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 _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:
yield from find_plugin_lexers()
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 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.lower() in cls.aliases:
return cls(**options)
raise ClassNotFound('no lexer for alias %r found' % _alias)
def find_lexer_class_by_name(_alias):
"""Lookup a lexer class by alias.
Like `get_lexer_by_name`, but does not instantiate the class.
.. versionadded:: 2.2
"""
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]
# continue with lexers from setuptools entrypoints
for cls in find_plugin_lexers():
if _alias.lower() in cls.aliases:
return cls
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 = guess_decode(code)
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, cls.__name__
return cls.priority + bonus, cls.__name__
if matches:
matches.sort(key=get_rating)
# print "Possible lexers, after sort:", matches
return matches[-1][0]
