blob: d3d78c5ab98fe546146e6d06f0f60fcd211c9de4 (
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
|
/*
* Copyright 2000-2013 JetBrains s.r.o.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.jetbrains.python;
import com.intellij.lang.Language;
import com.intellij.openapi.editor.Document;
import com.intellij.openapi.fileTypes.LanguageFileType;
import com.intellij.openapi.project.Project;
import com.intellij.openapi.util.TextRange;
import com.intellij.openapi.util.text.StringUtil;
import com.intellij.openapi.vfs.CharsetToolkit;
import com.intellij.openapi.vfs.VirtualFile;
import com.intellij.psi.PsiDocumentManager;
import com.intellij.psi.PsiFile;
import icons.PythonPsiApiIcons;
import org.jetbrains.annotations.NotNull;
import org.jetbrains.annotations.Nullable;
import javax.swing.*;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.StringReader;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.nio.charset.IllegalCharsetNameException;
import java.nio.charset.UnsupportedCharsetException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* @author yole
*/
public class PythonFileType extends LanguageFileType {
private static final Pattern ENCODING_PATTERN = Pattern.compile("coding[:=]\\s*([-\\w.]+)");
public static final int MAX_CHARSET_ENCODING_LINE = 2;
public static PythonFileType INSTANCE = new PythonFileType();
public PythonFileType() {
this(new PythonLanguage());
}
public PythonFileType(Language language) {
super(language);
}
@NotNull
public String getName() {
return "Python";
}
@NotNull
public String getDescription() {
return "Python files";
}
@NotNull
public String getDefaultExtension() {
return "py";
}
@NotNull
public Icon getIcon() {
return PythonPsiApiIcons.PythonFile;
}
@Override
public String getCharset(@NotNull VirtualFile file, byte[] content) {
if (CharsetToolkit.hasUTF8Bom(content)) {
return CharsetToolkit.UTF8;
}
ByteBuffer bytes = ByteBuffer.wrap(content, 0, Math.min(256, content.length));
String decoded = CharsetToolkit.UTF8_CHARSET.decode(bytes).toString();
return getCharsetFromEncodingDeclaration(StringUtil.convertLineSeparators(decoded));
}
@Override
public Charset extractCharsetFromFileContent(@Nullable Project project, @Nullable VirtualFile file, @NotNull String content) {
final String charsetName = getCharsetFromEncodingDeclaration(content);
if (charsetName == null) {
return null;
}
try {
return Charset.forName(charsetName);
}
catch (IllegalCharsetNameException e) {
return null;
}
catch (UnsupportedCharsetException e) {
return null;
}
}
@Nullable
public static String getCharsetFromEncodingDeclaration(@NotNull PsiFile file) {
final Document document = PsiDocumentManager.getInstance(file.getProject()).getDocument(file);
final String content;
if (document != null && document.getLineCount() > MAX_CHARSET_ENCODING_LINE) {
final int offset = document.getLineEndOffset(MAX_CHARSET_ENCODING_LINE);
content = document.getText(TextRange.create(0, offset));
}
else {
content = file.getText();
}
return getCharsetFromEncodingDeclaration(content);
}
@Nullable
private static String getCharsetFromEncodingDeclaration(@Nullable String content) {
if (content == null || content.isEmpty()) {
return null;
}
try {
final BufferedReader reader = new BufferedReader(new StringReader(content));
try {
for (int i = 0; i < MAX_CHARSET_ENCODING_LINE; i++) {
final String line = reader.readLine();
if (line == null) {
return null;
}
final Matcher matcher = ENCODING_PATTERN.matcher(line);
if (matcher.find()) {
final String charset = matcher.group(1);
return normalizeCharset(charset);
}
}
} finally {
reader.close();
}
}
catch (IOException ignored) {
}
return null;
}
@Nullable
private static String normalizeCharset(String charset) {
if (charset == null) {
return null;
}
charset = charset.toLowerCase();
if ("latin-1".equals(charset)) {
return "iso-8859-1";
}
return charset;
}
}
|
