pygments-main / pygments / lexers /

The branch 'trunk' does not exist.
# -*- coding: utf-8 -*-

    Pygments lexers.

    :copyright: 2006 by Georg Brandl.
    :license: GNU LGPL, see LICENSE for more details.
import fnmatch
import types
from os.path import basename

except NameError:
    from sets import Set as set

from pygments.lexers._mapping import LEXERS
from pygments.plugin import find_plugin_lexers

__all__ = ['get_lexer_by_name', 'get_lexer_for_filename',
           'guess_lexer'] + LEXERS.keys()

_lexer_cache = {}

def _load_lexers(module_name):
    Loads 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

def get_lexer_by_name(_alias, **options):
    Get a lexer by an alias.
    # lookup builtin lexers
    for module_name, name, aliases, _, _ in LEXERS.itervalues():
        if _alias in aliases:
            if name not in _lexer_cache:
            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 ValueError('no lexer for alias %r found' % _alias)

def get_lexer_for_filename(_fn, **options):
    Get a lexer for a filename.
    fn = basename(_fn)
    for modname, name, _, filenames, _ in LEXERS.itervalues():
        for filename in filenames:
            if fnmatch.fnmatch(_fn, filename):
                if name not in _lexer_cache:
                return _lexer_cache[name](**options)
    for cls in find_plugin_lexers():
        for filename in cls.filenames:
            if fnmatch.fnmatch(_fn, filename):
                return lexer(**options)
    raise ValueError('no lexer for filename %r found' % _fn)

def get_lexer_for_mimetype(_mime, **options):
    Get a lexer for a mimetype.
    for modname, name, _, _, mimetypes in LEXERS.itervalues():
        if _mime in mimetypes:
            if name not in _lexer_cache:
            return _lexer_cache[name](**options)
    for cls in find_plugin_lexers():
        if _mime in cls.mimetypes:
            return lexer(**options)
    raise ValueError('no lexer for mimetype %r found' % _mime)

def _iter_lexerclasses():
    Returns an iterator over all lexer classes.
    for module_name, name, _, _ in LEXERS.itervalues():
        if name not in _lexer_cache:
        yield _lexer_cache[name]
    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.


        >>> 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 fnmatch.fnmatch(fn, filename):
                primary = lexer
        for filename in lexer.alias_filenames:
            if fnmatch.fnmatch(fn, filename):
    if not matching_lexers:
        raise ValueError('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))
    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).
    #XXX: i (mitsuhiko) would like to drop this function in favor of the
    #     better guess_lexer_for_filename function.
    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 ValueError('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:
            cls = _lexer_cache[info[1]]
            setattr(self, name, cls)
            return cls
        raise AttributeError(name)

import sys
oldmod = sys.modules['pygments.lexers']
newmod = _automodule('pygments.lexers')
sys.modules['pygments.lexers'] = newmod
del newmod.newmod, newmod.oldmod, newmod.sys, newmod.types
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.