aboutsummaryrefslogtreecommitdiff
path: root/markdown/extensions/codehilite.py
blob: a54ba21c01d232b72a5d820a8b2f9211674be279 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
"""
CodeHilite Extension for Python-Markdown
========================================

Adds code/syntax highlighting to standard Python-Markdown code blocks.

See <https://Python-Markdown.github.io/extensions/code_hilite>
for documentation.

Original code Copyright 2006-2008 [Waylan Limberg](http://achinghead.com/).

All changes Copyright 2008-2014 The Python Markdown Project

License: [BSD](https://opensource.org/licenses/bsd-license.php)

"""

from . import Extension
from ..treeprocessors import Treeprocessor
from ..util import parseBoolValue

try:  # pragma: no cover
    from pygments import highlight
    from pygments.lexers import get_lexer_by_name, guess_lexer
    from pygments.formatters import get_formatter_by_name
    from pygments.util import ClassNotFound
    pygments = True
except ImportError:  # pragma: no cover
    pygments = False


def parse_hl_lines(expr):
    """Support our syntax for emphasizing certain lines of code.

    expr should be like '1 2' to emphasize lines 1 and 2 of a code block.
    Returns a list of ints, the line numbers to emphasize.
    """
    if not expr:
        return []

    try:
        return list(map(int, expr.split()))
    except ValueError:  # pragma: no cover
        return []


# ------------------ The Main CodeHilite Class ----------------------
class CodeHilite:
    """
    Determine language of source code, and pass it on to the Pygments highlighter.

    Usage:
        code = CodeHilite(src=some_code, lang='python')
        html = code.hilite()

    Arguments:
    * src: Source string or any object with a .readline attribute.

    * lang: String name of Pygments lexer to use for highlighting. Default: `None`.

    * guess_lang: Auto-detect which lexer to use. Ignored if `lang` is set to a valid
      value. Default: `True`.

    * use_pygments: Pass code to pygments for code highlighting. If `False`, the code is
      instead wrapped for highlighting by a JavaScript library. Default: `True`.

    * pygments_formatter: The name of a Pygments formatter or a formatter class used for
      highlighting the code blocks. Default: `html`.

    * linenums: An alias to Pygments `linenos` formatter option. Default: `None`.

    * css_class: An alias to Pygments `cssclass` formatter option. Default: 'codehilite'.

    * lang_prefix: Prefix prepended to the language. Default: "language-".

    Other Options:
    Any other options are accepted and passed on to the lexer and formatter. Therefore,
    valid options include any options which are accepted by the `html` formatter or
    whichever lexer the code's language uses. Note that most lexers do not have any
    options. However, a few have very useful options, such as PHP's `startinline` option.
    Any invalid options are ignored without error.

    Formatter options: https://pygments.org/docs/formatters/#HtmlFormatter
    Lexer Options: https://pygments.org/docs/lexers/

    Additionally, when Pygments is enabled, the code's language is passed to the
    formatter as an extra option `lang_str`, whose value being `{lang_prefix}{lang}`.
    This option has no effect to the Pygments's builtin formatters.

    Advanced Usage:
        code = CodeHilite(
            src = some_code,
            lang = 'php',
            startinline = True,      # Lexer option. Snippet does not start with `<?php`.
            linenostart = 42,        # Formatter option. Snippet starts on line 42.
            hl_lines = [45, 49, 50], # Formatter option. Highlight lines 45, 49, and 50.
            linenos = 'inline'       # Formatter option. Avoid alignment problems.
        )
        html = code.hilite()

    """

    def __init__(self, src, **options):
        self.src = src
        self.lang = options.pop('lang', None)
        self.guess_lang = options.pop('guess_lang', True)
        self.use_pygments = options.pop('use_pygments', True)
        self.lang_prefix = options.pop('lang_prefix', 'language-')
        self.pygments_formatter = options.pop('pygments_formatter', 'html')

        if 'linenos' not in options:
            options['linenos'] = options.pop('linenums', None)
        if 'cssclass' not in options:
            options['cssclass'] = options.pop('css_class', 'codehilite')
        if 'wrapcode' not in options:
            # Override pygments default
            options['wrapcode'] = True
        # Disallow use of `full` option
        options['full'] = False

        self.options = options

    def hilite(self, shebang=True):
        """
        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')

        if self.lang is None and shebang:
            self._parseHeader()

        if pygments and self.use_pygments:
            try:
                lexer = get_lexer_by_name(self.lang, **self.options)
            except ValueError:
                try:
                    if self.guess_lang:
                        lexer = guess_lexer(self.src, **self.options)
                    else:
                        lexer = get_lexer_by_name('text', **self.options)
                except ValueError:  # pragma: no cover
                    lexer = get_lexer_by_name('text', **self.options)
            if not self.lang:
                # Use the guessed lexer's language instead
                self.lang = lexer.aliases[0]
            lang_str = f'{self.lang_prefix}{self.lang}'
            if isinstance(self.pygments_formatter, str):
                try:
                    formatter = get_formatter_by_name(self.pygments_formatter, **self.options)
                except ClassNotFound:
                    formatter = get_formatter_by_name('html', **self.options)
            else:
                formatter = self.pygments_formatter(lang_str=lang_str, **self.options)
            return highlight(self.src, lexer, formatter)
        else:
            # just escape and build markup usable by JS highlighting libs
            txt = self.src.replace('&', '&amp;')
            txt = txt.replace('<', '&lt;')
            txt = txt.replace('>', '&gt;')
            txt = txt.replace('"', '&quot;')
            classes = []
            if self.lang:
                classes.append('{}{}'.format(self.lang_prefix, self.lang))
            if self.options['linenos']:
                classes.append('linenums')
            class_str = ''
            if classes:
                class_str = ' class="{}"'.format(' '.join(classes))
            return '<pre class="{}"><code{}>{}\n</code></pre>\n'.format(
                self.options['cssclass'],
                class_str,
                txt
            )

    def _parseHeader(self):
        """
        Determines language of a code block from shebang line and whether the
        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 line 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 identification 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.

        Also parses optional list of highlight lines, like:

            :::python hl_lines="1 3"
        """

        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
            \s*                             # Arbitrary whitespace
            # Optional highlight lines, single- or double-quote-delimited
            (hl_lines=(?P<quot>"|')(?P<hl_lines>.*?)(?P=quot))?
            ''',  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:  # pragma: no cover
                self.lang = None
            if m.group('path'):
                # path exists - restore first line
                lines.insert(0, fl)
            if self.options['linenos'] is None and m.group('shebang'):
                # Overridable and Shebang exists - use line numbers
                self.options['linenos'] = True

            self.options['hl_lines'] = parse_hl_lines(m.group('hl_lines'))
        else:
            # No match
            lines.insert(0, fl)

        self.src = "\n".join(lines).strip("\n")


# ------------------ The Markdown Extension -------------------------------


class HiliteTreeprocessor(Treeprocessor):
    """ Highlight source code in code blocks. """

    def code_unescape(self, text):
        """Unescape code."""
        text = text.replace("&lt;", "<")
        text = text.replace("&gt;", ">")
        # Escaped '&' should be replaced at the end to avoid
        # conflicting with < and >.
        text = text.replace("&amp;", "&")
        return text

    def run(self, root):
        """ Find code blocks and store in htmlStash. """
        blocks = root.iter('pre')
        for block in blocks:
            if len(block) == 1 and block[0].tag == 'code':
                local_config = self.config.copy()
                code = CodeHilite(
                    self.code_unescape(block[0].text),
                    tab_length=self.md.tab_length,
                    style=local_config.pop('pygments_style', 'default'),
                    **local_config
                )
                placeholder = self.md.htmlStash.store(code.hilite())
                # 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(Extension):
    """ Add source code highlighting to markdown codeblocks. """

    def __init__(self, **kwargs):
        # define default configs
        self.config = {
            'linenums': [None,
                         "Use lines numbers. True|table|inline=yes, False=no, None=auto"],
            'guess_lang': [True,
                           "Automatic language detection - Default: True"],
            'css_class': ["codehilite",
                          "Set class name for wrapper <div> - "
                          "Default: codehilite"],
            'pygments_style': ['default',
                               'Pygments HTML Formatter Style '
                               '(Colorscheme) - Default: default'],
            'noclasses': [False,
                          'Use inline styles instead of CSS classes - '
                          'Default false'],
            'use_pygments': [True,
                             'Use Pygments to Highlight code blocks. '
                             'Disable if using a JavaScript library. '
                             'Default: True'],
            'lang_prefix': [
                'language-',
                'Prefix prepended to the language when use_pygments is false. Default: "language-"'
            ],
            'pygments_formatter': ['html',
                                   'Use a specific formatter for Pygments highlighting.'
                                   'Default: "html"',
                                   ],
            }

        for key, value in kwargs.items():
            if key in self.config:
                self.setConfig(key, value)
            else:
                # manually set unknown keywords.
                if isinstance(value, str):
                    try:
                        # Attempt to parse str as a bool value
                        value = parseBoolValue(value, preserve_none=True)
                    except ValueError:
                        pass  # Assume it's not a bool value. Use as-is.
                self.config[key] = [value, '']

    def extendMarkdown(self, md):
        """ Add HilitePostprocessor to Markdown instance. """
        hiliter = HiliteTreeprocessor(md)
        hiliter.config = self.getConfigs()
        md.treeprocessors.register(hiliter, 'hilite', 30)

        md.registerExtension(self)


def makeExtension(**kwargs):  # pragma: no cover
    return CodeHiliteExtension(**kwargs)