backslash-escape the period: + + 1986\. What a great season. + + + +<h3 id="precode">Code Blocks</h3> + +Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both `<pre>` and `<code>` tags. + +To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input: + + This is a normal paragraph: + + This is a code block. + +Markdown will generate: + + <p>This is a normal paragraph:</p> + + <pre><code>This is a code block. + </code></pre> + +One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this: + + Here is an example of AppleScript: + + tell application "Foo" + beep + end tell + +will turn into: + + <p>Here is an example of AppleScript:</p> + + <pre><code>tell application "Foo" + beep + end tell + </code></pre> + +A code block continues until it reaches a line that is not indented +(or the end of the article). + +Within a code block, ampersands (`&`) and angle brackets (`<` and `>`) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this: + + <div class="footer"> + © 2004 Foo Corporation + </div> + +will turn into: + + <pre><code><div class="footer"> + &copy; 2004 Foo Corporation + </div> + </code></pre> + +Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax. + + + +<h3 id="hr">Horizontal Rules</h3> + +You can produce a horizontal rule tag (`<hr />`) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule: + + * * * + + *** + + ***** + + - - - + + --------------------------------------- + + _ _ _ + + +* * * + +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +Markdown supports two style of links: *inline* and *reference*. + +In both styles, the link text is delimited by [square brackets]. + +To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an *optional* +title for the link, surrounded in quotes. For example: + + This is [an example](http://example.com/ "Title") inline link. + + [This link](http://example.net/) has no title attribute. + +Will produce: + + <p>This is <a href="http://example.com/" title="Title"> + an example</a> inline link.</p> + + <p><a href="http://example.net/">This link</a> has no + title attribute.</p> + +If you're referring to a local resource on the same server, you can +use relative paths: + + See my [About](/about/) page for details. + +Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link: + + This is [an example][id] reference-style link. + +You can optionally use a space to separate the sets of brackets: + + This is [an example] [id] reference-style link. + +Then, anywhere in the document, you define your link label like this, +on a line by itself: + + [id]: http://example.com/ "Optional Title Here" + +That is: + +* Square brackets containing the link identifier (optionally + indented from the left margin using up to three spaces); +* followed by a colon; +* followed by one or more spaces (or tabs); +* followed by the URL for the link; +* optionally followed by a title attribute for the link, enclosed + in double or single quotes. + +The link URL may, optionally, be surrounded by angle brackets: + + [id]: <http://example.com/> "Optional Title Here" + +You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs: + + [id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" + +Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output. + +Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links: + + [link text][a] + [link text][A] + +are equivalent. + +The *implicit link name* shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write: + + [Google][] + +And then define the link: + + [Google]: http://google.com/ + +Because link names may contain spaces, this shortcut even works for +multiple words in the link text: + + Visit [Daring Fireball][] for more information. + +And then define the link: + + [Daring Fireball]: http://daringfireball.net/ + +Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes. + +Here's an example of reference links in action: + + I get 10 times more traffic from [Google] [1] than from + [Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Using the implicit link name shortcut, you could instead write: + + I get 10 times more traffic from [Google][] than from + [Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" + +Both of the above examples will produce the following HTML output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from + <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> + or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> + +For comparison, here is the same paragraph written using +Markdown's inline link style: + + I get 10 times more traffic from [Google](http://google.com/ "Google") + than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or + [MSN](http://search.msn.com/ "MSN Search"). + +The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text. + +With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose. + + +<h3 id="em">Emphasis</h3> + +Markdown treats asterisks (`*`) and underscores (`_`) as indicators of +emphasis. Text wrapped with one `*` or `_` will be wrapped with an +HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML +`<strong>` tag. E.g., this input: + + *single asterisks* + + _single underscores_ + + **double asterisks** + + __double underscores__ + +will produce: + + <em>single asterisks</em> + + <em>single underscores</em> + + <strong>double asterisks</strong> + + <strong>double underscores</strong> + +You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span. + +Emphasis can be used in the middle of a word: + + un*fucking*believable + +But if you surround an `*` or `_` with spaces, it'll be treated as a +literal asterisk or underscore. + +To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it: + + \*this text is surrounded by literal asterisks\* + + + +<h3 id="code">Code</h3> + +To indicate a span of code, wrap it with backtick quotes (`` ` ``). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example: + + Use the `printf()` function. + +will produce: + + <p>Use the <code>printf()</code> function.</p> + +To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters: + + ``There is a literal backtick (`) here.`` + +which will produce this: + + <p><code>There is a literal backtick (`) here.</code></p> + +The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span: + + A single backtick in a code span: `` ` `` + + A backtick-delimited string in a code span: `` `foo` `` + +will produce: + + <p>A single backtick in a code span: <code>`</code></p> + + <p>A backtick-delimited string in a code span: <code>`foo`</code></p> + +With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this: + + Please don't use any `<blink>` tags. + +into: + + <p>Please don't use any <code><blink></code> tags.</p> + +You can write this: + + `—` is the decimal-encoded equivalent of `—`. + +to produce: + + <p><code>&#8212;</code> is the decimal-encoded + equivalent of <code>&mdash;</code>.</p> + + + +<h3 id="img">Images</h3> + +Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format. + +Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: *inline* and *reference*. + +Inline image syntax looks like this: + +  + +  + +That is: + +* An exclamation mark: `!`; +* followed by a set of square brackets, containing the `alt` + attribute text for the image; +* followed by a set of parentheses, containing the URL or path to + the image, and an optional `title` attribute enclosed in double + or single quotes. + +Reference-style image syntax looks like this: + + ![Alt text][id] + +Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references: + + [id]: url/to/image "Optional title attribute" + +As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML `<img>` tags. + + +* * * + + +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this: + + <http://example.com/> + +Markdown will turn this into: + + <a href="http://example.com/">http://example.com/</a> + +Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this: + + <address@example.com> + +into something like this: + + <a href="mailto:addre + ss@example.co + m">address@exa + mple.com</a> + +which will render in a browser as a clickable link to "address@example.com". + +(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.) + + + +<h3 id="backslash">Backslash Escapes</h3> + +Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML `<em>` tag), you can backslashes +before the asterisks, like this: + + \*literal asterisks\* + +Markdown provides backslash escapes for the following characters: + + \ backslash + ` backtick + * asterisk + _ underscore + {} curly braces + [] square brackets + () parentheses + # hash mark + + plus sign + - minus sign (hyphen) + . dot + ! exclamation mark + diff --git a/tests/extensions-x-def_list/simple_def-lists.html b/tests/extensions-x-def_list/simple_def-lists.html new file mode 100644 index 0000000..278e1ec --- /dev/null +++ b/tests/extensions-x-def_list/simple_def-lists.html @@ -0,0 +1,37 @@ +<p>Some text</p> +<dl> +<dt>term1</dt> +<dd>Def1</dd> +<dt>term2-1</dt> +<dt>term2-2</dt> +<dd>Def2-1</dd> +<dd>Def2-2</dd> +</dl> +<p>more text</p> +<dl> +<dt>term <em>3</em></dt> +<dd> +<p>def 3 +line <strong>2</strong> of def 3</p> +<p>paragraph 2 of def 3.</p> +</dd> +<dd> +<p>def 3-2</p> +<pre><code># A code block in a def +</code></pre> +<blockquote> +<p>a blockquote</p> +</blockquote> +<ul> +<li> +<p>a list item</p> +</li> +<li> +<blockquote> +<p>blockquote in list</p> +</blockquote> +</li> +</ul> +</dd> +</dl> +<p>final text.</p>
\ No newline at end of file diff --git a/tests/extensions-x-def_list/simple_def-lists.txt b/tests/extensions-x-def_list/simple_def-lists.txt new file mode 100644 index 0000000..20c028a --- /dev/null +++ b/tests/extensions-x-def_list/simple_def-lists.txt @@ -0,0 +1,29 @@ +Some text + +term1 +: Def1 + +term2-1 +term2-2 +: Def2-1 +: Def2-2 + +more text + +term *3* +: def 3 + line __2__ of def 3 + + paragraph 2 of def 3. + +: def 3-2 + + # A code block in a def + + > a blockquote + + * a list item + + * > blockquote in list + +final text. diff --git a/tests/extensions-x-footnotes/footnote.html b/tests/extensions-x-footnotes/footnote.html new file mode 100644 index 0000000..6556dab --- /dev/null +++ b/tests/extensions-x-footnotes/footnote.html @@ -0,0 +1,29 @@ +<p>This is the body with a footnote<sup id="fnref:1"><a href="#fn:1" rel="footnote">1</a></sup> or two<sup id="fnref:2"><a href="#fn:2" rel="footnote">2</a></sup> or more<sup id="fnref:3"><a href="#fn:3" rel="footnote">3</a></sup> <sup id="fnref:4"><a href="#fn:4" rel="footnote">4</a></sup>.</p> +<div class="footnote"> +<hr /> +<ol> +<li id="fn:1"> +<p>Footnote that ends with a list:</p> +<ul> +<li>item 1</li> +<li>item 2</li> +</ul> +<p><a href="#fnref:1" rev="footnote" title="Jump back to footnote 1 in the text">↩</a></p> +</li> +<li id="fn:2"> +<blockquote> +<p>This footnote is a blockquote. +</p> +</blockquote> +<p><a href="#fnref:2" rev="footnote" title="Jump back to footnote 2 in the text">↩</a></p> +</li> +<li id="fn:3"> +<p>A simple oneliner. + <a href="#fnref:3" rev="footnote" title="Jump back to footnote 3 in the text">↩</a></p> +</li> +<li id="fn:4"> +<p>A footnote with multiple paragraphs.</p> +<p>Paragraph two. <a href="#fnref:4" rev="footnote" title="Jump back to footnote 4 in the text">↩</a></p> +</li> +</ol> +</div>
\ No newline at end of file diff --git a/tests/extensions-x-footnotes/footnote.txt b/tests/extensions-x-footnotes/footnote.txt new file mode 100644 index 0000000..07188d0 --- /dev/null +++ b/tests/extensions-x-footnotes/footnote.txt @@ -0,0 +1,14 @@ +This is the body with a footnote[^1] or two[^2] or more[^3] [^4]. + +[^1]: Footnote that ends with a list: + + * item 1 + * item 2 + +[^2]: > This footnote is a blockquote. + +[^3]: A simple oneliner. + +[^4]: A footnote with multiple paragraphs. + + Paragraph two. diff --git a/tests/extensions-x-footnotes/named_markers.html b/tests/extensions-x-footnotes/named_markers.html new file mode 100644 index 0000000..6996b5f --- /dev/null +++ b/tests/extensions-x-footnotes/named_markers.html @@ -0,0 +1,24 @@ +<p>This is the body with footnotes<sup id="fnref:foo"><a href="#fn:foo" rel="footnote">1</a></sup> +that have named<sup id="fnref:bar"><a href="#fn:bar" rel="footnote">2</a></sup> markers and +oddly<sup id="fnref:56"><a href="#fn:56" rel="footnote">3</a></sup> numbered<sup id="fnref:99"><a href="#fn:99" rel="footnote">4</a></sup> markers.</p> +<div class="footnote"> +<hr /> +<ol> +<li id="fn:foo"> +<p>Footnote marked <code>foo</code>. + <a href="#fnref:foo" rev="footnote" title="Jump back to footnote 1 in the text">↩</a></p> +</li> +<li id="fn:bar"> +<p>This one is marked <em>bar</em>. + <a href="#fnref:bar" rev="footnote" title="Jump back to footnote 2 in the text">↩</a></p> +</li> +<li id="fn:56"> +<p>A <strong>numbered</strong> footnote. + <a href="#fnref:56" rev="footnote" title="Jump back to footnote 3 in the text">↩</a></p> +</li> +<li id="fn:99"> +<p>The last one. + <a href="#fnref:99" rev="footnote" title="Jump back to footnote 4 in the text">↩</a></p> +</li> +</ol> +</div>
\ No newline at end of file diff --git a/tests/extensions-x-footnotes/named_markers.txt b/tests/extensions-x-footnotes/named_markers.txt new file mode 100644 index 0000000..d246524 --- /dev/null +++ b/tests/extensions-x-footnotes/named_markers.txt @@ -0,0 +1,9 @@ +This is the body with footnotes[^foo] +that have named[^bar] markers and +oddly[^56] numbered[^99] markers. + +[^foo]: Footnote marked ``foo``. +[^bar]: This one is marked *bar*. +[^56]: A __numbered__ footnote. +[^99]: The last one. + diff --git a/tests/extensions-x-tables/tables.html b/tests/extensions-x-tables/tables.html new file mode 100644 index 0000000..c931e6a --- /dev/null +++ b/tests/extensions-x-tables/tables.html @@ -0,0 +1,119 @@ +<h2>Table Tests</h2> +<table> +<thead> +<tr> +<th>First Header</th> +<th>Second Header</th> +</tr> +</thead> +<tbody> +<tr> +<td>Content Cell</td> +<td>Content Cell</td> +</tr> +<tr> +<td>Content Cell</td> +<td>Content Cell</td> +</tr> +</tbody> +</table> +<table> +<thead> +<tr> +<th>First Header</th> +<th>Second Header</th> +</tr> +</thead> +<tbody> +<tr> +<td>Content Cell</td> +<td>Content Cell</td> +</tr> +<tr> +<td>Content Cell</td> +<td>Content Cell</td> +</tr> +</tbody> +</table> +<table> +<thead> +<tr> +<th>Item</th> +<th align="right">Value</th> +</tr> +</thead> +<tbody> +<tr> +<td>Computer</td> +<td align="right">$1600</td> +</tr> +<tr> +<td>Phone</td> +<td align="right">$12</td> +</tr> +<tr> +<td>Pipe</td> +<td align="right">$1</td> +</tr> +</tbody> +</table> +<table> +<thead> +<tr> +<th>Function name</th> +<th>Description</th> +</tr> +</thead> +<tbody> +<tr> +<td><code>help()</code></td> +<td>Display the help window.</td> +</tr> +<tr> +<td><code>destroy()</code></td> +<td><strong>Destroy your computer!</strong></td> +</tr> +</tbody> +</table> +<table> +<thead> +<tr> +<th align="left">foo</th> +<th align="center">bar</th> +<th align="right">baz</th> +</tr> +</thead> +<tbody> +<tr> +<td align="left" /> +<td align="center">Q</td> +<td align="right" /> +</tr> +<tr> +<td align="left">W</td> +<td align="center" /> +<td align="right">W</td> +</tr> +</tbody> +</table> +<table> +<thead> +<tr> +<th>foo</th> +<th>bar</th> +<th>baz</th> +</tr> +</thead> +<tbody> +<tr> +<td /> +<td>Q</td> +<td /> +</tr> +<tr> +<td>W</td> +<td /> +<td>W</td> +</tr> +</tbody> +</table>
\ No newline at end of file diff --git a/tests/extensions-x-tables/tables.txt b/tests/extensions-x-tables/tables.txt new file mode 100644 index 0000000..64917ab --- /dev/null +++ b/tests/extensions-x-tables/tables.txt @@ -0,0 +1,34 @@ +Table Tests +----------- + +First Header | Second Header +------------- | ------------- +Content Cell | Content Cell +Content Cell | Content Cell + +| First Header | Second Header | +| ------------- | ------------- | +| Content Cell | Content Cell | +| Content Cell | Content Cell | + +| Item | Value | +| :-------- | -----:| +| Computer | $1600 | +| Phone | $12 | +| Pipe | $1 | + +| Function name | Description | +| ------------- | ------------------------------ | +| `help()` | Display the help window. | +| `destroy()` | **Destroy your computer!** | + +|foo|bar|baz| +|:--|:-:|--:| +| | Q | | +|W | | W| + +foo|bar|baz +---|---|--- + | Q | + W | | W + diff --git a/tests/extensions-x-toc/invalid.html b/tests/extensions-x-toc/invalid.html new file mode 100644 index 0000000..41a3b1f --- /dev/null +++ b/tests/extensions-x-toc/invalid.html @@ -0,0 +1,6 @@ +<h2 id="toc">[TOC]</h2> +<h1 id="header-1">Header 1</h1> +<p>The TOC marker cannot be inside a header. This test makes sure markdown doesn't +crash when it encounters this errant syntax. The unexpected output should +clue the author in that s/he needs to add a blank line between the TOC and +the <code><hr></code>.</p>
\ No newline at end of file diff --git a/tests/extensions-x-toc/invalid.txt b/tests/extensions-x-toc/invalid.txt new file mode 100644 index 0000000..f6c4ec4 --- /dev/null +++ b/tests/extensions-x-toc/invalid.txt @@ -0,0 +1,9 @@ +[TOC] +----- + +# Header 1 + +The TOC marker cannot be inside a header. This test makes sure markdown doesn't +crash when it encounters this errant syntax. The unexpected output should +clue the author in that s/he needs to add a blank line between the TOC and +the `<hr>`. diff --git a/tests/extensions-x-toc/nested.html b/tests/extensions-x-toc/nested.html new file mode 100644 index 0000000..a8a1583 --- /dev/null +++ b/tests/extensions-x-toc/nested.html @@ -0,0 +1,16 @@ +<h1 id="header-a">Header A</h1> +<h2 id="header-1">Header 1</h2> +<h3 id="header-i">Header i</h3> +<h1 id="header-b">Header B</h1> +<div class="toc"> +<ul> +<li><a href="#header-a">Header A</a><ul> +<li><a href="#header-1">Header 1</a><ul> +<li><a href="#header-i">Header i</a></li> +</ul> +</li> +</ul> +</li> +<li><a href="#header-b">Header B</a></li> +</ul> +</div>
\ No newline at end of file diff --git a/tests/extensions-x-toc/nested.txt b/tests/extensions-x-toc/nested.txt new file mode 100644 index 0000000..9b515f9 --- /dev/null +++ b/tests/extensions-x-toc/nested.txt @@ -0,0 +1,9 @@ +# Header A + +## Header 1 + +### Header i + +# Header B + +[TOC] diff --git a/tests/extensions-x-toc/syntax-toc.html b/tests/extensions-x-toc/syntax-toc.html new file mode 100644 index 0000000..eea5347 --- /dev/null +++ b/tests/extensions-x-toc/syntax-toc.html @@ -0,0 +1,699 @@ +<div class="toc"> +<ul> +<li><a href="#overview">Overview</a><ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#inline-html">Inline HTML</a></li> +<li><a href="#automatic-escaping-for-special-characters">Automatic Escaping for Special Characters</a></li> +</ul> +</li> +<li><a href="#block-elements">Block Elements</a><ul> +<li><a href="#paragraphs-and-line-breaks">Paragraphs and Line Breaks</a></li> +<li><a href="#headers">Headers</a></li> +<li><a href="#blockquotes">Blockquotes</a></li> +<li><a href="#lists">Lists</a></li> +<li><a href="#code-blocks">Code Blocks</a></li> +<li><a href="#horizontal-rules">Horizontal Rules</a></li> +</ul> +</li> +<li><a href="#span-elements">Span Elements</a><ul> +<li><a href="#links">Links</a></li> +<li><a href="#emphasis">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#images">Images</a></li> +</ul> +</li> +<li><a href="#miscellaneous">Miscellaneous</a><ul> +<li><a href="#automatic-links">Automatic Links</a></li> +<li><a href="#backslash-escapes">Backslash Escapes</a></li> +</ul> +</li> +</ul> +</div> +<h1 id="overview">Overview</h1> +<h2 id="philosophy">Philosophy</h2> +<p>Markdown is intended to be as easy-to-read and easy-to-write as is feasible.</p> +<p>Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, <a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href="http://textism.com/tools/textile/">Textile</a>, <a href="http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href="http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and <a href="http://ettext.taint.org/doc/">EtText</a> -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email.</p> +<p>To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like *emphasis*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email.</p> +<h2 id="inline-html">Inline HTML</h2> +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a <em>publishing</em> format; Markdown is a <em>writing</em> +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text.</p> +<p>For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags.</p> +<p>The only restrictions are that block-level HTML elements -- e.g. <code><div></code>, +<code><table></code>, <code><pre></code>, <code><p></code>, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) <code><p></code> tags around HTML block-level tags.</p> +<p>For example, to add an HTML table to a Markdown article:</p> +<pre><code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code></pre> +<p>Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style <code>*emphasis*</code> inside an +HTML block.</p> +<p>Span-level HTML tags -- e.g. <code><span></code>, <code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML <code><a></code> or <code><img></code> tags instead of Markdown's +link or image syntax, go right ahead.</p> +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> processed within +span-level tags.</p> +<h2 id="automatic-escaping-for-special-characters">Automatic Escaping for Special Characters</h2> +<p>In HTML, there are two characters that demand special treatment: <code><</code> +and <code>&</code>. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> +<p>Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '<code>AT&amp;T</code>'. You even need to +escape ampersands within URLs. Thus, if you want to link to:</p> +<pre><code>http://images.google.com/images?num=30&q=larry+bird +</code></pre> +<p>you need to encode the URL as:</p> +<pre><code>http://images.google.com/images?num=30&amp;q=larry+bird +</code></pre> +<p>in your anchor tag <code>href</code> attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites.</p> +<p>Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into <code>&amp;</code>.</p> +<p>So, if you want to include a copyright symbol in your article, you can write:</p> +<pre><code>&copy; +</code></pre> +<p>and Markdown will leave it alone. But if you write:</p> +<pre><code>AT&T +</code></pre> +<p>Markdown will translate it to:</p> +<pre><code>AT&amp;T +</code></pre> +<p>Similarly, because Markdown supports <a href="#html">inline HTML</a>, if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write:</p> +<pre><code>4 < 5 +</code></pre> +<p>Markdown will translate it to:</p> +<pre><code>4 &lt; 5 +</code></pre> +<p>However, inside Markdown code spans and blocks, angle brackets and +ampersands are <em>always</em> encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single <code><</code> +and <code>&</code> in your example code needs to be escaped.)</p> +<hr /> +<h1 id="block-elements">Block Elements</h1> +<h2 id="paragraphs-and-line-breaks">Paragraphs and Line Breaks</h2> +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> +<p>The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a <code><br /></code> tag.</p> +<p>When you <em>do</em> want to insert a <code><br /></code> break tag using Markdown, you +end a line with two or more spaces, then type return.</p> +<p>Yes, this takes a tad more effort to create a <code><br /></code>, but a simplistic +"every line break is a <code><br /></code>" rule wouldn't work for Markdown. +Markdown's email-style <a href="#blockquote">blockquoting</a> and multi-paragraph <a href="#list">list items</a> +work best -- and look better -- when you format them with hard breaks.</p> +<h2 id="headers">Headers</h2> +<p>Markdown supports two styles of headers, <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and <a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> +<p>Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example:</p> +<pre><code>This is an H1 +============= + +This is an H2 +------------- +</code></pre> +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s will work.</p> +<p>Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example:</p> +<pre><code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code></pre> +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) :</p> +<pre><code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code></pre> +<h2 id="blockquotes">Blockquotes</h2> +<p>Markdown uses email-style <code>></code> characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a <code>></code> before every line:</p> +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>Markdown allows you to be lazy and only put the <code>></code> before the first +line of a hard-wrapped paragraph:</p> +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> +<pre><code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code></pre> +<p>Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks:</p> +<pre><code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code></pre> +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> +<h2 id="lists">Lists</h2> +<p>Markdown supports ordered (numbered) and unordered (bulleted) lists.</p> +<p>Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers:</p> +<pre><code>* Red +* Green +* Blue +</code></pre> +<p>is equivalent to:</p> +<pre><code>+ Red ++ Green ++ Blue +</code></pre> +<p>and:</p> +<pre><code>- Red +- Green +- Blue +</code></pre> +<p>Ordered lists use numbers followed by periods:</p> +<pre><code>1. Bird +2. McHale +3. Parish +</code></pre> +<p>It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is:</p> +<pre><code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code></pre> +<p>If you instead wrote the list in Markdown like this:</p> +<pre><code>1. Bird +1. McHale +1. Parish +</code></pre> +<p>or even:</p> +<pre><code>3. Bird +1. McHale +8. Parish +</code></pre> +<p>you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to.</p> +<p>If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number.</p> +<p>List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab.</p> +<p>To make lists look nice, you can wrap items with hanging indents:</p> +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>But if you want to be lazy, you don't have to:</p> +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>If list items are separated by blank lines, Markdown will wrap the +items in <code><p></code> tags in the HTML output. For example, this input:</p> +<pre><code>* Bird +* Magic +</code></pre> +<p>will turn into:</p> +<pre><code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code></pre> +<p>But this:</p> +<pre><code>* Bird + +* Magic +</code></pre> +<p>will turn into:</p> +<pre><code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code></pre> +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab:</p> +<pre><code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy:</p> +<pre><code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code></pre> +<p>To put a blockquote within a list item, the blockquote's <code>></code> +delimiters need to be indented:</p> +<pre><code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code></pre> +<p>To put a code block within a list item, the code block needs +to be indented <em>twice</em> -- 8 spaces or two tabs:</p> +<pre><code>* A list item with a code block: + + <code goes here> +</code></pre> +<p>It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this:</p> +<pre><code>1986. What a great season. +</code></pre> +<p>In other words, a <em>number-period-space</em> sequence at the beginning of a +line. To avoid this, you can backslash-escape the period:</p> +<pre><code>1986\. What a great season. +</code></pre> +<h2 id="code-blocks">Code Blocks</h2> +<p>Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both <code><pre></code> and <code><code></code> tags.</p> +<p>To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input:</p> +<pre><code>This is a normal paragraph: + + This is a code block. +</code></pre> +<p>Markdown will generate:</p> +<pre><code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code></pre> +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this:</p> +<pre><code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code></pre> +<p>will turn into:</p> +<pre><code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code></pre> +<p>A code block continues until it reaches a line that is not indented +(or the end of the article).</p> +<p>Within a code block, ampersands (<code>&</code>) and angle brackets (<code><</code> and <code>></code>) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> +<pre><code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code></pre> +<p>will turn into:</p> +<pre><code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code></pre> +<p>Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax.</p> +<h2 id="horizontal-rules">Horizontal Rules</h2> +<p>You can produce a horizontal rule tag (<code><hr /></code>) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule:</p> +<pre><code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code></pre> +<hr /> +<h1 id="span-elements">Span Elements</h1> +<h2 id="links">Links</h2> +<p>Markdown supports two style of links: <em>inline</em> and <em>reference</em>.</p> +<p>In both styles, the link text is delimited by [square brackets].</p> +<p>To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an <em>optional</em> +title for the link, surrounded in quotes. For example:</p> +<pre><code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code></pre> +<p>Will produce:</p> +<pre><code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code></pre> +<p>If you're referring to a local resource on the same server, you can +use relative paths:</p> +<pre><code>See my [About](/about/) page for details. +</code></pre> +<p>Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link:</p> +<pre><code>This is [an example][id] reference-style link. +</code></pre> +<p>You can optionally use a space to separate the sets of brackets:</p> +<pre><code>This is [an example] [id] reference-style link. +</code></pre> +<p>Then, anywhere in the document, you define your link label like this, +on a line by itself:</p> +<pre><code>[id]: http://example.com/ "Optional Title Here" +</code></pre> +<p>That is:</p> +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> +<p>The link URL may, optionally, be surrounded by angle brackets:</p> +<pre><code>[id]: <http://example.com/> "Optional Title Here" +</code></pre> +<p>You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs:</p> +<pre><code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code></pre> +<p>Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output.</p> +<p>Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are <em>not</em> case sensitive. E.g. these two links:</p> +<pre><code>[link text][a] +[link text][A] +</code></pre> +<p>are equivalent.</p> +<p>The <em>implicit link name</em> shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write:</p> +<pre><code>[Google][] +</code></pre> +<p>And then define the link:</p> +<pre><code>[Google]: http://google.com/ +</code></pre> +<p>Because link names may contain spaces, this shortcut even works for +multiple words in the link text:</p> +<pre><code>Visit [Daring Fireball][] for more information. +</code></pre> +<p>And then define the link:</p> +<pre><code>[Daring Fireball]: http://daringfireball.net/ +</code></pre> +<p>Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes.</p> +<p>Here's an example of reference links in action:</p> +<pre><code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Using the implicit link name shortcut, you could instead write:</p> +<pre><code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Both of the above examples will produce the following HTML output:</p> +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code></pre> +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> +<pre><code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code></pre> +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text.</p> +<p>With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose.</p> +<h2 id="emphasis">Emphasis</h2> +<p>Markdown treats asterisks (<code>*</code>) and underscores (<code>_</code>) as indicators of +emphasis. Text wrapped with one <code>*</code> or <code>_</code> will be wrapped with an +HTML <code><em></code> tag; double <code>*</code>'s or <code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> +<pre><code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code></pre> +<p>will produce:</p> +<pre><code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code></pre> +<p>You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span.</p> +<p>Emphasis can be used in the middle of a word:</p> +<pre><code>un*fucking*believable +</code></pre> +<p>But if you surround an <code>*</code> or <code>_</code> with spaces, it'll be treated as a +literal asterisk or underscore.</p> +<p>To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it:</p> +<pre><code>\*this text is surrounded by literal asterisks\* +</code></pre> +<h2 id="code">Code</h2> +<p>To indicate a span of code, wrap it with backtick quotes (<code>`</code>). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example:</p> +<pre><code>Use the `printf()` function. +</code></pre> +<p>will produce:</p> +<pre><code><p>Use the <code>printf()</code> function.</p> +</code></pre> +<p>To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters:</p> +<pre><code>``There is a literal backtick (`) here.`` +</code></pre> +<p>which will produce this:</p> +<pre><code><p><code>There is a literal backtick (`) here.</code></p> +</code></pre> +<p>The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span:</p> +<pre><code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code></pre> +<p>will produce:</p> +<pre><code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code></pre> +<p>With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this:</p> +<pre><code>Please don't use any `<blink>` tags. +</code></pre> +<p>into:</p> +<pre><code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code></pre> +<p>You can write this:</p> +<pre><code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code></pre> +<p>to produce:</p> +<pre><code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code></pre> +<h2 id="images">Images</h2> +<p>Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format.</p> +<p>Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: <em>inline</em> and <em>reference</em>.</p> +<p>Inline image syntax looks like this:</p> +<pre><code> + + +</code></pre> +<p>That is:</p> +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the <code>alt</code> +attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in double +or single quotes.</li> +</ul> +<p>Reference-style image syntax looks like this:</p> +<pre><code>![Alt text][id] +</code></pre> +<p>Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references:</p> +<pre><code>[id]: url/to/image "Optional title attribute" +</code></pre> +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> +<hr /> +<h1 id="miscellaneous">Miscellaneous</h1> +<h2 id="automatic-links">Automatic Links</h2> +<p>Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:</p> +<pre><code><http://example.com/> +</code></pre> +<p>Markdown will turn this into:</p> +<pre><code><a href="http://example.com/">http://example.com/</a> +</code></pre> +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this:</p> +<pre><code><address@example.com> +</code></pre> +<p>into something like this:</p> +<pre><code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code></pre> +<p>which will render in a browser as a clickable link to "address@example.com".</p> +<p>(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.)</p> +<h2 id="backslash-escapes">Backslash Escapes</h2> +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML <code><em></code> tag), you can backslashes +before the asterisks, like this:</p> +<pre><code>\*literal asterisks\* +</code></pre> +<p>Markdown provides backslash escapes for the following characters:</p> +<pre><code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code></pre>
\ No newline at end of file diff --git a/tests/extensions-x-toc/syntax-toc.txt b/tests/extensions-x-toc/syntax-toc.txt new file mode 100644 index 0000000..f297200 --- /dev/null +++ b/tests/extensions-x-toc/syntax-toc.txt @@ -0,0 +1,851 @@ + +[TOC] + +# Overview + +## Philosophy + +Markdown is intended to be as easy-to-read and easy-to-write as is feasible. + +Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4], +[Grutatext] [5], and [EtText] [6] -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email. + + [1]: http://docutils.sourceforge.net/mirror/setext.html + [2]: http://www.aaronsw.com/2002/atx/ + [3]: http://textism.com/tools/textile/ + [4]: http://docutils.sourceforge.net/rst.html + [5]: http://www.triptico.com/software/grutatxt.html + [6]: http://ettext.taint.org/doc/ + +To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like \*emphasis\*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email. + + + +## Inline HTML + +Markdown's syntax is intended for one purpose: to be used as a +format for *writing* for the web. + +Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is *not* to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a *publishing* format; Markdown is a *writing* +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text. + +For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags. + +The only restrictions are that block-level HTML elements -- e.g. `<div>`, +`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) `<p>` tags around HTML block-level tags. + +For example, to add an HTML table to a Markdown article: + + This is a regular paragraph. + + <table> + <tr> + <td>Foo</td> + </tr> + </table> + + This is another regular paragraph. + +Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an +HTML block. + +Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's +link or image syntax, go right ahead. + +Unlike block-level HTML tags, Markdown syntax *is* processed within +span-level tags. + + +## Automatic Escaping for Special Characters + +In HTML, there are two characters that demand special treatment: `<` +and `&`. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. `<`, and +`&`. + +Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '`AT&T`'. You even need to +escape ampersands within URLs. Thus, if you want to link to: + + http://images.google.com/images?num=30&q=larry+bird + +you need to encode the URL as: + + http://images.google.com/images?num=30&q=larry+bird + +in your anchor tag `href` attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites. + +Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into `&`. + +So, if you want to include a copyright symbol in your article, you can write: + + © + +and Markdown will leave it alone. But if you write: + + AT&T + +Markdown will translate it to: + + AT&T + +Similarly, because Markdown supports [inline HTML](#html), if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write: + + 4 < 5 + +Markdown will translate it to: + + 4 < 5 + +However, inside Markdown code spans and blocks, angle brackets and +ampersands are *always* encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single `<` +and `&` in your example code needs to be escaped.) + + +* * * + + +# Block Elements + + +## Paragraphs and Line Breaks + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a `<br />` tag. + +When you *do* want to insert a `<br />` break tag using Markdown, you +end a line with two or more spaces, then type return. + +Yes, this takes a tad more effort to create a `<br />`, but a simplistic +"every line break is a `<br />`" rule wouldn't work for Markdown. +Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l] +work best -- and look better -- when you format them with hard breaks. + + [bq]: #blockquote + [l]: #list + + + +## Headers + +Markdown supports two styles of headers, [Setext] [1] and [atx] [2]. + +Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example: + + This is an H1 + ============= + + This is an H2 + ------------- + +Any number of underlining `=`'s or `-`'s will work. + +Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example: + + # This is an H1 + + ## This is an H2 + + ###### This is an H6 + +Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) : + + # This is an H1 # + + ## This is an H2 ## + + ### This is an H3 ###### + + +## Blockquotes + +Markdown uses email-style `>` characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a `>` before every line: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + > + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + > id sem consectetuer libero luctus adipiscing. + +Markdown allows you to be lazy and only put the `>` before the first +line of a hard-wrapped paragraph: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + id sem consectetuer libero luctus adipiscing. + +Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of `>`: + + > This is the first level of quoting. + > + > > This is nested blockquote. + > + > Back to the first level. + +Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks: + + > ## This is a header. + > + > 1. This is the first list item. + > 2. This is the second list item. + > + > Here's some example code: + > + > return shell_exec("echo $input | $markdown_script"); + +Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu. + + +## Lists + +Markdown supports ordered (numbered) and unordered (bulleted) lists. + +Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers: + + * Red + * Green + * Blue + +is equivalent to: + + + Red + + Green + + Blue + +and: + + - Red + - Green + - Blue + +Ordered lists use numbers followed by periods: + + 1. Bird + 2. McHale + 3. Parish + +It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is: + + <ol> + <li>Bird</li> + <li>McHale</li> + <li>Parish</li> + </ol> + +If you instead wrote the list in Markdown like this: + + 1. Bird + 1. McHale + 1. Parish + +or even: + + 3. Bird + 1. McHale + 8. Parish + +you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to. + +If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number. + +List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab. + +To make lists look nice, you can wrap items with hanging indents: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +But if you want to be lazy, you don't have to: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +If list items are separated by blank lines, Markdown will wrap the +items in `<p>` tags in the HTML output. For example, this input: + + * Bird + * Magic + +will turn into: + + <ul> + <li>Bird</li> + <li>Magic</li> + </ul> + +But this: + + * Bird + + * Magic + +will turn into: + + <ul> + <li><p>Bird</p></li> + <li><p>Magic</p></li> + </ul> + +List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab: + + 1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + + 2. Suspendisse id sem consectetuer libero luctus adipiscing. + +It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy: + + * This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're + only required to indent the first line. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. + + * Another item in the same list. + +To put a blockquote within a list item, the blockquote's `>` +delimiters need to be indented: + + * A list item with a blockquote: + + > This is a blockquote + > inside a list item. + +To put a code block within a list item, the code block needs +to be indented *twice* -- 8 spaces or two tabs: + + * A list item with a code block: + + <code goes here> + + +It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this: + + 1986. What a great season. + +In other words, a *number-period-space* sequence at the beginning of a +line. To avoid this, you can backslash-escape the period: + + 1986\. What a great season. + + + +## Code Blocks + +Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both `<pre>` and `<code>` tags. + +To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input: + + This is a normal paragraph: + + This is a code block. + +Markdown will generate: + + <p>This is a normal paragraph:</p> + + <pre><code>This is a code block. + </code></pre> + +One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this: + + Here is an example of AppleScript: + + tell application "Foo" + beep + end tell + +will turn into: + + <p>Here is an example of AppleScript:</p> + + <pre><code>tell application "Foo" + beep + end tell + </code></pre> + +A code block continues until it reaches a line that is not indented +(or the end of the article). + +Within a code block, ampersands (`&`) and angle brackets (`<` and `>`) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this: + + <div class="footer"> + © 2004 Foo Corporation + </div> + +will turn into: + + <pre><code><div class="footer"> + &copy; 2004 Foo Corporation + </div> + </code></pre> + +Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax. + + + +## Horizontal Rules + +You can produce a horizontal rule tag (`<hr />`) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule: + + * * * + + *** + + ***** + + - - - + + --------------------------------------- + + _ _ _ + + +* * * + +# Span Elements + +## Links + +Markdown supports two style of links: *inline* and *reference*. + +In both styles, the link text is delimited by [square brackets]. + +To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an *optional* +title for the link, surrounded in quotes. For example: + + This is [an example](http://example.com/ "Title") inline link. + + [This link](http://example.net/) has no title attribute. + +Will produce: + + <p>This is <a href="http://example.com/" title="Title"> + an example</a> inline link.</p> + + <p><a href="http://example.net/">This link</a> has no + title attribute.</p> + +If you're referring to a local resource on the same server, you can +use relative paths: + + See my [About](/about/) page for details. + +Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link: + + This is [an example][id] reference-style link. + +You can optionally use a space to separate the sets of brackets: + + This is [an example] [id] reference-style link. + +Then, anywhere in the document, you define your link label like this, +on a line by itself: + + [id]: http://example.com/ "Optional Title Here" + +That is: + +* Square brackets containing the link identifier (optionally + indented from the left margin using up to three spaces); +* followed by a colon; +* followed by one or more spaces (or tabs); +* followed by the URL for the link; +* optionally followed by a title attribute for the link, enclosed + in double or single quotes. + +The link URL may, optionally, be surrounded by angle brackets: + + [id]: <http://example.com/> "Optional Title Here" + +You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs: + + [id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" + +Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output. + +Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links: + + [link text][a] + [link text][A] + +are equivalent. + +The *implicit link name* shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write: + + [Google][] + +And then define the link: + + [Google]: http://google.com/ + +Because link names may contain spaces, this shortcut even works for +multiple words in the link text: + + Visit [Daring Fireball][] for more information. + +And then define the link: + + [Daring Fireball]: http://daringfireball.net/ + +Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes. + +Here's an example of reference links in action: + + I get 10 times more traffic from [Google] [1] than from + [Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Using the implicit link name shortcut, you could instead write: + + I get 10 times more traffic from [Google][] than from + [Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" + +Both of the above examples will produce the following HTML output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from + <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> + or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> + +For comparison, here is the same paragraph written using +Markdown's inline link style: + + I get 10 times more traffic from [Google](http://google.com/ "Google") + than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or + [MSN](http://search.msn.com/ "MSN Search"). + +The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text. + +With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose. + + +## Emphasis + +Markdown treats asterisks (`*`) and underscores (`_`) as indicators of +emphasis. Text wrapped with one `*` or `_` will be wrapped with an +HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML +`<strong>` tag. E.g., this input: + + *single asterisks* + + _single underscores_ + + **double asterisks** + + __double underscores__ + +will produce: + + <em>single asterisks</em> + + <em>single underscores</em> + + <strong>double asterisks</strong> + + <strong>double underscores</strong> + +You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span. + +Emphasis can be used in the middle of a word: + + un*fucking*believable + +But if you surround an `*` or `_` with spaces, it'll be treated as a +literal asterisk or underscore. + +To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it: + + \*this text is surrounded by literal asterisks\* + + + +## Code + +To indicate a span of code, wrap it with backtick quotes (`` ` ``). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example: + + Use the `printf()` function. + +will produce: + + <p>Use the <code>printf()</code> function.</p> + +To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters: + + ``There is a literal backtick (`) here.`` + +which will produce this: + + <p><code>There is a literal backtick (`) here.</code></p> + +The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span: + + A single backtick in a code span: `` ` `` + + A backtick-delimited string in a code span: `` `foo` `` + +will produce: + + <p>A single backtick in a code span: <code>`</code></p> + + <p>A backtick-delimited string in a code span: <code>`foo`</code></p> + +With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this: + + Please don't use any `<blink>` tags. + +into: + + <p>Please don't use any <code><blink></code> tags.</p> + +You can write this: + + `—` is the decimal-encoded equivalent of `—`. + +to produce: + + <p><code>&#8212;</code> is the decimal-encoded + equivalent of <code>&mdash;</code>.</p> + + + +## Images + +Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format. + +Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: *inline* and *reference*. + +Inline image syntax looks like this: + +  + +  + +That is: + +* An exclamation mark: `!`; +* followed by a set of square brackets, containing the `alt` + attribute text for the image; +* followed by a set of parentheses, containing the URL or path to + the image, and an optional `title` attribute enclosed in double + or single quotes. + +Reference-style image syntax looks like this: + + ![Alt text][id] + +Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references: + + [id]: url/to/image "Optional title attribute" + +As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML `<img>` tags. + + +* * * + + +# Miscellaneous + +## Automatic Links + +Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this: + + <http://example.com/> + +Markdown will turn this into: + + <a href="http://example.com/">http://example.com/</a> + +Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this: + + <address@example.com> + +into something like this: + + <a href="mailto:addre + ss@example.co + m">address@exa + mple.com</a> + +which will render in a browser as a clickable link to "address@example.com". + +(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.) + + + +## Backslash Escapes + +Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML `<em>` tag), you can backslashes +before the asterisks, like this: + + \*literal asterisks\* + +Markdown provides backslash escapes for the following characters: + + \ backslash + ` backtick + * asterisk + _ underscore + {} curly braces + [] square brackets + () parentheses + # hash mark + + plus sign + - minus sign (hyphen) + . dot + ! exclamation mark + diff --git a/tests/extensions-x-wikilinks/wikilinks.html b/tests/extensions-x-wikilinks/wikilinks.html new file mode 100644 index 0000000..1a38535 --- /dev/null +++ b/tests/extensions-x-wikilinks/wikilinks.html @@ -0,0 +1,6 @@ +<p>Some text with a <a class="wikilink" href="/WikiLink/">WikiLink</a>.</p> +<p>A link with <a class="wikilink" href="/white_space_and_underscores/">white space and_underscores</a> and a empty one.</p> +<p>And a <a href="http://example.com/RealLink">RealLink</a>.</p> +<p><a href="http://example.com/And_A_AutoLink">http://example.com/And_A_AutoLink</a></p> +<p>And a <a href="/MarkdownLink/" title="A MarkdownLink">MarkdownLink</a> for +completeness.</p>
\ No newline at end of file diff --git a/tests/extensions-x-wikilinks/wikilinks.txt b/tests/extensions-x-wikilinks/wikilinks.txt new file mode 100644 index 0000000..8e6911b --- /dev/null +++ b/tests/extensions-x-wikilinks/wikilinks.txt @@ -0,0 +1,14 @@ +Some text with a [[WikiLink]]. + +A link with [[ white space and_underscores ]] and a empty [[ ]] one. + +Another with [[double spaces]] and [[double__underscores]] and +one that [[has _emphasis_ inside]] and one [[with_multiple_underscores]] +and one that is _[[emphasised]]_. + +And a <a href="http://example.com/RealLink">RealLink</a>. + +<http://example.com/And_A_AutoLink> + +And a [MarkdownLink](/MarkdownLink/ "A MarkdownLink") for +completeness. diff --git a/tests/html4/html4.html b/tests/html4/html4.html new file mode 100644 index 0000000..7c88ad7 --- /dev/null +++ b/tests/html4/html4.html @@ -0,0 +1,2 @@ +<p>A test of the most<br> +basic of html/xhtml differences.</p>
\ No newline at end of file diff --git a/tests/html4/html4.txt b/tests/html4/html4.txt new file mode 100644 index 0000000..fddaf8e --- /dev/null +++ b/tests/html4/html4.txt @@ -0,0 +1,2 @@ +A test of the most +basic of html/xhtml differences.
\ No newline at end of file diff --git a/tests/markdown-test/amps-and-angle-encoding.html b/tests/markdown-test/amps-and-angle-encoding.html new file mode 100644 index 0000000..2c466c1 --- /dev/null +++ b/tests/markdown-test/amps-and-angle-encoding.html @@ -0,0 +1,9 @@ +<p>AT&T has an ampersand in their name.</p> +<p>AT&T is another way to write it.</p> +<p>This & that.</p> +<p>4 < 5.</p> +<p>6 > 5.</p> +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link</a> with an ampersand in the URL.</p> +<p>Here's a link with an amersand in the link text: <a href="http://att.com/" title="AT&T">AT&T</a>.</p> +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> +<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p>
\ No newline at end of file diff --git a/tests/markdown-test/amps-and-angle-encoding.txt b/tests/markdown-test/amps-and-angle-encoding.txt new file mode 100644 index 0000000..0e9527f --- /dev/null +++ b/tests/markdown-test/amps-and-angle-encoding.txt @@ -0,0 +1,21 @@ +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Here's a [link] [1] with an ampersand in the URL. + +Here's a link with an amersand in the link text: [AT&T] [2]. + +Here's an inline [link](/script?foo=1&bar=2). + +Here's an inline [link](</script?foo=1&bar=2>). + + +[1]: http://example.com/?foo=1&bar=2 +[2]: http://att.com/ "AT&T"
\ No newline at end of file diff --git a/tests/markdown-test/angle-links-and-img.html b/tests/markdown-test/angle-links-and-img.html new file mode 100644 index 0000000..1ca3b0b --- /dev/null +++ b/tests/markdown-test/angle-links-and-img.html @@ -0,0 +1,4 @@ +<p><a href="simple link" title="title">link</a> +<img alt="image" src="http://example.com/image.jpg" /> +<a href="http://example.com/(()((())923)(">link</a> +<img alt="image" src="link(()))(" /></p>
\ No newline at end of file diff --git a/tests/markdown-test/angle-links-and-img.txt b/tests/markdown-test/angle-links-and-img.txt new file mode 100644 index 0000000..1dbf404 --- /dev/null +++ b/tests/markdown-test/angle-links-and-img.txt @@ -0,0 +1,4 @@ +[link](<simple link> "title") + +[link](<http://example.com/(()((())923)(>) +))(>) diff --git a/tests/markdown-test/auto-links.html b/tests/markdown-test/auto-links.html new file mode 100644 index 0000000..7481fe2 --- /dev/null +++ b/tests/markdown-test/auto-links.html @@ -0,0 +1,15 @@ +<p>Link: <a href="http://example.com/">http://example.com/</a>.</p> +<p>Https link: <a href="https://example.com">https://example.com</a></p> +<p>Ftp link: <a href="ftp://example.com">ftp://example.com</a></p> +<p>With an ampersand: <a href="http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</a></p> +<ul> +<li>In a list?</li> +<li><a href="http://example.com/">http://example.com/</a></li> +<li>It should.</li> +</ul> +<blockquote> +<p>Blockquoted: <a href="http://example.com/">http://example.com/</a></p> +</blockquote> +<p>Auto-links should not occur here: <code><http://example.com/></code></p> +<pre><code>or here: <http://example.com/> +</code></pre>
\ No newline at end of file diff --git a/tests/markdown-test/auto-links.txt b/tests/markdown-test/auto-links.txt new file mode 100644 index 0000000..a188b40 --- /dev/null +++ b/tests/markdown-test/auto-links.txt @@ -0,0 +1,17 @@ +Link: <http://example.com/>. + +Https link: <https://example.com> + +Ftp link: <ftp://example.com> + +With an ampersand: <http://example.com/?foo=1&bar=2> + +* In a list? +* <http://example.com/> +* It should. + +> Blockquoted: <http://example.com/> + +Auto-links should not occur here: `<http://example.com/>` + + or here: <http://example.com/> diff --git a/tests/markdown-test/backlash-escapes.html b/tests/markdown-test/backlash-escapes.html new file mode 100644 index 0000000..876775f --- /dev/null +++ b/tests/markdown-test/backlash-escapes.html @@ -0,0 +1,67 @@ +<p>These should all get escaped:</p> +<p>Backslash: \</p> +<p>Backtick: `</p> +<p>Asterisk: *</p> +<p>Underscore: _</p> +<p>Left brace: {</p> +<p>Right brace: }</p> +<p>Left bracket: [</p> +<p>Right bracket: ]</p> +<p>Left paren: (</p> +<p>Right paren: )</p> +<p>Greater-than: ></p> +<p>Hash: #</p> +<p>Period: .</p> +<p>Bang: !</p> +<p>Plus: +</p> +<p>Minus: -</p> +<p>These should not, because they occur within a code block:</p> +<pre><code>Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- +</code></pre> +<p>Nor should these, which occur in code spans:</p> +<p>Backslash: <code>\\</code></p> +<p>Backtick: <code>\`</code></p> +<p>Asterisk: <code>\*</code></p> +<p>Underscore: <code>\_</code></p> +<p>Left brace: <code>\{</code></p> +<p>Right brace: <code>\}</code></p> +<p>Left bracket: <code>\[</code></p> +<p>Right bracket: <code>\]</code></p> +<p>Left paren: <code>\(</code></p> +<p>Right paren: <code>\)</code></p> +<p>Greater-than: <code>\></code></p> +<p>Hash: <code>\#</code></p> +<p>Period: <code>\.</code></p> +<p>Bang: <code>\!</code></p> +<p>Plus: <code>\+</code></p> +<p>Minus: <code>\-</code></p>
\ No newline at end of file diff --git a/tests/markdown-test/backlash-escapes.txt b/tests/markdown-test/backlash-escapes.txt new file mode 100644 index 0000000..16447a0 --- /dev/null +++ b/tests/markdown-test/backlash-escapes.txt @@ -0,0 +1,104 @@ +These should all get escaped: + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- + + + +These should not, because they occur within a code block: + + Backslash: \\ + + Backtick: \` + + Asterisk: \* + + Underscore: \_ + + Left brace: \{ + + Right brace: \} + + Left bracket: \[ + + Right bracket: \] + + Left paren: \( + + Right paren: \) + + Greater-than: \> + + Hash: \# + + Period: \. + + Bang: \! + + Plus: \+ + + Minus: \- + + +Nor should these, which occur in code spans: + +Backslash: `\\` + +Backtick: `` \` `` + +Asterisk: `\*` + +Underscore: `\_` + +Left brace: `\{` + +Right brace: `\}` + +Left bracket: `\[` + +Right bracket: `\]` + +Left paren: `\(` + +Right paren: `\)` + +Greater-than: `\>` + +Hash: `\#` + +Period: `\.` + +Bang: `\!` + +Plus: `\+` + +Minus: `\-` diff --git a/tests/markdown-test/benchmark.dat b/tests/markdown-test/benchmark.dat new file mode 100644 index 0000000..3d549dd --- /dev/null +++ b/tests/markdown-test/benchmark.dat @@ -0,0 +1,20 @@ +construction:0.000000:0.000000 +amps-and-angle-encoding:0.070000:131072.000000 +auto-links:0.080000:397312.000000 +backlash-escapes:0.270000:884736.000000 +blockquotes-with-dode-blocks:0.020000:0.000000 +hard-wrapped:0.020000:0.000000 +horizontal-rules:0.180000:135168.000000 +inline-html-advanced:0.070000:0.000000 +inline-html-comments:0.080000:0.000000 +inline-html-simple:0.210000:0.000000 +links-inline:0.140000:0.000000 +links-reference:0.170000:0.000000 +literal-quotes:0.090000:0.000000 +markdown-documentation-basics:0.690000:1806336.000000 +markdown-syntax:3.310000:6696960.000000 +nested-blockquotes:0.200000:0.000000 +ordered-and-unordered-list:0.530000:0.000000 +strong-and-em-together:0.200000:0.000000 +tabs:0.200000:0.000000 +tidyness:0.200000:0.000000 diff --git a/tests/markdown-test/blockquotes-with-code-blocks.html b/tests/markdown-test/blockquotes-with-code-blocks.html new file mode 100644 index 0000000..5fc98b1 --- /dev/null +++ b/tests/markdown-test/blockquotes-with-code-blocks.html @@ -0,0 +1,12 @@ +<blockquote> +<p>Example:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +<p>Or:</p> +<pre><code>sub status { + return "working"; +} +</code></pre> +</blockquote>
\ No newline at end of file diff --git a/tests/markdown-test/blockquotes-with-code-blocks.txt b/tests/markdown-test/blockquotes-with-code-blocks.txt new file mode 100644 index 0000000..c31d171 --- /dev/null +++ b/tests/markdown-test/blockquotes-with-code-blocks.txt @@ -0,0 +1,11 @@ +> Example: +> +> sub status { +> print "working"; +> } +> +> Or: +> +> sub status { +> return "working"; +> } diff --git a/tests/markdown-test/codeblock-in-list.html b/tests/markdown-test/codeblock-in-list.html new file mode 100644 index 0000000..49edd56 --- /dev/null +++ b/tests/markdown-test/codeblock-in-list.html @@ -0,0 +1,14 @@ +<ul> +<li> +<p>A list item with a code block</p> +<pre><code>Some *code* +</code></pre> +</li> +<li> +<p>Another list item</p> +<pre><code>More code + +And more code +</code></pre> +</li> +</ul>
\ No newline at end of file diff --git a/tests/markdown-test/codeblock-in-list.txt b/tests/markdown-test/codeblock-in-list.txt new file mode 100644 index 0000000..87d4e3b --- /dev/null +++ b/tests/markdown-test/codeblock-in-list.txt @@ -0,0 +1,10 @@ +* A list item with a code block + + Some *code* + +* Another list item + + More code + + And more code + diff --git a/tests/markdown-test/hard-wrapped.html b/tests/markdown-test/hard-wrapped.html new file mode 100644 index 0000000..e28e900 --- /dev/null +++ b/tests/markdown-test/hard-wrapped.html @@ -0,0 +1,7 @@ +<p>In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item.</p> +<p>Here's one with a bullet. +* criminey.</p>
\ No newline at end of file diff --git a/tests/markdown-test/hard-wrapped.txt b/tests/markdown-test/hard-wrapped.txt new file mode 100644 index 0000000..f8a5b27 --- /dev/null +++ b/tests/markdown-test/hard-wrapped.txt @@ -0,0 +1,8 @@ +In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item. + +Here's one with a bullet. +* criminey. diff --git a/tests/markdown-test/horizontal-rules.html b/tests/markdown-test/horizontal-rules.html new file mode 100644 index 0000000..478e8c5 --- /dev/null +++ b/tests/markdown-test/horizontal-rules.html @@ -0,0 +1,39 @@ +<p>Dashes:</p> +<hr /> +<hr /> +<hr /> +<hr /> +<pre><code>--- +</code></pre> +<hr /> +<hr /> +<hr /> +<hr /> +<pre><code>- - - +</code></pre> +<p>Asterisks:</p> +<hr /> +<hr /> +<hr /> +<hr /> +<pre><code>*** +</code></pre> +<hr /> +<hr /> +<hr /> +<hr /> +<pre><code>* * * +</code></pre> +<p>Underscores:</p> +<hr /> +<hr /> +<hr /> +<hr /> +<pre><code>___ +</code></pre> +<hr /> +<hr /> +<hr /> +<hr /> +<pre><code>_ _ _ +</code></pre>
\ No newline at end of file diff --git a/tests/markdown-test/horizontal-rules.txt b/tests/markdown-test/horizontal-rules.txt new file mode 100644 index 0000000..1594bda --- /dev/null +++ b/tests/markdown-test/horizontal-rules.txt @@ -0,0 +1,67 @@ +Dashes: + +--- + + --- + + --- + + --- + + --- + +- - - + + - - - + + - - - + + - - - + + - - - + + +Asterisks: + +*** + + *** + + *** + + *** + + *** + +* * * + + * * * + + * * * + + * * * + + * * * + + +Underscores: + +___ + + ___ + + ___ + + ___ + + ___ + +_ _ _ + + _ _ _ + + _ _ _ + + _ _ _ + + _ _ _ diff --git a/tests/markdown-test/inline-html-advanced.html b/tests/markdown-test/inline-html-advanced.html new file mode 100644 index 0000000..af1dec1 --- /dev/null +++ b/tests/markdown-test/inline-html-advanced.html @@ -0,0 +1,12 @@ +<p>Simple block on one line:</p> +<div>foo</div> + +<p>And nested without indentation:</p> +<div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div>
\ No newline at end of file diff --git a/tests/markdown-test/inline-html-advanced.txt b/tests/markdown-test/inline-html-advanced.txt new file mode 100644 index 0000000..9d71ddc --- /dev/null +++ b/tests/markdown-test/inline-html-advanced.txt @@ -0,0 +1,14 @@ +Simple block on one line: + +<div>foo</div> + +And nested without indentation: + +<div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div> diff --git a/tests/markdown-test/inline-html-comments.html b/tests/markdown-test/inline-html-comments.html new file mode 100644 index 0000000..0d4cad9 --- /dev/null +++ b/tests/markdown-test/inline-html-comments.html @@ -0,0 +1,11 @@ +<p>Paragraph one.</p> +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +<p>Paragraph two.</p> +<!-- one comment block -- -- with two comments --> + +<p>The end.</p>
\ No newline at end of file diff --git a/tests/markdown-test/inline-html-comments.txt b/tests/markdown-test/inline-html-comments.txt new file mode 100644 index 0000000..41d830d --- /dev/null +++ b/tests/markdown-test/inline-html-comments.txt @@ -0,0 +1,13 @@ +Paragraph one. + +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +Paragraph two. + +<!-- one comment block -- -- with two comments --> + +The end. diff --git a/tests/markdown-test/inline-html-simple.html b/tests/markdown-test/inline-html-simple.html new file mode 100644 index 0000000..cb10451 --- /dev/null +++ b/tests/markdown-test/inline-html-simple.html @@ -0,0 +1,58 @@ +<p>Here's a simple block:</p> +<div> + foo +</div> + +<p>This should be a code block, though:</p> +<pre><code><div> + foo +</div> +</code></pre> +<p>As should this:</p> +<pre><code><div>foo</div> +</code></pre> +<p>Now, nested:</p> +<div> + <div> + <div> + foo + </div> + </div> +</div> + +<p>This should just be an HTML comment:</p> +<!-- Comment --> + +<p>Multiline:</p> +<!-- +Blah +Blah +--> + +<p>Code block:</p> +<pre><code><!-- Comment --> +</code></pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<!-- foo --> + +<p>Code:</p> +<pre><code><hr /> +</code></pre> +<p>Hr's:</p> +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" >
\ No newline at end of file diff --git a/tests/markdown-test/inline-html-simple.txt b/tests/markdown-test/inline-html-simple.txt new file mode 100644 index 0000000..14aa2dc --- /dev/null +++ b/tests/markdown-test/inline-html-simple.txt @@ -0,0 +1,69 @@ +Here's a simple block: + +<div> + foo +</div> + +This should be a code block, though: + + <div> + foo + </div> + +As should this: + + <div>foo</div> + +Now, nested: + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +This should just be an HTML comment: + +<!-- Comment --> + +Multiline: + +<!-- +Blah +Blah +--> + +Code block: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +<!-- foo --> + +Code: + + <hr /> + +Hr's: + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > + diff --git a/tests/markdown-test/links-inline.html b/tests/markdown-test/links-inline.html new file mode 100644 index 0000000..707937a --- /dev/null +++ b/tests/markdown-test/links-inline.html @@ -0,0 +1,5 @@ +<p>Just a <a href="/url/">URL</a>.</p> +<p><a href="/url/" title="title">URL and title</a>.</p> +<p><a href="/url/" title="title preceded by two spaces">URL and title</a>.</p> +<p><a href="/url/" title="title preceded by a tab">URL and title</a>.</p> +<p><a href="">Empty</a>.</p>
\ No newline at end of file diff --git a/tests/markdown-test/links-inline.txt b/tests/markdown-test/links-inline.txt new file mode 100644 index 0000000..4d0c1c2 --- /dev/null +++ b/tests/markdown-test/links-inline.txt @@ -0,0 +1,9 @@ +Just a [URL](/url/). + +[URL and title](/url/ "title"). + +[URL and title](/url/ "title preceded by two spaces"). + +[URL and title](/url/ "title preceded by a tab"). + +[Empty](). diff --git a/tests/markdown-test/links-reference.html b/tests/markdown-test/links-reference.html new file mode 100644 index 0000000..165c71a --- /dev/null +++ b/tests/markdown-test/links-reference.html @@ -0,0 +1,10 @@ +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>Foo <a href="/url/" title="Title">bar</a>.</p> +<p>With <a href="/url/">embedded [brackets]</a>.</p> +<p>Indented <a href="/url">once</a>.</p> +<p>Indented <a href="/url">twice</a>.</p> +<p>Indented <a href="/url">thrice</a>.</p> +<p>Indented [four][] times.</p> +<pre><code>[four]: /url +</code></pre>
\ No newline at end of file diff --git a/tests/markdown-test/links-reference.txt b/tests/markdown-test/links-reference.txt new file mode 100644 index 0000000..b2fa734 --- /dev/null +++ b/tests/markdown-test/links-reference.txt @@ -0,0 +1,31 @@ +Foo [bar] [1]. + +Foo [bar][1]. + +Foo [bar] +[1]. + +[1]: /url/ "Title" + + +With [embedded [brackets]] [b]. + + +Indented [once][]. + +Indented [twice][]. + +Indented [thrice][]. + +Indented [four][] times. + + [once]: /url + + [twice]: /url + + [thrice]: /url + + [four]: /url + + +[b]: /url/ diff --git a/tests/markdown-test/literal-quotes.html b/tests/markdown-test/literal-quotes.html new file mode 100644 index 0000000..0342589 --- /dev/null +++ b/tests/markdown-test/literal-quotes.html @@ -0,0 +1,2 @@ +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p>
\ No newline at end of file diff --git a/tests/markdown-test/literal-quotes.txt b/tests/markdown-test/literal-quotes.txt new file mode 100644 index 0000000..29d0e42 --- /dev/null +++ b/tests/markdown-test/literal-quotes.txt @@ -0,0 +1,7 @@ +Foo [bar][]. + +Foo [bar](/url/ "Title with "quotes" inside"). + + + [bar]: /url/ "Title with "quotes" inside" + diff --git a/tests/markdown-test/markdown-documentation-basics.html b/tests/markdown-test/markdown-documentation-basics.html new file mode 100644 index 0000000..3bcaea9 --- /dev/null +++ b/tests/markdown-test/markdown-documentation-basics.html @@ -0,0 +1,243 @@ +<h1>Markdown: Basics</h1> +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a class="selected" title="Markdown Basics">Basics</a></li> + <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<h2>Getting the Gist of Markdown's Formatting Syntax</h2> +<p>This page offers a brief overview of what it's like to use Markdown. +The <a href="/projects/markdown/syntax" title="Markdown Syntax">syntax page</a> provides complete, detailed documentation for +every feature, but Markdown should be very easy to pick up simply by +looking at a few examples of it in action. The examples on this page +are written in a before/after style, showing example syntax and the +HTML output produced by Markdown.</p> +<p>It's also helpful to simply try Markdown out; the <a href="/projects/markdown/dingus" title="Markdown Dingus">Dingus</a> is a +web application that allows you type your own Markdown-formatted text +and translate it to XHTML.</p> +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/basics.text">see the source for it by adding '.text' to the URL</a>.</p> +<h2>Paragraphs, Headers, Blockquotes</h2> +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> +<p>Markdown offers two styles of headers: <em>Setext</em> and <em>atx</em>. +Setext-style headers for <code><h1></code> and <code><h2></code> are created by +"underlining" with equal signs (<code>=</code>) and hyphens (<code>-</code>), respectively. +To create an atx-style header, you put 1-6 hash marks (<code>#</code>) at the +beginning of the line -- the number of hashes equals the resulting +HTML header level.</p> +<p>Blockquotes are indicated using email-style '<code>></code>' angle brackets.</p> +<p>Markdown:</p> +<pre><code>A First Level Header +==================== + +A Second Level Header +--------------------- + +Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph. + +The quick brown fox jumped over the lazy +dog's back. + +### Header 3 + +> This is a blockquote. +> +> This is the second paragraph in the blockquote. +> +> ## This is an H2 in a blockquote +</code></pre> +<p>Output:</p> +<pre><code><h1>A First Level Header</h1> + +<h2>A Second Level Header</h2> + +<p>Now is the time for all good men to come to +the aid of their country. This is just a +regular paragraph.</p> + +<p>The quick brown fox jumped over the lazy +dog's back.</p> + +<h3>Header 3</h3> + +<blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> +</blockquote> +</code></pre> +<h3>Phrase Emphasis</h3> +<p>Markdown uses asterisks and underscores to indicate spans of emphasis.</p> +<p>Markdown:</p> +<pre><code>Some of these words *are emphasized*. +Some of these words _are emphasized also_. + +Use two asterisks for **strong emphasis**. +Or, if you prefer, __use two underscores instead__. +</code></pre> +<p>Output:</p> +<pre><code><p>Some of these words <em>are emphasized</em>. +Some of these words <em>are emphasized also</em>.</p> + +<p>Use two asterisks for <strong>strong emphasis</strong>. +Or, if you prefer, <strong>use two underscores instead</strong>.</p> +</code></pre> +<h2>Lists</h2> +<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens (<code>*</code>, +<code>+</code>, and <code>-</code>) as list markers. These three markers are +interchangable; this:</p> +<pre><code>* Candy. +* Gum. +* Booze. +</code></pre> +<p>this:</p> +<pre><code>+ Candy. ++ Gum. ++ Booze. +</code></pre> +<p>and this:</p> +<pre><code>- Candy. +- Gum. +- Booze. +</code></pre> +<p>all produce the same output:</p> +<pre><code><ul> +<li>Candy.</li> +<li>Gum.</li> +<li>Booze.</li> +</ul> +</code></pre> +<p>Ordered (numbered) lists use regular numbers, followed by periods, as +list markers:</p> +<pre><code>1. Red +2. Green +3. Blue +</code></pre> +<p>Output:</p> +<pre><code><ol> +<li>Red</li> +<li>Green</li> +<li>Blue</li> +</ol> +</code></pre> +<p>If you put blank lines between items, you'll get <code><p></code> tags for the +list item text. You can create multi-paragraph list items by indenting +the paragraphs by 4 spaces or 1 tab:</p> +<pre><code>* A list item. + + With multiple paragraphs. + +* Another item in the list. +</code></pre> +<p>Output:</p> +<pre><code><ul> +<li><p>A list item.</p> +<p>With multiple paragraphs.</p></li> +<li><p>Another item in the list.</p></li> +</ul> +</code></pre> +<h3>Links</h3> +<p>Markdown supports two styles for creating links: <em>inline</em> and +<em>reference</em>. With both styles, you use square brackets to delimit the +text you want to turn into a link.</p> +<p>Inline-style links use parentheses immediately after the link text. +For example:</p> +<pre><code>This is an [example link](http://example.com/). +</code></pre> +<p>Output:</p> +<pre><code><p>This is an <a href="http://example.com/"> +example link</a>.</p> +</code></pre> +<p>Optionally, you may include a title attribute in the parentheses:</p> +<pre><code>This is an [example link](http://example.com/ "With a Title"). +</code></pre> +<p>Output:</p> +<pre><code><p>This is an <a href="http://example.com/" title="With a Title"> +example link</a>.</p> +</code></pre> +<p>Reference-style links allow you to refer to your links by names, which +you define elsewhere in your document:</p> +<pre><code>I get 10 times more traffic from [Google][1] than from +[Yahoo][2] or [MSN][3]. + +[1]: http://google.com/ "Google" +[2]: http://search.yahoo.com/ "Yahoo Search" +[3]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Output:</p> +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from <a href="http://search.yahoo.com/" +title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" +title="MSN Search">MSN</a>.</p> +</code></pre> +<p>The title attribute is optional. Link names may contain letters, +numbers and spaces, but are <em>not</em> case sensitive:</p> +<pre><code>I start my morning with a cup of coffee and +[The New York Times][NY Times]. + +[ny times]: http://www.nytimes.com/ +</code></pre> +<p>Output:</p> +<pre><code><p>I start my morning with a cup of coffee and +<a href="http://www.nytimes.com/">The New York Times</a>.</p> +</code></pre> +<h3>Images</h3> +<p>Image syntax is very much like link syntax.</p> +<p>Inline (titles are optional):</p> +<pre><code> +</code></pre> +<p>Reference-style:</p> +<pre><code>![alt text][id] + +[id]: /path/to/img.jpg "Title" +</code></pre> +<p>Both of the above examples produce the same output:</p> +<pre><code><img src="/path/to/img.jpg" alt="alt text" title="Title" /> +</code></pre> +<h3>Code</h3> +<p>In a regular paragraph, you can create code span by wrapping text in +backtick quotes. Any ampersands (<code>&</code>) and angle brackets (<code><</code> or +<code>></code>) will automatically be translated into HTML entities. This makes +it easy to use Markdown to write about HTML example code:</p> +<pre><code>I strongly recommend against using any `<blink>` tags. + +I wish SmartyPants used named entities like `&mdash;` +instead of decimal-encoded entites like `&#8212;`. +</code></pre> +<p>Output:</p> +<pre><code><p>I strongly recommend against using any +<code>&lt;blink&gt;</code> tags.</p> + +<p>I wish SmartyPants used named entities like +<code>&amp;mdash;</code> instead of decimal-encoded +entites like <code>&amp;#8212;</code>.</p> +</code></pre> +<p>To specify an entire block of pre-formatted code, indent every line of +the block by 4 spaces or 1 tab. Just like with code spans, <code>&</code>, <code><</code>, +and <code>></code> characters will be escaped automatically.</p> +<p>Markdown:</p> +<pre><code>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> +</code></pre> +<p>Output:</p> +<pre><code><p>If you want your page to validate under XHTML 1.0 Strict, +you've got to put paragraph tags in your blockquotes:</p> + +<pre><code>&lt;blockquote&gt; + &lt;p&gt;For example.&lt;/p&gt; +&lt;/blockquote&gt; +</code></pre> +</code></pre>
\ No newline at end of file diff --git a/tests/markdown-test/markdown-documentation-basics.txt b/tests/markdown-test/markdown-documentation-basics.txt new file mode 100644 index 0000000..486055c --- /dev/null +++ b/tests/markdown-test/markdown-documentation-basics.txt @@ -0,0 +1,306 @@ +Markdown: Basics +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a class="selected" title="Markdown Basics">Basics</a></li> + <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +Getting the Gist of Markdown's Formatting Syntax +------------------------------------------------ + +This page offers a brief overview of what it's like to use Markdown. +The [syntax page] [s] provides complete, detailed documentation for +every feature, but Markdown should be very easy to pick up simply by +looking at a few examples of it in action. The examples on this page +are written in a before/after style, showing example syntax and the +HTML output produced by Markdown. + +It's also helpful to simply try Markdown out; the [Dingus] [d] is a +web application that allows you type your own Markdown-formatted text +and translate it to XHTML. + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL] [src]. + + [s]: /projects/markdown/syntax "Markdown Syntax" + [d]: /projects/markdown/dingus "Markdown Dingus" + [src]: /projects/markdown/basics.text + + +## Paragraphs, Headers, Blockquotes ## + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +Markdown offers two styles of headers: *Setext* and *atx*. +Setext-style headers for `<h1>` and `<h2>` are created by +"underlining" with equal signs (`=`) and hyphens (`-`), respectively. +To create an atx-style header, you put 1-6 hash marks (`#`) at the +beginning of the line -- the number of hashes equals the resulting +HTML header level. + +Blockquotes are indicated using email-style '`>`' angle brackets. + +Markdown: + + A First Level Header + ==================== + + A Second Level Header + --------------------- + + Now is the time for all good men to come to + the aid of their country. This is just a + regular paragraph. + + The quick brown fox jumped over the lazy + dog's back. + + ### Header 3 + + > This is a blockquote. + > + > This is the second paragraph in the blockquote. + > + > ## This is an H2 in a blockquote + + +Output: + + <h1>A First Level Header</h1> + + <h2>A Second Level Header</h2> + + <p>Now is the time for all good men to come to + the aid of their country. This is just a + regular paragraph.</p> + + <p>The quick brown fox jumped over the lazy + dog's back.</p> + + <h3>Header 3</h3> + + <blockquote> + <p>This is a blockquote.</p> + + <p>This is the second paragraph in the blockquote.</p> + + <h2>This is an H2 in a blockquote</h2> + </blockquote> + + + +### Phrase Emphasis ### + +Markdown uses asterisks and underscores to indicate spans of emphasis. + +Markdown: + + Some of these words *are emphasized*. + Some of these words _are emphasized also_. + + Use two asterisks for **strong emphasis**. + Or, if you prefer, __use two underscores instead__. + +Output: + + <p>Some of these words <em>are emphasized</em>. + Some of these words <em>are emphasized also</em>.</p> + + <p>Use two asterisks for <strong>strong emphasis</strong>. + Or, if you prefer, <strong>use two underscores instead</strong>.</p> + + + +## Lists ## + +Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`, +`+`, and `-`) as list markers. These three markers are +interchangable; this: + + * Candy. + * Gum. + * Booze. + +this: + + + Candy. + + Gum. + + Booze. + +and this: + + - Candy. + - Gum. + - Booze. + +all produce the same output: + + <ul> + <li>Candy.</li> + <li>Gum.</li> + <li>Booze.</li> + </ul> + +Ordered (numbered) lists use regular numbers, followed by periods, as +list markers: + + 1. Red + 2. Green + 3. Blue + +Output: + + <ol> + <li>Red</li> + <li>Green</li> + <li>Blue</li> + </ol> + +If you put blank lines between items, you'll get `<p>` tags for the +list item text. You can create multi-paragraph list items by indenting +the paragraphs by 4 spaces or 1 tab: + + * A list item. + + With multiple paragraphs. + + * Another item in the list. + +Output: + + <ul> + <li><p>A list item.</p> + <p>With multiple paragraphs.</p></li> + <li><p>Another item in the list.</p></li> + </ul> + + + +### Links ### + +Markdown supports two styles for creating links: *inline* and +*reference*. With both styles, you use square brackets to delimit the +text you want to turn into a link. + +Inline-style links use parentheses immediately after the link text. +For example: + + This is an [example link](http://example.com/). + +Output: + + <p>This is an <a href="http://example.com/"> + example link</a>.</p> + +Optionally, you may include a title attribute in the parentheses: + + This is an [example link](http://example.com/ "With a Title"). + +Output: + + <p>This is an <a href="http://example.com/" title="With a Title"> + example link</a>.</p> + +Reference-style links allow you to refer to your links by names, which +you define elsewhere in your document: + + I get 10 times more traffic from [Google][1] than from + [Yahoo][2] or [MSN][3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from <a href="http://search.yahoo.com/" + title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" + title="MSN Search">MSN</a>.</p> + +The title attribute is optional. Link names may contain letters, +numbers and spaces, but are *not* case sensitive: + + I start my morning with a cup of coffee and + [The New York Times][NY Times]. + + [ny times]: http://www.nytimes.com/ + +Output: + + <p>I start my morning with a cup of coffee and + <a href="http://www.nytimes.com/">The New York Times</a>.</p> + + +### Images ### + +Image syntax is very much like link syntax. + +Inline (titles are optional): + +  + +Reference-style: + + ![alt text][id] + + [id]: /path/to/img.jpg "Title" + +Both of the above examples produce the same output: + + <img src="/path/to/img.jpg" alt="alt text" title="Title" /> + + + +### Code ### + +In a regular paragraph, you can create code span by wrapping text in +backtick quotes. Any ampersands (`&`) and angle brackets (`<` or +`>`) will automatically be translated into HTML entities. This makes +it easy to use Markdown to write about HTML example code: + + I strongly recommend against using any `<blink>` tags. + + I wish SmartyPants used named entities like `—` + instead of decimal-encoded entites like `—`. + +Output: + + <p>I strongly recommend against using any + <code><blink></code> tags.</p> + + <p>I wish SmartyPants used named entities like + <code>&mdash;</code> instead of decimal-encoded + entites like <code>&#8212;</code>.</p> + + +To specify an entire block of pre-formatted code, indent every line of +the block by 4 spaces or 1 tab. Just like with code spans, `&`, `<`, +and `>` characters will be escaped automatically. + +Markdown: + + If you want your page to validate under XHTML 1.0 Strict, + you've got to put paragraph tags in your blockquotes: + + <blockquote> + <p>For example.</p> + </blockquote> + +Output: + + <p>If you want your page to validate under XHTML 1.0 Strict, + you've got to put paragraph tags in your blockquotes:</p> + + <pre><code><blockquote> + <p>For example.</p> + </blockquote> + </code></pre> diff --git a/tests/markdown-test/markdown-syntax.html b/tests/markdown-test/markdown-syntax.html new file mode 100644 index 0000000..2f63b4b --- /dev/null +++ b/tests/markdown-test/markdown-syntax.html @@ -0,0 +1,728 @@ +<h1>Markdown: Syntax</h1> +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + +<ul> +<li><a href="#overview">Overview</a><ul> +<li><a href="#philosophy">Philosophy</a></li> +<li><a href="#html">Inline HTML</a></li> +<li><a href="#autoescape">Automatic Escaping for Special Characters</a></li> +</ul> +</li> +<li><a href="#block">Block Elements</a><ul> +<li><a href="#p">Paragraphs and Line Breaks</a></li> +<li><a href="#header">Headers</a></li> +<li><a href="#blockquote">Blockquotes</a></li> +<li><a href="#list">Lists</a></li> +<li><a href="#precode">Code Blocks</a></li> +<li><a href="#hr">Horizontal Rules</a></li> +</ul> +</li> +<li><a href="#span">Span Elements</a><ul> +<li><a href="#link">Links</a></li> +<li><a href="#em">Emphasis</a></li> +<li><a href="#code">Code</a></li> +<li><a href="#img">Images</a></li> +</ul> +</li> +<li><a href="#misc">Miscellaneous</a><ul> +<li><a href="#backslash">Backslash Escapes</a></li> +<li><a href="#autolink">Automatic Links</a></li> +</ul> +</li> +</ul> +<p><strong>Note:</strong> This document is itself written using Markdown; you +can <a href="/projects/markdown/syntax.text">see the source for it by adding '.text' to the URL</a>.</p> +<hr /> +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +<p>Markdown is intended to be as easy-to-read and easy-to-write as is feasible.</p> +<p>Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, <a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href="http://textism.com/tools/textile/">Textile</a>, <a href="http://docutils.sourceforge.net/rst.html">reStructuredText</a>, +<a href="http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and <a href="http://ettext.taint.org/doc/">EtText</a> -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email.</p> +<p>To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like *emphasis*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email.</p> +<h3 id="html">Inline HTML</h3> + +<p>Markdown's syntax is intended for one purpose: to be used as a +format for <em>writing</em> for the web.</p> +<p>Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is <em>not</em> to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a <em>publishing</em> format; Markdown is a <em>writing</em> +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text.</p> +<p>For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags.</p> +<p>The only restrictions are that block-level HTML elements -- e.g. <code><div></code>, +<code><table></code>, <code><pre></code>, <code><p></code>, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) <code><p></code> tags around HTML block-level tags.</p> +<p>For example, to add an HTML table to a Markdown article:</p> +<pre><code>This is a regular paragraph. + +<table> + <tr> + <td>Foo</td> + </tr> +</table> + +This is another regular paragraph. +</code></pre> +<p>Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style <code>*emphasis*</code> inside an +HTML block.</p> +<p>Span-level HTML tags -- e.g. <code><span></code>, <code><cite></code>, or <code><del></code> -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML <code><a></code> or <code><img></code> tags instead of Markdown's +link or image syntax, go right ahead.</p> +<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> processed within +span-level tags.</p> +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +<p>In HTML, there are two characters that demand special treatment: <code><</code> +and <code>&</code>. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. <code>&lt;</code>, and +<code>&amp;</code>.</p> +<p>Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '<code>AT&amp;T</code>'. You even need to +escape ampersands within URLs. Thus, if you want to link to:</p> +<pre><code>http://images.google.com/images?num=30&q=larry+bird +</code></pre> +<p>you need to encode the URL as:</p> +<pre><code>http://images.google.com/images?num=30&amp;q=larry+bird +</code></pre> +<p>in your anchor tag <code>href</code> attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites.</p> +<p>Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into <code>&amp;</code>.</p> +<p>So, if you want to include a copyright symbol in your article, you can write:</p> +<pre><code>&copy; +</code></pre> +<p>and Markdown will leave it alone. But if you write:</p> +<pre><code>AT&T +</code></pre> +<p>Markdown will translate it to:</p> +<pre><code>AT&amp;T +</code></pre> +<p>Similarly, because Markdown supports <a href="#html">inline HTML</a>, if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write:</p> +<pre><code>4 < 5 +</code></pre> +<p>Markdown will translate it to:</p> +<pre><code>4 &lt; 5 +</code></pre> +<p>However, inside Markdown code spans and blocks, angle brackets and +ampersands are <em>always</em> encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single <code><</code> +and <code>&</code> in your example code needs to be escaped.)</p> +<hr /> +<h2 id="block">Block Elements</h2> + +<h3 id="p">Paragraphs and Line Breaks</h3> + +<p>A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs.</p> +<p>The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a <code><br /></code> tag.</p> +<p>When you <em>do</em> want to insert a <code><br /></code> break tag using Markdown, you +end a line with two or more spaces, then type return.</p> +<p>Yes, this takes a tad more effort to create a <code><br /></code>, but a simplistic +"every line break is a <code><br /></code>" rule wouldn't work for Markdown. +Markdown's email-style <a href="#blockquote">blockquoting</a> and multi-paragraph <a href="#list">list items</a> +work best -- and look better -- when you format them with hard breaks.</p> +<h3 id="header">Headers</h3> + +<p>Markdown supports two styles of headers, <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and <a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> +<p>Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example:</p> +<pre><code>This is an H1 +============= + +This is an H2 +------------- +</code></pre> +<p>Any number of underlining <code>=</code>'s or <code>-</code>'s will work.</p> +<p>Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example:</p> +<pre><code># This is an H1 + +## This is an H2 + +###### This is an H6 +</code></pre> +<p>Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) :</p> +<pre><code># This is an H1 # + +## This is an H2 ## + +### This is an H3 ###### +</code></pre> +<h3 id="blockquote">Blockquotes</h3> + +<p>Markdown uses email-style <code>></code> characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a <code>></code> before every line:</p> +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. +> +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +> id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>Markdown allows you to be lazy and only put the <code>></code> before the first +line of a hard-wrapped paragraph:</p> +<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, +consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. +Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + +> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse +id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of <code>></code>:</p> +<pre><code>> This is the first level of quoting. +> +> > This is nested blockquote. +> +> Back to the first level. +</code></pre> +<p>Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks:</p> +<pre><code>> ## This is a header. +> +> 1. This is the first list item. +> 2. This is the second list item. +> +> Here's some example code: +> +> return shell_exec("echo $input | $markdown_script"); +</code></pre> +<p>Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu.</p> +<h3 id="list">Lists</h3> + +<p>Markdown supports ordered (numbered) and unordered (bulleted) lists.</p> +<p>Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers:</p> +<pre><code>* Red +* Green +* Blue +</code></pre> +<p>is equivalent to:</p> +<pre><code>+ Red ++ Green ++ Blue +</code></pre> +<p>and:</p> +<pre><code>- Red +- Green +- Blue +</code></pre> +<p>Ordered lists use numbers followed by periods:</p> +<pre><code>1. Bird +2. McHale +3. Parish +</code></pre> +<p>It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is:</p> +<pre><code><ol> +<li>Bird</li> +<li>McHale</li> +<li>Parish</li> +</ol> +</code></pre> +<p>If you instead wrote the list in Markdown like this:</p> +<pre><code>1. Bird +1. McHale +1. Parish +</code></pre> +<p>or even:</p> +<pre><code>3. Bird +1. McHale +8. Parish +</code></pre> +<p>you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to.</p> +<p>If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number.</p> +<p>List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab.</p> +<p>To make lists look nice, you can wrap items with hanging indents:</p> +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>But if you want to be lazy, you don't have to:</p> +<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. +Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, +viverra nec, fringilla in, laoreet vitae, risus. +* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. +Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>If list items are separated by blank lines, Markdown will wrap the +items in <code><p></code> tags in the HTML output. For example, this input:</p> +<pre><code>* Bird +* Magic +</code></pre> +<p>will turn into:</p> +<pre><code><ul> +<li>Bird</li> +<li>Magic</li> +</ul> +</code></pre> +<p>But this:</p> +<pre><code>* Bird + +* Magic +</code></pre> +<p>will turn into:</p> +<pre><code><ul> +<li><p>Bird</p></li> +<li><p>Magic</p></li> +</ul> +</code></pre> +<p>List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab:</p> +<pre><code>1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + +2. Suspendisse id sem consectetuer libero luctus adipiscing. +</code></pre> +<p>It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy:</p> +<pre><code>* This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're +only required to indent the first line. Lorem ipsum dolor +sit amet, consectetuer adipiscing elit. + +* Another item in the same list. +</code></pre> +<p>To put a blockquote within a list item, the blockquote's <code>></code> +delimiters need to be indented:</p> +<pre><code>* A list item with a blockquote: + + > This is a blockquote + > inside a list item. +</code></pre> +<p>To put a code block within a list item, the code block needs +to be indented <em>twice</em> -- 8 spaces or two tabs:</p> +<pre><code>* A list item with a code block: + + <code goes here> +</code></pre> +<p>It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this:</p> +<pre><code>1986. What a great season. +</code></pre> +<p>In other words, a <em>number-period-space</em> sequence at the beginning of a +line. To avoid this, you can backslash-escape the period:</p> +<pre><code>1986\. What a great season. +</code></pre> +<h3 id="precode">Code Blocks</h3> + +<p>Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both <code><pre></code> and <code><code></code> tags.</p> +<p>To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input:</p> +<pre><code>This is a normal paragraph: + + This is a code block. +</code></pre> +<p>Markdown will generate:</p> +<pre><code><p>This is a normal paragraph:</p> + +<pre><code>This is a code block. +</code></pre> +</code></pre> +<p>One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this:</p> +<pre><code>Here is an example of AppleScript: + + tell application "Foo" + beep + end tell +</code></pre> +<p>will turn into:</p> +<pre><code><p>Here is an example of AppleScript:</p> + +<pre><code>tell application "Foo" + beep +end tell +</code></pre> +</code></pre> +<p>A code block continues until it reaches a line that is not indented +(or the end of the article).</p> +<p>Within a code block, ampersands (<code>&</code>) and angle brackets (<code><</code> and <code>></code>) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this:</p> +<pre><code> <div class="footer"> + &copy; 2004 Foo Corporation + </div> +</code></pre> +<p>will turn into:</p> +<pre><code><pre><code>&lt;div class="footer"&gt; + &amp;copy; 2004 Foo Corporation +&lt;/div&gt; +</code></pre> +</code></pre> +<p>Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax.</p> +<h3 id="hr">Horizontal Rules</h3> + +<p>You can produce a horizontal rule tag (<code><hr /></code>) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule:</p> +<pre><code>* * * + +*** + +***** + +- - - + +--------------------------------------- + +_ _ _ +</code></pre> +<hr /> +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +<p>Markdown supports two style of links: <em>inline</em> and <em>reference</em>.</p> +<p>In both styles, the link text is delimited by [square brackets].</p> +<p>To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an <em>optional</em> +title for the link, surrounded in quotes. For example:</p> +<pre><code>This is [an example](http://example.com/ "Title") inline link. + +[This link](http://example.net/) has no title attribute. +</code></pre> +<p>Will produce:</p> +<pre><code><p>This is <a href="http://example.com/" title="Title"> +an example</a> inline link.</p> + +<p><a href="http://example.net/">This link</a> has no +title attribute.</p> +</code></pre> +<p>If you're referring to a local resource on the same server, you can +use relative paths:</p> +<pre><code>See my [About](/about/) page for details. +</code></pre> +<p>Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link:</p> +<pre><code>This is [an example][id] reference-style link. +</code></pre> +<p>You can optionally use a space to separate the sets of brackets:</p> +<pre><code>This is [an example] [id] reference-style link. +</code></pre> +<p>Then, anywhere in the document, you define your link label like this, +on a line by itself:</p> +<pre><code>[id]: http://example.com/ "Optional Title Here" +</code></pre> +<p>That is:</p> +<ul> +<li>Square brackets containing the link identifier (optionally +indented from the left margin using up to three spaces);</li> +<li>followed by a colon;</li> +<li>followed by one or more spaces (or tabs);</li> +<li>followed by the URL for the link;</li> +<li>optionally followed by a title attribute for the link, enclosed +in double or single quotes.</li> +</ul> +<p>The link URL may, optionally, be surrounded by angle brackets:</p> +<pre><code>[id]: <http://example.com/> "Optional Title Here" +</code></pre> +<p>You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs:</p> +<pre><code>[id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" +</code></pre> +<p>Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output.</p> +<p>Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are <em>not</em> case sensitive. E.g. these two links:</p> +<pre><code>[link text][a] +[link text][A] +</code></pre> +<p>are equivalent.</p> +<p>The <em>implicit link name</em> shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write:</p> +<pre><code>[Google][] +</code></pre> +<p>And then define the link:</p> +<pre><code>[Google]: http://google.com/ +</code></pre> +<p>Because link names may contain spaces, this shortcut even works for +multiple words in the link text:</p> +<pre><code>Visit [Daring Fireball][] for more information. +</code></pre> +<p>And then define the link:</p> +<pre><code>[Daring Fireball]: http://daringfireball.net/ +</code></pre> +<p>Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes.</p> +<p>Here's an example of reference links in action:</p> +<pre><code>I get 10 times more traffic from [Google] [1] than from +[Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Using the implicit link name shortcut, you could instead write:</p> +<pre><code>I get 10 times more traffic from [Google][] than from +[Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" +</code></pre> +<p>Both of the above examples will produce the following HTML output:</p> +<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" +title="Google">Google</a> than from +<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> +or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> +</code></pre> +<p>For comparison, here is the same paragraph written using +Markdown's inline link style:</p> +<pre><code>I get 10 times more traffic from [Google](http://google.com/ "Google") +than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or +[MSN](http://search.msn.com/ "MSN Search"). +</code></pre> +<p>The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text.</p> +<p>With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose.</p> +<h3 id="em">Emphasis</h3> + +<p>Markdown treats asterisks (<code>*</code>) and underscores (<code>_</code>) as indicators of +emphasis. Text wrapped with one <code>*</code> or <code>_</code> will be wrapped with an +HTML <code><em></code> tag; double <code>*</code>'s or <code>_</code>'s will be wrapped with an HTML +<code><strong></code> tag. E.g., this input:</p> +<pre><code>*single asterisks* + +_single underscores_ + +**double asterisks** + +__double underscores__ +</code></pre> +<p>will produce:</p> +<pre><code><em>single asterisks</em> + +<em>single underscores</em> + +<strong>double asterisks</strong> + +<strong>double underscores</strong> +</code></pre> +<p>You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span.</p> +<p>Emphasis can be used in the middle of a word:</p> +<pre><code>un*fucking*believable +</code></pre> +<p>But if you surround an <code>*</code> or <code>_</code> with spaces, it'll be treated as a +literal asterisk or underscore.</p> +<p>To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it:</p> +<pre><code>\*this text is surrounded by literal asterisks\* +</code></pre> +<h3 id="code">Code</h3> + +<p>To indicate a span of code, wrap it with backtick quotes (<code>`</code>). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example:</p> +<pre><code>Use the `printf()` function. +</code></pre> +<p>will produce:</p> +<pre><code><p>Use the <code>printf()</code> function.</p> +</code></pre> +<p>To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters:</p> +<pre><code>``There is a literal backtick (`) here.`` +</code></pre> +<p>which will produce this:</p> +<pre><code><p><code>There is a literal backtick (`) here.</code></p> +</code></pre> +<p>The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span:</p> +<pre><code>A single backtick in a code span: `` ` `` + +A backtick-delimited string in a code span: `` `foo` `` +</code></pre> +<p>will produce:</p> +<pre><code><p>A single backtick in a code span: <code>`</code></p> + +<p>A backtick-delimited string in a code span: <code>`foo`</code></p> +</code></pre> +<p>With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this:</p> +<pre><code>Please don't use any `<blink>` tags. +</code></pre> +<p>into:</p> +<pre><code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> +</code></pre> +<p>You can write this:</p> +<pre><code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. +</code></pre> +<p>to produce:</p> +<pre><code><p><code>&amp;#8212;</code> is the decimal-encoded +equivalent of <code>&amp;mdash;</code>.</p> +</code></pre> +<h3 id="img">Images</h3> + +<p>Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format.</p> +<p>Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: <em>inline</em> and <em>reference</em>.</p> +<p>Inline image syntax looks like this:</p> +<pre><code> + + +</code></pre> +<p>That is:</p> +<ul> +<li>An exclamation mark: <code>!</code>;</li> +<li>followed by a set of square brackets, containing the <code>alt</code> +attribute text for the image;</li> +<li>followed by a set of parentheses, containing the URL or path to +the image, and an optional <code>title</code> attribute enclosed in double +or single quotes.</li> +</ul> +<p>Reference-style image syntax looks like this:</p> +<pre><code>![Alt text][id] +</code></pre> +<p>Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references:</p> +<pre><code>[id]: url/to/image "Optional title attribute" +</code></pre> +<p>As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML <code><img></code> tags.</p> +<hr /> +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +<p>Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:</p> +<pre><code><http://example.com/> +</code></pre> +<p>Markdown will turn this into:</p> +<pre><code><a href="http://example.com/">http://example.com/</a> +</code></pre> +<p>Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this:</p> +<pre><code><address@example.com> +</code></pre> +<p>into something like this:</p> +<pre><code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; +&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; +&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; +&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> +</code></pre> +<p>which will render in a browser as a clickable link to "address@example.com".</p> +<p>(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.)</p> +<h3 id="backslash">Backslash Escapes</h3> + +<p>Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML <code><em></code> tag), you can backslashes +before the asterisks, like this:</p> +<pre><code>\*literal asterisks\* +</code></pre> +<p>Markdown provides backslash escapes for the following characters:</p> +<pre><code>\ backslash +` backtick +* asterisk +_ underscore +{} curly braces +[] square brackets +() parentheses +# hash mark ++ plus sign +- minus sign (hyphen) +. dot +! exclamation mark +</code></pre>
\ No newline at end of file diff --git a/tests/markdown-test/markdown-syntax.txt b/tests/markdown-test/markdown-syntax.txt new file mode 100644 index 0000000..dabd75c --- /dev/null +++ b/tests/markdown-test/markdown-syntax.txt @@ -0,0 +1,888 @@ +Markdown: Syntax +================ + +<ul id="ProjectSubmenu"> + <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> + <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> + <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> + <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> + <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> +</ul> + + +* [Overview](#overview) + * [Philosophy](#philosophy) + * [Inline HTML](#html) + * [Automatic Escaping for Special Characters](#autoescape) +* [Block Elements](#block) + * [Paragraphs and Line Breaks](#p) + * [Headers](#header) + * [Blockquotes](#blockquote) + * [Lists](#list) + * [Code Blocks](#precode) + * [Horizontal Rules](#hr) +* [Span Elements](#span) + * [Links](#link) + * [Emphasis](#em) + * [Code](#code) + * [Images](#img) +* [Miscellaneous](#misc) + * [Backslash Escapes](#backslash) + * [Automatic Links](#autolink) + + +**Note:** This document is itself written using Markdown; you +can [see the source for it by adding '.text' to the URL][src]. + + [src]: /projects/markdown/syntax.text + +* * * + +<h2 id="overview">Overview</h2> + +<h3 id="philosophy">Philosophy</h3> + +Markdown is intended to be as easy-to-read and easy-to-write as is feasible. + +Readability, however, is emphasized above all else. A Markdown-formatted +document should be publishable as-is, as plain text, without looking +like it's been marked up with tags or formatting instructions. While +Markdown's syntax has been influenced by several existing text-to-HTML +filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4], +[Grutatext] [5], and [EtText] [6] -- the single biggest source of +inspiration for Markdown's syntax is the format of plain text email. + + [1]: http://docutils.sourceforge.net/mirror/setext.html + [2]: http://www.aaronsw.com/2002/atx/ + [3]: http://textism.com/tools/textile/ + [4]: http://docutils.sourceforge.net/rst.html + [5]: http://www.triptico.com/software/grutatxt.html + [6]: http://ettext.taint.org/doc/ + +To this end, Markdown's syntax is comprised entirely of punctuation +characters, which punctuation characters have been carefully chosen so +as to look like what they mean. E.g., asterisks around a word actually +look like \*emphasis\*. Markdown lists look like, well, lists. Even +blockquotes look like quoted passages of text, assuming you've ever +used email. + + + +<h3 id="html">Inline HTML</h3> + +Markdown's syntax is intended for one purpose: to be used as a +format for *writing* for the web. + +Markdown is not a replacement for HTML, or even close to it. Its +syntax is very small, corresponding only to a very small subset of +HTML tags. The idea is *not* to create a syntax that makes it easier +to insert HTML tags. In my opinion, HTML tags are already easy to +insert. The idea for Markdown is to make it easy to read, write, and +edit prose. HTML is a *publishing* format; Markdown is a *writing* +format. Thus, Markdown's formatting syntax only addresses issues that +can be conveyed in plain text. + +For any markup that is not covered by Markdown's syntax, you simply +use HTML itself. There's no need to preface it or delimit it to +indicate that you're switching from Markdown to HTML; you just use +the tags. + +The only restrictions are that block-level HTML elements -- e.g. `<div>`, +`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding +content by blank lines, and the start and end tags of the block should +not be indented with tabs or spaces. Markdown is smart enough not +to add extra (unwanted) `<p>` tags around HTML block-level tags. + +For example, to add an HTML table to a Markdown article: + + This is a regular paragraph. + + <table> + <tr> + <td>Foo</td> + </tr> + </table> + + This is another regular paragraph. + +Note that Markdown formatting syntax is not processed within block-level +HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an +HTML block. + +Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be +used anywhere in a Markdown paragraph, list item, or header. If you +want, you can even use HTML tags instead of Markdown formatting; e.g. if +you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's +link or image syntax, go right ahead. + +Unlike block-level HTML tags, Markdown syntax *is* processed within +span-level tags. + + +<h3 id="autoescape">Automatic Escaping for Special Characters</h3> + +In HTML, there are two characters that demand special treatment: `<` +and `&`. Left angle brackets are used to start tags; ampersands are +used to denote HTML entities. If you want to use them as literal +characters, you must escape them as entities, e.g. `<`, and +`&`. + +Ampersands in particular are bedeviling for web writers. If you want to +write about 'AT&T', you need to write '`AT&T`'. You even need to +escape ampersands within URLs. Thus, if you want to link to: + + http://images.google.com/images?num=30&q=larry+bird + +you need to encode the URL as: + + http://images.google.com/images?num=30&q=larry+bird + +in your anchor tag `href` attribute. Needless to say, this is easy to +forget, and is probably the single most common source of HTML validation +errors in otherwise well-marked-up web sites. + +Markdown allows you to use these characters naturally, taking care of +all the necessary escaping for you. If you use an ampersand as part of +an HTML entity, it remains unchanged; otherwise it will be translated +into `&`. + +So, if you want to include a copyright symbol in your article, you can write: + + © + +and Markdown will leave it alone. But if you write: + + AT&T + +Markdown will translate it to: + + AT&T + +Similarly, because Markdown supports [inline HTML](#html), if you use +angle brackets as delimiters for HTML tags, Markdown will treat them as +such. But if you write: + + 4 < 5 + +Markdown will translate it to: + + 4 < 5 + +However, inside Markdown code spans and blocks, angle brackets and +ampersands are *always* encoded automatically. This makes it easy to use +Markdown to write about HTML code. (As opposed to raw HTML, which is a +terrible format for writing about HTML syntax, because every single `<` +and `&` in your example code needs to be escaped.) + + +* * * + + +<h2 id="block">Block Elements</h2> + + +<h3 id="p">Paragraphs and Line Breaks</h3> + +A paragraph is simply one or more consecutive lines of text, separated +by one or more blank lines. (A blank line is any line that looks like a +blank line -- a line containing nothing but spaces or tabs is considered +blank.) Normal paragraphs should not be intended with spaces or tabs. + +The implication of the "one or more consecutive lines of text" rule is +that Markdown supports "hard-wrapped" text paragraphs. This differs +significantly from most other text-to-HTML formatters (including Movable +Type's "Convert Line Breaks" option) which translate every line break +character in a paragraph into a `<br />` tag. + +When you *do* want to insert a `<br />` break tag using Markdown, you +end a line with two or more spaces, then type return. + +Yes, this takes a tad more effort to create a `<br />`, but a simplistic +"every line break is a `<br />`" rule wouldn't work for Markdown. +Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l] +work best -- and look better -- when you format them with hard breaks. + + [bq]: #blockquote + [l]: #list + + + +<h3 id="header">Headers</h3> + +Markdown supports two styles of headers, [Setext] [1] and [atx] [2]. + +Setext-style headers are "underlined" using equal signs (for first-level +headers) and dashes (for second-level headers). For example: + + This is an H1 + ============= + + This is an H2 + ------------- + +Any number of underlining `=`'s or `-`'s will work. + +Atx-style headers use 1-6 hash characters at the start of the line, +corresponding to header levels 1-6. For example: + + # This is an H1 + + ## This is an H2 + + ###### This is an H6 + +Optionally, you may "close" atx-style headers. This is purely +cosmetic -- you can use this if you think it looks better. The +closing hashes don't even need to match the number of hashes +used to open the header. (The number of opening hashes +determines the header level.) : + + # This is an H1 # + + ## This is an H2 ## + + ### This is an H3 ###### + + +<h3 id="blockquote">Blockquotes</h3> + +Markdown uses email-style `>` characters for blockquoting. If you're +familiar with quoting passages of text in an email message, then you +know how to create a blockquote in Markdown. It looks best if you hard +wrap the text and put a `>` before every line: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + > + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + > id sem consectetuer libero luctus adipiscing. + +Markdown allows you to be lazy and only put the `>` before the first +line of a hard-wrapped paragraph: + + > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, + consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. + Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. + + > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse + id sem consectetuer libero luctus adipiscing. + +Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by +adding additional levels of `>`: + + > This is the first level of quoting. + > + > > This is nested blockquote. + > + > Back to the first level. + +Blockquotes can contain other Markdown elements, including headers, lists, +and code blocks: + + > ## This is a header. + > + > 1. This is the first list item. + > 2. This is the second list item. + > + > Here's some example code: + > + > return shell_exec("echo $input | $markdown_script"); + +Any decent text editor should make email-style quoting easy. For +example, with BBEdit, you can make a selection and choose Increase +Quote Level from the Text menu. + + +<h3 id="list">Lists</h3> + +Markdown supports ordered (numbered) and unordered (bulleted) lists. + +Unordered lists use asterisks, pluses, and hyphens -- interchangably +-- as list markers: + + * Red + * Green + * Blue + +is equivalent to: + + + Red + + Green + + Blue + +and: + + - Red + - Green + - Blue + +Ordered lists use numbers followed by periods: + + 1. Bird + 2. McHale + 3. Parish + +It's important to note that the actual numbers you use to mark the +list have no effect on the HTML output Markdown produces. The HTML +Markdown produces from the above list is: + + <ol> + <li>Bird</li> + <li>McHale</li> + <li>Parish</li> + </ol> + +If you instead wrote the list in Markdown like this: + + 1. Bird + 1. McHale + 1. Parish + +or even: + + 3. Bird + 1. McHale + 8. Parish + +you'd get the exact same HTML output. The point is, if you want to, +you can use ordinal numbers in your ordered Markdown lists, so that +the numbers in your source match the numbers in your published HTML. +But if you want to be lazy, you don't have to. + +If you do use lazy list numbering, however, you should still start the +list with the number 1. At some point in the future, Markdown may support +starting ordered lists at an arbitrary number. + +List markers typically start at the left margin, but may be indented by +up to three spaces. List markers must be followed by one or more spaces +or a tab. + +To make lists look nice, you can wrap items with hanging indents: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +But if you want to be lazy, you don't have to: + + * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. + Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, + viverra nec, fringilla in, laoreet vitae, risus. + * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. + Suspendisse id sem consectetuer libero luctus adipiscing. + +If list items are separated by blank lines, Markdown will wrap the +items in `<p>` tags in the HTML output. For example, this input: + + * Bird + * Magic + +will turn into: + + <ul> + <li>Bird</li> + <li>Magic</li> + </ul> + +But this: + + * Bird + + * Magic + +will turn into: + + <ul> + <li><p>Bird</p></li> + <li><p>Magic</p></li> + </ul> + +List items may consist of multiple paragraphs. Each subsequent +paragraph in a list item must be intended by either 4 spaces +or one tab: + + 1. This is a list item with two paragraphs. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. Aliquam hendrerit + mi posuere lectus. + + Vestibulum enim wisi, viverra nec, fringilla in, laoreet + vitae, risus. Donec sit amet nisl. Aliquam semper ipsum + sit amet velit. + + 2. Suspendisse id sem consectetuer libero luctus adipiscing. + +It looks nice if you indent every line of the subsequent +paragraphs, but here again, Markdown will allow you to be +lazy: + + * This is a list item with two paragraphs. + + This is the second paragraph in the list item. You're + only required to indent the first line. Lorem ipsum dolor + sit amet, consectetuer adipiscing elit. + + * Another item in the same list. + +To put a blockquote within a list item, the blockquote's `>` +delimiters need to be indented: + + * A list item with a blockquote: + + > This is a blockquote + > inside a list item. + +To put a code block within a list item, the code block needs +to be indented *twice* -- 8 spaces or two tabs: + + * A list item with a code block: + + <code goes here> + + +It's worth noting that it's possible to trigger an ordered list by +accident, by writing something like this: + + 1986. What a great season. + +In other words, a *number-period-space* sequence at the beginning of a +line. To avoid this, you can backslash-escape the period: + + 1986\. What a great season. + + + +<h3 id="precode">Code Blocks</h3> + +Pre-formatted code blocks are used for writing about programming or +markup source code. Rather than forming normal paragraphs, the lines +of a code block are interpreted literally. Markdown wraps a code block +in both `<pre>` and `<code>` tags. + +To produce a code block in Markdown, simply indent every line of the +block by at least 4 spaces or 1 tab. For example, given this input: + + This is a normal paragraph: + + This is a code block. + +Markdown will generate: + + <p>This is a normal paragraph:</p> + + <pre><code>This is a code block. + </code></pre> + +One level of indentation -- 4 spaces or 1 tab -- is removed from each +line of the code block. For example, this: + + Here is an example of AppleScript: + + tell application "Foo" + beep + end tell + +will turn into: + + <p>Here is an example of AppleScript:</p> + + <pre><code>tell application "Foo" + beep + end tell + </code></pre> + +A code block continues until it reaches a line that is not indented +(or the end of the article). + +Within a code block, ampersands (`&`) and angle brackets (`<` and `>`) +are automatically converted into HTML entities. This makes it very +easy to include example HTML source code using Markdown -- just paste +it and indent it, and Markdown will handle the hassle of encoding the +ampersands and angle brackets. For example, this: + + <div class="footer"> + © 2004 Foo Corporation + </div> + +will turn into: + + <pre><code><div class="footer"> + &copy; 2004 Foo Corporation + </div> + </code></pre> + +Regular Markdown syntax is not processed within code blocks. E.g., +asterisks are just literal asterisks within a code block. This means +it's also easy to use Markdown to write about Markdown's own syntax. + + + +<h3 id="hr">Horizontal Rules</h3> + +You can produce a horizontal rule tag (`<hr />`) by placing three or +more hyphens, asterisks, or underscores on a line by themselves. If you +wish, you may use spaces between the hyphens or asterisks. Each of the +following lines will produce a horizontal rule: + + * * * + + *** + + ***** + + - - - + + --------------------------------------- + + _ _ _ + + +* * * + +<h2 id="span">Span Elements</h2> + +<h3 id="link">Links</h3> + +Markdown supports two style of links: *inline* and *reference*. + +In both styles, the link text is delimited by [square brackets]. + +To create an inline link, use a set of regular parentheses immediately +after the link text's closing square bracket. Inside the parentheses, +put the URL where you want the link to point, along with an *optional* +title for the link, surrounded in quotes. For example: + + This is [an example](http://example.com/ "Title") inline link. + + [This link](http://example.net/) has no title attribute. + +Will produce: + + <p>This is <a href="http://example.com/" title="Title"> + an example</a> inline link.</p> + + <p><a href="http://example.net/">This link</a> has no + title attribute.</p> + +If you're referring to a local resource on the same server, you can +use relative paths: + + See my [About](/about/) page for details. + +Reference-style links use a second set of square brackets, inside +which you place a label of your choosing to identify the link: + + This is [an example][id] reference-style link. + +You can optionally use a space to separate the sets of brackets: + + This is [an example] [id] reference-style link. + +Then, anywhere in the document, you define your link label like this, +on a line by itself: + + [id]: http://example.com/ "Optional Title Here" + +That is: + +* Square brackets containing the link identifier (optionally + indented from the left margin using up to three spaces); +* followed by a colon; +* followed by one or more spaces (or tabs); +* followed by the URL for the link; +* optionally followed by a title attribute for the link, enclosed + in double or single quotes. + +The link URL may, optionally, be surrounded by angle brackets: + + [id]: <http://example.com/> "Optional Title Here" + +You can put the title attribute on the next line and use extra spaces +or tabs for padding, which tends to look better with longer URLs: + + [id]: http://example.com/longish/path/to/resource/here + "Optional Title Here" + +Link definitions are only used for creating links during Markdown +processing, and are stripped from your document in the HTML output. + +Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links: + + [link text][a] + [link text][A] + +are equivalent. + +The *implicit link name* shortcut allows you to omit the name of the +link, in which case the link text itself is used as the name. +Just use an empty set of square brackets -- e.g., to link the word +"Google" to the google.com web site, you could simply write: + + [Google][] + +And then define the link: + + [Google]: http://google.com/ + +Because link names may contain spaces, this shortcut even works for +multiple words in the link text: + + Visit [Daring Fireball][] for more information. + +And then define the link: + + [Daring Fireball]: http://daringfireball.net/ + +Link definitions can be placed anywhere in your Markdown document. I +tend to put them immediately after each paragraph in which they're +used, but if you want, you can put them all at the end of your +document, sort of like footnotes. + +Here's an example of reference links in action: + + I get 10 times more traffic from [Google] [1] than from + [Yahoo] [2] or [MSN] [3]. + + [1]: http://google.com/ "Google" + [2]: http://search.yahoo.com/ "Yahoo Search" + [3]: http://search.msn.com/ "MSN Search" + +Using the implicit link name shortcut, you could instead write: + + I get 10 times more traffic from [Google][] than from + [Yahoo][] or [MSN][]. + + [google]: http://google.com/ "Google" + [yahoo]: http://search.yahoo.com/ "Yahoo Search" + [msn]: http://search.msn.com/ "MSN Search" + +Both of the above examples will produce the following HTML output: + + <p>I get 10 times more traffic from <a href="http://google.com/" + title="Google">Google</a> than from + <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> + or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> + +For comparison, here is the same paragraph written using +Markdown's inline link style: + + I get 10 times more traffic from [Google](http://google.com/ "Google") + than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or + [MSN](http://search.msn.com/ "MSN Search"). + +The point of reference-style links is not that they're easier to +write. The point is that with reference-style links, your document +source is vastly more readable. Compare the above examples: using +reference-style links, the paragraph itself is only 81 characters +long; with inline-style links, it's 176 characters; and as raw HTML, +it's 234 characters. In the raw HTML, there's more markup than there +is text. + +With Markdown's reference-style links, a source document much more +closely resembles the final output, as rendered in a browser. By +allowing you to move the markup-related metadata out of the paragraph, +you can add links without interrupting the narrative flow of your +prose. + + +<h3 id="em">Emphasis</h3> + +Markdown treats asterisks (`*`) and underscores (`_`) as indicators of +emphasis. Text wrapped with one `*` or `_` will be wrapped with an +HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML +`<strong>` tag. E.g., this input: + + *single asterisks* + + _single underscores_ + + **double asterisks** + + __double underscores__ + +will produce: + + <em>single asterisks</em> + + <em>single underscores</em> + + <strong>double asterisks</strong> + + <strong>double underscores</strong> + +You can use whichever style you prefer; the lone restriction is that +the same character must be used to open and close an emphasis span. + +Emphasis can be used in the middle of a word: + + un*fucking*believable + +But if you surround an `*` or `_` with spaces, it'll be treated as a +literal asterisk or underscore. + +To produce a literal asterisk or underscore at a position where it +would otherwise be used as an emphasis delimiter, you can backslash +escape it: + + \*this text is surrounded by literal asterisks\* + + + +<h3 id="code">Code</h3> + +To indicate a span of code, wrap it with backtick quotes (`` ` ``). +Unlike a pre-formatted code block, a code span indicates code within a +normal paragraph. For example: + + Use the `printf()` function. + +will produce: + + <p>Use the <code>printf()</code> function.</p> + +To include a literal backtick character within a code span, you can use +multiple backticks as the opening and closing delimiters: + + ``There is a literal backtick (`) here.`` + +which will produce this: + + <p><code>There is a literal backtick (`) here.</code></p> + +The backtick delimiters surrounding a code span may include spaces -- +one after the opening, one before the closing. This allows you to place +literal backtick characters at the beginning or end of a code span: + + A single backtick in a code span: `` ` `` + + A backtick-delimited string in a code span: `` `foo` `` + +will produce: + + <p>A single backtick in a code span: <code>`</code></p> + + <p>A backtick-delimited string in a code span: <code>`foo`</code></p> + +With a code span, ampersands and angle brackets are encoded as HTML +entities automatically, which makes it easy to include example HTML +tags. Markdown will turn this: + + Please don't use any `<blink>` tags. + +into: + + <p>Please don't use any <code><blink></code> tags.</p> + +You can write this: + + `—` is the decimal-encoded equivalent of `—`. + +to produce: + + <p><code>&#8212;</code> is the decimal-encoded + equivalent of <code>&mdash;</code>.</p> + + + +<h3 id="img">Images</h3> + +Admittedly, it's fairly difficult to devise a "natural" syntax for +placing images into a plain text document format. + +Markdown uses an image syntax that is intended to resemble the syntax +for links, allowing for two styles: *inline* and *reference*. + +Inline image syntax looks like this: + +  + +  + +That is: + +* An exclamation mark: `!`; +* followed by a set of square brackets, containing the `alt` + attribute text for the image; +* followed by a set of parentheses, containing the URL or path to + the image, and an optional `title` attribute enclosed in double + or single quotes. + +Reference-style image syntax looks like this: + + ![Alt text][id] + +Where "id" is the name of a defined image reference. Image references +are defined using syntax identical to link references: + + [id]: url/to/image "Optional title attribute" + +As of this writing, Markdown has no syntax for specifying the +dimensions of an image; if this is important to you, you can simply +use regular HTML `<img>` tags. + + +* * * + + +<h2 id="misc">Miscellaneous</h2> + +<h3 id="autolink">Automatic Links</h3> + +Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this: + + <http://example.com/> + +Markdown will turn this into: + + <a href="http://example.com/">http://example.com/</a> + +Automatic links for email addresses work similarly, except that +Markdown will also perform a bit of randomized decimal and hex +entity-encoding to help obscure your address from address-harvesting +spambots. For example, Markdown will turn this: + + <address@example.com> + +into something like this: + + <a href="mailto:addre + ss@example.co + m">address@exa + mple.com</a> + +which will render in a browser as a clickable link to "address@example.com". + +(This sort of entity-encoding trick will indeed fool many, if not +most, address-harvesting bots, but it definitely won't fool all of +them. It's better than nothing, but an address published in this way +will probably eventually start receiving spam.) + + + +<h3 id="backslash">Backslash Escapes</h3> + +Markdown allows you to use backslash escapes to generate literal +characters which would otherwise have special meaning in Markdown's +formatting syntax. For example, if you wanted to surround a word with +literal asterisks (instead of an HTML `<em>` tag), you can backslashes +before the asterisks, like this: + + \*literal asterisks\* + +Markdown provides backslash escapes for the following characters: + + \ backslash + ` backtick + * asterisk + _ underscore + {} curly braces + [] square brackets + () parentheses + # hash mark + + plus sign + - minus sign (hyphen) + . dot + ! exclamation mark + diff --git a/tests/markdown-test/nested-blockquotes.html b/tests/markdown-test/nested-blockquotes.html new file mode 100644 index 0000000..f1b017e --- /dev/null +++ b/tests/markdown-test/nested-blockquotes.html @@ -0,0 +1,7 @@ +<blockquote> +<p>foo</p> +<blockquote> +<p>bar</p> +</blockquote> +<p>foo</p> +</blockquote>
\ No newline at end of file diff --git a/tests/markdown-test/nested-blockquotes.txt b/tests/markdown-test/nested-blockquotes.txt new file mode 100644 index 0000000..ed3c624 --- /dev/null +++ b/tests/markdown-test/nested-blockquotes.txt @@ -0,0 +1,5 @@ +> foo +> +> > bar +> +> foo diff --git a/tests/markdown-test/ordered-and-unordered-list.html b/tests/markdown-test/ordered-and-unordered-list.html new file mode 100644 index 0000000..090c43c --- /dev/null +++ b/tests/markdown-test/ordered-and-unordered-list.html @@ -0,0 +1,146 @@ +<h2>Unordered</h2> +<p>Asterisks tight:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +<p>Asterisks loose:</p> +<ul> +<li> +<p>asterisk 1</p> +</li> +<li> +<p>asterisk 2</p> +</li> +<li> +<p>asterisk 3</p> +</li> +</ul> +<hr /> +<p>Pluses tight:</p> +<ul> +<li>Plus 1</li> +<li>Plus 2</li> +<li>Plus 3</li> +</ul> +<p>Pluses loose:</p> +<ul> +<li> +<p>Plus 1</p> +</li> +<li> +<p>Plus 2</p> +</li> +<li> +<p>Plus 3</p> +</li> +</ul> +<hr /> +<p>Minuses tight:</p> +<ul> +<li>Minus 1</li> +<li>Minus 2</li> +<li>Minus 3</li> +</ul> +<p>Minuses loose:</p> +<ul> +<li> +<p>Minus 1</p> +</li> +<li> +<p>Minus 2</p> +</li> +<li> +<p>Minus 3</p> +</li> +</ul> +<h2>Ordered</h2> +<p>Tight:</p> +<ol> +<li>First</li> +<li>Second</li> +<li>Third</li> +</ol> +<p>and:</p> +<ol> +<li>One</li> +<li>Two</li> +<li>Three</li> +</ol> +<p>Loose using tabs:</p> +<ol> +<li> +<p>First</p> +</li> +<li> +<p>Second</p> +</li> +<li> +<p>Third</p> +</li> +</ol> +<p>and using spaces:</p> +<ol> +<li> +<p>One</p> +</li> +<li> +<p>Two</p> +</li> +<li> +<p>Three</p> +</li> +</ol> +<p>Multiple paragraphs:</p> +<ol> +<li> +<p>Item 1, graf one.</p> +<p>Item 2. graf two. The quick brown fox jumped over the lazy dog's +back.</p> +</li> +<li> +<p>Item 2.</p> +</li> +<li> +<p>Item 3.</p> +</li> +</ol> +<h2>Nested</h2> +<ul> +<li>Tab<ul> +<li>Tab<ul> +<li>Tab</li> +</ul> +</li> +</ul> +</li> +</ul> +<p>Here's another:</p> +<ol> +<li>First</li> +<li>Second:<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul> +</li> +<li>Third</li> +</ol> +<p>Same thing but with paragraphs:</p> +<ol> +<li> +<p>First</p> +</li> +<li> +<p>Second:</p> +<ul> +<li>Fee</li> +<li>Fie</li> +<li>Foe</li> +</ul> +</li> +<li> +<p>Third</p> +</li> +</ol>
\ No newline at end of file diff --git a/tests/markdown-test/ordered-and-unordered-list.txt b/tests/markdown-test/ordered-and-unordered-list.txt new file mode 100644 index 0000000..621db58 --- /dev/null +++ b/tests/markdown-test/ordered-and-unordered-list.txt @@ -0,0 +1,122 @@ +## Unordered + +Asterisks tight: + +* asterisk 1 +* asterisk 2 +* asterisk 3 + + +Asterisks loose: + +* asterisk 1 + +* asterisk 2 + +* asterisk 3 + +* * * + +Pluses tight: + ++ Plus 1 ++ Plus 2 ++ Plus 3 + + +Pluses loose: + ++ Plus 1 + ++ Plus 2 + ++ Plus 3 + +* * * + + +Minuses tight: + +- Minus 1 +- Minus 2 +- Minus 3 + + +Minuses loose: + +- Minus 1 + +- Minus 2 + +- Minus 3 + + +## Ordered + +Tight: + +1. First +2. Second +3. Third + +and: + +1. One +2. Two +3. Three + + +Loose using tabs: + +1. First + +2. Second + +3. Third + +and using spaces: + +1. One + +2. Two + +3. Three + +Multiple paragraphs: + +1. Item 1, graf one. + + Item 2. graf two. The quick brown fox jumped over the lazy dog's + back. + +2. Item 2. + +3. Item 3. + + + +## Nested + +* Tab + * Tab + * Tab + +Here's another: + +1. First +2. Second: + * Fee + * Fie + * Foe +3. Third + +Same thing but with paragraphs: + +1. First + +2. Second: + * Fee + * Fie + * Foe + +3. Third diff --git a/tests/markdown-test/strong-and-em-together.html b/tests/markdown-test/strong-and-em-together.html new file mode 100644 index 0000000..7bf5163 --- /dev/null +++ b/tests/markdown-test/strong-and-em-together.html @@ -0,0 +1,4 @@ +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p>
\ No newline at end of file diff --git a/tests/markdown-test/strong-and-em-together.txt b/tests/markdown-test/strong-and-em-together.txt new file mode 100644 index 0000000..95ee690 --- /dev/null +++ b/tests/markdown-test/strong-and-em-together.txt @@ -0,0 +1,7 @@ +***This is strong and em.*** + +So is ***this*** word. + +___This is strong and em.___ + +So is ___this___ word. diff --git a/tests/markdown-test/tabs.html b/tests/markdown-test/tabs.html new file mode 100644 index 0000000..b26391b --- /dev/null +++ b/tests/markdown-test/tabs.html @@ -0,0 +1,23 @@ +<ul> +<li> +<p>this is a list item +indented with tabs</p> +</li> +<li> +<p>this is a list item +indented with spaces</p> +</li> +</ul> +<p>Code:</p> +<pre><code>this code block is indented by one tab +</code></pre> +<p>And:</p> +<pre><code> this code block is indented by two tabs +</code></pre> +<p>And:</p> +<pre><code>+ this is an example list item + indented with tabs + ++ this is an example list item + indented with spaces +</code></pre>
\ No newline at end of file diff --git a/tests/markdown-test/tabs.txt b/tests/markdown-test/tabs.txt new file mode 100644 index 0000000..589d113 --- /dev/null +++ b/tests/markdown-test/tabs.txt @@ -0,0 +1,21 @@ ++ this is a list item + indented with tabs + ++ this is a list item + indented with spaces + +Code: + + this code block is indented by one tab + +And: + + this code block is indented by two tabs + +And: + + + this is an example list item + indented with tabs + + + this is an example list item + indented with spaces diff --git a/tests/markdown-test/tidyness.html b/tests/markdown-test/tidyness.html new file mode 100644 index 0000000..52b2eaf --- /dev/null +++ b/tests/markdown-test/tidyness.html @@ -0,0 +1,8 @@ +<blockquote> +<p>A list within a blockquote:</p> +<ul> +<li>asterisk 1</li> +<li>asterisk 2</li> +<li>asterisk 3</li> +</ul> +</blockquote>
\ No newline at end of file diff --git a/tests/markdown-test/tidyness.txt b/tests/markdown-test/tidyness.txt new file mode 100644 index 0000000..5f18b8d --- /dev/null +++ b/tests/markdown-test/tidyness.txt @@ -0,0 +1,5 @@ +> A list within a blockquote: +> +> * asterisk 1 +> * asterisk 2 +> * asterisk 3 diff --git a/tests/misc/CRLF_line_ends.html b/tests/misc/CRLF_line_ends.html new file mode 100644 index 0000000..a72b1ca --- /dev/null +++ b/tests/misc/CRLF_line_ends.html @@ -0,0 +1,4 @@ +<p>foo</p> +<div> +bar +</div>
\ No newline at end of file diff --git a/tests/misc/CRLF_line_ends.txt b/tests/misc/CRLF_line_ends.txt new file mode 100644 index 0000000..7d5e324 --- /dev/null +++ b/tests/misc/CRLF_line_ends.txt @@ -0,0 +1,5 @@ +foo
+
+<div>
+bar
+</div>
diff --git a/tests/misc/adjacent-headers.html b/tests/misc/adjacent-headers.html new file mode 100644 index 0000000..bd171aa --- /dev/null +++ b/tests/misc/adjacent-headers.html @@ -0,0 +1,2 @@ +<h1>this is a huge header</h1> +<h2>this is a smaller header</h2>
\ No newline at end of file diff --git a/tests/misc/adjacent-headers.txt b/tests/misc/adjacent-headers.txt new file mode 100644 index 0000000..0e626b9 --- /dev/null +++ b/tests/misc/adjacent-headers.txt @@ -0,0 +1,2 @@ +# this is a huge header # +## this is a smaller header ## diff --git a/tests/misc/amp-in-url.html b/tests/misc/amp-in-url.html new file mode 100644 index 0000000..2170a54 --- /dev/null +++ b/tests/misc/amp-in-url.html @@ -0,0 +1 @@ +<p><a href="http://www.freewisdom.org/this&that">link</a></p>
\ No newline at end of file diff --git a/tests/misc/amp-in-url.txt b/tests/misc/amp-in-url.txt new file mode 100644 index 0000000..471106e --- /dev/null +++ b/tests/misc/amp-in-url.txt @@ -0,0 +1 @@ +[link](http://www.freewisdom.org/this&that) diff --git a/tests/misc/ampersand.html b/tests/misc/ampersand.html new file mode 100644 index 0000000..94ed80c --- /dev/null +++ b/tests/misc/ampersand.html @@ -0,0 +1,2 @@ +<p>&</p> +<p>AT&T</p>
\ No newline at end of file diff --git a/tests/misc/ampersand.txt b/tests/misc/ampersand.txt new file mode 100644 index 0000000..367d32c --- /dev/null +++ b/tests/misc/ampersand.txt @@ -0,0 +1,5 @@ +& + +AT&T + + diff --git a/tests/misc/arabic.html b/tests/misc/arabic.html new file mode 100644 index 0000000..55991de --- /dev/null +++ b/tests/misc/arabic.html @@ -0,0 +1,27 @@ +<h1>بايثون</h1> +<p><strong>بايثون</strong> لغة برمجة حديثة بسيطة، واضحة، سريعة ، تستخدم أسلوب البرمجة الكائنية (OOP) وقابلة للتطوير بالإضافة إلى أنها مجانية و مفتوحة المصدر. صُنفت بالأساس كلغة تفسيرية ، بايثون مصممة أصلاً للأداء بعض المهام الخاصة أو المحدودة. إلا أنه يمكن استخدامها بايثون لإنجاز المشاريع الضخمه كأي لغة برمجية أخرى، غالباً ما يُنصح المبتدئين في ميدان البرمجة بتعلم هذه اللغة لأنها من بين أسهل اللغات البرمجية تعلماً.</p> +<p>نشأت بايثون في مركز CWI (مركز العلوم والحاسب الآلي) بأمستردام على يد جويدو فان رُزوم. تم تطويرها بلغة C. أطلق فان رُزوم اسم "بايثون" على لغته تعبيرًا عن إعجابه بفِرقَة مسرحية هزلية شهيرة من بريطانيا، كانت تطلق على نفسها اسم مونتي بايثون Monty Python.</p> +<p>تتميز بايثون بمجتمعها النشط ، كما أن لها الكثير من المكتبات البرمجية ذات الأغراض الخاصة والتي برمجها أشخاص من مجتمع هذه اللغة ، مثلاً مكتبة PyGame التي توفر مجموعه من الوظائف من اجل برمجة الالعاب. ويمكن لبايثون التعامل مع العديد من أنواع قواعد البيانات مثل MySQL وغيره.</p> +<h2>أمثلة</h2> +<p>مثال Hello World!</p> +<pre><code>print "Hello World!" +</code></pre> +<p>مثال لاستخراج المضروب Factorial :</p> +<pre><code>num = 1 +x = raw_input('Insert the number please ') +x = int(x) + +if x > 69: + print 'Math Error !' +else: + while x > 1: + num *= x + x = x-1 + + print num +</code></pre> +<h2>وصلات خارجية</h2> +<ul> +<li><a href="http://www.python.org">الموقع الرسمي للغة بايثون</a></li> +</ul> +<p>بذرة حاس </p>
\ No newline at end of file diff --git a/tests/misc/arabic.txt b/tests/misc/arabic.txt new file mode 100644 index 0000000..ba2fef4 --- /dev/null +++ b/tests/misc/arabic.txt @@ -0,0 +1,37 @@ + +بايثون +===== + +**بايثون** لغة برمجة حديثة بسيطة، واضحة، سريعة ، تستخدم أسلوب البرمجة الكائنية (OOP) وقابلة للتطوير بالإضافة إلى أنها مجانية و مفتوحة المصدر. صُنفت بالأساس كلغة تفسيرية ، بايثون مصممة أصلاً للأداء بعض المهام الخاصة أو المحدودة. إلا أنه يمكن استخدامها بايثون لإنجاز المشاريع الضخمه كأي لغة برمجية أخرى، غالباً ما يُنصح المبتدئين في ميدان البرمجة بتعلم هذه اللغة لأنها من بين أسهل اللغات البرمجية تعلماً. + +نشأت بايثون في مركز CWI (مركز العلوم والحاسب الآلي) بأمستردام على يد جويدو فان رُزوم. تم تطويرها بلغة C. أطلق فان رُزوم اسم "بايثون" على لغته تعبيرًا عن إعجابه بفِرقَة مسرحية هزلية شهيرة من بريطانيا، كانت تطلق على نفسها اسم مونتي بايثون Monty Python. + +تتميز بايثون بمجتمعها النشط ، كما أن لها الكثير من المكتبات البرمجية ذات الأغراض الخاصة والتي برمجها أشخاص من مجتمع هذه اللغة ، مثلاً مكتبة PyGame التي توفر مجموعه من الوظائف من اجل برمجة الالعاب. ويمكن لبايثون التعامل مع العديد من أنواع قواعد البيانات مثل MySQL وغيره. + +##أمثلة +مثال Hello World! + + print "Hello World!" + + +مثال لاستخراج المضروب Factorial : + + num = 1 + x = raw_input('Insert the number please ') + x = int(x) + + if x > 69: + print 'Math Error !' + else: + while x > 1: + num *= x + x = x-1 + + print num + + + +##وصلات خارجية +* [الموقع الرسمي للغة بايثون](http://www.python.org) + + بذرة حاس diff --git a/tests/misc/attributes2.html b/tests/misc/attributes2.html new file mode 100644 index 0000000..5971cc8 --- /dev/null +++ b/tests/misc/attributes2.html @@ -0,0 +1,6 @@ +<p id="TABLE.OF.CONTENTS" /> +<ul> +<li id="TABLEOFCONTENTS" /> +</ul> +<p id="TABLEOFCONTENTS">Or in the middle of the text </p> +<p id="tableofcontents" />
\ No newline at end of file diff --git a/tests/misc/attributes2.txt b/tests/misc/attributes2.txt new file mode 100644 index 0000000..d635cb2 --- /dev/null +++ b/tests/misc/attributes2.txt @@ -0,0 +1,10 @@ +{@id=TABLE.OF.CONTENTS} + + +* {@id=TABLEOFCONTENTS} + + +Or in the middle of the text {@id=TABLEOFCONTENTS} + +{@id=tableofcontents} + diff --git a/tests/misc/autolinks_with_asterisks.html b/tests/misc/autolinks_with_asterisks.html new file mode 100644 index 0000000..7cb852f --- /dev/null +++ b/tests/misc/autolinks_with_asterisks.html @@ -0,0 +1 @@ +<p><a href="http://some.site/weird*url*thing">http://some.site/weird*url*thing</a></p>
\ No newline at end of file diff --git a/tests/misc/autolinks_with_asterisks.txt b/tests/misc/autolinks_with_asterisks.txt new file mode 100644 index 0000000..24de5d9 --- /dev/null +++ b/tests/misc/autolinks_with_asterisks.txt @@ -0,0 +1,2 @@ +<http://some.site/weird*url*thing> + diff --git a/tests/misc/autolinks_with_asterisks_russian.html b/tests/misc/autolinks_with_asterisks_russian.html new file mode 100644 index 0000000..64cd635 --- /dev/null +++ b/tests/misc/autolinks_with_asterisks_russian.html @@ -0,0 +1 @@ +<p><a href="http://some.site/нечто*очень*странное">http://some.site/нечто*очень*странное</a></p>
\ No newline at end of file diff --git a/tests/misc/autolinks_with_asterisks_russian.txt b/tests/misc/autolinks_with_asterisks_russian.txt new file mode 100644 index 0000000..74465f1 --- /dev/null +++ b/tests/misc/autolinks_with_asterisks_russian.txt @@ -0,0 +1,3 @@ +<http://some.site/нечто*очень*странное> + + diff --git a/tests/misc/backtick-escape.html b/tests/misc/backtick-escape.html new file mode 100644 index 0000000..07f5115 --- /dev/null +++ b/tests/misc/backtick-escape.html @@ -0,0 +1,3 @@ +<p>\`This should not be in code.\` +`This also should not be in code.` +`And finally this should not be in code.`</p>
\ No newline at end of file diff --git a/tests/misc/backtick-escape.txt b/tests/misc/backtick-escape.txt new file mode 100644 index 0000000..b4d80b2 --- /dev/null +++ b/tests/misc/backtick-escape.txt @@ -0,0 +1,3 @@ +\\`This should not be in code.\\` +\`This also should not be in code.\` +\`And finally this should not be in code.` diff --git a/tests/misc/benchmark.dat b/tests/misc/benchmark.dat new file mode 100644 index 0000000..ac0334c --- /dev/null +++ b/tests/misc/benchmark.dat @@ -0,0 +1,56 @@ +construction:0.000000:0.000000 +CRLF_line_ends:0.020000:0.000000 +adjacent-headers:0.020000:0.000000 +amp-in-url:0.020000:0.000000 +ampersand:0.010000:0.000000 +arabic:0.110000:0.000000 +attributes2:0.020000:0.000000 +bidi:0.310000:0.000000 +blank-block-quote:0.010000:0.000000 +blockquote:0.090000:0.000000 +blockquote-hr:0.060000:0.000000 +bold_links:0.020000:0.000000 +br:0.040000:0.000000 +bracket_re:7.490000:0.000000 +code-first-line:0.020000:0.000000 +comments:0.040000:0.000000 +div:0.040000:0.000000 +email:0.030000:0.000000 +funky-list:0.060000:0.000000 +h1:0.040000:0.000000 +hash:0.040000:0.000000 +headers:0.060000:0.000000 +hline:0.020000:0.000000 +html:0.090000:0.000000 +image:0.040000:0.000000 +image-2:0.060000:0.000000 +image_in_links:0.060000:0.000000 +inside_html:0.040000:0.000000 +japanese:0.150000:0.000000 +lazy-block-quote:0.050000:0.000000 +lists:0.110000:0.000000 +lists2:0.040000:0.000000 +lists3:0.040000:0.000000 +lists4:0.050000:0.000000 +lists5:0.070000:0.000000 +markup-inside-p:0.080000:0.000000 +mismatched-tags:0.070000:0.000000 +more_comments:0.060000:0.000000 +multi-line-tags:0.080000:0.000000 +multi-paragraph-block-quote:0.070000:0.000000 +multi-test:0.150000:0.000000 +multiline-comments:0.090000:0.000000 +normalize:0.060000:0.000000 +numeric-entity:0.090000:0.000000 +php:0.080000:0.000000 +pre:0.080000:0.000000 +russian:0.200000:0.000000 +some-test:0.200000:0.000000 +span:0.140000:0.000000 +strong-with-underscores:0.090000:0.000000 +stronintags:0.160000:0.000000 +tabs-in-lists:0.170000:0.000000 +two-spaces:0.160000:0.000000 +uche:0.150000:0.000000 +underscores:0.120000:0.000000 +url_spaces:0.120000:0.000000 diff --git a/tests/misc/bidi.html b/tests/misc/bidi.html new file mode 100644 index 0000000..ffe04dc --- /dev/null +++ b/tests/misc/bidi.html @@ -0,0 +1,39 @@ +<p><strong>Python</strong>（パイソン）は、<a href="http://en.wikipedia.org/wiki/Guido_van_Rossum">Guido van Rossum</a> によって作られたオープンソースのオブジェクト指向スクリプト言語。<a href="http://ja.wikipedia.org/wiki/Perl">Perl</a>とともに欧米で広く普及している。イギリスのテレビ局 BBC が製作したコメディ番組『空飛ぶモンティ・パイソン』にちなんで名付けられた。 (Pythonには、爬虫類のニシキヘビの意味があり、Python言語のマスコットやアイコンとして使われることがある。)</p> +<p>|||||||||||||||||||||||||||||THIS SHOULD BE LTR|||||||||||||||||||||||||</p> +<p dir="rtl">|||||||||||||||||||||||||||||THIS SHOULD BE RTL||||||||||||||||||||||||| </p> +<p dir="ltr">(<strong>بايثون</strong> لغة برمجة حديثة بسيطة، واضحة، سريعة ، تستخدم أسلوب البرمجة الكائنية (THIS SHOULD BE LTR ) وقابلة للتطوير بالإضافة إلى أنها مجانية و مفتوح </p> +<p>پایتون زبان برنامهنویسی تفسیری و سطح بالا ، شیگرا و یک زبان برنامهنویسی تفسیری سمت سرور قدرتمند است که توسط گیدو ون روسوم در سال ۱۹۹۰ ساخته شد. این زبان در ویژگیها شبیه پرل، روبی، اسکیم، اسمالتاک و تیسیال است و از مدیریت خودکار حافظه استفاده میکند</p> +<p>Python，是一种面向对象的、直譯式的计算机程序设计语言，也是一种功能强大而完善的通用型语言，已经具有十多年的发展历史，成熟且稳定。</p> +<p>ބްލޫ ވޭލްގެ ދޫ މަތީގައި އެއްފަހަރާ 50 މީހުންނަށް ތިބެވިދާނެވެ. ބޮޑު މަހުގެ ދުލަކީ އެހާމެ ބޮޑު އެއްޗެކެވެ.</p> +<p><strong>உருது</strong> 13ஆம் நூற்றாண்டில் உருவான ஒரு இந்தோ-ஐரோப்பிய மொழியாகும். உருது, ஹிந்தியுடன் சேர்த்து "ஹிந்துஸ்தானி" என அழைக்கப்படுகின்றது. மண்டரின், ஆங்கிலம் ஆகியவற்றுக்கு அடுத்தபடியாக மூன்றாவது கூடிய அளவு மக்களால் புரிந்து கொள்ளப்படக்கூடியது ஹிந்துஸ்தானியேயாகும். தாய் மொழியாகப் பேசுபவர்கள் எண்ணிக்கையின் அடிப்படையில் உருது உலகின் 20 ஆவது பெரிய மொழியாகும். 6 கோடி மக்கள் இதனைத் தாய் மொழியாகக் கொண்டுள்ளார்கள். இரண்டாவது மொழியாகக் கொண்டுள்ளவர்கள் உட்பட 11 கோடிப் பேர் இதனைப் பேசுகிறார்கள். உருது பாகிஸ்தானின் அரசகரும மொழியாகவும், இந்தியாவின் அரசகரும மொழிகளுள் ஒன்றாகவும் விளங்குகிறது.</p> +<p>اردو ہندوآریائی زبانوں کی ہندويورپی شاخ کی ایک زبان ہے جو تيرھويں صدی ميں بر صغير ميں پيدا ہوئی ـ اردو پاکستان کی سرکاری زبان ہے اور بھارت کی سرکاری زبانوں ميں سے ايک ہے۔ اردو بھارت ميں 5 کروڑ اور پاکستان ميں 1 کروڑ لوگوں کی مادری زبان ہے مگر اسے بھارت اور پاکستان کے تقریباً 50 کروڑ لوگ بول اور سمجھ سکتے ھیں ۔ جن میں سے تقریباً 10.5 کروڑ لوگ اسے باقاعدہ بولتے ھیں۔</p> +<h1>بايثون</h1> +<p><strong>بايثون</strong> لغة برمجة حديثة بسيطة، واضحة، سريعة ، تستخدم أسلوب البرمجة الكائنية (OOP) وقابلة للتطوير بالإضافة إلى أنها مجانية و مفتوحة المصدر. صُنفت بالأساس كلغة تفسيرية ، بايثون مصممة أصلاً للأداء بعض المهام الخاصة أو المحدودة. إلا أنه يمكن استخدامها بايثون لإنجاز المشاريع الضخمه كأي لغة برمجية أخرى، غالباً ما يُنصح المبتدئين في ميدان البرمجة بتعلم هذه اللغة لأنها من بين أسهل اللغات البرمجية تعلماً.</p> +<p>|||||||||||||||||||||||||||||THIS SHOULD BE RTL|||||||||||||||||||||||||</p> +<p>(نشأت بايثون في مركز CWI (مركز العلوم والحاسب الآلي) بأمستردام على يد جويدو فان رُزوم. تم تطويرها بلغة C. أطلق فان رُزوم اسم "بايثون" على لغته تعبيرًا عن إعجابه بفِرقَة مسرحية هزلية شهيرة من بريطانيا، كانت تطلق على نفسها اسم مونتي بايثون Monty Python.</p> +<p>تتميز بايثون بمجتمعها النشط ، كما أن لها الكثير من المكتبات البرمجية ذات الأغراض الخاصة والتي برمجها أشخاص من مجتمع هذه اللغة ، مثلاً مكتبة PyGame التي توفر مجموعه من الوظائف من اجل برمجة الالعاب. ويمكن لبايثون التعامل مع العديد من أنواع قواعد البيانات مثل MySQL وغيره.</p> +<h2>أمثلة</h2> +<p>مثال Hello World!</p> +<pre><code>print "Hello World!" +</code></pre> +<p>مثال لاستخراج المضروب Factorial :</p> +<pre><code>num = 1 +x = raw_input('Insert the number please ') +x = int(x) + +if x > 69: + print 'Math Error !' +else: + while x > 1: + num *= x + x = x-1 + + print num +</code></pre> +<h2>وصلات خارجية</h2> +<ul> +<li><a href="http://www.python.org">الموقع الرسمي للغة بايثون</a></li> +</ul> +<p>بذرة حاس </p> +<p><strong>Недвард «Нед» Фландерс</strong> (Nedward «Ned» Flanders) — вымышленный персонаж мультсериала «[Симпсоны][]», озвученный Гарри Ширером. Он и его семья живут по соседству от семьи Симпсонов. Набожный христианин, Нед является одним из столпов морали Спрингфилда. В эпизоде «Alone Again, Natura-Diddily» он овдовел, его жена Мод погибла в результате несчастного случая. </p> +<p>Нед был одним из первых персонажей в мультсериале, который не был членом семьи Симпсонов. Начиная с первых серий, он регулярно появляется в «Симпсонах». Считается, что Нед Фландерс был назван в честь улицы <em>Northeast Flanders St.</em> в <a href="http://www.portland.gov">Портленде</a>, Орегон, родном городе создателя мультсериала Мэтта Грейнинга]]. Надпись на указателе улицы <em>NE Flanders St.</em> хулиганы часто исправляли на <em>NED Flanders St.</em></p>
\ No newline at end of file diff --git a/tests/misc/bidi.txt b/tests/misc/bidi.txt new file mode 100644 index 0000000..f11ff1c --- /dev/null +++ b/tests/misc/bidi.txt @@ -0,0 +1,68 @@ +**Python**（パイソン）は、[Guido van Rossum](http://en.wikipedia.org/wiki/Guido_van_Rossum) によって作られたオープンソースのオブジェクト指向スクリプト言語。[Perl](http://ja.wikipedia.org/wiki/Perl)とともに欧米で広く普及している。イギリスのテレビ局 BBC が製作したコメディ番組『空飛ぶモンティ・パイソン』にちなんで名付けられた。 (Pythonには、爬虫類のニシキヘビの意味があり、Python言語のマスコットやアイコンとして使われることがある。) + +|||||||||||||||||||||||||||||THIS SHOULD BE LTR||||||||||||||||||||||||| + +|||||||||||||||||||||||||||||THIS SHOULD BE RTL||||||||||||||||||||||||| {@dir=rtl} + + +(**بايثون** لغة برمجة حديثة بسيطة، واضحة، سريعة ، تستخدم أسلوب البرمجة الكائنية (THIS SHOULD BE LTR ) وقابلة للتطوير {@dir=ltr} بالإضافة إلى أنها مجانية و مفتوح + + + + + +پایتون زبان برنامهنویسی تفسیری و سطح بالا ، شیگرا و یک زبان برنامهنویسی تفسیری سمت سرور قدرتمند است که توسط گیدو ون روسوم در سال ۱۹۹۰ ساخته شد. این زبان در ویژگیها شبیه پرل، روبی، اسکیم، اسمالتاک و تیسیال است و از مدیریت خودکار حافظه استفاده میکند + +Python，是一种面向对象的、直譯式的计算机程序设计语言，也是一种功能强大而完善的通用型语言，已经具有十多年的发展历史，成熟且稳定。 + +ބްލޫ ވޭލްގެ ދޫ މަތީގައި އެއްފަހަރާ 50 މީހުންނަށް ތިބެވިދާނެވެ. ބޮޑު މަހުގެ ދުލަކީ އެހާމެ ބޮޑު އެއްޗެކެވެ. + +**உருது** 13ஆம் நூற்றாண்டில் உருவான ஒரு இந்தோ-ஐரோப்பிய மொழியாகும். உருது, ஹிந்தியுடன் சேர்த்து "ஹிந்துஸ்தானி" என அழைக்கப்படுகின்றது. மண்டரின், ஆங்கிலம் ஆகியவற்றுக்கு அடுத்தபடியாக மூன்றாவது கூடிய அளவு மக்களால் புரிந்து கொள்ளப்படக்கூடியது ஹிந்துஸ்தானியேயாகும். தாய் மொழியாகப் பேசுபவர்கள் எண்ணிக்கையின் அடிப்படையில் உருது உலகின் 20 ஆவது பெரிய மொழியாகும். 6 கோடி மக்கள் இதனைத் தாய் மொழியாகக் கொண்டுள்ளார்கள். இரண்டாவது மொழியாகக் கொண்டுள்ளவர்கள் உட்பட 11 கோடிப் பேர் இதனைப் பேசுகிறார்கள். உருது பாகிஸ்தானின் அரசகரும மொழியாகவும், இந்தியாவின் அரசகரும மொழிகளுள் ஒன்றாகவும் விளங்குகிறது. + +اردو ہندوآریائی زبانوں کی ہندويورپی شاخ کی ایک زبان ہے جو تيرھويں صدی ميں بر صغير ميں پيدا ہوئی ـ اردو پاکستان کی سرکاری زبان ہے اور بھارت کی سرکاری زبانوں ميں سے ايک ہے۔ اردو بھارت ميں 5 کروڑ اور پاکستان ميں 1 کروڑ لوگوں کی مادری زبان ہے مگر اسے بھارت اور پاکستان کے تقریباً 50 کروڑ لوگ بول اور سمجھ سکتے ھیں ۔ جن میں سے تقریباً 10.5 کروڑ لوگ اسے باقاعدہ بولتے ھیں۔ + +بايثون +===== + +**بايثون** لغة برمجة حديثة بسيطة، واضحة، سريعة ، تستخدم أسلوب البرمجة الكائنية (OOP) وقابلة للتطوير بالإضافة إلى أنها مجانية و مفتوحة المصدر. صُنفت بالأساس كلغة تفسيرية ، بايثون مصممة أصلاً للأداء بعض المهام الخاصة أو المحدودة. إلا أنه يمكن استخدامها بايثون لإنجاز المشاريع الضخمه كأي لغة برمجية أخرى، غالباً ما يُنصح المبتدئين في ميدان البرمجة بتعلم هذه اللغة لأنها من بين أسهل اللغات البرمجية تعلماً. + +|||||||||||||||||||||||||||||THIS SHOULD BE RTL||||||||||||||||||||||||| + +(نشأت بايثون في مركز CWI (مركز العلوم والحاسب الآلي) بأمستردام على يد جويدو فان رُزوم. تم تطويرها بلغة C. أطلق فان رُزوم اسم "بايثون" على لغته تعبيرًا عن إعجابه بفِرقَة مسرحية هزلية شهيرة من بريطانيا، كانت تطلق على نفسها اسم مونتي بايثون Monty Python. + +تتميز بايثون بمجتمعها النشط ، كما أن لها الكثير من المكتبات البرمجية ذات الأغراض الخاصة والتي برمجها أشخاص من مجتمع هذه اللغة ، مثلاً مكتبة PyGame التي توفر مجموعه من الوظائف من اجل برمجة الالعاب. ويمكن لبايثون التعامل مع العديد من أنواع قواعد البيانات مثل MySQL وغيره. + +##أمثلة +مثال Hello World! + + print "Hello World!" + + +مثال لاستخراج المضروب Factorial : + + num = 1 + x = raw_input('Insert the number please ') + x = int(x) + + if x > 69: + print 'Math Error !' + else: + while x > 1: + num *= x + x = x-1 + + print num + + + +##وصلات خارجية +* [الموقع الرسمي للغة بايثون](http://www.python.org) + + بذرة حاس + + +**Недвард «Нед» Фландерс** (Nedward «Ned» Flanders) — вымышленный персонаж мультсериала «[Симпсоны][]», озвученный Гарри Ширером. Он и его семья живут по соседству от семьи Симпсонов. Набожный христианин, Нед является одним из столпов морали Спрингфилда. В эпизоде «Alone Again, Natura-Diddily» он овдовел, его жена Мод погибла в результате несчастного случая. + +Нед был одним из первых персонажей в мультсериале, который не был членом семьи Симпсонов. Начиная с первых серий, он регулярно появляется в «Симпсонах». Считается, что Нед Фландерс был назван в честь улицы *Northeast Flanders St.* в [Портленде](http://www.portland.gov), Орегон, родном городе создателя мультсериала Мэтта Грейнинга]]. Надпись на указателе улицы *NE Flanders St.* хулиганы часто исправляли на _NED Flanders St._ + + diff --git a/tests/misc/blank-block-quote.html b/tests/misc/blank-block-quote.html new file mode 100644 index 0000000..23df17a --- /dev/null +++ b/tests/misc/blank-block-quote.html @@ -0,0 +1,3 @@ +<p>aaaaaaaaaaa</p> +<blockquote /> +<p>bbbbbbbbbbb</p>
\ No newline at end of file diff --git a/tests/misc/blank-block-quote.txt b/tests/misc/blank-block-quote.txt new file mode 100644 index 0000000..75bfc74 --- /dev/null +++ b/tests/misc/blank-block-quote.txt @@ -0,0 +1,6 @@ + +aaaaaaaaaaa + +> + +bbbbbbbbbbb diff --git a/tests/misc/blockquote-below-paragraph.html b/tests/misc/blockquote-below-paragraph.html new file mode 100644 index 0000000..a138933 --- /dev/null +++ b/tests/misc/blockquote-below-paragraph.html @@ -0,0 +1,15 @@ +<p>Paragraph</p> +<blockquote> +<p>Block quote +Yep</p> +</blockquote> +<p>Paragraph</p> +<blockquote> +<p>no space +Nope</p> +</blockquote> +<p>Paragraph one</p> +<blockquote> +<p>blockquote +More blockquote.</p> +</blockquote>
\ No newline at end of file diff --git a/tests/misc/blockquote-below-paragraph.txt b/tests/misc/blockquote-below-paragraph.txt new file mode 100644 index 0000000..529e5a9 --- /dev/null +++ b/tests/misc/blockquote-below-paragraph.txt @@ -0,0 +1,11 @@ +Paragraph +> Block quote +> Yep + +Paragraph +>no space +>Nope + +Paragraph one +> blockquote +More blockquote. diff --git a/tests/misc/blockquote-hr.html b/tests/misc/blockquote-hr.html new file mode 100644 index 0000000..61c1a3c --- /dev/null +++ b/tests/misc/blockquote-hr.html @@ -0,0 +1,16 @@ +<p>This is a paragraph.</p> +<hr /> +<blockquote> +<p>Block quote with horizontal lines.</p> +<hr /> +<blockquote> +<p>Double block quote.</p> +<hr /> +<p>End of the double block quote.</p> +</blockquote> +<p>A new paragraph. +With multiple lines. +Even a lazy line.</p> +<hr /> +<p>The last line.</p> +</blockquote>
\ No newline at end of file diff --git a/tests/misc/blockquote-hr.txt b/tests/misc/blockquote-hr.txt new file mode 100644 index 0000000..ef9c44f --- /dev/null +++ b/tests/misc/blockquote-hr.txt @@ -0,0 +1,21 @@ +This is a paragraph. + +--- + +> Block quote with horizontal lines. + +> --- + +> > Double block quote. + +> > --- + +> > End of the double block quote. + +> A new paragraph. +> With multiple lines. +Even a lazy line. + +> --- + +> The last line. diff --git a/tests/misc/blockquote.html b/tests/misc/blockquote.html new file mode 100644 index 0000000..4481d51 --- /dev/null +++ b/tests/misc/blockquote.html @@ -0,0 +1,24 @@ +<blockquote> +<p>blockquote with no whitespace before <code>></code>.</p> +</blockquote> +<p>foo</p> +<blockquote> +<p>blockquote with one space before the <code>></code>.</p> +</blockquote> +<p>bar</p> +<blockquote> +<p>blockquote with 2 spaces.</p> +</blockquote> +<p>baz</p> +<blockquote> +<p>this has three spaces so its a paragraph.</p> +</blockquote> +<p>blah</p> +<pre><code>> this one had four so it's a code block. +</code></pre> +<blockquote> +<blockquote> +<p>this nested blockquote has 0 on level one and 3 (one after the first <code>></code> + 2 more) on level 2.</p> +<p>and this has 4 on level 2 - another code block.</p> +</blockquote> +</blockquote>
\ No newline at end of file diff --git a/tests/misc/blockquote.txt b/tests/misc/blockquote.txt new file mode 100644 index 0000000..be3ff90 --- /dev/null +++ b/tests/misc/blockquote.txt @@ -0,0 +1,21 @@ +> blockquote with no whitespace before `>`. + +foo + + > blockquote with one space before the `>`. + +bar + + > blockquote with 2 spaces. + +baz + + > this has three spaces so its a paragraph. + +blah + + > this one had four so it's a code block. + +> > this nested blockquote has 0 on level one and 3 (one after the first `>` + 2 more) on level 2. + +> > and this has 4 on level 2 - another code block. diff --git a/tests/misc/bold_links.html b/tests/misc/bold_links.html new file mode 100644 index 0000000..5a78e57 --- /dev/null +++ b/tests/misc/bold_links.html @@ -0,0 +1 @@ +<p><strong>bold <a href="http://example.com">link</a></strong></p>
\ No newline at end of file diff --git a/tests/misc/bold_links.txt b/tests/misc/bold_links.txt new file mode 100644 index 0000000..a07f441 --- /dev/null +++ b/tests/misc/bold_links.txt @@ -0,0 +1 @@ +**bold [link](http://example.com)** diff --git a/tests/misc/br.html b/tests/misc/br.html new file mode 100644 index 0000000..08563a5 --- /dev/null +++ b/tests/misc/br.html @@ -0,0 +1,11 @@ +<p>Output:</p> +<pre><code><p>Some of these words <em>are emphasized</em>. +Some of these words <em>are emphasized also</em>.</p> + +<p>Use two asterisks for <strong>strong emphasis</strong>. +Or, if you prefer, <strong>use two underscores instead</strong>.</p> +</code></pre> +<h2>Lists</h2> +<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens (<code>*</code>, +<code>+</code>, and <code>-</code>) as list markers. These three markers are +interchangable; this:</p>
\ No newline at end of file diff --git a/tests/misc/br.txt b/tests/misc/br.txt new file mode 100644 index 0000000..59d29e0 --- /dev/null +++ b/tests/misc/br.txt @@ -0,0 +1,16 @@ +Output: + + <p>Some of these words <em>are emphasized</em>. + Some of these words <em>are emphasized also</em>.</p> + + <p>Use two asterisks for <strong>strong emphasis</strong>. + Or, if you prefer, <strong>use two underscores instead</strong>.</p> + + + +## Lists ## + +Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`, +`+`, and `-`) as list markers. These three markers are +interchangable; this: + diff --git a/tests/misc/bracket_re.html b/tests/misc/bracket_re.html new file mode 100644 index 0000000..f48a612 --- /dev/null +++ b/tests/misc/bracket_re.html @@ -0,0 +1,60 @@ +<p>[x +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx</p>
\ No newline at end of file diff --git a/tests/misc/bracket_re.txt b/tests/misc/bracket_re.txt new file mode 100644 index 0000000..545e061 --- /dev/null +++ b/tests/misc/bracket_re.txt @@ -0,0 +1,61 @@ + +[x +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx +xxx xxx xxx xxx xxx xxx xxx xxx diff --git a/tests/misc/code-first-line.html b/tests/misc/code-first-line.html new file mode 100644 index 0000000..1fb0b7c --- /dev/null +++ b/tests/misc/code-first-line.html @@ -0,0 +1,2 @@ +<pre><code>print "This is a code block." +</code></pre>
\ No newline at end of file diff --git a/tests/misc/code-first-line.txt b/tests/misc/code-first-line.txt new file mode 100644 index 0000000..952614d --- /dev/null +++ b/tests/misc/code-first-line.txt @@ -0,0 +1 @@ + print "This is a code block." diff --git a/tests/misc/comments.html b/tests/misc/comments.html new file mode 100644 index 0000000..005a755 --- /dev/null +++ b/tests/misc/comments.html @@ -0,0 +1,5 @@ +<p>X<0</p> +<p>X>0</p> +<!-- A comment --> + +<div>as if</div>
\ No newline at end of file diff --git a/tests/misc/comments.txt b/tests/misc/comments.txt new file mode 100644 index 0000000..68302b0 --- /dev/null +++ b/tests/misc/comments.txt @@ -0,0 +1,7 @@ +X<0 + +X>0 + +<!-- A comment --> + +<div>as if</div> diff --git a/tests/misc/div.html b/tests/misc/div.html new file mode 100644 index 0000000..7cd0d6d --- /dev/null +++ b/tests/misc/div.html @@ -0,0 +1,4 @@ +<div id="sidebar"> + +<p><em>foo</em></p> +</div>
\ No newline at end of file diff --git a/tests/misc/div.txt b/tests/misc/div.txt new file mode 100644 index 0000000..ca87745 --- /dev/null +++ b/tests/misc/div.txt @@ -0,0 +1,5 @@ +<div id="sidebar"> + + _foo_ + +</div> diff --git a/tests/misc/em-around-links.html b/tests/misc/em-around-links.html new file mode 100644 index 0000000..06bfa8e --- /dev/null +++ b/tests/misc/em-around-links.html @@ -0,0 +1,16 @@ +<h1>Title</h1> + +<ul> + <li><em><a href="http://www.freewisdom.org/projects/python-markdown/">Python in Markdown</a> by some + great folks</em> - This <em>does</em> work as expected.</li> + <li><em><a href="http://www.freewisdom.org/projects/python-markdown/">Python in Markdown</a> by some + great folks</em> - This <em>does</em> work as expected.</li> + <li><a href="http://www.freewisdom.org/projects/python-markdown/"><em>Python in Markdown</em></a> by some + great folks - This <em>does</em> work as expected.</li> + <li><a href="http://www.freewisdom.org/projects/python-markdown/"><em>Python in Markdown</em></a> <em>by some + great folks</em> - This <em>does</em> work as expected.</li> +</ul> + +<p><em><a href="http://www.freewisdom.org/projects/python-markdown/">Python in Markdown</a> by some + great folks</em> - This <em>does</em> work as expected.</p> + diff --git a/tests/misc/em-around-links.txt b/tests/misc/em-around-links.txt new file mode 100644 index 0000000..5b15be4 --- /dev/null +++ b/tests/misc/em-around-links.txt @@ -0,0 +1,14 @@ +# Title + + - *[Python in Markdown](http://www.freewisdom.org/projects/python-markdown/) by some + great folks* - This *does* work as expected. + - _[Python in Markdown](http://www.freewisdom.org/projects/python-markdown/) by some + great folks_ - This *does* work as expected. + - [_Python in Markdown_](http://www.freewisdom.org/projects/python-markdown/) by some + great folks - This *does* work as expected. + - [_Python in Markdown_](http://www.freewisdom.org/projects/python-markdown/) _by some + great folks_ - This *does* work as expected. + +_[Python in Markdown](http://www.freewisdom.org/projects/python-markdown/) by some +great folks_ - This *does* work as expected. + diff --git a/tests/misc/em_strong.html b/tests/misc/em_strong.html new file mode 100644 index 0000000..75c92d8 --- /dev/null +++ b/tests/misc/em_strong.html @@ -0,0 +1,10 @@ +<p>One asterisk: *</p> +<p>One underscore: _</p> +<p>Two asterisks: **</p> +<p>With spaces: * *</p> +<p>Two underscores __</p> +<p>with spaces: _ _</p> +<p>three asterisks: ***</p> +<p>with spaces: * * *</p> +<p>three underscores: ___</p> +<p>with spaces: _ _ _</p>
\ No newline at end of file diff --git a/tests/misc/em_strong.txt b/tests/misc/em_strong.txt new file mode 100644 index 0000000..d0774ad --- /dev/null +++ b/tests/misc/em_strong.txt @@ -0,0 +1,20 @@ +One asterisk: * + +One underscore: _ + +Two asterisks: ** + +With spaces: * * + +Two underscores __ + +with spaces: _ _ + +three asterisks: *** + +with spaces: * * * + +three underscores: ___ + +with spaces: _ _ _ + diff --git a/tests/misc/email.html b/tests/misc/email.html new file mode 100644 index 0000000..0d033bb --- /dev/null +++ b/tests/misc/email.html @@ -0,0 +1,2 @@ +<p>asdfasdfadsfasd <a href="mailto:yuri@freewisdom.org">yuri@freewisdom.org</a> or you can say +instead <a href="mailto:yuri@freewisdom.org">yuri@freewisdom.org</a></p>
\ No newline at end of file diff --git a/tests/misc/email.txt b/tests/misc/email.txt new file mode 100644 index 0000000..ece8801 --- /dev/null +++ b/tests/misc/email.txt @@ -0,0 +1,3 @@ + +asdfasdfadsfasd <yuri@freewisdom.org> or you can say +instead <mailto:yuri@freewisdom.org> diff --git a/tests/misc/funky-list.html b/tests/misc/funky-list.html new file mode 100644 index 0000000..313db8f --- /dev/null +++ b/tests/misc/funky-list.html @@ -0,0 +1,11 @@ +<ol> +<li>this starts a list <em>with</em> numbers</li> +<li>this will show as number "2"</li> +<li>this will show as number "3."</li> +<li>any number, +, -, or * will keep the list going.</li> +</ol> +<p>aaaaaaaaaaaaaaa</p> +<ul> +<li>now a normal list</li> +<li>and more</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/funky-list.txt b/tests/misc/funky-list.txt new file mode 100644 index 0000000..48ecd60 --- /dev/null +++ b/tests/misc/funky-list.txt @@ -0,0 +1,9 @@ +1. this starts a list *with* numbers ++ this will show as number "2" +* this will show as number "3." +9. any number, +, -, or * will keep the list going. + +aaaaaaaaaaaaaaa + +- now a normal list +- and more diff --git a/tests/misc/h1.html b/tests/misc/h1.html new file mode 100644 index 0000000..fbf9b4d --- /dev/null +++ b/tests/misc/h1.html @@ -0,0 +1,3 @@ +<h2>Header</h2> +<h1>Header 2</h1> +<h3>H3</h3>
\ No newline at end of file diff --git a/tests/misc/h1.txt b/tests/misc/h1.txt new file mode 100644 index 0000000..0a1c8f9 --- /dev/null +++ b/tests/misc/h1.txt @@ -0,0 +1,7 @@ +Header +------ + +Header 2 +======== + +### H3 diff --git a/tests/misc/hash.html b/tests/misc/hash.html new file mode 100644 index 0000000..1865994 --- /dev/null +++ b/tests/misc/hash.html @@ -0,0 +1,11 @@ +<p>a</p> +<pre> +#!/usr/bin/python +hello</pre> + +<p>a</p> +<pre> +!/usr/bin/python +hello</pre> + +<p>a</p>
\ No newline at end of file diff --git a/tests/misc/hash.txt b/tests/misc/hash.txt new file mode 100644 index 0000000..634758d --- /dev/null +++ b/tests/misc/hash.txt @@ -0,0 +1,13 @@ +a + +<pre> +#!/usr/bin/python +hello</pre> + +a + +<pre> +!/usr/bin/python +hello</pre> + +a diff --git a/tests/misc/headers.html b/tests/misc/headers.html new file mode 100644 index 0000000..2a737e2 --- /dev/null +++ b/tests/misc/headers.html @@ -0,0 +1,10 @@ +<h3>Hello world</h3> +<p>Line 2 +Line 3</p> +<h1>[Markdown][5]</h1> +<h1><a href="http://some.link.com/">Markdown</a></h1> +<h1>[5]: http://foo.com/</h1> +<h1>Issue #1: Markdown</h1> +<p>Text</p> +<h1>Header</h1> +<p>Some other text</p>
\ No newline at end of file diff --git a/tests/misc/headers.txt b/tests/misc/headers.txt new file mode 100644 index 0000000..db114ed --- /dev/null +++ b/tests/misc/headers.txt @@ -0,0 +1,15 @@ +### Hello world +Line 2 +Line 3 + +# [Markdown][5] + +# [Markdown](http://some.link.com/) + +# [5]: http://foo.com/ + +# Issue #1: Markdown + +Text +# Header +Some other text diff --git a/tests/misc/hline.html b/tests/misc/hline.html new file mode 100644 index 0000000..b18a311 --- /dev/null +++ b/tests/misc/hline.html @@ -0,0 +1,2 @@ +<h1>Header</h1> +<p>Next line</p>
\ No newline at end of file diff --git a/tests/misc/hline.txt b/tests/misc/hline.txt new file mode 100644 index 0000000..e39b7a2 --- /dev/null +++ b/tests/misc/hline.txt @@ -0,0 +1,5 @@ + +#Header +Next line + + diff --git a/tests/misc/html-comments.html b/tests/misc/html-comments.html new file mode 100644 index 0000000..7b36246 --- /dev/null +++ b/tests/misc/html-comments.html @@ -0,0 +1,2 @@ +<p>Here is HTML <!-- **comment** --> +and once more <p><!--comment--></p></p>
\ No newline at end of file diff --git a/tests/misc/html-comments.txt b/tests/misc/html-comments.txt new file mode 100644 index 0000000..cac4da5 --- /dev/null +++ b/tests/misc/html-comments.txt @@ -0,0 +1,2 @@ +Here is HTML <!-- **comment** --> +and once more <p><!--comment--></p> diff --git a/tests/misc/html.html b/tests/misc/html.html new file mode 100644 index 0000000..81ac5ee --- /dev/null +++ b/tests/misc/html.html @@ -0,0 +1,9 @@ +<h1>Block level html</h1> + +<p>Some inline <b>stuff<b>.<br /> +</p> +<p>Now some <arbitrary>arbitrary tags</arbitrary>.</p> +<div>More block level html.</div> + +<p>And of course <script>blah</script>.</p> +<p><a href="script>stuff</script">this <script>link</a></p>
\ No newline at end of file diff --git a/tests/misc/html.txt b/tests/misc/html.txt new file mode 100644 index 0000000..3ac3ae0 --- /dev/null +++ b/tests/misc/html.txt @@ -0,0 +1,13 @@ + +<h1>Block level html</h1> + +Some inline <b>stuff<b>. + +Now some <arbitrary>arbitrary tags</arbitrary>. + +<div>More block level html.</div> + +And of course <script>blah</script>. + +[this <script>link](<script>stuff</script>) + diff --git a/tests/misc/image-2.html b/tests/misc/image-2.html new file mode 100644 index 0000000..9343d29 --- /dev/null +++ b/tests/misc/image-2.html @@ -0,0 +1,2 @@ +<p><a href="http://src.com/"><em>link!</em></a></p> +<p><em><a href="http://www.freewisdom.org">link</a></em></p>
\ No newline at end of file diff --git a/tests/misc/image-2.txt b/tests/misc/image-2.txt new file mode 100644 index 0000000..6228383 --- /dev/null +++ b/tests/misc/image-2.txt @@ -0,0 +1,3 @@ +[*link!*](http://src.com/) + +*[link](http://www.freewisdom.org)* diff --git a/tests/misc/image.html b/tests/misc/image.html new file mode 100644 index 0000000..16be2d5 --- /dev/null +++ b/tests/misc/image.html @@ -0,0 +1 @@ +<p><img alt="Poster" src="http://humane_man.jpg" title="The most humane man." /></p>
\ No newline at end of file diff --git a/tests/misc/image.txt b/tests/misc/image.txt new file mode 100644 index 0000000..5553bd4 --- /dev/null +++ b/tests/misc/image.txt @@ -0,0 +1,2 @@ + + diff --git a/tests/misc/image_in_links.html b/tests/misc/image_in_links.html new file mode 100644 index 0000000..5a8cdc3 --- /dev/null +++ b/tests/misc/image_in_links.html @@ -0,0 +1 @@ +<p><a href="path/to/image.png"><img alt="altname" src="path/to/img_thumb.png" /></a></p>
\ No newline at end of file diff --git a/tests/misc/image_in_links.txt b/tests/misc/image_in_links.txt new file mode 100644 index 0000000..6d739e6 --- /dev/null +++ b/tests/misc/image_in_links.txt @@ -0,0 +1,3 @@ + + +[](path/to/image.png) diff --git a/tests/misc/inside_html.html b/tests/misc/inside_html.html new file mode 100644 index 0000000..6343dd9 --- /dev/null +++ b/tests/misc/inside_html.html @@ -0,0 +1 @@ +<p><a href="stuff"> <strong>ok</strong>? </a></p>
\ No newline at end of file diff --git a/tests/misc/inside_html.txt b/tests/misc/inside_html.txt new file mode 100644 index 0000000..4f068bf --- /dev/null +++ b/tests/misc/inside_html.txt @@ -0,0 +1 @@ +<a href="stuff"> __ok__? </a> diff --git a/tests/misc/japanese.html b/tests/misc/japanese.html new file mode 100644 index 0000000..930891b --- /dev/null +++ b/tests/misc/japanese.html @@ -0,0 +1,11 @@ +<h1>パイソン (Python)</h1> +<p><strong>Python</strong>（パイソン）は、<a href="http://en.wikipedia.org/wiki/Guido_van_Rossum">Guido van Rossum</a> によって作られたオープンソースのオブジェクト指向スクリプト言語。<a href="http://ja.wikipedia.org/wiki/Perl">Perl</a>とともに欧米で広く普及している。イギリスのテレビ局 BBC が製作したコメディ番組『空飛ぶモンティ・パイソン』にちなんで名付けられた。 (Pythonには、爬虫類のニシキヘビの意味があり、Python言語のマスコットやアイコンとして使われることがある。)</p> +<h2>概要</h2> +<p>プログラミング言語 Python は初心者から専門家まで幅広いユーザ層を獲得している。利用目的は汎用で、方向性としてはJavaに近い。ただし、最初からネットワーク利用をメインとして考えられているJavaよりセキュリティについてはやや寛大である。多くのプラットフォームをサポートしており（⇒<a href="#somelink">動作するプラットフォーム</a>)、豊富なライブラリがあることから、産業界でも利用が増えつつある。また、Pythonは純粋なプログラミング言語のほかにも、多くの異なる言語で書かれたモジュールをまとめる糊言語のひとつとして位置づけることができる。実際Pythonは多くの商用アプリケーションでスクリプト言語として採用されている（⇒Pythonを使っている製品あるいはソフトウェアの一覧）。豊富なドキュメントをもち、Unicodeによる文字列操作をサポートしており、日本語処理も標準で可能である。</p> +<p>Python は基本的にインタプリタ上で実行されることを念頭において設計されており、以下のような特徴をもっている:</p> +<ul> +<li>動的な型付け。</li> +<li>オブジェクトのメンバに対するアクセスが制限されていない。（属性や専用のメソッドフックを実装することによって制限は可能。）</li> +<li>モジュール、クラス、オブジェクト等の言語の要素が内部からアクセス可能であり、リフレクションを利用した記述が可能。</li> +</ul> +<p>また、Pythonではインデントによりブロックを指定する構文を採用している（⇒<a href="#jklj">オフサイドルール</a>）。この構文はPythonに慣れたユーザからは称賛をもって受け入れられているが、他の言語のユーザからは批判も多い。このほかにも、大きすぎる実行ファイルや、Javaに比べて遅い処理速度などが欠点として指摘されている。しかし <strong>プロトタイピング</strong> の際にはこれらの点はさして問題とはならないことから、研究開発部門では頻繁に利用されている。</p>
\ No newline at end of file diff --git a/tests/misc/japanese.txt b/tests/misc/japanese.txt new file mode 100644 index 0000000..b2bd38c --- /dev/null +++ b/tests/misc/japanese.txt @@ -0,0 +1,15 @@ +パイソン (Python) +======= + +**Python**（パイソン）は、[Guido van Rossum](http://en.wikipedia.org/wiki/Guido_van_Rossum) によって作られたオープンソースのオブジェクト指向スクリプト言語。[Perl](http://ja.wikipedia.org/wiki/Perl)とともに欧米で広く普及している。イギリスのテレビ局 BBC が製作したコメディ番組『空飛ぶモンティ・パイソン』にちなんで名付けられた。 (Pythonには、爬虫類のニシキヘビの意味があり、Python言語のマスコットやアイコンとして使われることがある。) + +## 概要 +プログラミング言語 Python は初心者から専門家まで幅広いユーザ層を獲得している。利用目的は汎用で、方向性としてはJavaに近い。ただし、最初からネットワーク利用をメインとして考えられているJavaよりセキュリティについてはやや寛大である。多くのプラットフォームをサポートしており（⇒[動作するプラットフォーム](#somelink))、豊富なライブラリがあることから、産業界でも利用が増えつつある。また、Pythonは純粋なプログラミング言語のほかにも、多くの異なる言語で書かれたモジュールをまとめる糊言語のひとつとして位置づけることができる。実際Pythonは多くの商用アプリケーションでスクリプト言語として採用されている（⇒Pythonを使っている製品あるいはソフトウェアの一覧）。豊富なドキュメントをもち、Unicodeによる文字列操作をサポートしており、日本語処理も標準で可能である。 + +Python は基本的にインタプリタ上で実行されることを念頭において設計されており、以下のような特徴をもっている: + +* 動的な型付け。 +* オブジェクトのメンバに対するアクセスが制限されていない。（属性や専用のメソッドフックを実装することによって制限は可能。） +* モジュール、クラス、オブジェクト等の言語の要素が内部からアクセス可能であり、リフレクションを利用した記述が可能。 + +また、Pythonではインデントによりブロックを指定する構文を採用している（⇒[オフサイドルール](#jklj)）。この構文はPythonに慣れたユーザからは称賛をもって受け入れられているが、他の言語のユーザからは批判も多い。このほかにも、大きすぎる実行ファイルや、Javaに比べて遅い処理速度などが欠点として指摘されている。しかし **プロトタイピング** の際にはこれらの点はさして問題とはならないことから、研究開発部門では頻繁に利用されている。 diff --git a/tests/misc/lazy-block-quote.html b/tests/misc/lazy-block-quote.html new file mode 100644 index 0000000..7a88263 --- /dev/null +++ b/tests/misc/lazy-block-quote.html @@ -0,0 +1,6 @@ +<blockquote> +<p>Line one of lazy block quote. +Line two of lazy block quote.</p> +<p>Line one of paragraph two. +Line two of paragraph two.</p> +</blockquote>
\ No newline at end of file diff --git a/tests/misc/lazy-block-quote.txt b/tests/misc/lazy-block-quote.txt new file mode 100644 index 0000000..e7c17ca --- /dev/null +++ b/tests/misc/lazy-block-quote.txt @@ -0,0 +1,5 @@ +> Line one of lazy block quote. +Line two of lazy block quote. + +> Line one of paragraph two. +Line two of paragraph two. diff --git a/tests/misc/link-with-parenthesis.html b/tests/misc/link-with-parenthesis.html new file mode 100644 index 0000000..a56ed8d --- /dev/null +++ b/tests/misc/link-with-parenthesis.html @@ -0,0 +1 @@ +<p><a href="http://en.wikipedia.org/wiki/ZIP_(file_format)" title="ZIP (file format) - Wikipedia, the free encyclopedia">ZIP archives</a></p>
\ No newline at end of file diff --git a/tests/misc/link-with-parenthesis.txt b/tests/misc/link-with-parenthesis.txt new file mode 100644 index 0000000..8affc98 --- /dev/null +++ b/tests/misc/link-with-parenthesis.txt @@ -0,0 +1 @@ +[ZIP archives](http://en.wikipedia.org/wiki/ZIP_(file_format) "ZIP (file format) - Wikipedia, the free encyclopedia") diff --git a/tests/misc/lists.html b/tests/misc/lists.html new file mode 100644 index 0000000..bf4a02b --- /dev/null +++ b/tests/misc/lists.html @@ -0,0 +1,36 @@ +<ul> +<li>A multi-paragraph list, +unindented.</li> +</ul> +<p>Simple tight list</p> +<ul> +<li>Uno</li> +<li>Due</li> +<li>Tri</li> +</ul> +<p>A singleton tight list:</p> +<ul> +<li>Uno</li> +</ul> +<p>A lose list:</p> +<ul> +<li> +<p>One</p> +</li> +<li> +<p>Two</p> +</li> +<li> +<p>Three</p> +</li> +</ul> +<p>A lose list with paragraphs</p> +<ul> +<li> +<p>One one one one</p> +<p>one one one one</p> +</li> +<li> +<p>Two two two two</p> +</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/lists.txt b/tests/misc/lists.txt new file mode 100644 index 0000000..6db0dc3 --- /dev/null +++ b/tests/misc/lists.txt @@ -0,0 +1,31 @@ + +* A multi-paragraph list, +unindented. + + + +Simple tight list + +* Uno +* Due +* Tri + +A singleton tight list: + +* Uno + +A lose list: + +* One + +* Two + +* Three + +A lose list with paragraphs + +* One one one one + + one one one one + +* Two two two two diff --git a/tests/misc/lists2.html b/tests/misc/lists2.html new file mode 100644 index 0000000..991395b --- /dev/null +++ b/tests/misc/lists2.html @@ -0,0 +1,5 @@ +<ul> +<li>blah blah blah +sdf asdf asdf asdf asdf +asda asdf asdfasd</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/lists2.txt b/tests/misc/lists2.txt new file mode 100644 index 0000000..cbff761 --- /dev/null +++ b/tests/misc/lists2.txt @@ -0,0 +1,3 @@ +* blah blah blah +sdf asdf asdf asdf asdf +asda asdf asdfasd diff --git a/tests/misc/lists3.html b/tests/misc/lists3.html new file mode 100644 index 0000000..991395b --- /dev/null +++ b/tests/misc/lists3.html @@ -0,0 +1,5 @@ +<ul> +<li>blah blah blah +sdf asdf asdf asdf asdf +asda asdf asdfasd</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/lists3.txt b/tests/misc/lists3.txt new file mode 100644 index 0000000..6b45bd4 --- /dev/null +++ b/tests/misc/lists3.txt @@ -0,0 +1,3 @@ +* blah blah blah + sdf asdf asdf asdf asdf + asda asdf asdfasd diff --git a/tests/misc/lists4.html b/tests/misc/lists4.html new file mode 100644 index 0000000..4b6b32c --- /dev/null +++ b/tests/misc/lists4.html @@ -0,0 +1,8 @@ +<ul> +<li>item1</li> +<li>item2<ol> +<li>Number 1</li> +<li>Number 2</li> +</ol> +</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/lists4.txt b/tests/misc/lists4.txt new file mode 100644 index 0000000..a21493d --- /dev/null +++ b/tests/misc/lists4.txt @@ -0,0 +1,5 @@ + +* item1 +* item2 + 1. Number 1 + 2. Number 2 diff --git a/tests/misc/lists5.html b/tests/misc/lists5.html new file mode 100644 index 0000000..c3dbda4 --- /dev/null +++ b/tests/misc/lists5.html @@ -0,0 +1,14 @@ +<blockquote> +<p>This is a test of a block quote +With just two lines</p> +</blockquote> +<p>A paragraph</p> +<blockquote> +<p>This is a more difficult case +With a list item inside the quote</p> +<ul> +<li>Alpha</li> +<li>Beta +Etc.</li> +</ul> +</blockquote>
\ No newline at end of file diff --git a/tests/misc/lists5.txt b/tests/misc/lists5.txt new file mode 100644 index 0000000..566e0f1 --- /dev/null +++ b/tests/misc/lists5.txt @@ -0,0 +1,12 @@ +> This is a test of a block quote +> With just two lines + +A paragraph + +> This is a more difficult case +> With a list item inside the quote +> +> * Alpha +> * Beta +> Etc. + diff --git a/tests/misc/lists6.html b/tests/misc/lists6.html new file mode 100644 index 0000000..24aad38 --- /dev/null +++ b/tests/misc/lists6.html @@ -0,0 +1,18 @@ +<p>Test five or more spaces as start of list:</p> +<ul> +<li>five spaces</li> +</ul> +<p>not first item:</p> +<ul> +<li>one space</li> +<li>five spaces</li> +</ul> +<p>loose list:</p> +<ul> +<li> +<p>one space</p> +</li> +<li> +<p>five spaces</p> +</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/lists6.txt b/tests/misc/lists6.txt new file mode 100644 index 0000000..f12788f --- /dev/null +++ b/tests/misc/lists6.txt @@ -0,0 +1,14 @@ +Test five or more spaces as start of list: + +* five spaces + +not first item: + +* one space +* five spaces + +loose list: + +* one space + +* five spaces diff --git a/tests/misc/markup-inside-p.html b/tests/misc/markup-inside-p.html new file mode 100644 index 0000000..1b6b420 --- /dev/null +++ b/tests/misc/markup-inside-p.html @@ -0,0 +1,21 @@ +<p> + +_foo_ + +</p> + +<p> +_foo_ +</p> + +<p>_foo_</p> + +<p> + +_foo_ +</p> + +<p> +_foo_ + +</p>
\ No newline at end of file diff --git a/tests/misc/markup-inside-p.txt b/tests/misc/markup-inside-p.txt new file mode 100644 index 0000000..ab7dd0f --- /dev/null +++ b/tests/misc/markup-inside-p.txt @@ -0,0 +1,21 @@ +<p> + +_foo_ + +</p> + +<p> +_foo_ +</p> + +<p>_foo_</p> + +<p> + +_foo_ +</p> + +<p> +_foo_ + +</p> diff --git a/tests/misc/mismatched-tags.html b/tests/misc/mismatched-tags.html new file mode 100644 index 0000000..ec087e1 --- /dev/null +++ b/tests/misc/mismatched-tags.html @@ -0,0 +1,11 @@ +<p>Some text</p> + +<div>some more text</div> + +<p>and a bit more</p> +<p>And this output</p> + +<p><em>Compatible with PHP Markdown Extra 1.2.2 and Markdown.pl1.0.2b8:</em></p> +<!-- comment --><p><div>text</div><br /></p><br /> + +<p>Should be in p</p>
\ No newline at end of file diff --git a/tests/misc/mismatched-tags.txt b/tests/misc/mismatched-tags.txt new file mode 100644 index 0000000..8e6a52f --- /dev/null +++ b/tests/misc/mismatched-tags.txt @@ -0,0 +1,9 @@ +<p>Some text</p><div>some more text</div> + +and a bit more + +<p>And this output</p> *Compatible with PHP Markdown Extra 1.2.2 and Markdown.pl1.0.2b8:* + +<!-- comment --><p><div>text</div><br /></p><br /> + +Should be in p diff --git a/tests/misc/missing-link-def.html b/tests/misc/missing-link-def.html new file mode 100644 index 0000000..e04b5eb --- /dev/null +++ b/tests/misc/missing-link-def.html @@ -0,0 +1 @@ +<p>This is a [missing link][empty] and a <a href="http://example.com">valid</a> and [missing][again].</p>
\ No newline at end of file diff --git a/tests/misc/missing-link-def.txt b/tests/misc/missing-link-def.txt new file mode 100644 index 0000000..44bc656 --- /dev/null +++ b/tests/misc/missing-link-def.txt @@ -0,0 +1,4 @@ +This is a [missing link][empty] and a [valid][link] and [missing][again]. + +[link]: http://example.com + diff --git a/tests/misc/more_comments.html b/tests/misc/more_comments.html new file mode 100644 index 0000000..97074d5 --- /dev/null +++ b/tests/misc/more_comments.html @@ -0,0 +1,7 @@ +<!--asd@asdfd.com> + +<!asd@asdfd.com> + +<asd!@asdfd.com> + +<p>Test</p>
\ No newline at end of file diff --git a/tests/misc/more_comments.txt b/tests/misc/more_comments.txt new file mode 100644 index 0000000..0397f9c --- /dev/null +++ b/tests/misc/more_comments.txt @@ -0,0 +1,9 @@ +<!--asd@asdfd.com> + + +<!asd@asdfd.com> + + +<asd!@asdfd.com> + +Test diff --git a/tests/misc/multi-line-tags.html b/tests/misc/multi-line-tags.html new file mode 100644 index 0000000..763a050 --- /dev/null +++ b/tests/misc/multi-line-tags.html @@ -0,0 +1,4 @@ +<div> + +<p>asdf asdfasd</p> +</div>
\ No newline at end of file diff --git a/tests/misc/multi-line-tags.txt b/tests/misc/multi-line-tags.txt new file mode 100644 index 0000000..4ea3b02 --- /dev/null +++ b/tests/misc/multi-line-tags.txt @@ -0,0 +1,6 @@ + +<div> + +asdf asdfasd + +</div> diff --git a/tests/misc/multi-paragraph-block-quote.html b/tests/misc/multi-paragraph-block-quote.html new file mode 100644 index 0000000..e13986a --- /dev/null +++ b/tests/misc/multi-paragraph-block-quote.html @@ -0,0 +1,6 @@ +<blockquote> +<p>This is line one of paragraph one + This is line two of paragraph one</p> +<p>This is line one of paragraph two</p> +<p>This is another blockquote.</p> +</blockquote>
\ No newline at end of file diff --git a/tests/misc/multi-paragraph-block-quote.txt b/tests/misc/multi-paragraph-block-quote.txt new file mode 100644 index 0000000..f8a986f --- /dev/null +++ b/tests/misc/multi-paragraph-block-quote.txt @@ -0,0 +1,8 @@ +> This is line one of paragraph one +> This is line two of paragraph one + +> This is line one of paragraph two + + + +> This is another blockquote. diff --git a/tests/misc/multi-test.html b/tests/misc/multi-test.html new file mode 100644 index 0000000..2c8fe9e --- /dev/null +++ b/tests/misc/multi-test.html @@ -0,0 +1,20 @@ +<h1 id="inthebeginning">Header </h1> +<p>Now, let's try something <em class="special">inline</em>, to see if it works</p> +<p>Blah blah blah <a href="http://www.slashdot.org">http://www.slashdot.org</a></p> +<ul> +<li>Basic list</li> +<li>Basic list 2</li> +</ul> +<p>addss</p> +<ul> +<li>Lazy list</li> +</ul> +<p>An <a href="http://example.com" title="Title">example</a> (oops)</p> +<p>Now, let's use a footnote[^1]. Not bad, eh? +Let's continue.</p> +<p>[^1]: Here is the text of the footnote + continued on several lines. + some more of the footnote, etc.</p> +<pre><code>Actually, another paragraph too. +</code></pre> +<p>And then there is a little bit of text.</p>
\ No newline at end of file diff --git a/tests/misc/multi-test.txt b/tests/misc/multi-test.txt new file mode 100644 index 0000000..c4ab1c1 --- /dev/null +++ b/tests/misc/multi-test.txt @@ -0,0 +1,32 @@ + +# Header {@id=inthebeginning} + +Now, let's try something *inline{@class=special}*, to see if it works + + +Blah blah blah <http://www.slashdot.org> + +* Basic list +* Basic list 2 + +addss + + * Lazy list + +An [example][ref] (oops) + + [ref]: http://example.com "Title" + + +Now, let's use a footnote[^1]. Not bad, eh? +Let's continue. + + [^1]: Here is the text of the footnote + continued on several lines. + some more of the footnote, etc. + + Actually, another paragraph too. + +And then there is a little bit of text. + + diff --git a/tests/misc/multiline-comments.html b/tests/misc/multiline-comments.html new file mode 100644 index 0000000..547ba0b --- /dev/null +++ b/tests/misc/multiline-comments.html @@ -0,0 +1,16 @@ +<!-- + +foo + +--> + +<p> + +foo + +</p> + +<div> + +<p>foo</p> +</div>
\ No newline at end of file diff --git a/tests/misc/multiline-comments.txt b/tests/misc/multiline-comments.txt new file mode 100644 index 0000000..71bc418 --- /dev/null +++ b/tests/misc/multiline-comments.txt @@ -0,0 +1,18 @@ +<!-- + +foo + +--> + +<p> + +foo + +</p> + + +<div> + +foo + +</div> diff --git a/tests/misc/nested-lists.html b/tests/misc/nested-lists.html new file mode 100644 index 0000000..bb73784 --- /dev/null +++ b/tests/misc/nested-lists.html @@ -0,0 +1,39 @@ +<ul> +<li> +<p>item 1</p> +<p>paragraph 2</p> +</li> +<li> +<p>item 2</p> +<ul> +<li>item 2-1</li> +<li> +<p>item 2-2</p> +<ul> +<li>item 2-2-1</li> +</ul> +</li> +<li> +<p>item 2-3</p> +<ul> +<li>item 2-3-1</li> +</ul> +</li> +</ul> +</li> +<li> +<p>item 3</p> +</li> +</ul> +<p>plain text</p> +<ul> +<li>item 1<ul> +<li>item 1-1</li> +<li>item 1-2<ul> +<li>item 1-2-1</li> +</ul> +</li> +</ul> +</li> +<li>item 2</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/nested-lists.txt b/tests/misc/nested-lists.txt new file mode 100644 index 0000000..38aae15 --- /dev/null +++ b/tests/misc/nested-lists.txt @@ -0,0 +1,24 @@ +* item 1 + + paragraph 2 + +* item 2 + + * item 2-1 + * item 2-2 + + * item 2-2-1 + + * item 2-3 + + * item 2-3-1 + +* item 3 + +plain text + +* item 1 + * item 1-1 + * item 1-2 + * item 1-2-1 +* item 2 diff --git a/tests/misc/nested-patterns.html b/tests/misc/nested-patterns.html new file mode 100644 index 0000000..b90d46d --- /dev/null +++ b/tests/misc/nested-patterns.html @@ -0,0 +1,7 @@ +<p><strong><em><a href="http://www.freewisdom.org">link</a></em></strong> +<strong><em><a href="http://www.freewisdom.org">link</a></em></strong> +<strong><a href="http://www.freewisdom.org"><em>link</em></a></strong> +<strong><a href="http://www.freewisdom.org"><em>link</em></a></strong> +<strong><a href="http://www.freewisdom.org"><em>link</em></a></strong> +<strong><a href="http://www.freewisdom.org"><em>link</em></a></strong> +<a href="http://www.freewisdom.org"><strong><em>link</em></strong></a></p>
\ No newline at end of file diff --git a/tests/misc/nested-patterns.txt b/tests/misc/nested-patterns.txt new file mode 100644 index 0000000..3f5dc3e --- /dev/null +++ b/tests/misc/nested-patterns.txt @@ -0,0 +1,7 @@ +___[link](http://www.freewisdom.org)___ +***[link](http://www.freewisdom.org)*** +**[*link*](http://www.freewisdom.org)** +__[_link_](http://www.freewisdom.org)__ +__[*link*](http://www.freewisdom.org)__ +**[_link_](http://www.freewisdom.org)** +[***link***](http://www.freewisdom.org) diff --git a/tests/misc/normalize.html b/tests/misc/normalize.html new file mode 100644 index 0000000..8d05375 --- /dev/null +++ b/tests/misc/normalize.html @@ -0,0 +1 @@ +<p><a href="http://www.stuff.com/q?x=1&y=2<>">Link</a></p>
\ No newline at end of file diff --git a/tests/misc/normalize.txt b/tests/misc/normalize.txt new file mode 100644 index 0000000..fe0cf17 --- /dev/null +++ b/tests/misc/normalize.txt @@ -0,0 +1,2 @@ + +[Link](http://www.stuff.com/q?x=1&y=2<>) diff --git a/tests/misc/numeric-entity.html b/tests/misc/numeric-entity.html new file mode 100644 index 0000000..3ad3b7a --- /dev/null +++ b/tests/misc/numeric-entity.html @@ -0,0 +1,2 @@ +<p><a href="mailto:user@gmail.com">user@gmail.com</a></p> +<p>This is an entity: ê </p>
\ No newline at end of file diff --git a/tests/misc/numeric-entity.txt b/tests/misc/numeric-entity.txt new file mode 100644 index 0000000..fd2052b --- /dev/null +++ b/tests/misc/numeric-entity.txt @@ -0,0 +1,4 @@ + +<user@gmail.com> + +This is an entity: ê diff --git a/tests/misc/para-with-hr.html b/tests/misc/para-with-hr.html new file mode 100644 index 0000000..8569fec --- /dev/null +++ b/tests/misc/para-with-hr.html @@ -0,0 +1,3 @@ +<p>Here is a paragraph, followed by a horizontal rule.</p> +<hr /> +<p>Followed by another paragraph.</p>
\ No newline at end of file diff --git a/tests/misc/para-with-hr.txt b/tests/misc/para-with-hr.txt new file mode 100644 index 0000000..20735fb --- /dev/null +++ b/tests/misc/para-with-hr.txt @@ -0,0 +1,4 @@ +Here is a paragraph, followed by a horizontal rule. +*** +Followed by another paragraph. + diff --git a/tests/misc/php.html b/tests/misc/php.html new file mode 100644 index 0000000..8cd4ed5 --- /dev/null +++ b/tests/misc/php.html @@ -0,0 +1,11 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" + "http://www.w3.org/TR/html4/strict.dtd"> + +<p><b>This should have a p tag</b></p> +<!--This is a comment --> + +<div>This shouldn't</div> + +<?php echo "block_level";?> + +<p><?php echo "not_block_level";?></p>
\ No newline at end of file diff --git a/tests/misc/php.txt b/tests/misc/php.txt new file mode 100644 index 0000000..ca5be45 --- /dev/null +++ b/tests/misc/php.txt @@ -0,0 +1,13 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" + "http://www.w3.org/TR/html4/strict.dtd"> + +<b>This should have a p tag</b> + +<!--This is a comment --> + +<div>This shouldn't</div> + +<?php echo "block_level";?> + + <?php echo "not_block_level";?> + diff --git a/tests/misc/pre.html b/tests/misc/pre.html new file mode 100644 index 0000000..a44ae12 --- /dev/null +++ b/tests/misc/pre.html @@ -0,0 +1,13 @@ +<pre> + +aaa + +bbb +</pre> + +<pre> +* and this is pre-formatted content +* and it should be printed just like this +* and not formatted as a list + +</pre>
\ No newline at end of file diff --git a/tests/misc/pre.txt b/tests/misc/pre.txt new file mode 100644 index 0000000..31243b5 --- /dev/null +++ b/tests/misc/pre.txt @@ -0,0 +1,14 @@ +<pre> + +aaa + +bbb +</pre> + +<pre> +* and this is pre-formatted content +* and it should be printed just like this +* and not formatted as a list + +</pre> + diff --git a/tests/misc/russian.html b/tests/misc/russian.html new file mode 100644 index 0000000..57c9688 --- /dev/null +++ b/tests/misc/russian.html @@ -0,0 +1,6 @@ +<h1>Недвард «Нед» Фландерс</h1> +<p><strong>Недвард «Нед» Фландерс</strong> (Nedward «Ned» Flanders) — вымышленный персонаж мультсериала «[Симпсоны][]», озвученный Гарри Ширером. Он и его семья живут по соседству от семьи Симпсонов. Набожный христианин, Нед является одним из столпов морали Спрингфилда. В эпизоде «Alone Again, Natura-Diddily» он овдовел, его жена Мод погибла в результате несчастного случая. </p> +<p>Нед был одним из первых персонажей в мультсериале, который не был членом семьи Симпсонов. Начиная с первых серий, он регулярно появляется в «Симпсонах». Считается, что Нед Фландерс был назван в честь улицы <em>Northeast Flanders St.</em> в <a href="http://www.portland.gov">Портленде</a>, Орегон, родном городе создателя мультсериала Мэтта Грейнинга]]. Надпись на указателе улицы <em>NE Flanders St.</em> хулиганы часто исправляли на <em>NED Flanders St.</em></p> +<h2>Биография</h2> +<p>Нед Фландерс родился в Нью-Йорке, его родители были битниками. Его отец в точности похож на взрослого Неда, только он носил козлиную бородку. Их отказ от воспитания Неда и то, что они, в общем-то, были плохими родителями («мы ничего в этом не понимаем и не знаем как начать») привело к тому, что Нед превратился в ужасного сорванца. В конце концов они согласились на экспериментальную восьмимесячную шлепологическую терапию Миннесотского Университета (воспоминания Неда в эпизоде «Hurricane Neddy»), которая научила его подавлять чувство злости. Побочным эфектом терапии стало то, что Нед стал ненавидеть своих родителей (это одна из двух вещей которые ненавидит Фландерс, вторая — отделения почты, чьи длинные очереди, суета и угрюмый персонал раздражают его).</p> +<p>У Неда есть странная привычка добавлять «дидли», «дадли» и другие бессмысленные слова в свои фразы при разговоре, например: «Hi-diddly-ho, neighbor-ino» («Приветик, соседушка»). Это результат сублимации его злости, вызванной сдерживанием гнева, который не имеет никакого другого выхода.</p>
\ No newline at end of file diff --git a/tests/misc/russian.txt b/tests/misc/russian.txt new file mode 100644 index 0000000..a742065 --- /dev/null +++ b/tests/misc/russian.txt @@ -0,0 +1,15 @@ +Недвард «Нед» Фландерс +====================== + + +**Недвард «Нед» Фландерс** (Nedward «Ned» Flanders) — вымышленный персонаж мультсериала «[Симпсоны][]», озвученный Гарри Ширером. Он и его семья живут по соседству от семьи Симпсонов. Набожный христианин, Нед является одним из столпов морали Спрингфилда. В эпизоде «Alone Again, Natura-Diddily» он овдовел, его жена Мод погибла в результате несчастного случая. + +Нед был одним из первых персонажей в мультсериале, который не был членом семьи Симпсонов. Начиная с первых серий, он регулярно появляется в «Симпсонах». Считается, что Нед Фландерс был назван в честь улицы *Northeast Flanders St.* в [Портленде](http://www.portland.gov), Орегон, родном городе создателя мультсериала Мэтта Грейнинга]]. Надпись на указателе улицы *NE Flanders St.* хулиганы часто исправляли на _NED Flanders St._ + +## Биография + +Нед Фландерс родился в Нью-Йорке, его родители были битниками. Его отец в точности похож на взрослого Неда, только он носил козлиную бородку. Их отказ от воспитания Неда и то, что они, в общем-то, были плохими родителями («мы ничего в этом не понимаем и не знаем как начать») привело к тому, что Нед превратился в ужасного сорванца. В конце концов они согласились на экспериментальную восьмимесячную шлепологическую терапию Миннесотского Университета (воспоминания Неда в эпизоде «Hurricane Neddy»), которая научила его подавлять чувство злости. Побочным эфектом терапии стало то, что Нед стал ненавидеть своих родителей (это одна из двух вещей которые ненавидит Фландерс, вторая — отделения почты, чьи длинные очереди, суета и угрюмый персонал раздражают его). + +У Неда есть странная привычка добавлять «дидли», «дадли» и другие бессмысленные слова в свои фразы при разговоре, например: «Hi-diddly-ho, neighbor-ino» («Приветик, соседушка»). Это результат сублимации его злости, вызванной сдерживанием гнева, который не имеет никакого другого выхода. + + diff --git a/tests/misc/smart_em.html b/tests/misc/smart_em.html new file mode 100644 index 0000000..5683b25 --- /dev/null +++ b/tests/misc/smart_em.html @@ -0,0 +1,5 @@ +<p><em>emphasis</em></p> +<p>this_is_not_emphasis</p> +<p>[<em>punctuation with emphasis</em>]</p> +<p>[<em>punctuation_with_emphasis</em>]</p> +<p>[punctuation_without_emphasis]</p>
\ No newline at end of file diff --git a/tests/misc/smart_em.txt b/tests/misc/smart_em.txt new file mode 100644 index 0000000..3c56842 --- /dev/null +++ b/tests/misc/smart_em.txt @@ -0,0 +1,9 @@ +_emphasis_ + +this_is_not_emphasis + +[_punctuation with emphasis_] + +[_punctuation_with_emphasis_] + +[punctuation_without_emphasis] diff --git a/tests/misc/some-test.html b/tests/misc/some-test.html new file mode 100644 index 0000000..a36d1ee --- /dev/null +++ b/tests/misc/some-test.html @@ -0,0 +1,66 @@ +<hr /> +<ul> +<li> +<p>as if</p> +</li> +<li> +<p>as if2</p> +</li> +</ul> +<hr /> +<ul> +<li> +<p>as if</p> +</li> +<li> +<p>as if2</p> +</li> +</ul> +<hr /> +<ul> +<li>as if + non_code</li> +<li>as if2</li> +</ul> +<p>Markdown</p> +<ul> +<li>Python + is ok<ul> +<li>Therefore i am</li> +</ul> +</li> +<li> +<p>Perl sucks + big time</p> +<ul> +<li>But that's +ok</li> +</ul> +</li> +<li> +<p>Python is +ok + Or not?</p> +</li> +</ul> +<p>Here is a normal paragraph</p> +<ol> +<li>Another list +with a bunch of items</li> +<li> +<p>Mostly fruits</p> +<ol> +<li>Apple</li> +<li>Pare</li> +</ol> +</li> +</ol> +<p>asdfasdfasd</p> +<pre><code># This is a code example +import stuff + +Another code example +* Lists and similar stuff + +> Should be ignored +</code></pre>
\ No newline at end of file diff --git a/tests/misc/some-test.txt b/tests/misc/some-test.txt new file mode 100644 index 0000000..0708817 --- /dev/null +++ b/tests/misc/some-test.txt @@ -0,0 +1,57 @@ +---------------------- + +* as if + +* as if2 + +---------------------- + +* as if + +* as if2 + +---------------------- + +* as if + non_code +* as if2 + + + + +Markdown + +* Python + is ok + * Therefore i am + +* Perl sucks + big time + * But that's + ok + +* Python is +ok + Or not? + +Here is a normal paragraph + +1. Another list +with a bunch of items +2. Mostly fruits + + + + 3. Apple + 4. Pare + +asdfasdfasd + + + # This is a code example + import stuff + + Another code example + * Lists and similar stuff + + > Should be ignored diff --git a/tests/misc/span.html b/tests/misc/span.html new file mode 100644 index 0000000..bafcf0f --- /dev/null +++ b/tests/misc/span.html @@ -0,0 +1,6 @@ +<p><span id="someId"> Foo <em>bar</em> Baz </span></p> +<div><b>*foo*</b></div> + +<div id="someId"> Foo *bar* Baz </div> + +<p><baza id="someId"> Foo <em>bar</em> Baz </baza></p>
\ No newline at end of file diff --git a/tests/misc/span.txt b/tests/misc/span.txt new file mode 100644 index 0000000..62bcf9b --- /dev/null +++ b/tests/misc/span.txt @@ -0,0 +1,10 @@ + +<span id="someId"> Foo *bar* Baz </span> + +<div><b>*foo*</b></div> + +<div id="someId"> Foo *bar* Baz </div> + +<baza id="someId"> Foo *bar* Baz </baza> + + diff --git a/tests/misc/strong-with-underscores.html b/tests/misc/strong-with-underscores.html new file mode 100644 index 0000000..08e6744 --- /dev/null +++ b/tests/misc/strong-with-underscores.html @@ -0,0 +1 @@ +<p><strong>this_is_strong</strong></p>
\ No newline at end of file diff --git a/tests/misc/strong-with-underscores.txt b/tests/misc/strong-with-underscores.txt new file mode 100644 index 0000000..1a3544f --- /dev/null +++ b/tests/misc/strong-with-underscores.txt @@ -0,0 +1 @@ +__this_is_strong__ diff --git a/tests/misc/stronintags.html b/tests/misc/stronintags.html new file mode 100644 index 0000000..cf18bd0 --- /dev/null +++ b/tests/misc/stronintags.html @@ -0,0 +1,4 @@ +<p>this is a <a href="http://example.com/"><strong>test</strong></a></p> +<p>this is a second <strong><a href="http://example.com">test</a></strong></p> +<p>reference <strong>[test][]</strong> +reference [<strong>test</strong>][]</p>
\ No newline at end of file diff --git a/tests/misc/stronintags.txt b/tests/misc/stronintags.txt new file mode 100644 index 0000000..01c118f --- /dev/null +++ b/tests/misc/stronintags.txt @@ -0,0 +1,8 @@ +this is a [**test**](http://example.com/) + +this is a second **[test](http://example.com)** + +reference **[test][]** +reference [**test**][] + + diff --git a/tests/misc/tabs-in-lists.html b/tests/misc/tabs-in-lists.html new file mode 100644 index 0000000..a1a92ec --- /dev/null +++ b/tests/misc/tabs-in-lists.html @@ -0,0 +1,42 @@ +<p>First a list with a tabbed line</p> +<ul> +<li> +<p>A</p> +</li> +<li> +<p>B</p> +</li> +</ul> +<p>Just a blank line:</p> +<ul> +<li> +<p>A</p> +</li> +<li> +<p>B</p> +</li> +</ul> +<p>Now a list with 4 spaces and some text:</p> +<ul> +<li>A +abcdef</li> +<li>B</li> +</ul> +<p>Now with a tab and an extra space:</p> +<ul> +<li> +<p>A</p> +</li> +<li> +<p>B</p> +</li> +</ul> +<p>Now a list with 4 spaces:</p> +<ul> +<li> +<p>A</p> +</li> +<li> +<p>B</p> +</li> +</ul>
\ No newline at end of file diff --git a/tests/misc/tabs-in-lists.txt b/tests/misc/tabs-in-lists.txt new file mode 100644 index 0000000..05fde23 --- /dev/null +++ b/tests/misc/tabs-in-lists.txt @@ -0,0 +1,32 @@ +First a list with a tabbed line + +* A + +* B + +Just a blank line: + +* A + +* B + + +Now a list with 4 spaces and some text: + +* A + abcdef +* B + + +Now with a tab and an extra space: + +* A + +* B + +Now a list with 4 spaces: + +* A + +* B + diff --git a/tests/misc/two-spaces.html b/tests/misc/two-spaces.html new file mode 100644 index 0000000..102d1db --- /dev/null +++ b/tests/misc/two-spaces.html @@ -0,0 +1,21 @@ +<p>This line has two spaces at the end<br /> +but this one has none +but this line has three <br /> +and this is the second from last line +in this test message</p> +<ul> +<li>This list item has two spaces.<br /> +</li> +<li> +<p>This has none. + This line has three. <br /> + This line has none. + And this line two.<br /> +</p> +<p>This line has none.</p> +</li> +<li> +<p>This line has none.</p> +</li> +</ul> +<p>And this is the end.</p>
\ No newline at end of file diff --git a/tests/misc/two-spaces.txt b/tests/misc/two-spaces.txt new file mode 100644 index 0000000..61c19f7 --- /dev/null +++ b/tests/misc/two-spaces.txt @@ -0,0 +1,17 @@ +This line has two spaces at the end +but this one has none +but this line has three +and this is the second from last line +in this test message + +* This list item has two spaces. +* This has none. + This line has three. + This line has none. + And this line two. + + This line has none. + +* This line has none. + +And this is the end. diff --git a/tests/misc/uche.html b/tests/misc/uche.html new file mode 100644 index 0000000..e62329d --- /dev/null +++ b/tests/misc/uche.html @@ -0,0 +1,3 @@ +<p><img alt="asif" src="http://fourthought.com/images/ftlogo.png" title="Fourthought logo" /></p> +<p><a href="http://fourthought.com/"><img alt="" src="http://fourthought.com/images/ftlogo.png" style="float: left; margin: 10px; border: none;" title="Fourthought logo" /></a></p> +<p><a href="http://link.com/"><img alt="text" src="x" /></a></p>
\ No newline at end of file diff --git a/tests/misc/uche.txt b/tests/misc/uche.txt new file mode 100644 index 0000000..a3dda1a --- /dev/null +++ b/tests/misc/uche.txt @@ -0,0 +1,7 @@ + + +[](http://fourthought.com/) + +[](http://link.com/) diff --git a/tests/misc/underscores.html b/tests/misc/underscores.html new file mode 100644 index 0000000..54bd9f9 --- /dev/null +++ b/tests/misc/underscores.html @@ -0,0 +1,6 @@ +<p>THIS_SHOULD_STAY_AS_IS</p> +<p>Here is some <em>emphasis</em>, ok?</p> +<p>Ok, at least <em>this</em> should work.</p> +<p>THIS<strong>SHOULD</strong>STAY</p> +<p>Here is some <strong>strong</strong> stuff.</p> +<p>THIS<strong><em>SHOULD</em></strong>STAY?</p>
\ No newline at end of file diff --git a/tests/misc/underscores.txt b/tests/misc/underscores.txt new file mode 100644 index 0000000..3c7f4bd --- /dev/null +++ b/tests/misc/underscores.txt @@ -0,0 +1,11 @@ +THIS_SHOULD_STAY_AS_IS + +Here is some _emphasis_, ok? + +Ok, at least _this_ should work. + +THIS__SHOULD__STAY + +Here is some __strong__ stuff. + +THIS___SHOULD___STAY? diff --git a/tests/misc/url_spaces.html b/tests/misc/url_spaces.html new file mode 100644 index 0000000..ebacb75 --- /dev/null +++ b/tests/misc/url_spaces.html @@ -0,0 +1,2 @@ +<p><a href="http://wikipedia.org/wiki/Dawn of War">Dawn of War</a></p> +<p><a href="http://wikipedia.org/wiki/Dawn of War" title="Dawn of War">Dawn of War</a></p>
\ No newline at end of file diff --git a/tests/misc/url_spaces.txt b/tests/misc/url_spaces.txt new file mode 100644 index 0000000..3d2a82d --- /dev/null +++ b/tests/misc/url_spaces.txt @@ -0,0 +1,4 @@ +[Dawn of War](http://wikipedia.org/wiki/Dawn of War) + + +[Dawn of War](http://wikipedia.org/wiki/Dawn of War "Dawn of War") diff --git a/tests/safe_mode/inline-html-advanced.html b/tests/safe_mode/inline-html-advanced.html new file mode 100644 index 0000000..e9dd2ec --- /dev/null +++ b/tests/safe_mode/inline-html-advanced.html @@ -0,0 +1,11 @@ +<p>Simple block on one line:</p> +<p><div>foo</div></p> +<p>And nested without indentation:</p> +<p><div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div></p>
\ No newline at end of file diff --git a/tests/safe_mode/inline-html-advanced.txt b/tests/safe_mode/inline-html-advanced.txt new file mode 100644 index 0000000..9d71ddc --- /dev/null +++ b/tests/safe_mode/inline-html-advanced.txt @@ -0,0 +1,14 @@ +Simple block on one line: + +<div>foo</div> + +And nested without indentation: + +<div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div> diff --git a/tests/safe_mode/inline-html-comments.html b/tests/safe_mode/inline-html-comments.html new file mode 100644 index 0000000..0f1e417 --- /dev/null +++ b/tests/safe_mode/inline-html-comments.html @@ -0,0 +1,8 @@ +<p>Paragraph one.</p> +<p><!-- This is a simple comment --></p> +<p><!-- + This is another comment. +--></p> +<p>Paragraph two.</p> +<p><!-- one comment block -- -- with two comments --></p> +<p>The end.</p>
\ No newline at end of file diff --git a/tests/safe_mode/inline-html-comments.txt b/tests/safe_mode/inline-html-comments.txt new file mode 100644 index 0000000..41d830d --- /dev/null +++ b/tests/safe_mode/inline-html-comments.txt @@ -0,0 +1,13 @@ +Paragraph one. + +<!-- This is a simple comment --> + +<!-- + This is another comment. +--> + +Paragraph two. + +<!-- one comment block -- -- with two comments --> + +The end. diff --git a/tests/safe_mode/inline-html-simple.html b/tests/safe_mode/inline-html-simple.html new file mode 100644 index 0000000..ad19a77 --- /dev/null +++ b/tests/safe_mode/inline-html-simple.html @@ -0,0 +1,45 @@ +<p>Here's a simple block:</p> +<p><div> + foo +</div></p> +<p>This should be a code block, though:</p> +<pre><code><div> + foo +</div> +</code></pre> +<p>As should this:</p> +<pre><code><div>foo</div> +</code></pre> +<p>Now, nested:</p> +<p><div> + <div> + <div> + foo + </div> + </div> +</div></p> +<p>This should just be an HTML comment:</p> +<p><!-- Comment --></p> +<p>Multiline:</p> +<p><!-- +Blah +Blah +--></p> +<p>Code block:</p> +<pre><code><!-- Comment --> +</code></pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<p><!-- foo --></p> +<p>Code:</p> +<pre><code><hr /> +</code></pre> +<p>Hr's:</p> +<p><hr></p> +<p><hr/></p> +<p><hr /></p> +<p><hr></p> +<p><hr/></p> +<p><hr /></p> +<p><hr class="foo" id="bar" /></p> +<p><hr class="foo" id="bar"/></p> +<p><hr class="foo" id="bar" ></p>
\ No newline at end of file diff --git a/tests/safe_mode/inline-html-simple.txt b/tests/safe_mode/inline-html-simple.txt new file mode 100644 index 0000000..14aa2dc --- /dev/null +++ b/tests/safe_mode/inline-html-simple.txt @@ -0,0 +1,69 @@ +Here's a simple block: + +<div> + foo +</div> + +This should be a code block, though: + + <div> + foo + </div> + +As should this: + + <div>foo</div> + +Now, nested: + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +This should just be an HTML comment: + +<!-- Comment --> + +Multiline: + +<!-- +Blah +Blah +--> + +Code block: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +<!-- foo --> + +Code: + + <hr /> + +Hr's: + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > + diff --git a/tests/safe_mode/script_tags.html b/tests/safe_mode/script_tags.html new file mode 100644 index 0000000..df63ffc --- /dev/null +++ b/tests/safe_mode/script_tags.html @@ -0,0 +1,28 @@ +<p>This should be stripped/escaped in safe_mode.</p> +<p><script> +alert("Hello world!") +</script></p> +<p>With blank lines.</p> +<p><script> + +alert("Hello world!") + +</script></p> +<p>Now with some weirdness</p> +<p><code><script <!-- +alert("Hello world!") +</script <></code> `</p> +<p>Try another way.</p> +<p><script <!-- +alert("Hello world!") +</script <> + +This time with blank lines. + +<script <!-- + +alert("Hello world!") + +</script <> + +</p>
\ No newline at end of file diff --git a/tests/safe_mode/script_tags.txt b/tests/safe_mode/script_tags.txt new file mode 100644 index 0000000..44041c2 --- /dev/null +++ b/tests/safe_mode/script_tags.txt @@ -0,0 +1,33 @@ +This should be stripped/escaped in safe_mode. + +<script> +alert("Hello world!") +</script> + +With blank lines. + +<script> + +alert("Hello world!") + +</script> + +Now with some weirdness + +``<script <!-- +alert("Hello world!") +</script <>`` ` + +Try another way. + +<script <!-- +alert("Hello world!") +</script <> + +This time with blank lines. + +<script <!-- + +alert("Hello world!") + +</script <> diff --git a/tests/safe_mode/unsafe_urls.html b/tests/safe_mode/unsafe_urls.html new file mode 100644 index 0000000..e617f35 --- /dev/null +++ b/tests/safe_mode/unsafe_urls.html @@ -0,0 +1,20 @@ +<p>These links should be unsafe and not allowed in safe_mode</p> +<p><a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a> +<a href="">link</a></p> +<p><img alt="img" src="" /> +<a href="">ref</a> +<img alt="imgref" src="" /></p> +<p>These should work regardless:</p> +<p><a href="relative/url.html">relative</a> +<a href="mailto:foo@bar.com">email</a> +<a href="news:some.news.group.com">news scheme</a> +<a href="http://example.com">http link</a></p>
\ No newline at end of file diff --git a/tests/safe_mode/unsafe_urls.txt b/tests/safe_mode/unsafe_urls.txt new file mode 100644 index 0000000..7bfd81d --- /dev/null +++ b/tests/safe_mode/unsafe_urls.txt @@ -0,0 +1,27 @@ +These links should be unsafe and not allowed in safe_mode + +[link](javascript:alert%28'Hello%20world!'%29) +[link](vbscript:msgbox%28%22Hello%20world!%22%29) +[link](livescript:alert%28'Hello%20world!'%29) +[link](mocha:[code]) +[link](jAvAsCrIpT:alert%28'Hello%20world!'%29) +[link](ja vas cr ipt:alert%28'Hello%20world!'%29) +[link](ja vas cr ipt:alert%28'Hello%20world!'%29) +[link](ja vas cr ipt:alert%28'Hello%20world!'%29) +[link](ja%09 %0Avas cr
ipt:alert%28'Hello%20world!'%29) +[link](ja%20vas%20cr%20ipt:alert%28'Hello%20world!'%29) +[link](live%20script:alert%28'Hello%20world!'%29) + + +[ref][] +![imgref][] + +[ref]: javascript:alert%29'XSS'%29 +[imgref]: javascript:alert%29'XSS'%29 + +These should work regardless: + +[relative](relative/url.html) +[email](mailto:foo@bar.com) +[news scheme](news:some.news.group.com) +[http link](http://example.com) |