Python源码示例：pygments.util.guess_decode()
示例1
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
return cls.priority + bonus
if matches:
matches.sort(key=get_rating)
# print "Possible lexers, after sort:", matches
return matches[-1][0]
示例2
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]
示例3
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 LEXERS.values():
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 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]
示例4
def guess_lexer(_text, **options):
"""Guess a lexer by strong distinctions in the text (eg, shebang)."""
if not isinstance(_text, str):
inencoding = options.get('inencoding', options.get('encoding'))
if inencoding:
_text = _text.decode(inencoding or 'utf8')
else:
_text, _ = guess_decode(_text)
# 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)
示例5
def test_guess_decode():
# UTF-8 should be decoded as UTF-8
s = util.guess_decode(u'\xff'.encode('utf-8'))
assert s == (u'\xff', 'utf-8')
# otherwise, it could be latin1 or the locale encoding...
import locale
s = util.guess_decode(b'\xff')
assert s[1] in ('latin1', locale.getpreferredencoding())
示例6
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]
示例7
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]
示例8
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 LEXERS.values():
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 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]
示例9
def guess_lexer(_text, **options):
"""Guess a lexer by strong distinctions in the text (eg, shebang)."""
if not isinstance(_text, str):
inencoding = options.get('inencoding', options.get('encoding'))
if inencoding:
_text = _text.decode(inencoding or 'utf8')
else:
_text, _ = guess_decode(_text)
# 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)
示例10
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
return cls.priority + bonus
if matches:
matches.sort(key=get_rating)
# print "Possible lexers, after sort:", matches
return matches[-1][0]
示例11
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]
示例12
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]
