Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/Pygments/pygments/lexers/__init__.py
eric6/ThirdParty/Pygments/pygments/lexers/__init__.py
- changeset 6942
- 2602857055c5
- parent 5713
- 6762afd9f963
- child 7547
- 21b0534faebc
equal
deleted
inserted
replaced
| 6941:f99d60d6b59b | 6942:2602857055c5 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers | |
| 4 ~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Pygments lexers. | |
| 7 | |
| 8 :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. | |
| 9 :license: BSD, see LICENSE for details. | |
| 10 """ | |
| 11 | |
| 12 import re | |
| 13 import sys | |
| 14 import types | |
| 15 import fnmatch | |
| 16 from os.path import basename | |
| 17 | |
| 18 from pygments.lexers._mapping import LEXERS | |
| 19 from pygments.modeline import get_filetype_from_buffer | |
| 20 from pygments.plugin import find_plugin_lexers | |
| 21 from pygments.util import ClassNotFound, itervalues, guess_decode | |
| 22 | |
| 23 | |
| 24 __all__ = ['get_lexer_by_name', 'get_lexer_for_filename', 'find_lexer_class', | |
| 25 'guess_lexer', 'load_lexer_from_file'] + list(LEXERS) | |
| 26 | |
| 27 _lexer_cache = {} | |
| 28 _pattern_cache = {} | |
| 29 | |
| 30 | |
| 31 def _fn_matches(fn, glob): | |
| 32 """Return whether the supplied file name fn matches pattern filename.""" | |
| 33 if glob not in _pattern_cache: | |
| 34 pattern = _pattern_cache[glob] = re.compile(fnmatch.translate(glob)) | |
| 35 return pattern.match(fn) | |
| 36 return _pattern_cache[glob].match(fn) | |
| 37 | |
| 38 | |
| 39 def _load_lexers(module_name): | |
| 40 """Load a lexer (and all others in the module too).""" | |
| 41 mod = __import__(module_name, None, None, ['__all__']) | |
| 42 for lexer_name in mod.__all__: | |
| 43 cls = getattr(mod, lexer_name) | |
| 44 _lexer_cache[cls.name] = cls | |
| 45 | |
| 46 | |
| 47 def get_all_lexers(): | |
| 48 """Return a generator of tuples in the form ``(name, aliases, | |
| 49 filenames, mimetypes)`` of all know lexers. | |
| 50 """ | |
| 51 for item in itervalues(LEXERS): | |
| 52 yield item[1:] | |
| 53 for lexer in find_plugin_lexers(): | |
| 54 yield lexer.name, lexer.aliases, lexer.filenames, lexer.mimetypes | |
| 55 | |
| 56 | |
| 57 def find_lexer_class(name): | |
| 58 """Lookup a lexer class by name. | |
| 59 | |
| 60 Return None if not found. | |
| 61 """ | |
| 62 if name in _lexer_cache: | |
| 63 return _lexer_cache[name] | |
| 64 # lookup builtin lexers | |
| 65 for module_name, lname, aliases, _, _ in itervalues(LEXERS): | |
| 66 if name == lname: | |
| 67 _load_lexers(module_name) | |
| 68 return _lexer_cache[name] | |
| 69 # continue with lexers from setuptools entrypoints | |
| 70 for cls in find_plugin_lexers(): | |
| 71 if cls.name == name: | |
| 72 return cls | |
| 73 | |
| 74 | |
| 75 def find_lexer_class_by_name(_alias): | |
| 76 """Lookup a lexer class by alias. | |
| 77 | |
| 78 Like `get_lexer_by_name`, but does not instantiate the class. | |
| 79 | |
| 80 .. versionadded:: 2.2 | |
| 81 """ | |
| 82 if not _alias: | |
| 83 raise ClassNotFound('no lexer for alias %r found' % _alias) | |
| 84 # lookup builtin lexers | |
| 85 for module_name, name, aliases, _, _ in itervalues(LEXERS): | |
| 86 if _alias.lower() in aliases: | |
| 87 if name not in _lexer_cache: | |
| 88 _load_lexers(module_name) | |
| 89 return _lexer_cache[name] | |
| 90 # continue with lexers from setuptools entrypoints | |
| 91 for cls in find_plugin_lexers(): | |
| 92 if _alias.lower() in cls.aliases: | |
| 93 return cls | |
| 94 raise ClassNotFound('no lexer for alias %r found' % _alias) | |
| 95 | |
| 96 | |
| 97 def get_lexer_by_name(_alias, **options): | |
| 98 """Get a lexer by an alias. | |
| 99 | |
| 100 Raises ClassNotFound if not found. | |
| 101 """ | |
| 102 if not _alias: | |
| 103 raise ClassNotFound('no lexer for alias %r found' % _alias) | |
| 104 | |
| 105 # lookup builtin lexers | |
| 106 for module_name, name, aliases, _, _ in itervalues(LEXERS): | |
| 107 if _alias.lower() in aliases: | |
| 108 if name not in _lexer_cache: | |
| 109 _load_lexers(module_name) | |
| 110 return _lexer_cache[name](**options) | |
| 111 # continue with lexers from setuptools entrypoints | |
| 112 for cls in find_plugin_lexers(): | |
| 113 if _alias.lower() in cls.aliases: | |
| 114 return cls(**options) | |
| 115 raise ClassNotFound('no lexer for alias %r found' % _alias) | |
| 116 | |
| 117 | |
| 118 def load_lexer_from_file(filename, lexername="CustomLexer", **options): | |
| 119 """Load a lexer from a file. | |
| 120 | |
| 121 This method expects a file located relative to the current working | |
| 122 directory, which contains a Lexer class. By default, it expects the | |
| 123 Lexer to be name CustomLexer; you can specify your own class name | |
| 124 as the second argument to this function. | |
| 125 | |
| 126 Users should be very careful with the input, because this method | |
| 127 is equivalent to running eval on the input file. | |
| 128 | |
| 129 Raises ClassNotFound if there are any problems importing the Lexer. | |
| 130 | |
| 131 .. versionadded:: 2.2 | |
| 132 """ | |
| 133 try: | |
| 134 # This empty dict will contain the namespace for the exec'd file | |
| 135 custom_namespace = {} | |
| 136 exec(open(filename, 'rb').read(), custom_namespace) | |
| 137 # Retrieve the class `lexername` from that namespace | |
| 138 if lexername not in custom_namespace: | |
| 139 raise ClassNotFound('no valid %s class found in %s' % | |
| 140 (lexername, filename)) | |
| 141 lexer_class = custom_namespace[lexername] | |
| 142 # And finally instantiate it with the options | |
| 143 return lexer_class(**options) | |
| 144 except IOError as err: | |
| 145 raise ClassNotFound('cannot read %s' % filename) | |
| 146 except ClassNotFound as err: | |
| 147 raise | |
| 148 except Exception as err: | |
| 149 raise ClassNotFound('error when loading custom lexer: %s' % err) | |
| 150 | |
| 151 | |
| 152 def find_lexer_class_for_filename(_fn, code=None): | |
| 153 """Get a lexer for a filename. | |
| 154 | |
| 155 If multiple lexers match the filename pattern, use ``analyse_text()`` to | |
| 156 figure out which one is more appropriate. | |
| 157 | |
| 158 Returns None if not found. | |
| 159 """ | |
| 160 matches = [] | |
| 161 fn = basename(_fn) | |
| 162 for modname, name, _, filenames, _ in itervalues(LEXERS): | |
| 163 for filename in filenames: | |
| 164 if _fn_matches(fn, filename): | |
| 165 if name not in _lexer_cache: | |
| 166 _load_lexers(modname) | |
| 167 matches.append((_lexer_cache[name], filename)) | |
| 168 for cls in find_plugin_lexers(): | |
| 169 for filename in cls.filenames: | |
| 170 if _fn_matches(fn, filename): | |
| 171 matches.append((cls, filename)) | |
| 172 | |
| 173 if sys.version_info > (3,) and isinstance(code, bytes): | |
| 174 # decode it, since all analyse_text functions expect unicode | |
| 175 code = guess_decode(code) | |
| 176 | |
| 177 def get_rating(info): | |
| 178 cls, filename = info | |
| 179 # explicit patterns get a bonus | |
| 180 bonus = '*' not in filename and 0.5 or 0 | |
| 181 # The class _always_ defines analyse_text because it's included in | |
| 182 # the Lexer class. The default implementation returns None which | |
| 183 # gets turned into 0.0. Run scripts/detect_missing_analyse_text.py | |
| 184 # to find lexers which need it overridden. | |
| 185 if code: | |
| 186 return cls.analyse_text(code) + bonus, cls.__name__ | |
| 187 return cls.priority + bonus, cls.__name__ | |
| 188 | |
| 189 if matches: | |
| 190 matches.sort(key=get_rating) | |
| 191 # print "Possible lexers, after sort:", matches | |
| 192 return matches[-1][0] | |
| 193 | |
| 194 | |
| 195 def get_lexer_for_filename(_fn, code=None, **options): | |
| 196 """Get a lexer for a filename. | |
| 197 | |
| 198 If multiple lexers match the filename pattern, use ``analyse_text()`` to | |
| 199 figure out which one is more appropriate. | |
| 200 | |
| 201 Raises ClassNotFound if not found. | |
| 202 """ | |
| 203 res = find_lexer_class_for_filename(_fn, code) | |
| 204 if not res: | |
| 205 raise ClassNotFound('no lexer for filename %r found' % _fn) | |
| 206 return res(**options) | |
| 207 | |
| 208 | |
| 209 def get_lexer_for_mimetype(_mime, **options): | |
| 210 """Get a lexer for a mimetype. | |
| 211 | |
| 212 Raises ClassNotFound if not found. | |
| 213 """ | |
| 214 for modname, name, _, _, mimetypes in itervalues(LEXERS): | |
| 215 if _mime in mimetypes: | |
| 216 if name not in _lexer_cache: | |
| 217 _load_lexers(modname) | |
| 218 return _lexer_cache[name](**options) | |
| 219 for cls in find_plugin_lexers(): | |
| 220 if _mime in cls.mimetypes: | |
| 221 return cls(**options) | |
| 222 raise ClassNotFound('no lexer for mimetype %r found' % _mime) | |
| 223 | |
| 224 | |
| 225 def _iter_lexerclasses(plugins=True): | |
| 226 """Return an iterator over all lexer classes.""" | |
| 227 for key in sorted(LEXERS): | |
| 228 module_name, name = LEXERS[key][:2] | |
| 229 if name not in _lexer_cache: | |
| 230 _load_lexers(module_name) | |
| 231 yield _lexer_cache[name] | |
| 232 if plugins: | |
| 233 for lexer in find_plugin_lexers(): | |
| 234 yield lexer | |
| 235 | |
| 236 | |
| 237 def guess_lexer_for_filename(_fn, _text, **options): | |
| 238 """ | |
| 239 Lookup all lexers that handle those filenames primary (``filenames``) | |
| 240 or secondary (``alias_filenames``). Then run a text analysis for those | |
| 241 lexers and choose the best result. | |
| 242 | |
| 243 usage:: | |
| 244 | |
| 245 >>> from pygments.lexers import guess_lexer_for_filename | |
| 246 >>> guess_lexer_for_filename('hello.html', '<%= @foo %>') | |
| 247 <pygments.lexers.templates.RhtmlLexer object at 0xb7d2f32c> | |
| 248 >>> guess_lexer_for_filename('hello.html', '<h1>{{ title|e }}</h1>') | |
| 249 <pygments.lexers.templates.HtmlDjangoLexer object at 0xb7d2f2ac> | |
| 250 >>> guess_lexer_for_filename('style.css', 'a { color: <?= $link ?> }') | |
| 251 <pygments.lexers.templates.CssPhpLexer object at 0xb7ba518c> | |
| 252 """ | |
| 253 fn = basename(_fn) | |
| 254 primary = {} | |
| 255 matching_lexers = set() | |
| 256 for lexer in _iter_lexerclasses(): | |
| 257 for filename in lexer.filenames: | |
| 258 if _fn_matches(fn, filename): | |
| 259 matching_lexers.add(lexer) | |
| 260 primary[lexer] = True | |
| 261 for filename in lexer.alias_filenames: | |
| 262 if _fn_matches(fn, filename): | |
| 263 matching_lexers.add(lexer) | |
| 264 primary[lexer] = False | |
| 265 if not matching_lexers: | |
| 266 raise ClassNotFound('no lexer for filename %r found' % fn) | |
| 267 if len(matching_lexers) == 1: | |
| 268 return matching_lexers.pop()(**options) | |
| 269 result = [] | |
| 270 for lexer in matching_lexers: | |
| 271 rv = lexer.analyse_text(_text) | |
| 272 if rv == 1.0: | |
| 273 return lexer(**options) | |
| 274 result.append((rv, lexer)) | |
| 275 | |
| 276 def type_sort(t): | |
| 277 # sort by: | |
| 278 # - analyse score | |
| 279 # - is primary filename pattern? | |
| 280 # - priority | |
| 281 # - last resort: class name | |
| 282 return (t[0], primary[t[1]], t[1].priority, t[1].__name__) | |
| 283 result.sort(key=type_sort) | |
| 284 | |
| 285 return result[-1][1](**options) | |
| 286 | |
| 287 | |
| 288 def guess_lexer(_text, **options): | |
| 289 """Guess a lexer by strong distinctions in the text (eg, shebang).""" | |
| 290 | |
| 291 # try to get a vim modeline first | |
| 292 ft = get_filetype_from_buffer(_text) | |
| 293 | |
| 294 if ft is not None: | |
| 295 try: | |
| 296 return get_lexer_by_name(ft, **options) | |
| 297 except ClassNotFound: | |
| 298 pass | |
| 299 | |
| 300 best_lexer = [0.0, None] | |
| 301 for lexer in _iter_lexerclasses(): | |
| 302 rv = lexer.analyse_text(_text) | |
| 303 if rv == 1.0: | |
| 304 return lexer(**options) | |
| 305 if rv > best_lexer[0]: | |
| 306 best_lexer[:] = (rv, lexer) | |
| 307 if not best_lexer[0] or best_lexer[1] is None: | |
| 308 raise ClassNotFound('no lexer matching the text found') | |
| 309 return best_lexer[1](**options) | |
| 310 | |
| 311 | |
| 312 class _automodule(types.ModuleType): | |
| 313 """Automatically import lexers.""" | |
| 314 | |
| 315 def __getattr__(self, name): | |
| 316 info = LEXERS.get(name) | |
| 317 if info: | |
| 318 _load_lexers(info[0]) | |
| 319 cls = _lexer_cache[info[1]] | |
| 320 setattr(self, name, cls) | |
| 321 return cls | |
| 322 raise AttributeError(name) | |
| 323 | |
| 324 | |
| 325 oldmod = sys.modules[__name__] | |
| 326 newmod = _automodule(__name__) | |
| 327 newmod.__dict__.update(oldmod.__dict__) | |
| 328 sys.modules[__name__] = newmod | |
| 329 del newmod.newmod, newmod.oldmod, newmod.sys, newmod.types |
