summaryrefslogtreecommitdiff
path: root/pygments/lexers/__init__.py
blob: 578a9101533e52ef676346c2175f96bcb29d24dc (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
# -*- coding: utf-8 -*-
"""
    pygments.lexers
    ~~~~~~~~~~~~~~~

    Pygments lexers.

    :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
import sys
import types
import fnmatch
from os.path import basename

from pygments.lexers._mapping import LEXERS
from pygments.modeline import get_filetype_from_buffer
from pygments.plugin import find_plugin_lexers
from pygments.util import ClassNotFound, itervalues


__all__ = ['get_lexer_by_name', 'get_lexer_for_filename', 'find_lexer_class',
           'guess_lexer'] + list(LEXERS)

_lexer_cache = {}
_pattern_cache = {}


def _fn_matches(fn, glob):
    """Return whether the supplied file name fn matches pattern filename."""
    if glob not in _pattern_cache:
        pattern = _pattern_cache[glob] = re.compile(fnmatch.translate(glob))
        return pattern.match(fn)
    return _pattern_cache[glob].match(fn)


def _load_lexers(module_name):
    """Load a lexer (and all others in the module too)."""
    mod = __import__(module_name, None, None, ['__all__'])
    for lexer_name in mod.__all__:
        cls = getattr(mod, lexer_name)
        _lexer_cache[cls.name] = cls


def get_all_lexers():
    """Return a generator of tuples in the form ``(name, aliases,
    filenames, mimetypes)`` of all know lexers.
    """
    for item in itervalues(LEXERS):
        yield item[1:]
    for lexer in find_plugin_lexers():
        yield lexer.name, lexer.aliases, lexer.filenames, lexer.mimetypes


def find_lexer_class(name):
    """Lookup a lexer class by name.

    Return None if not found.
    """
    if name in _lexer_cache:
        return _lexer_cache[name]
    # lookup builtin lexers
    for module_name, lname, aliases, _, _ in itervalues(LEXERS):
        if name == lname:
            _load_lexers(module_name)
            return _lexer_cache[name]
    # continue with lexers from setuptools entrypoints
    for cls in find_plugin_lexers():
        if cls.name == name:
            return cls


def get_lexer_by_name(_alias, **options):
    """Get a lexer by an alias.

    Raises ClassNotFound if not found.
    """
    if not _alias:
        raise ClassNotFound('no lexer for alias %r found' % _alias)

    # lookup builtin lexers
    for module_name, name, aliases, _, _ in itervalues(LEXERS):
        if _alias.lower() in aliases:
            if name not in _lexer_cache:
                _load_lexers(module_name)
            return _lexer_cache[name](**options)
    # continue with lexers from setuptools entrypoints
    for cls in find_plugin_lexers():
        if _alias in cls.aliases:
            return cls(**options)
    raise ClassNotFound('no lexer for alias %r found' % _alias)


def find_lexer_class_for_filename(_fn, code=None):
    """Get a lexer for a filename.

    If multiple lexers match the filename pattern, use ``analyse_text()`` to
    figure out which one is more appropriate.

    Returns None if not found.
    """
    matches = []
    fn = basename(_fn)
    for modname, name, _, filenames, _ in itervalues(LEXERS):
        for filename in filenames:
            if _fn_matches(fn, filename):
                if name not in _lexer_cache:
                    _load_lexers(modname)
                matches.append((_lexer_cache[name], filename))
    for cls in find_plugin_lexers():
        for filename in cls.filenames:
            if _fn_matches(fn, filename):
                matches.append((cls, filename))

    if sys.version_info > (3,) and isinstance(code, bytes):
        # decode it, since all analyse_text functions expect unicode
        code = code.decode('latin1')

    def get_rating(info):
        cls, filename = info
        # explicit patterns get a bonus
        bonus = '*' not in filename and 0.5 or 0
        # The class _always_ defines analyse_text because it's included in
        # the Lexer class.  The default implementation returns None which
        # gets turned into 0.0.  Run scripts/detect_missing_analyse_text.py
        # to find lexers which need it overridden.
        if code:
            return cls.analyse_text(code) + bonus
        return cls.priority + bonus

    if matches:
        matches.sort(key=get_rating)
        # print "Possible lexers, after sort:", matches
        return matches[-1][0]


def get_lexer_for_filename(_fn, code=None, **options):
    """Get a lexer for a filename.

    If multiple lexers match the filename pattern, use ``analyse_text()`` to
    figure out which one is more appropriate.

    Raises ClassNotFound if not found.
    """
    res = find_lexer_class_for_filename(_fn, code)
    if not res:
        raise ClassNotFound('no lexer for filename %r found' % _fn)
    return res(**options)


def get_lexer_for_mimetype(_mime, **options):
    """Get a lexer for a mimetype.

    Raises ClassNotFound if not found.
    """
    for modname, name, _, _, mimetypes in itervalues(LEXERS):
        if _mime in mimetypes:
            if name not in _lexer_cache:
                _load_lexers(modname)
            return _lexer_cache[name](**options)
    for cls in find_plugin_lexers():
        if _mime in cls.mimetypes:
            return cls(**options)
    raise ClassNotFound('no lexer for mimetype %r found' % _mime)


def _iter_lexerclasses(plugins=True):
    """Return an iterator over all lexer classes."""
    for key in sorted(LEXERS):
        module_name, name = LEXERS[key][:2]
        if name not in _lexer_cache:
            _load_lexers(module_name)
        yield _lexer_cache[name]
    if plugins:
        for lexer in find_plugin_lexers():
            yield lexer


def guess_lexer_for_filename(_fn, _text, **options):
    """
    Lookup all lexers that handle those filenames primary (``filenames``)
    or secondary (``alias_filenames``). Then run a text analysis for those
    lexers and choose the best result.

    usage::

        >>> from pygments.lexers import guess_lexer_for_filename
        >>> guess_lexer_for_filename('hello.html', '<%= @foo %>')
        <pygments.lexers.templates.RhtmlLexer object at 0xb7d2f32c>
        >>> guess_lexer_for_filename('hello.html', '<h1>{{ title|e }}</h1>')
        <pygments.lexers.templates.HtmlDjangoLexer object at 0xb7d2f2ac>
        >>> guess_lexer_for_filename('style.css', 'a { color: <?= $link ?> }')
        <pygments.lexers.templates.CssPhpLexer object at 0xb7ba518c>
    """
    fn = basename(_fn)
    primary = None
    matching_lexers = set()
    for lexer in _iter_lexerclasses():
        for filename in lexer.filenames:
            if _fn_matches(fn, filename):
                matching_lexers.add(lexer)
                primary = lexer
        for filename in lexer.alias_filenames:
            if _fn_matches(fn, filename):
                matching_lexers.add(lexer)
    if not matching_lexers:
        raise ClassNotFound('no lexer for filename %r found' % fn)
    if len(matching_lexers) == 1:
        return matching_lexers.pop()(**options)
    result = []
    for lexer in matching_lexers:
        rv = lexer.analyse_text(_text)
        if rv == 1.0:
            return lexer(**options)
        result.append((rv, lexer))

    # since py3 can no longer sort by class name by default, here is the
    # sorting function that works in both
    def type_sort(type_):
        return (type_[0], type_[1].__name__)
    result.sort(key=type_sort)

    if not result[-1][0] and primary is not None:
        return primary(**options)
    return result[-1][1](**options)


def guess_lexer(_text, **options):
    """Guess a lexer by strong distinctions in the text (eg, shebang)."""

    # try to get a vim modeline first
    ft = get_filetype_from_buffer(_text)

    if ft is not None:
        try:
            return get_lexer_by_name(ft, **options)
        except ClassNotFound:
            pass

    best_lexer = [0.0, None]
    for lexer in _iter_lexerclasses():
        rv = lexer.analyse_text(_text)
        if rv == 1.0:
            return lexer(**options)
        if rv > best_lexer[0]:
            best_lexer[:] = (rv, lexer)
    if not best_lexer[0] or best_lexer[1] is None:
        raise ClassNotFound('no lexer matching the text found')
    return best_lexer[1](**options)


class _automodule(types.ModuleType):
    """Automatically import lexers."""

    def __getattr__(self, name):
        info = LEXERS.get(name)
        if info:
            _load_lexers(info[0])
            cls = _lexer_cache[info[1]]
            setattr(self, name, cls)
            return cls
        raise AttributeError(name)


oldmod = sys.modules[__name__]
newmod = _automodule(__name__)
newmod.__dict__.update(oldmod.__dict__)
sys.modules[__name__] = newmod
del newmod.newmod, newmod.oldmod, newmod.sys, newmod.types