tests versuch 2

This commit is contained in:
2000-Trek 2023-07-28 23:30:45 +02:00
parent fdf385fe06
commit c88f7df83a
2363 changed files with 408191 additions and 0 deletions

View file

@ -0,0 +1,82 @@
"""
Pygments
~~~~~~~~
Pygments is a syntax highlighting package written in Python.
It is a generic syntax highlighter for general use in all kinds of software
such as forum systems, wikis or other applications that need to prettify
source code. Highlights are:
* a wide range of common languages and markup formats is supported
* special attention is paid to details, increasing quality by a fair amount
* support for new languages and formats are added easily
* a number of output formats, presently HTML, LaTeX, RTF, SVG, all image
formats that PIL supports, and ANSI sequences
* it is usable as a command-line tool and as a library
* ... and it highlights even Brainfuck!
The `Pygments master branch`_ is installable with ``easy_install Pygments==dev``.
.. _Pygments master branch:
https://github.com/pygments/pygments/archive/master.zip#egg=Pygments-dev
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from io import StringIO, BytesIO
__version__ = '2.15.1'
__docformat__ = 'restructuredtext'
__all__ = ['lex', 'format', 'highlight']
def lex(code, lexer):
"""
Lex `code` with the `lexer` (must be a `Lexer` instance)
and return an iterable of tokens. Currently, this only calls
`lexer.get_tokens()`.
"""
try:
return lexer.get_tokens(code)
except TypeError:
# Heuristic to catch a common mistake.
from pip._vendor.pygments.lexer import RegexLexer
if isinstance(lexer, type) and issubclass(lexer, RegexLexer):
raise TypeError('lex() argument must be a lexer instance, '
'not a class')
raise
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format ``tokens`` (an iterable of tokens) with the formatter ``formatter``
(a `Formatter` instance).
If ``outfile`` is given and a valid file object (an object with a
``write`` method), the result will be written to it, otherwise it
is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError:
# Heuristic to catch a common mistake.
from pip._vendor.pygments.formatter import Formatter
if isinstance(formatter, type) and issubclass(formatter, Formatter):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def highlight(code, lexer, formatter, outfile=None):
"""
This is the most high-level highlighting function. It combines `lex` and
`format` in one function.
"""
return format(lex(code, lexer), formatter, outfile)

View file

@ -0,0 +1,17 @@
"""
pygments.__main__
~~~~~~~~~~~~~~~~~
Main entry point for ``python -m pygments``.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
from pip._vendor.pygments.cmdline import main
try:
sys.exit(main(sys.argv))
except KeyboardInterrupt:
sys.exit(1)

View file

@ -0,0 +1,668 @@
"""
pygments.cmdline
~~~~~~~~~~~~~~~~
Command line interface.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import sys
import shutil
import argparse
from textwrap import dedent
from pip._vendor.pygments import __version__, highlight
from pip._vendor.pygments.util import ClassNotFound, OptionError, docstring_headline, \
guess_decode, guess_decode_from_terminal, terminal_encoding, \
UnclosingTextIOWrapper
from pip._vendor.pygments.lexers import get_all_lexers, get_lexer_by_name, guess_lexer, \
load_lexer_from_file, get_lexer_for_filename, find_lexer_class_for_filename
from pip._vendor.pygments.lexers.special import TextLexer
from pip._vendor.pygments.formatters.latex import LatexEmbeddedLexer, LatexFormatter
from pip._vendor.pygments.formatters import get_all_formatters, get_formatter_by_name, \
load_formatter_from_file, get_formatter_for_filename, find_formatter_class
from pip._vendor.pygments.formatters.terminal import TerminalFormatter
from pip._vendor.pygments.formatters.terminal256 import Terminal256Formatter, TerminalTrueColorFormatter
from pip._vendor.pygments.filters import get_all_filters, find_filter_class
from pip._vendor.pygments.styles import get_all_styles, get_style_by_name
def _parse_options(o_strs):
opts = {}
if not o_strs:
return opts
for o_str in o_strs:
if not o_str.strip():
continue
o_args = o_str.split(',')
for o_arg in o_args:
o_arg = o_arg.strip()
try:
o_key, o_val = o_arg.split('=', 1)
o_key = o_key.strip()
o_val = o_val.strip()
except ValueError:
opts[o_arg] = True
else:
opts[o_key] = o_val
return opts
def _parse_filters(f_strs):
filters = []
if not f_strs:
return filters
for f_str in f_strs:
if ':' in f_str:
fname, fopts = f_str.split(':', 1)
filters.append((fname, _parse_options([fopts])))
else:
filters.append((f_str, {}))
return filters
def _print_help(what, name):
try:
if what == 'lexer':
cls = get_lexer_by_name(name)
print("Help on the %s lexer:" % cls.name)
print(dedent(cls.__doc__))
elif what == 'formatter':
cls = find_formatter_class(name)
print("Help on the %s formatter:" % cls.name)
print(dedent(cls.__doc__))
elif what == 'filter':
cls = find_filter_class(name)
print("Help on the %s filter:" % name)
print(dedent(cls.__doc__))
return 0
except (AttributeError, ValueError):
print("%s not found!" % what, file=sys.stderr)
return 1
def _print_list(what):
if what == 'lexer':
print()
print("Lexers:")
print("~~~~~~~")
info = []
for fullname, names, exts, _ in get_all_lexers():
tup = (', '.join(names)+':', fullname,
exts and '(filenames ' + ', '.join(exts) + ')' or '')
info.append(tup)
info.sort()
for i in info:
print(('* %s\n %s %s') % i)
elif what == 'formatter':
print()
print("Formatters:")
print("~~~~~~~~~~~")
info = []
for cls in get_all_formatters():
doc = docstring_headline(cls)
tup = (', '.join(cls.aliases) + ':', doc, cls.filenames and
'(filenames ' + ', '.join(cls.filenames) + ')' or '')
info.append(tup)
info.sort()
for i in info:
print(('* %s\n %s %s') % i)
elif what == 'filter':
print()
print("Filters:")
print("~~~~~~~~")
for name in get_all_filters():
cls = find_filter_class(name)
print("* " + name + ':')
print(" %s" % docstring_headline(cls))
elif what == 'style':
print()
print("Styles:")
print("~~~~~~~")
for name in get_all_styles():
cls = get_style_by_name(name)
print("* " + name + ':')
print(" %s" % docstring_headline(cls))
def _print_list_as_json(requested_items):
import json
result = {}
if 'lexer' in requested_items:
info = {}
for fullname, names, filenames, mimetypes in get_all_lexers():
info[fullname] = {
'aliases': names,
'filenames': filenames,
'mimetypes': mimetypes
}
result['lexers'] = info
if 'formatter' in requested_items:
info = {}
for cls in get_all_formatters():
doc = docstring_headline(cls)
info[cls.name] = {
'aliases': cls.aliases,
'filenames': cls.filenames,
'doc': doc
}
result['formatters'] = info
if 'filter' in requested_items:
info = {}
for name in get_all_filters():
cls = find_filter_class(name)
info[name] = {
'doc': docstring_headline(cls)
}
result['filters'] = info
if 'style' in requested_items:
info = {}
for name in get_all_styles():
cls = get_style_by_name(name)
info[name] = {
'doc': docstring_headline(cls)
}
result['styles'] = info
json.dump(result, sys.stdout)
def main_inner(parser, argns):
if argns.help:
parser.print_help()
return 0
if argns.V:
print('Pygments version %s, (c) 2006-2023 by Georg Brandl, Matthäus '
'Chajdas and contributors.' % __version__)
return 0
def is_only_option(opt):
return not any(v for (k, v) in vars(argns).items() if k != opt)
# handle ``pygmentize -L``
if argns.L is not None:
arg_set = set()
for k, v in vars(argns).items():
if v:
arg_set.add(k)
arg_set.discard('L')
arg_set.discard('json')
if arg_set:
parser.print_help(sys.stderr)
return 2
# print version
if not argns.json:
main(['', '-V'])
allowed_types = {'lexer', 'formatter', 'filter', 'style'}
largs = [arg.rstrip('s') for arg in argns.L]
if any(arg not in allowed_types for arg in largs):
parser.print_help(sys.stderr)
return 0
if not largs:
largs = allowed_types
if not argns.json:
for arg in largs:
_print_list(arg)
else:
_print_list_as_json(largs)
return 0
# handle ``pygmentize -H``
if argns.H:
if not is_only_option('H'):
parser.print_help(sys.stderr)
return 2
what, name = argns.H
if what not in ('lexer', 'formatter', 'filter'):
parser.print_help(sys.stderr)
return 2
return _print_help(what, name)
# parse -O options
parsed_opts = _parse_options(argns.O or [])
# parse -P options
for p_opt in argns.P or []:
try:
name, value = p_opt.split('=', 1)
except ValueError:
parsed_opts[p_opt] = True
else:
parsed_opts[name] = value
# encodings
inencoding = parsed_opts.get('inencoding', parsed_opts.get('encoding'))
outencoding = parsed_opts.get('outencoding', parsed_opts.get('encoding'))
# handle ``pygmentize -N``
if argns.N:
lexer = find_lexer_class_for_filename(argns.N)
if lexer is None:
lexer = TextLexer
print(lexer.aliases[0])
return 0
# handle ``pygmentize -C``
if argns.C:
inp = sys.stdin.buffer.read()
try:
lexer = guess_lexer(inp, inencoding=inencoding)
except ClassNotFound:
lexer = TextLexer
print(lexer.aliases[0])
return 0
# handle ``pygmentize -S``
S_opt = argns.S
a_opt = argns.a
if S_opt is not None:
f_opt = argns.f
if not f_opt:
parser.print_help(sys.stderr)
return 2
if argns.l or argns.INPUTFILE:
parser.print_help(sys.stderr)
return 2
try:
parsed_opts['style'] = S_opt
fmter = get_formatter_by_name(f_opt, **parsed_opts)
except ClassNotFound as err:
print(err, file=sys.stderr)
return 1
print(fmter.get_style_defs(a_opt or ''))
return 0
# if no -S is given, -a is not allowed
if argns.a is not None:
parser.print_help(sys.stderr)
return 2
# parse -F options
F_opts = _parse_filters(argns.F or [])
# -x: allow custom (eXternal) lexers and formatters
allow_custom_lexer_formatter = bool(argns.x)
# select lexer
lexer = None
# given by name?
lexername = argns.l
if lexername:
# custom lexer, located relative to user's cwd
if allow_custom_lexer_formatter and '.py' in lexername:
try:
filename = None
name = None
if ':' in lexername:
filename, name = lexername.rsplit(':', 1)
if '.py' in name:
# This can happen on Windows: If the lexername is
# C:\lexer.py -- return to normal load path in that case
name = None
if filename and name:
lexer = load_lexer_from_file(filename, name,
**parsed_opts)
else:
lexer = load_lexer_from_file(lexername, **parsed_opts)
except ClassNotFound as err:
print('Error:', err, file=sys.stderr)
return 1
else:
try:
lexer = get_lexer_by_name(lexername, **parsed_opts)
except (OptionError, ClassNotFound) as err:
print('Error:', err, file=sys.stderr)
return 1
# read input code
code = None
if argns.INPUTFILE:
if argns.s:
print('Error: -s option not usable when input file specified',
file=sys.stderr)
return 2
infn = argns.INPUTFILE
try:
with open(infn, 'rb') as infp:
code = infp.read()
except Exception as err:
print('Error: cannot read infile:', err, file=sys.stderr)
return 1
if not inencoding:
code, inencoding = guess_decode(code)
# do we have to guess the lexer?
if not lexer:
try:
lexer = get_lexer_for_filename(infn, code, **parsed_opts)
except ClassNotFound as err:
if argns.g:
try:
lexer = guess_lexer(code, **parsed_opts)
except ClassNotFound:
lexer = TextLexer(**parsed_opts)
else:
print('Error:', err, file=sys.stderr)
return 1
except OptionError as err:
print('Error:', err, file=sys.stderr)
return 1
elif not argns.s: # treat stdin as full file (-s support is later)
# read code from terminal, always in binary mode since we want to
# decode ourselves and be tolerant with it
code = sys.stdin.buffer.read() # use .buffer to get a binary stream
if not inencoding:
code, inencoding = guess_decode_from_terminal(code, sys.stdin)
# else the lexer will do the decoding
if not lexer:
try:
lexer = guess_lexer(code, **parsed_opts)
except ClassNotFound:
lexer = TextLexer(**parsed_opts)
else: # -s option needs a lexer with -l
if not lexer:
print('Error: when using -s a lexer has to be selected with -l',
file=sys.stderr)
return 2
# process filters
for fname, fopts in F_opts:
try:
lexer.add_filter(fname, **fopts)
except ClassNotFound as err:
print('Error:', err, file=sys.stderr)
return 1
# select formatter
outfn = argns.o
fmter = argns.f
if fmter:
# custom formatter, located relative to user's cwd
if allow_custom_lexer_formatter and '.py' in fmter:
try:
filename = None
name = None
if ':' in fmter:
# Same logic as above for custom lexer
filename, name = fmter.rsplit(':', 1)
if '.py' in name:
name = None
if filename and name:
fmter = load_formatter_from_file(filename, name,
**parsed_opts)
else:
fmter = load_formatter_from_file(fmter, **parsed_opts)
except ClassNotFound as err:
print('Error:', err, file=sys.stderr)
return 1
else:
try:
fmter = get_formatter_by_name(fmter, **parsed_opts)
except (OptionError, ClassNotFound) as err:
print('Error:', err, file=sys.stderr)
return 1
if outfn:
if not fmter:
try:
fmter = get_formatter_for_filename(outfn, **parsed_opts)
except (OptionError, ClassNotFound) as err:
print('Error:', err, file=sys.stderr)
return 1
try:
outfile = open(outfn, 'wb')
except Exception as err:
print('Error: cannot open outfile:', err, file=sys.stderr)
return 1
else:
if not fmter:
if os.environ.get('COLORTERM','') in ('truecolor', '24bit'):
fmter = TerminalTrueColorFormatter(**parsed_opts)
elif '256' in os.environ.get('TERM', ''):
fmter = Terminal256Formatter(**parsed_opts)
else:
fmter = TerminalFormatter(**parsed_opts)
outfile = sys.stdout.buffer
# determine output encoding if not explicitly selected
if not outencoding:
if outfn:
# output file? use lexer encoding for now (can still be None)
fmter.encoding = inencoding
else:
# else use terminal encoding
fmter.encoding = terminal_encoding(sys.stdout)
# provide coloring under Windows, if possible
if not outfn and sys.platform in ('win32', 'cygwin') and \
fmter.name in ('Terminal', 'Terminal256'): # pragma: no cover
# unfortunately colorama doesn't support binary streams on Py3
outfile = UnclosingTextIOWrapper(outfile, encoding=fmter.encoding)
fmter.encoding = None
try:
import pip._vendor.colorama.initialise as colorama_initialise
except ImportError:
pass
else:
outfile = colorama_initialise.wrap_stream(
outfile, convert=None, strip=None, autoreset=False, wrap=True)
# When using the LaTeX formatter and the option `escapeinside` is
# specified, we need a special lexer which collects escaped text
# before running the chosen language lexer.
escapeinside = parsed_opts.get('escapeinside', '')
if len(escapeinside) == 2 and isinstance(fmter, LatexFormatter):
left = escapeinside[0]
right = escapeinside[1]
lexer = LatexEmbeddedLexer(left, right, lexer)
# ... and do it!
if not argns.s:
# process whole input as per normal...
try:
highlight(code, lexer, fmter, outfile)
finally:
if outfn:
outfile.close()
return 0
else:
# line by line processing of stdin (eg: for 'tail -f')...
try:
while 1:
line = sys.stdin.buffer.readline()
if not line:
break
if not inencoding:
line = guess_decode_from_terminal(line, sys.stdin)[0]
highlight(line, lexer, fmter, outfile)
if hasattr(outfile, 'flush'):
outfile.flush()
return 0
except KeyboardInterrupt: # pragma: no cover
return 0
finally:
if outfn:
outfile.close()
class HelpFormatter(argparse.HelpFormatter):
def __init__(self, prog, indent_increment=2, max_help_position=16, width=None):
if width is None:
try:
width = shutil.get_terminal_size().columns - 2
except Exception:
pass
argparse.HelpFormatter.__init__(self, prog, indent_increment,
max_help_position, width)
def main(args=sys.argv):
"""
Main command line entry point.
"""
desc = "Highlight an input file and write the result to an output file."
parser = argparse.ArgumentParser(description=desc, add_help=False,
formatter_class=HelpFormatter)
operation = parser.add_argument_group('Main operation')
lexersel = operation.add_mutually_exclusive_group()
lexersel.add_argument(
'-l', metavar='LEXER',
help='Specify the lexer to use. (Query names with -L.) If not '
'given and -g is not present, the lexer is guessed from the filename.')
lexersel.add_argument(
'-g', action='store_true',
help='Guess the lexer from the file contents, or pass through '
'as plain text if nothing can be guessed.')
operation.add_argument(
'-F', metavar='FILTER[:options]', action='append',
help='Add a filter to the token stream. (Query names with -L.) '
'Filter options are given after a colon if necessary.')
operation.add_argument(
'-f', metavar='FORMATTER',
help='Specify the formatter to use. (Query names with -L.) '
'If not given, the formatter is guessed from the output filename, '
'and defaults to the terminal formatter if the output is to the '
'terminal or an unknown file extension.')
operation.add_argument(
'-O', metavar='OPTION=value[,OPTION=value,...]', action='append',
help='Give options to the lexer and formatter as a comma-separated '
'list of key-value pairs. '
'Example: `-O bg=light,python=cool`.')
operation.add_argument(
'-P', metavar='OPTION=value', action='append',
help='Give a single option to the lexer and formatter - with this '
'you can pass options whose value contains commas and equal signs. '
'Example: `-P "heading=Pygments, the Python highlighter"`.')
operation.add_argument(
'-o', metavar='OUTPUTFILE',
help='Where to write the output. Defaults to standard output.')
operation.add_argument(
'INPUTFILE', nargs='?',
help='Where to read the input. Defaults to standard input.')
flags = parser.add_argument_group('Operation flags')
flags.add_argument(
'-v', action='store_true',
help='Print a detailed traceback on unhandled exceptions, which '
'is useful for debugging and bug reports.')
flags.add_argument(
'-s', action='store_true',
help='Process lines one at a time until EOF, rather than waiting to '
'process the entire file. This only works for stdin, only for lexers '
'with no line-spanning constructs, and is intended for streaming '
'input such as you get from `tail -f`. '
'Example usage: `tail -f sql.log | pygmentize -s -l sql`.')
flags.add_argument(
'-x', action='store_true',
help='Allow custom lexers and formatters to be loaded from a .py file '
'relative to the current working directory. For example, '
'`-l ./customlexer.py -x`. By default, this option expects a file '
'with a class named CustomLexer or CustomFormatter; you can also '
'specify your own class name with a colon (`-l ./lexer.py:MyLexer`). '
'Users should be very careful not to use this option with untrusted '
'files, because it will import and run them.')
flags.add_argument('--json', help='Output as JSON. This can '
'be only used in conjunction with -L.',
default=False,
action='store_true')
special_modes_group = parser.add_argument_group(
'Special modes - do not do any highlighting')
special_modes = special_modes_group.add_mutually_exclusive_group()
special_modes.add_argument(
'-S', metavar='STYLE -f formatter',
help='Print style definitions for STYLE for a formatter '
'given with -f. The argument given by -a is formatter '
'dependent.')
special_modes.add_argument(
'-L', nargs='*', metavar='WHAT',
help='List lexers, formatters, styles or filters -- '
'give additional arguments for the thing(s) you want to list '
'(e.g. "styles"), or omit them to list everything.')
special_modes.add_argument(
'-N', metavar='FILENAME',
help='Guess and print out a lexer name based solely on the given '
'filename. Does not take input or highlight anything. If no specific '
'lexer can be determined, "text" is printed.')
special_modes.add_argument(
'-C', action='store_true',
help='Like -N, but print out a lexer name based solely on '
'a given content from standard input.')
special_modes.add_argument(
'-H', action='store', nargs=2, metavar=('NAME', 'TYPE'),
help='Print detailed help for the object <name> of type <type>, '
'where <type> is one of "lexer", "formatter" or "filter".')
special_modes.add_argument(
'-V', action='store_true',
help='Print the package version.')
special_modes.add_argument(
'-h', '--help', action='store_true',
help='Print this help.')
special_modes_group.add_argument(
'-a', metavar='ARG',
help='Formatter-specific additional argument for the -S (print '
'style sheet) mode.')
argns = parser.parse_args(args[1:])
try:
return main_inner(parser, argns)
except BrokenPipeError:
# someone closed our stdout, e.g. by quitting a pager.
return 0
except Exception:
if argns.v:
print(file=sys.stderr)
print('*' * 65, file=sys.stderr)
print('An unhandled exception occurred while highlighting.',
file=sys.stderr)
print('Please report the whole traceback to the issue tracker at',
file=sys.stderr)
print('<https://github.com/pygments/pygments/issues>.',
file=sys.stderr)
print('*' * 65, file=sys.stderr)
print(file=sys.stderr)
raise
import traceback
info = traceback.format_exception(*sys.exc_info())
msg = info[-1].strip()
if len(info) >= 3:
# extract relevant file and position info
msg += '\n (f%s)' % info[-2].split('\n')[0].strip()[1:]
print(file=sys.stderr)
print('*** Error while highlighting:', file=sys.stderr)
print(msg, file=sys.stderr)
print('*** If this is a bug you want to report, please rerun with -v.',
file=sys.stderr)
return 1

View file

@ -0,0 +1,70 @@
"""
pygments.console
~~~~~~~~~~~~~~~~
Format colored console output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
esc = "\x1b["
codes = {}
codes[""] = ""
codes["reset"] = esc + "39;49;00m"
codes["bold"] = esc + "01m"
codes["faint"] = esc + "02m"
codes["standout"] = esc + "03m"
codes["underline"] = esc + "04m"
codes["blink"] = esc + "05m"
codes["overline"] = esc + "06m"
dark_colors = ["black", "red", "green", "yellow", "blue",
"magenta", "cyan", "gray"]
light_colors = ["brightblack", "brightred", "brightgreen", "brightyellow", "brightblue",
"brightmagenta", "brightcyan", "white"]
x = 30
for d, l in zip(dark_colors, light_colors):
codes[d] = esc + "%im" % x
codes[l] = esc + "%im" % (60 + x)
x += 1
del d, l, x
codes["white"] = codes["bold"]
def reset_color():
return codes["reset"]
def colorize(color_key, text):
return codes[color_key] + text + codes["reset"]
def ansiformat(attr, text):
"""
Format ``text`` with a color and/or some attributes::
color normal color
*color* bold color
_color_ underlined color
+color+ blinking color
"""
result = []
if attr[:1] == attr[-1:] == '+':
result.append(codes['blink'])
attr = attr[1:-1]
if attr[:1] == attr[-1:] == '*':
result.append(codes['bold'])
attr = attr[1:-1]
if attr[:1] == attr[-1:] == '_':
result.append(codes['underline'])
attr = attr[1:-1]
result.append(codes[attr])
result.append(text)
result.append(codes['reset'])
return ''.join(result)

View file

@ -0,0 +1,71 @@
"""
pygments.filter
~~~~~~~~~~~~~~~
Module that implements the default filter.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
def apply_filters(stream, filters, lexer=None):
"""
Use this method to apply an iterable of filters to
a stream. If lexer is given it's forwarded to the
filter, otherwise the filter receives `None`.
"""
def _apply(filter_, stream):
yield from filter_.filter(lexer, stream)
for filter_ in filters:
stream = _apply(filter_, stream)
return stream
def simplefilter(f):
"""
Decorator that converts a function into a filter::
@simplefilter
def lowercase(self, lexer, stream, options):
for ttype, value in stream:
yield ttype, value.lower()
"""
return type(f.__name__, (FunctionFilter,), {
'__module__': getattr(f, '__module__'),
'__doc__': f.__doc__,
'function': f,
})
class Filter:
"""
Default filter. Subclass this class or use the `simplefilter`
decorator to create own filters.
"""
def __init__(self, **options):
self.options = options
def filter(self, lexer, stream):
raise NotImplementedError()
class FunctionFilter(Filter):
"""
Abstract class used by `simplefilter` to create simple
function filters on the fly. The `simplefilter` decorator
automatically creates subclasses of this class for
functions passed to it.
"""
function = None
def __init__(self, **options):
if not hasattr(self, 'function'):
raise TypeError('%r used without bound function' %
self.__class__.__name__)
Filter.__init__(self, **options)
def filter(self, lexer, stream):
# pylint: disable=not-callable
yield from self.function(lexer, stream, self.options)

View file

@ -0,0 +1,940 @@
"""
pygments.filters
~~~~~~~~~~~~~~~~
Module containing filter lookup functions and default
filters.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pip._vendor.pygments.token import String, Comment, Keyword, Name, Error, Whitespace, \
string_to_tokentype
from pip._vendor.pygments.filter import Filter
from pip._vendor.pygments.util import get_list_opt, get_int_opt, get_bool_opt, \
get_choice_opt, ClassNotFound, OptionError
from pip._vendor.pygments.plugin import find_plugin_filters
def find_filter_class(filtername):
"""Lookup a filter by name. Return None if not found."""
if filtername in FILTERS:
return FILTERS[filtername]
for name, cls in find_plugin_filters():
if name == filtername:
return cls
return None
def get_filter_by_name(filtername, **options):
"""Return an instantiated filter.
Options are passed to the filter initializer if wanted.
Raise a ClassNotFound if not found.
"""
cls = find_filter_class(filtername)
if cls:
return cls(**options)
else:
raise ClassNotFound('filter %r not found' % filtername)
def get_all_filters():
"""Return a generator of all filter names."""
yield from FILTERS
for name, _ in find_plugin_filters():
yield name
def _replace_special(ttype, value, regex, specialttype,
replacefunc=lambda x: x):
last = 0
for match in regex.finditer(value):
start, end = match.start(), match.end()
if start != last:
yield ttype, value[last:start]
yield specialttype, replacefunc(value[start:end])
last = end
if last != len(value):
yield ttype, value[last:]
class CodeTagFilter(Filter):
"""Highlight special code tags in comments and docstrings.
Options accepted:
`codetags` : list of strings
A list of strings that are flagged as code tags. The default is to
highlight ``XXX``, ``TODO``, ``FIXME``, ``BUG`` and ``NOTE``.
.. versionchanged:: 2.13
Now recognizes ``FIXME`` by default.
"""
def __init__(self, **options):
Filter.__init__(self, **options)
tags = get_list_opt(options, 'codetags',
['XXX', 'TODO', 'FIXME', 'BUG', 'NOTE'])
self.tag_re = re.compile(r'\b(%s)\b' % '|'.join([
re.escape(tag) for tag in tags if tag
]))
def filter(self, lexer, stream):
regex = self.tag_re
for ttype, value in stream:
if ttype in String.Doc or \
ttype in Comment and \
ttype not in Comment.Preproc:
yield from _replace_special(ttype, value, regex, Comment.Special)
else:
yield ttype, value
class SymbolFilter(Filter):
"""Convert mathematical symbols such as \\<longrightarrow> in Isabelle
or \\longrightarrow in LaTeX into Unicode characters.
This is mostly useful for HTML or console output when you want to
approximate the source rendering you'd see in an IDE.
Options accepted:
`lang` : string
The symbol language. Must be one of ``'isabelle'`` or
``'latex'``. The default is ``'isabelle'``.
"""
latex_symbols = {
'\\alpha' : '\U000003b1',
'\\beta' : '\U000003b2',
'\\gamma' : '\U000003b3',
'\\delta' : '\U000003b4',
'\\varepsilon' : '\U000003b5',
'\\zeta' : '\U000003b6',
'\\eta' : '\U000003b7',
'\\vartheta' : '\U000003b8',
'\\iota' : '\U000003b9',
'\\kappa' : '\U000003ba',
'\\lambda' : '\U000003bb',
'\\mu' : '\U000003bc',
'\\nu' : '\U000003bd',
'\\xi' : '\U000003be',
'\\pi' : '\U000003c0',
'\\varrho' : '\U000003c1',
'\\sigma' : '\U000003c3',
'\\tau' : '\U000003c4',
'\\upsilon' : '\U000003c5',
'\\varphi' : '\U000003c6',
'\\chi' : '\U000003c7',
'\\psi' : '\U000003c8',
'\\omega' : '\U000003c9',
'\\Gamma' : '\U00000393',
'\\Delta' : '\U00000394',
'\\Theta' : '\U00000398',
'\\Lambda' : '\U0000039b',
'\\Xi' : '\U0000039e',
'\\Pi' : '\U000003a0',
'\\Sigma' : '\U000003a3',
'\\Upsilon' : '\U000003a5',
'\\Phi' : '\U000003a6',
'\\Psi' : '\U000003a8',
'\\Omega' : '\U000003a9',
'\\leftarrow' : '\U00002190',
'\\longleftarrow' : '\U000027f5',
'\\rightarrow' : '\U00002192',
'\\longrightarrow' : '\U000027f6',
'\\Leftarrow' : '\U000021d0',
'\\Longleftarrow' : '\U000027f8',
'\\Rightarrow' : '\U000021d2',
'\\Longrightarrow' : '\U000027f9',
'\\leftrightarrow' : '\U00002194',
'\\longleftrightarrow' : '\U000027f7',
'\\Leftrightarrow' : '\U000021d4',
'\\Longleftrightarrow' : '\U000027fa',
'\\mapsto' : '\U000021a6',
'\\longmapsto' : '\U000027fc',
'\\relbar' : '\U00002500',
'\\Relbar' : '\U00002550',
'\\hookleftarrow' : '\U000021a9',
'\\hookrightarrow' : '\U000021aa',
'\\leftharpoondown' : '\U000021bd',
'\\rightharpoondown' : '\U000021c1',
'\\leftharpoonup' : '\U000021bc',
'\\rightharpoonup' : '\U000021c0',
'\\rightleftharpoons' : '\U000021cc',
'\\leadsto' : '\U0000219d',
'\\downharpoonleft' : '\U000021c3',
'\\downharpoonright' : '\U000021c2',
'\\upharpoonleft' : '\U000021bf',
'\\upharpoonright' : '\U000021be',
'\\restriction' : '\U000021be',
'\\uparrow' : '\U00002191',
'\\Uparrow' : '\U000021d1',
'\\downarrow' : '\U00002193',
'\\Downarrow' : '\U000021d3',
'\\updownarrow' : '\U00002195',
'\\Updownarrow' : '\U000021d5',
'\\langle' : '\U000027e8',
'\\rangle' : '\U000027e9',
'\\lceil' : '\U00002308',
'\\rceil' : '\U00002309',
'\\lfloor' : '\U0000230a',
'\\rfloor' : '\U0000230b',
'\\flqq' : '\U000000ab',
'\\frqq' : '\U000000bb',
'\\bot' : '\U000022a5',
'\\top' : '\U000022a4',
'\\wedge' : '\U00002227',
'\\bigwedge' : '\U000022c0',
'\\vee' : '\U00002228',
'\\bigvee' : '\U000022c1',
'\\forall' : '\U00002200',
'\\exists' : '\U00002203',
'\\nexists' : '\U00002204',
'\\neg' : '\U000000ac',
'\\Box' : '\U000025a1',
'\\Diamond' : '\U000025c7',
'\\vdash' : '\U000022a2',
'\\models' : '\U000022a8',
'\\dashv' : '\U000022a3',
'\\surd' : '\U0000221a',
'\\le' : '\U00002264',
'\\ge' : '\U00002265',
'\\ll' : '\U0000226a',
'\\gg' : '\U0000226b',
'\\lesssim' : '\U00002272',
'\\gtrsim' : '\U00002273',
'\\lessapprox' : '\U00002a85',
'\\gtrapprox' : '\U00002a86',
'\\in' : '\U00002208',
'\\notin' : '\U00002209',
'\\subset' : '\U00002282',
'\\supset' : '\U00002283',
'\\subseteq' : '\U00002286',
'\\supseteq' : '\U00002287',
'\\sqsubset' : '\U0000228f',
'\\sqsupset' : '\U00002290',
'\\sqsubseteq' : '\U00002291',
'\\sqsupseteq' : '\U00002292',
'\\cap' : '\U00002229',
'\\bigcap' : '\U000022c2',
'\\cup' : '\U0000222a',
'\\bigcup' : '\U000022c3',
'\\sqcup' : '\U00002294',
'\\bigsqcup' : '\U00002a06',
'\\sqcap' : '\U00002293',
'\\Bigsqcap' : '\U00002a05',
'\\setminus' : '\U00002216',
'\\propto' : '\U0000221d',
'\\uplus' : '\U0000228e',
'\\bigplus' : '\U00002a04',
'\\sim' : '\U0000223c',
'\\doteq' : '\U00002250',
'\\simeq' : '\U00002243',
'\\approx' : '\U00002248',
'\\asymp' : '\U0000224d',
'\\cong' : '\U00002245',
'\\equiv' : '\U00002261',
'\\Join' : '\U000022c8',
'\\bowtie' : '\U00002a1d',
'\\prec' : '\U0000227a',
'\\succ' : '\U0000227b',
'\\preceq' : '\U0000227c',
'\\succeq' : '\U0000227d',
'\\parallel' : '\U00002225',
'\\mid' : '\U000000a6',
'\\pm' : '\U000000b1',
'\\mp' : '\U00002213',
'\\times' : '\U000000d7',
'\\div' : '\U000000f7',
'\\cdot' : '\U000022c5',
'\\star' : '\U000022c6',
'\\circ' : '\U00002218',
'\\dagger' : '\U00002020',
'\\ddagger' : '\U00002021',
'\\lhd' : '\U000022b2',
'\\rhd' : '\U000022b3',
'\\unlhd' : '\U000022b4',
'\\unrhd' : '\U000022b5',
'\\triangleleft' : '\U000025c3',
'\\triangleright' : '\U000025b9',
'\\triangle' : '\U000025b3',
'\\triangleq' : '\U0000225c',
'\\oplus' : '\U00002295',
'\\bigoplus' : '\U00002a01',
'\\otimes' : '\U00002297',
'\\bigotimes' : '\U00002a02',
'\\odot' : '\U00002299',
'\\bigodot' : '\U00002a00',
'\\ominus' : '\U00002296',
'\\oslash' : '\U00002298',
'\\dots' : '\U00002026',
'\\cdots' : '\U000022ef',
'\\sum' : '\U00002211',
'\\prod' : '\U0000220f',
'\\coprod' : '\U00002210',
'\\infty' : '\U0000221e',
'\\int' : '\U0000222b',
'\\oint' : '\U0000222e',
'\\clubsuit' : '\U00002663',
'\\diamondsuit' : '\U00002662',
'\\heartsuit' : '\U00002661',
'\\spadesuit' : '\U00002660',
'\\aleph' : '\U00002135',
'\\emptyset' : '\U00002205',
'\\nabla' : '\U00002207',
'\\partial' : '\U00002202',
'\\flat' : '\U0000266d',
'\\natural' : '\U0000266e',
'\\sharp' : '\U0000266f',
'\\angle' : '\U00002220',
'\\copyright' : '\U000000a9',
'\\textregistered' : '\U000000ae',
'\\textonequarter' : '\U000000bc',
'\\textonehalf' : '\U000000bd',
'\\textthreequarters' : '\U000000be',
'\\textordfeminine' : '\U000000aa',
'\\textordmasculine' : '\U000000ba',
'\\euro' : '\U000020ac',
'\\pounds' : '\U000000a3',
'\\yen' : '\U000000a5',
'\\textcent' : '\U000000a2',
'\\textcurrency' : '\U000000a4',
'\\textdegree' : '\U000000b0',
}
isabelle_symbols = {
'\\<zero>' : '\U0001d7ec',
'\\<one>' : '\U0001d7ed',
'\\<two>' : '\U0001d7ee',
'\\<three>' : '\U0001d7ef',
'\\<four>' : '\U0001d7f0',
'\\<five>' : '\U0001d7f1',
'\\<six>' : '\U0001d7f2',
'\\<seven>' : '\U0001d7f3',
'\\<eight>' : '\U0001d7f4',
'\\<nine>' : '\U0001d7f5',
'\\<A>' : '\U0001d49c',
'\\<B>' : '\U0000212c',
'\\<C>' : '\U0001d49e',
'\\<D>' : '\U0001d49f',
'\\<E>' : '\U00002130',
'\\<F>' : '\U00002131',
'\\<G>' : '\U0001d4a2',
'\\<H>' : '\U0000210b',
'\\<I>' : '\U00002110',
'\\<J>' : '\U0001d4a5',
'\\<K>' : '\U0001d4a6',
'\\<L>' : '\U00002112',
'\\<M>' : '\U00002133',
'\\<N>' : '\U0001d4a9',
'\\<O>' : '\U0001d4aa',
'\\<P>' : '\U0001d4ab',
'\\<Q>' : '\U0001d4ac',
'\\<R>' : '\U0000211b',
'\\<S>' : '\U0001d4ae',
'\\<T>' : '\U0001d4af',
'\\<U>' : '\U0001d4b0',
'\\<V>' : '\U0001d4b1',
'\\<W>' : '\U0001d4b2',
'\\<X>' : '\U0001d4b3',
'\\<Y>' : '\U0001d4b4',
'\\<Z>' : '\U0001d4b5',
'\\<a>' : '\U0001d5ba',
'\\<b>' : '\U0001d5bb',
'\\<c>' : '\U0001d5bc',
'\\<d>' : '\U0001d5bd',
'\\<e>' : '\U0001d5be',
'\\<f>' : '\U0001d5bf',
'\\<g>' : '\U0001d5c0',
'\\<h>' : '\U0001d5c1',
'\\<i>' : '\U0001d5c2',
'\\<j>' : '\U0001d5c3',
'\\<k>' : '\U0001d5c4',
'\\<l>' : '\U0001d5c5',
'\\<m>' : '\U0001d5c6',
'\\<n>' : '\U0001d5c7',
'\\<o>' : '\U0001d5c8',
'\\<p>' : '\U0001d5c9',
'\\<q>' : '\U0001d5ca',
'\\<r>' : '\U0001d5cb',
'\\<s>' : '\U0001d5cc',
'\\<t>' : '\U0001d5cd',
'\\<u>' : '\U0001d5ce',
'\\<v>' : '\U0001d5cf',
'\\<w>' : '\U0001d5d0',
'\\<x>' : '\U0001d5d1',
'\\<y>' : '\U0001d5d2',
'\\<z>' : '\U0001d5d3',
'\\<AA>' : '\U0001d504',
'\\<BB>' : '\U0001d505',
'\\<CC>' : '\U0000212d',
'\\<DD>' : '\U0001d507',
'\\<EE>' : '\U0001d508',
'\\<FF>' : '\U0001d509',
'\\<GG>' : '\U0001d50a',
'\\<HH>' : '\U0000210c',
'\\<II>' : '\U00002111',
'\\<JJ>' : '\U0001d50d',
'\\<KK>' : '\U0001d50e',
'\\<LL>' : '\U0001d50f',
'\\<MM>' : '\U0001d510',
'\\<NN>' : '\U0001d511',
'\\<OO>' : '\U0001d512',
'\\<PP>' : '\U0001d513',
'\\<QQ>' : '\U0001d514',
'\\<RR>' : '\U0000211c',
'\\<SS>' : '\U0001d516',
'\\<TT>' : '\U0001d517',
'\\<UU>' : '\U0001d518',
'\\<VV>' : '\U0001d519',
'\\<WW>' : '\U0001d51a',
'\\<XX>' : '\U0001d51b',
'\\<YY>' : '\U0001d51c',
'\\<ZZ>' : '\U00002128',
'\\<aa>' : '\U0001d51e',
'\\<bb>' : '\U0001d51f',
'\\<cc>' : '\U0001d520',
'\\<dd>' : '\U0001d521',
'\\<ee>' : '\U0001d522',
'\\<ff>' : '\U0001d523',
'\\<gg>' : '\U0001d524',
'\\<hh>' : '\U0001d525',
'\\<ii>' : '\U0001d526',
'\\<jj>' : '\U0001d527',
'\\<kk>' : '\U0001d528',
'\\<ll>' : '\U0001d529',
'\\<mm>' : '\U0001d52a',
'\\<nn>' : '\U0001d52b',
'\\<oo>' : '\U0001d52c',
'\\<pp>' : '\U0001d52d',
'\\<qq>' : '\U0001d52e',
'\\<rr>' : '\U0001d52f',
'\\<ss>' : '\U0001d530',
'\\<tt>' : '\U0001d531',
'\\<uu>' : '\U0001d532',
'\\<vv>' : '\U0001d533',
'\\<ww>' : '\U0001d534',
'\\<xx>' : '\U0001d535',
'\\<yy>' : '\U0001d536',
'\\<zz>' : '\U0001d537',
'\\<alpha>' : '\U000003b1',
'\\<beta>' : '\U000003b2',
'\\<gamma>' : '\U000003b3',
'\\<delta>' : '\U000003b4',
'\\<epsilon>' : '\U000003b5',
'\\<zeta>' : '\U000003b6',
'\\<eta>' : '\U000003b7',
'\\<theta>' : '\U000003b8',
'\\<iota>' : '\U000003b9',
'\\<kappa>' : '\U000003ba',
'\\<lambda>' : '\U000003bb',
'\\<mu>' : '\U000003bc',
'\\<nu>' : '\U000003bd',
'\\<xi>' : '\U000003be',
'\\<pi>' : '\U000003c0',
'\\<rho>' : '\U000003c1',
'\\<sigma>' : '\U000003c3',
'\\<tau>' : '\U000003c4',
'\\<upsilon>' : '\U000003c5',
'\\<phi>' : '\U000003c6',
'\\<chi>' : '\U000003c7',
'\\<psi>' : '\U000003c8',
'\\<omega>' : '\U000003c9',
'\\<Gamma>' : '\U00000393',
'\\<Delta>' : '\U00000394',
'\\<Theta>' : '\U00000398',
'\\<Lambda>' : '\U0000039b',
'\\<Xi>' : '\U0000039e',
'\\<Pi>' : '\U000003a0',
'\\<Sigma>' : '\U000003a3',
'\\<Upsilon>' : '\U000003a5',
'\\<Phi>' : '\U000003a6',
'\\<Psi>' : '\U000003a8',
'\\<Omega>' : '\U000003a9',
'\\<bool>' : '\U0001d539',
'\\<complex>' : '\U00002102',
'\\<nat>' : '\U00002115',
'\\<rat>' : '\U0000211a',
'\\<real>' : '\U0000211d',
'\\<int>' : '\U00002124',
'\\<leftarrow>' : '\U00002190',
'\\<longleftarrow>' : '\U000027f5',
'\\<rightarrow>' : '\U00002192',
'\\<longrightarrow>' : '\U000027f6',
'\\<Leftarrow>' : '\U000021d0',
'\\<Longleftarrow>' : '\U000027f8',
'\\<Rightarrow>' : '\U000021d2',
'\\<Longrightarrow>' : '\U000027f9',
'\\<leftrightarrow>' : '\U00002194',
'\\<longleftrightarrow>' : '\U000027f7',
'\\<Leftrightarrow>' : '\U000021d4',
'\\<Longleftrightarrow>' : '\U000027fa',
'\\<mapsto>' : '\U000021a6',
'\\<longmapsto>' : '\U000027fc',
'\\<midarrow>' : '\U00002500',
'\\<Midarrow>' : '\U00002550',
'\\<hookleftarrow>' : '\U000021a9',
'\\<hookrightarrow>' : '\U000021aa',
'\\<leftharpoondown>' : '\U000021bd',
'\\<rightharpoondown>' : '\U000021c1',
'\\<leftharpoonup>' : '\U000021bc',
'\\<rightharpoonup>' : '\U000021c0',
'\\<rightleftharpoons>' : '\U000021cc',
'\\<leadsto>' : '\U0000219d',
'\\<downharpoonleft>' : '\U000021c3',
'\\<downharpoonright>' : '\U000021c2',
'\\<upharpoonleft>' : '\U000021bf',
'\\<upharpoonright>' : '\U000021be',
'\\<restriction>' : '\U000021be',
'\\<Colon>' : '\U00002237',
'\\<up>' : '\U00002191',
'\\<Up>' : '\U000021d1',
'\\<down>' : '\U00002193',
'\\<Down>' : '\U000021d3',
'\\<updown>' : '\U00002195',
'\\<Updown>' : '\U000021d5',
'\\<langle>' : '\U000027e8',
'\\<rangle>' : '\U000027e9',
'\\<lceil>' : '\U00002308',
'\\<rceil>' : '\U00002309',
'\\<lfloor>' : '\U0000230a',
'\\<rfloor>' : '\U0000230b',
'\\<lparr>' : '\U00002987',
'\\<rparr>' : '\U00002988',
'\\<lbrakk>' : '\U000027e6',
'\\<rbrakk>' : '\U000027e7',
'\\<lbrace>' : '\U00002983',
'\\<rbrace>' : '\U00002984',
'\\<guillemotleft>' : '\U000000ab',
'\\<guillemotright>' : '\U000000bb',
'\\<bottom>' : '\U000022a5',
'\\<top>' : '\U000022a4',
'\\<and>' : '\U00002227',
'\\<And>' : '\U000022c0',
'\\<or>' : '\U00002228',
'\\<Or>' : '\U000022c1',
'\\<forall>' : '\U00002200',
'\\<exists>' : '\U00002203',
'\\<nexists>' : '\U00002204',
'\\<not>' : '\U000000ac',
'\\<box>' : '\U000025a1',
'\\<diamond>' : '\U000025c7',
'\\<turnstile>' : '\U000022a2',
'\\<Turnstile>' : '\U000022a8',
'\\<tturnstile>' : '\U000022a9',
'\\<TTurnstile>' : '\U000022ab',
'\\<stileturn>' : '\U000022a3',
'\\<surd>' : '\U0000221a',
'\\<le>' : '\U00002264',
'\\<ge>' : '\U00002265',
'\\<lless>' : '\U0000226a',
'\\<ggreater>' : '\U0000226b',
'\\<lesssim>' : '\U00002272',
'\\<greatersim>' : '\U00002273',
'\\<lessapprox>' : '\U00002a85',
'\\<greaterapprox>' : '\U00002a86',
'\\<in>' : '\U00002208',
'\\<notin>' : '\U00002209',
'\\<subset>' : '\U00002282',
'\\<supset>' : '\U00002283',
'\\<subseteq>' : '\U00002286',
'\\<supseteq>' : '\U00002287',
'\\<sqsubset>' : '\U0000228f',
'\\<sqsupset>' : '\U00002290',
'\\<sqsubseteq>' : '\U00002291',
'\\<sqsupseteq>' : '\U00002292',
'\\<inter>' : '\U00002229',
'\\<Inter>' : '\U000022c2',
'\\<union>' : '\U0000222a',
'\\<Union>' : '\U000022c3',
'\\<squnion>' : '\U00002294',
'\\<Squnion>' : '\U00002a06',
'\\<sqinter>' : '\U00002293',
'\\<Sqinter>' : '\U00002a05',
'\\<setminus>' : '\U00002216',
'\\<propto>' : '\U0000221d',
'\\<uplus>' : '\U0000228e',
'\\<Uplus>' : '\U00002a04',
'\\<noteq>' : '\U00002260',
'\\<sim>' : '\U0000223c',
'\\<doteq>' : '\U00002250',
'\\<simeq>' : '\U00002243',
'\\<approx>' : '\U00002248',
'\\<asymp>' : '\U0000224d',
'\\<cong>' : '\U00002245',
'\\<smile>' : '\U00002323',
'\\<equiv>' : '\U00002261',
'\\<frown>' : '\U00002322',
'\\<Join>' : '\U000022c8',
'\\<bowtie>' : '\U00002a1d',
'\\<prec>' : '\U0000227a',
'\\<succ>' : '\U0000227b',
'\\<preceq>' : '\U0000227c',
'\\<succeq>' : '\U0000227d',
'\\<parallel>' : '\U00002225',
'\\<bar>' : '\U000000a6',
'\\<plusminus>' : '\U000000b1',
'\\<minusplus>' : '\U00002213',
'\\<times>' : '\U000000d7',
'\\<div>' : '\U000000f7',
'\\<cdot>' : '\U000022c5',
'\\<star>' : '\U000022c6',
'\\<bullet>' : '\U00002219',
'\\<circ>' : '\U00002218',
'\\<dagger>' : '\U00002020',
'\\<ddagger>' : '\U00002021',
'\\<lhd>' : '\U000022b2',
'\\<rhd>' : '\U000022b3',
'\\<unlhd>' : '\U000022b4',
'\\<unrhd>' : '\U000022b5',
'\\<triangleleft>' : '\U000025c3',
'\\<triangleright>' : '\U000025b9',
'\\<triangle>' : '\U000025b3',
'\\<triangleq>' : '\U0000225c',
'\\<oplus>' : '\U00002295',
'\\<Oplus>' : '\U00002a01',
'\\<otimes>' : '\U00002297',
'\\<Otimes>' : '\U00002a02',
'\\<odot>' : '\U00002299',
'\\<Odot>' : '\U00002a00',
'\\<ominus>' : '\U00002296',
'\\<oslash>' : '\U00002298',
'\\<dots>' : '\U00002026',
'\\<cdots>' : '\U000022ef',
'\\<Sum>' : '\U00002211',
'\\<Prod>' : '\U0000220f',
'\\<Coprod>' : '\U00002210',
'\\<infinity>' : '\U0000221e',
'\\<integral>' : '\U0000222b',
'\\<ointegral>' : '\U0000222e',
'\\<clubsuit>' : '\U00002663',
'\\<diamondsuit>' : '\U00002662',
'\\<heartsuit>' : '\U00002661',
'\\<spadesuit>' : '\U00002660',
'\\<aleph>' : '\U00002135',
'\\<emptyset>' : '\U00002205',
'\\<nabla>' : '\U00002207',
'\\<partial>' : '\U00002202',
'\\<flat>' : '\U0000266d',
'\\<natural>' : '\U0000266e',
'\\<sharp>' : '\U0000266f',
'\\<angle>' : '\U00002220',
'\\<copyright>' : '\U000000a9',
'\\<registered>' : '\U000000ae',
'\\<hyphen>' : '\U000000ad',
'\\<inverse>' : '\U000000af',
'\\<onequarter>' : '\U000000bc',
'\\<onehalf>' : '\U000000bd',
'\\<threequarters>' : '\U000000be',
'\\<ordfeminine>' : '\U000000aa',
'\\<ordmasculine>' : '\U000000ba',
'\\<section>' : '\U000000a7',
'\\<paragraph>' : '\U000000b6',
'\\<exclamdown>' : '\U000000a1',
'\\<questiondown>' : '\U000000bf',
'\\<euro>' : '\U000020ac',
'\\<pounds>' : '\U000000a3',
'\\<yen>' : '\U000000a5',
'\\<cent>' : '\U000000a2',
'\\<currency>' : '\U000000a4',
'\\<degree>' : '\U000000b0',
'\\<amalg>' : '\U00002a3f',
'\\<mho>' : '\U00002127',
'\\<lozenge>' : '\U000025ca',
'\\<wp>' : '\U00002118',
'\\<wrong>' : '\U00002240',
'\\<struct>' : '\U000022c4',
'\\<acute>' : '\U000000b4',
'\\<index>' : '\U00000131',
'\\<dieresis>' : '\U000000a8',
'\\<cedilla>' : '\U000000b8',
'\\<hungarumlaut>' : '\U000002dd',
'\\<some>' : '\U000003f5',
'\\<newline>' : '\U000023ce',
'\\<open>' : '\U00002039',
'\\<close>' : '\U0000203a',
'\\<here>' : '\U00002302',
'\\<^sub>' : '\U000021e9',
'\\<^sup>' : '\U000021e7',
'\\<^bold>' : '\U00002759',
'\\<^bsub>' : '\U000021d8',
'\\<^esub>' : '\U000021d9',
'\\<^bsup>' : '\U000021d7',
'\\<^esup>' : '\U000021d6',
}
lang_map = {'isabelle' : isabelle_symbols, 'latex' : latex_symbols}
def __init__(self, **options):
Filter.__init__(self, **options)
lang = get_choice_opt(options, 'lang',
['isabelle', 'latex'], 'isabelle')
self.symbols = self.lang_map[lang]
def filter(self, lexer, stream):
for ttype, value in stream:
if value in self.symbols:
yield ttype, self.symbols[value]
else:
yield ttype, value
class KeywordCaseFilter(Filter):
"""Convert keywords to lowercase or uppercase or capitalize them, which
means first letter uppercase, rest lowercase.
This can be useful e.g. if you highlight Pascal code and want to adapt the
code to your styleguide.
Options accepted:
`case` : string
The casing to convert keywords to. Must be one of ``'lower'``,
``'upper'`` or ``'capitalize'``. The default is ``'lower'``.
"""
def __init__(self, **options):
Filter.__init__(self, **options)
case = get_choice_opt(options, 'case',
['lower', 'upper', 'capitalize'], 'lower')
self.convert = getattr(str, case)
def filter(self, lexer, stream):
for ttype, value in stream:
if ttype in Keyword:
yield ttype, self.convert(value)
else:
yield ttype, value
class NameHighlightFilter(Filter):
"""Highlight a normal Name (and Name.*) token with a different token type.
Example::
filter = NameHighlightFilter(
names=['foo', 'bar', 'baz'],
tokentype=Name.Function,
)
This would highlight the names "foo", "bar" and "baz"
as functions. `Name.Function` is the default token type.
Options accepted:
`names` : list of strings
A list of names that should be given the different token type.
There is no default.
`tokentype` : TokenType or string
A token type or a string containing a token type name that is
used for highlighting the strings in `names`. The default is
`Name.Function`.
"""
def __init__(self, **options):
Filter.__init__(self, **options)
self.names = set(get_list_opt(options, 'names', []))
tokentype = options.get('tokentype')
if tokentype:
self.tokentype = string_to_tokentype(tokentype)
else:
self.tokentype = Name.Function
def filter(self, lexer, stream):
for ttype, value in stream:
if ttype in Name and value in self.names:
yield self.tokentype, value
else:
yield ttype, value
class ErrorToken(Exception):
pass
class RaiseOnErrorTokenFilter(Filter):
"""Raise an exception when the lexer generates an error token.
Options accepted:
`excclass` : Exception class
The exception class to raise.
The default is `pygments.filters.ErrorToken`.
.. versionadded:: 0.8
"""
def __init__(self, **options):
Filter.__init__(self, **options)
self.exception = options.get('excclass', ErrorToken)
try:
# issubclass() will raise TypeError if first argument is not a class
if not issubclass(self.exception, Exception):
raise TypeError
except TypeError:
raise OptionError('excclass option is not an exception class')
def filter(self, lexer, stream):
for ttype, value in stream:
if ttype is Error:
raise self.exception(value)
yield ttype, value
class VisibleWhitespaceFilter(Filter):
"""Convert tabs, newlines and/or spaces to visible characters.
Options accepted:
`spaces` : string or bool
If this is a one-character string, spaces will be replaces by this string.
If it is another true value, spaces will be replaced by ``·`` (unicode
MIDDLE DOT). If it is a false value, spaces will not be replaced. The
default is ``False``.
`tabs` : string or bool
The same as for `spaces`, but the default replacement character is ``»``
(unicode RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK). The default value
is ``False``. Note: this will not work if the `tabsize` option for the
lexer is nonzero, as tabs will already have been expanded then.
`tabsize` : int
If tabs are to be replaced by this filter (see the `tabs` option), this
is the total number of characters that a tab should be expanded to.
The default is ``8``.
`newlines` : string or bool
The same as for `spaces`, but the default replacement character is ````
(unicode PILCROW SIGN). The default value is ``False``.
`wstokentype` : bool
If true, give whitespace the special `Whitespace` token type. This allows
styling the visible whitespace differently (e.g. greyed out), but it can
disrupt background colors. The default is ``True``.
.. versionadded:: 0.8
"""
def __init__(self, **options):
Filter.__init__(self, **options)
for name, default in [('spaces', '·'),
('tabs', '»'),
('newlines', '')]:
opt = options.get(name, False)
if isinstance(opt, str) and len(opt) == 1:
setattr(self, name, opt)
else:
setattr(self, name, (opt and default or ''))
tabsize = get_int_opt(options, 'tabsize', 8)
if self.tabs:
self.tabs += ' ' * (tabsize - 1)
if self.newlines:
self.newlines += '\n'
self.wstt = get_bool_opt(options, 'wstokentype', True)
def filter(self, lexer, stream):
if self.wstt:
spaces = self.spaces or ' '
tabs = self.tabs or '\t'
newlines = self.newlines or '\n'
regex = re.compile(r'\s')
def replacefunc(wschar):
if wschar == ' ':
return spaces
elif wschar == '\t':
return tabs
elif wschar == '\n':
return newlines
return wschar
for ttype, value in stream:
yield from _replace_special(ttype, value, regex, Whitespace,
replacefunc)
else:
spaces, tabs, newlines = self.spaces, self.tabs, self.newlines
# simpler processing
for ttype, value in stream:
if spaces:
value = value.replace(' ', spaces)
if tabs:
value = value.replace('\t', tabs)
if newlines:
value = value.replace('\n', newlines)
yield ttype, value
class GobbleFilter(Filter):
"""Gobbles source code lines (eats initial characters).
This filter drops the first ``n`` characters off every line of code. This
may be useful when the source code fed to the lexer is indented by a fixed
amount of space that isn't desired in the output.
Options accepted:
`n` : int
The number of characters to gobble.
.. versionadded:: 1.2
"""
def __init__(self, **options):
Filter.__init__(self, **options)
self.n = get_int_opt(options, 'n', 0)
def gobble(self, value, left):
if left < len(value):
return value[left:], 0
else:
return '', left - len(value)
def filter(self, lexer, stream):
n = self.n
left = n # How many characters left to gobble.
for ttype, value in stream:
# Remove ``left`` tokens from first line, ``n`` from all others.
parts = value.split('\n')
(parts[0], left) = self.gobble(parts[0], left)
for i in range(1, len(parts)):
(parts[i], left) = self.gobble(parts[i], n)
value = '\n'.join(parts)
if value != '':
yield ttype, value
class TokenMergeFilter(Filter):
"""Merges consecutive tokens with the same token type in the output
stream of a lexer.
.. versionadded:: 1.2
"""
def __init__(self, **options):
Filter.__init__(self, **options)
def filter(self, lexer, stream):
current_type = None
current_value = None
for ttype, value in stream:
if ttype is current_type:
current_value += value
else:
if current_type is not None:
yield current_type, current_value
current_type = ttype
current_value = value
if current_type is not None:
yield current_type, current_value
FILTERS = {
'codetagify': CodeTagFilter,
'keywordcase': KeywordCaseFilter,
'highlight': NameHighlightFilter,
'raiseonerror': RaiseOnErrorTokenFilter,
'whitespace': VisibleWhitespaceFilter,
'gobble': GobbleFilter,
'tokenmerge': TokenMergeFilter,
'symbols': SymbolFilter,
}

View file

@ -0,0 +1,124 @@
"""
pygments.formatter
~~~~~~~~~~~~~~~~~~
Base formatter class.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import codecs
from pip._vendor.pygments.util import get_bool_opt
from pip._vendor.pygments.styles import get_style_by_name
__all__ = ['Formatter']
def _lookup_style(style):
if isinstance(style, str):
return get_style_by_name(style)
return style
class Formatter:
"""
Converts a token stream to text.
Formatters should have attributes to help selecting them. These
are similar to the corresponding :class:`~pygments.lexer.Lexer`
attributes.
.. autoattribute:: name
:no-value:
.. autoattribute:: aliases
:no-value:
.. autoattribute:: filenames
:no-value:
You can pass options as keyword arguments to the constructor.
All formatters accept these basic options:
``style``
The style to use, can be a string or a Style subclass
(default: "default"). Not used by e.g. the
TerminalFormatter.
``full``
Tells the formatter to output a "full" document, i.e.
a complete self-contained document. This doesn't have
any effect for some formatters (default: false).
``title``
If ``full`` is true, the title that should be used to
caption the document (default: '').
``encoding``
If given, must be an encoding name. This will be used to
convert the Unicode token strings to byte strings in the
output. If it is "" or None, Unicode strings will be written
to the output file, which most file-like objects do not
support (default: None).
``outencoding``
Overrides ``encoding`` if given.
"""
#: Full name for the formatter, in human-readable form.
name = None
#: A list of short, unique identifiers that can be used to lookup
#: the formatter from a list, e.g. using :func:`.get_formatter_by_name()`.
aliases = []
#: A list of fnmatch patterns that match filenames for which this
#: formatter can produce output. The patterns in this list should be unique
#: among all formatters.
filenames = []
#: If True, this formatter outputs Unicode strings when no encoding
#: option is given.
unicodeoutput = True
def __init__(self, **options):
"""
As with lexers, this constructor takes arbitrary optional arguments,
and if you override it, you should first process your own options, then
call the base class implementation.
"""
self.style = _lookup_style(options.get('style', 'default'))
self.full = get_bool_opt(options, 'full', False)
self.title = options.get('title', '')
self.encoding = options.get('encoding', None) or None
if self.encoding in ('guess', 'chardet'):
# can happen for e.g. pygmentize -O encoding=guess
self.encoding = 'utf-8'
self.encoding = options.get('outencoding') or self.encoding
self.options = options
def get_style_defs(self, arg=''):
"""
This method must return statements or declarations suitable to define
the current style for subsequent highlighted text (e.g. CSS classes
in the `HTMLFormatter`).
The optional argument `arg` can be used to modify the generation and
is formatter dependent (it is standardized because it can be given on
the command line).
This method is called by the ``-S`` :doc:`command-line option <cmdline>`,
the `arg` is then given by the ``-a`` option.
"""
return ''
def format(self, tokensource, outfile):
"""
This method must format the tokens from the `tokensource` iterable and
write the formatted version to the file object `outfile`.
Formatter options can control how exactly the tokens are converted.
"""
if self.encoding:
# wrap the outfile in a StreamWriter
outfile = codecs.lookup(self.encoding)[3](outfile)
return self.format_unencoded(tokensource, outfile)

View file

@ -0,0 +1,158 @@
"""
pygments.formatters
~~~~~~~~~~~~~~~~~~~
Pygments formatters.
:copyright: Copyright 2006-2023 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 pip._vendor.pygments.formatters._mapping import FORMATTERS
from pip._vendor.pygments.plugin import find_plugin_formatters
from pip._vendor.pygments.util import ClassNotFound
__all__ = ['get_formatter_by_name', 'get_formatter_for_filename',
'get_all_formatters', 'load_formatter_from_file'] + list(FORMATTERS)
_formatter_cache = {} # classes by name
_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_formatters(module_name):
"""Load a formatter (and all others in the module too)."""
mod = __import__(module_name, None, None, ['__all__'])
for formatter_name in mod.__all__:
cls = getattr(mod, formatter_name)
_formatter_cache[cls.name] = cls
def get_all_formatters():
"""Return a generator for all formatter classes."""
# NB: this returns formatter classes, not info like get_all_lexers().
for info in FORMATTERS.values():
if info[1] not in _formatter_cache:
_load_formatters(info[0])
yield _formatter_cache[info[1]]
for _, formatter in find_plugin_formatters():
yield formatter
def find_formatter_class(alias):
"""Lookup a formatter by alias.
Returns None if not found.
"""
for module_name, name, aliases, _, _ in FORMATTERS.values():
if alias in aliases:
if name not in _formatter_cache:
_load_formatters(module_name)
return _formatter_cache[name]
for _, cls in find_plugin_formatters():
if alias in cls.aliases:
return cls
def get_formatter_by_name(_alias, **options):
"""
Return an instance of a :class:`.Formatter` subclass that has `alias` in its
aliases list. The formatter is given the `options` at its instantiation.
Will raise :exc:`pygments.util.ClassNotFound` if no formatter with that
alias is found.
"""
cls = find_formatter_class(_alias)
if cls is None:
raise ClassNotFound("no formatter found for name %r" % _alias)
return cls(**options)
def load_formatter_from_file(filename, formattername="CustomFormatter", **options):
"""
Return a `Formatter` subclass instance loaded from the provided file, relative
to the current directory.
The file is expected to contain a Formatter class named ``formattername``
(by default, CustomFormatter). Users should be very careful with the input, because
this method is equivalent to running ``eval()`` on the input file. The formatter is
given the `options` at its instantiation.
:exc:`pygments.util.ClassNotFound` is raised if there are any errors loading
the formatter.
.. versionadded:: 2.2
"""
try:
# This empty dict will contain the namespace for the exec'd file
custom_namespace = {}
with open(filename, 'rb') as f:
exec(f.read(), custom_namespace)
# Retrieve the class `formattername` from that namespace
if formattername not in custom_namespace:
raise ClassNotFound('no valid %s class found in %s' %
(formattername, filename))
formatter_class = custom_namespace[formattername]
# And finally instantiate it with the options
return formatter_class(**options)
except OSError as err:
raise ClassNotFound('cannot read %s: %s' % (filename, err))
except ClassNotFound:
raise
except Exception as err:
raise ClassNotFound('error when loading custom formatter: %s' % err)
def get_formatter_for_filename(fn, **options):
"""
Return a :class:`.Formatter` subclass instance that has a filename pattern
matching `fn`. The formatter is given the `options` at its instantiation.
Will raise :exc:`pygments.util.ClassNotFound` if no formatter for that filename
is found.
"""
fn = basename(fn)
for modname, name, _, filenames, _ in FORMATTERS.values():
for filename in filenames:
if _fn_matches(fn, filename):
if name not in _formatter_cache:
_load_formatters(modname)
return _formatter_cache[name](**options)
for cls in find_plugin_formatters():
for filename in cls.filenames:
if _fn_matches(fn, filename):
return cls(**options)
raise ClassNotFound("no formatter found for file name %r" % fn)
class _automodule(types.ModuleType):
"""Automatically import formatters."""
def __getattr__(self, name):
info = FORMATTERS.get(name)
if info:
_load_formatters(info[0])
cls = _formatter_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

View file

@ -0,0 +1,23 @@
# Automatically generated by scripts/gen_mapfiles.py.
# DO NOT EDIT BY HAND; run `tox -e mapfiles` instead.
FORMATTERS = {
'BBCodeFormatter': ('pygments.formatters.bbcode', 'BBCode', ('bbcode', 'bb'), (), 'Format tokens with BBcodes. These formatting codes are used by many bulletin boards, so you can highlight your sourcecode with pygments before posting it there.'),
'BmpImageFormatter': ('pygments.formatters.img', 'img_bmp', ('bmp', 'bitmap'), ('*.bmp',), 'Create a bitmap image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
'GifImageFormatter': ('pygments.formatters.img', 'img_gif', ('gif',), ('*.gif',), 'Create a GIF image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
'GroffFormatter': ('pygments.formatters.groff', 'groff', ('groff', 'troff', 'roff'), (), 'Format tokens with groff escapes to change their color and font style.'),
'HtmlFormatter': ('pygments.formatters.html', 'HTML', ('html',), ('*.html', '*.htm'), "Format tokens as HTML 4 ``<span>`` tags. By default, the content is enclosed in a ``<pre>`` tag, itself wrapped in a ``<div>`` tag (but see the `nowrap` option). The ``<div>``'s CSS class can be set by the `cssclass` option."),
'IRCFormatter': ('pygments.formatters.irc', 'IRC', ('irc', 'IRC'), (), 'Format tokens with IRC color sequences'),
'ImageFormatter': ('pygments.formatters.img', 'img', ('img', 'IMG', 'png'), ('*.png',), 'Create a PNG image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
'JpgImageFormatter': ('pygments.formatters.img', 'img_jpg', ('jpg', 'jpeg'), ('*.jpg',), 'Create a JPEG image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
'LatexFormatter': ('pygments.formatters.latex', 'LaTeX', ('latex', 'tex'), ('*.tex',), 'Format tokens as LaTeX code. This needs the `fancyvrb` and `color` standard packages.'),
'NullFormatter': ('pygments.formatters.other', 'Text only', ('text', 'null'), ('*.txt',), 'Output the text unchanged without any formatting.'),
'PangoMarkupFormatter': ('pygments.formatters.pangomarkup', 'Pango Markup', ('pango', 'pangomarkup'), (), 'Format tokens as Pango Markup code. It can then be rendered to an SVG.'),
'RawTokenFormatter': ('pygments.formatters.other', 'Raw tokens', ('raw', 'tokens'), ('*.raw',), 'Format tokens as a raw representation for storing token streams.'),
'RtfFormatter': ('pygments.formatters.rtf', 'RTF', ('rtf',), ('*.rtf',), 'Format tokens as RTF markup. This formatter automatically outputs full RTF documents with color information and other useful stuff. Perfect for Copy and Paste into Microsoft(R) Word(R) documents.'),
'SvgFormatter': ('pygments.formatters.svg', 'SVG', ('svg',), ('*.svg',), 'Format tokens as an SVG graphics file. This formatter is still experimental. Each line of code is a ``<text>`` element with explicit ``x`` and ``y`` coordinates containing ``<tspan>`` elements with the individual token styles.'),
'Terminal256Formatter': ('pygments.formatters.terminal256', 'Terminal256', ('terminal256', 'console256', '256'), (), 'Format tokens with ANSI color sequences, for output in a 256-color terminal or console. Like in `TerminalFormatter` color sequences are terminated at newlines, so that paging the output works correctly.'),
'TerminalFormatter': ('pygments.formatters.terminal', 'Terminal', ('terminal', 'console'), (), 'Format tokens with ANSI color sequences, for output in a text console. Color sequences are terminated at newlines, so that paging the output works correctly.'),
'TerminalTrueColorFormatter': ('pygments.formatters.terminal256', 'TerminalTrueColor', ('terminal16m', 'console16m', '16m'), (), 'Format tokens with ANSI color sequences, for output in a true-color terminal or console. Like in `TerminalFormatter` color sequences are terminated at newlines, so that paging the output works correctly.'),
'TestcaseFormatter': ('pygments.formatters.other', 'Testcase', ('testcase',), (), 'Format tokens as appropriate for a new testcase.'),
}

View file

@ -0,0 +1,108 @@
"""
pygments.formatters.bbcode
~~~~~~~~~~~~~~~~~~~~~~~~~~
BBcode formatter.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.util import get_bool_opt
__all__ = ['BBCodeFormatter']
class BBCodeFormatter(Formatter):
"""
Format tokens with BBcodes. These formatting codes are used by many
bulletin boards, so you can highlight your sourcecode with pygments before
posting it there.
This formatter has no support for background colors and borders, as there
are no common BBcode tags for that.
Some board systems (e.g. phpBB) don't support colors in their [code] tag,
so you can't use the highlighting together with that tag.
Text in a [code] tag usually is shown with a monospace font (which this
formatter can do with the ``monofont`` option) and no spaces (which you
need for indentation) are removed.
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`codetag`
If set to true, put the output into ``[code]`` tags (default:
``false``)
`monofont`
If set to true, add a tag to show the code with a monospace font
(default: ``false``).
"""
name = 'BBCode'
aliases = ['bbcode', 'bb']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self._code = get_bool_opt(options, 'codetag', False)
self._mono = get_bool_opt(options, 'monofont', False)
self.styles = {}
self._make_styles()
def _make_styles(self):
for ttype, ndef in self.style:
start = end = ''
if ndef['color']:
start += '[color=#%s]' % ndef['color']
end = '[/color]' + end
if ndef['bold']:
start += '[b]'
end = '[/b]' + end
if ndef['italic']:
start += '[i]'
end = '[/i]' + end
if ndef['underline']:
start += '[u]'
end = '[/u]' + end
# there are no common BBcodes for background-color and border
self.styles[ttype] = start, end
def format_unencoded(self, tokensource, outfile):
if self._code:
outfile.write('[code]')
if self._mono:
outfile.write('[font=monospace]')
lastval = ''
lasttype = None
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
if ttype == lasttype:
lastval += value
else:
if lastval:
start, end = self.styles[lasttype]
outfile.write(''.join((start, lastval, end)))
lastval = value
lasttype = ttype
if lastval:
start, end = self.styles[lasttype]
outfile.write(''.join((start, lastval, end)))
if self._mono:
outfile.write('[/font]')
if self._code:
outfile.write('[/code]')
if self._code or self._mono:
outfile.write('\n')

View file

@ -0,0 +1,170 @@
"""
pygments.formatters.groff
~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for groff output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import math
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.util import get_bool_opt, get_int_opt
__all__ = ['GroffFormatter']
class GroffFormatter(Formatter):
"""
Format tokens with groff escapes to change their color and font style.
.. versionadded:: 2.11
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`monospaced`
If set to true, monospace font will be used (default: ``true``).
`linenos`
If set to true, print the line numbers (default: ``false``).
`wrap`
Wrap lines to the specified number of characters. Disabled if set to 0
(default: ``0``).
"""
name = 'groff'
aliases = ['groff','troff','roff']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.monospaced = get_bool_opt(options, 'monospaced', True)
self.linenos = get_bool_opt(options, 'linenos', False)
self._lineno = 0
self.wrap = get_int_opt(options, 'wrap', 0)
self._linelen = 0
self.styles = {}
self._make_styles()
def _make_styles(self):
regular = '\\f[CR]' if self.monospaced else '\\f[R]'
bold = '\\f[CB]' if self.monospaced else '\\f[B]'
italic = '\\f[CI]' if self.monospaced else '\\f[I]'
for ttype, ndef in self.style:
start = end = ''
if ndef['color']:
start += '\\m[%s]' % ndef['color']
end = '\\m[]' + end
if ndef['bold']:
start += bold
end = regular + end
if ndef['italic']:
start += italic
end = regular + end
if ndef['bgcolor']:
start += '\\M[%s]' % ndef['bgcolor']
end = '\\M[]' + end
self.styles[ttype] = start, end
def _define_colors(self, outfile):
colors = set()
for _, ndef in self.style:
if ndef['color'] is not None:
colors.add(ndef['color'])
for color in sorted(colors):
outfile.write('.defcolor ' + color + ' rgb #' + color + '\n')
def _write_lineno(self, outfile):
self._lineno += 1
outfile.write("%s% 4d " % (self._lineno != 1 and '\n' or '', self._lineno))
def _wrap_line(self, line):
length = len(line.rstrip('\n'))
space = ' ' if self.linenos else ''
newline = ''
if length > self.wrap:
for i in range(0, math.floor(length / self.wrap)):
chunk = line[i*self.wrap:i*self.wrap+self.wrap]
newline += (chunk + '\n' + space)
remainder = length % self.wrap
if remainder > 0:
newline += line[-remainder-1:]
self._linelen = remainder
elif self._linelen + length > self.wrap:
newline = ('\n' + space) + line
self._linelen = length
else:
newline = line
self._linelen += length
return newline
def _escape_chars(self, text):
text = text.replace('\\', '\\[u005C]'). \
replace('.', '\\[char46]'). \
replace('\'', '\\[u0027]'). \
replace('`', '\\[u0060]'). \
replace('~', '\\[u007E]')
copy = text
for char in copy:
if len(char) != len(char.encode()):
uni = char.encode('unicode_escape') \
.decode()[1:] \
.replace('x', 'u00') \
.upper()
text = text.replace(char, '\\[u' + uni[1:] + ']')
return text
def format_unencoded(self, tokensource, outfile):
self._define_colors(outfile)
outfile.write('.nf\n\\f[CR]\n')
if self.linenos:
self._write_lineno(outfile)
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
start, end = self.styles[ttype]
for line in value.splitlines(True):
if self.wrap > 0:
line = self._wrap_line(line)
if start and end:
text = self._escape_chars(line.rstrip('\n'))
if text != '':
outfile.write(''.join((start, text, end)))
else:
outfile.write(self._escape_chars(line.rstrip('\n')))
if line.endswith('\n'):
if self.linenos:
self._write_lineno(outfile)
self._linelen = 0
else:
outfile.write('\n')
self._linelen = 0
outfile.write('\n.fi')

View file

@ -0,0 +1,989 @@
"""
pygments.formatters.html
~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for HTML output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import functools
import os
import sys
import os.path
from io import StringIO
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.token import Token, Text, STANDARD_TYPES
from pip._vendor.pygments.util import get_bool_opt, get_int_opt, get_list_opt
try:
import ctags
except ImportError:
ctags = None
__all__ = ['HtmlFormatter']
_escape_html_table = {
ord('&'): '&amp;',
ord('<'): '&lt;',
ord('>'): '&gt;',
ord('"'): '&quot;',
ord("'"): '&#39;',
}
def escape_html(text, table=_escape_html_table):
"""Escape &, <, > as well as single and double quotes for HTML."""
return text.translate(table)
def webify(color):
if color.startswith('calc') or color.startswith('var'):
return color
else:
return '#' + color
def _get_ttype_class(ttype):
fname = STANDARD_TYPES.get(ttype)
if fname:
return fname
aname = ''
while fname is None:
aname = '-' + ttype[-1] + aname
ttype = ttype.parent
fname = STANDARD_TYPES.get(ttype)
return fname + aname
CSSFILE_TEMPLATE = '''\
/*
generated by Pygments <https://pygments.org/>
Copyright 2006-2023 by the Pygments team.
Licensed under the BSD license, see LICENSE for details.
*/
%(styledefs)s
'''
DOC_HEADER = '''\
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<!--
generated by Pygments <https://pygments.org/>
Copyright 2006-2023 by the Pygments team.
Licensed under the BSD license, see LICENSE for details.
-->
<html>
<head>
<title>%(title)s</title>
<meta http-equiv="content-type" content="text/html; charset=%(encoding)s">
<style type="text/css">
''' + CSSFILE_TEMPLATE + '''
</style>
</head>
<body>
<h2>%(title)s</h2>
'''
DOC_HEADER_EXTERNALCSS = '''\
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>%(title)s</title>
<meta http-equiv="content-type" content="text/html; charset=%(encoding)s">
<link rel="stylesheet" href="%(cssfile)s" type="text/css">
</head>
<body>
<h2>%(title)s</h2>
'''
DOC_FOOTER = '''\
</body>
</html>
'''
class HtmlFormatter(Formatter):
r"""
Format tokens as HTML 4 ``<span>`` tags. By default, the content is enclosed
in a ``<pre>`` tag, itself wrapped in a ``<div>`` tag (but see the `nowrap` option).
The ``<div>``'s CSS class can be set by the `cssclass` option.
If the `linenos` option is set to ``"table"``, the ``<pre>`` is
additionally wrapped inside a ``<table>`` which has one row and two
cells: one containing the line numbers and one containing the code.
Example:
.. sourcecode:: html
<div class="highlight" >
<table><tr>
<td class="linenos" title="click to toggle"
onclick="with (this.firstChild.style)
{ display = (display == '') ? 'none' : '' }">
<pre>1
2</pre>
</td>
<td class="code">
<pre><span class="Ke">def </span><span class="NaFu">foo</span>(bar):
<span class="Ke">pass</span>
</pre>
</td>
</tr></table></div>
(whitespace added to improve clarity).
A list of lines can be specified using the `hl_lines` option to make these
lines highlighted (as of Pygments 0.11).
With the `full` option, a complete HTML 4 document is output, including
the style definitions inside a ``<style>`` tag, or in a separate file if
the `cssfile` option is given.
When `tagsfile` is set to the path of a ctags index file, it is used to
generate hyperlinks from names to their definition. You must enable
`lineanchors` and run ctags with the `-n` option for this to work. The
`python-ctags` module from PyPI must be installed to use this feature;
otherwise a `RuntimeError` will be raised.
The `get_style_defs(arg='')` method of a `HtmlFormatter` returns a string
containing CSS rules for the CSS classes used by the formatter. The
argument `arg` can be used to specify additional CSS selectors that
are prepended to the classes. A call `fmter.get_style_defs('td .code')`
would result in the following CSS classes:
.. sourcecode:: css
td .code .kw { font-weight: bold; color: #00FF00 }
td .code .cm { color: #999999 }
...
If you have Pygments 0.6 or higher, you can also pass a list or tuple to the
`get_style_defs()` method to request multiple prefixes for the tokens:
.. sourcecode:: python
formatter.get_style_defs(['div.syntax pre', 'pre.syntax'])
The output would then look like this:
.. sourcecode:: css
div.syntax pre .kw,
pre.syntax .kw { font-weight: bold; color: #00FF00 }
div.syntax pre .cm,
pre.syntax .cm { color: #999999 }
...
Additional options accepted:
`nowrap`
If set to ``True``, don't add a ``<pre>`` and a ``<div>`` tag
around the tokens. This disables most other options (default: ``False``).
`full`
Tells the formatter to output a "full" document, i.e. a complete
self-contained document (default: ``False``).
`title`
If `full` is true, the title that should be used to caption the
document (default: ``''``).
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``). This option has no effect if the `cssfile`
and `noclobber_cssfile` option are given and the file specified in
`cssfile` exists.
`noclasses`
If set to true, token ``<span>`` tags (as well as line number elements)
will not use CSS classes, but inline styles. This is not recommended
for larger pieces of code since it increases output size by quite a bit
(default: ``False``).
`classprefix`
Since the token types use relatively short class names, they may clash
with some of your own class names. In this case you can use the
`classprefix` option to give a string to prepend to all Pygments-generated
CSS class names for token types.
Note that this option also affects the output of `get_style_defs()`.
`cssclass`
CSS class for the wrapping ``<div>`` tag (default: ``'highlight'``).
If you set this option, the default selector for `get_style_defs()`
will be this class.
.. versionadded:: 0.9
If you select the ``'table'`` line numbers, the wrapping table will
have a CSS class of this string plus ``'table'``, the default is
accordingly ``'highlighttable'``.
`cssstyles`
Inline CSS styles for the wrapping ``<div>`` tag (default: ``''``).
`prestyles`
Inline CSS styles for the ``<pre>`` tag (default: ``''``).
.. versionadded:: 0.11
`cssfile`
If the `full` option is true and this option is given, it must be the
name of an external file. If the filename does not include an absolute
path, the file's path will be assumed to be relative to the main output
file's path, if the latter can be found. The stylesheet is then written
to this file instead of the HTML file.
.. versionadded:: 0.6
`noclobber_cssfile`
If `cssfile` is given and the specified file exists, the css file will
not be overwritten. This allows the use of the `full` option in
combination with a user specified css file. Default is ``False``.
.. versionadded:: 1.1
`linenos`
If set to ``'table'``, output line numbers as a table with two cells,
one containing the line numbers, the other the whole code. This is
copy-and-paste-friendly, but may cause alignment problems with some
browsers or fonts. If set to ``'inline'``, the line numbers will be
integrated in the ``<pre>`` tag that contains the code (that setting
is *new in Pygments 0.8*).
For compatibility with Pygments 0.7 and earlier, every true value
except ``'inline'`` means the same as ``'table'`` (in particular, that
means also ``True``).
The default value is ``False``, which means no line numbers at all.
**Note:** with the default ("table") line number mechanism, the line
numbers and code can have different line heights in Internet Explorer
unless you give the enclosing ``<pre>`` tags an explicit ``line-height``
CSS property (you get the default line spacing with ``line-height:
125%``).
`hl_lines`
Specify a list of lines to be highlighted. The line numbers are always
relative to the input (i.e. the first line is line 1) and are
independent of `linenostart`.
.. versionadded:: 0.11
`linenostart`
The line number for the first line (default: ``1``).
`linenostep`
If set to a number n > 1, only every nth line number is printed.
`linenospecial`
If set to a number n > 0, every nth line number is given the CSS
class ``"special"`` (default: ``0``).
`nobackground`
If set to ``True``, the formatter won't output the background color
for the wrapping element (this automatically defaults to ``False``
when there is no wrapping element [eg: no argument for the
`get_syntax_defs` method given]) (default: ``False``).
.. versionadded:: 0.6
`lineseparator`
This string is output between lines of code. It defaults to ``"\n"``,
which is enough to break a line inside ``<pre>`` tags, but you can
e.g. set it to ``"<br>"`` to get HTML line breaks.
.. versionadded:: 0.7
`lineanchors`
If set to a nonempty string, e.g. ``foo``, the formatter will wrap each
output line in an anchor tag with an ``id`` (and `name`) of ``foo-linenumber``.
This allows easy linking to certain lines.
.. versionadded:: 0.9
`linespans`
If set to a nonempty string, e.g. ``foo``, the formatter will wrap each
output line in a span tag with an ``id`` of ``foo-linenumber``.
This allows easy access to lines via javascript.
.. versionadded:: 1.6
`anchorlinenos`
If set to `True`, will wrap line numbers in <a> tags. Used in
combination with `linenos` and `lineanchors`.
`tagsfile`
If set to the path of a ctags file, wrap names in anchor tags that
link to their definitions. `lineanchors` should be used, and the
tags file should specify line numbers (see the `-n` option to ctags).
.. versionadded:: 1.6
`tagurlformat`
A string formatting pattern used to generate links to ctags definitions.
Available variables are `%(path)s`, `%(fname)s` and `%(fext)s`.
Defaults to an empty string, resulting in just `#prefix-number` links.
.. versionadded:: 1.6
`filename`
A string used to generate a filename when rendering ``<pre>`` blocks,
for example if displaying source code. If `linenos` is set to
``'table'`` then the filename will be rendered in an initial row
containing a single `<th>` which spans both columns.
.. versionadded:: 2.1
`wrapcode`
Wrap the code inside ``<pre>`` blocks using ``<code>``, as recommended
by the HTML5 specification.
.. versionadded:: 2.4
`debug_token_types`
Add ``title`` attributes to all token ``<span>`` tags that show the
name of the token.
.. versionadded:: 2.10
**Subclassing the HTML formatter**
.. versionadded:: 0.7
The HTML formatter is now built in a way that allows easy subclassing, thus
customizing the output HTML code. The `format()` method calls
`self._format_lines()` which returns a generator that yields tuples of ``(1,
line)``, where the ``1`` indicates that the ``line`` is a line of the
formatted source code.
If the `nowrap` option is set, the generator is the iterated over and the
resulting HTML is output.
Otherwise, `format()` calls `self.wrap()`, which wraps the generator with
other generators. These may add some HTML code to the one generated by
`_format_lines()`, either by modifying the lines generated by the latter,
then yielding them again with ``(1, line)``, and/or by yielding other HTML
code before or after the lines, with ``(0, html)``. The distinction between
source lines and other code makes it possible to wrap the generator multiple
times.
The default `wrap()` implementation adds a ``<div>`` and a ``<pre>`` tag.
A custom `HtmlFormatter` subclass could look like this:
.. sourcecode:: python
class CodeHtmlFormatter(HtmlFormatter):
def wrap(self, source, *, include_div):
return self._wrap_code(source)
def _wrap_code(self, source):
yield 0, '<code>'
for i, t in source:
if i == 1:
# it's a line of formatted code
t += '<br>'
yield i, t
yield 0, '</code>'
This results in wrapping the formatted lines with a ``<code>`` tag, where the
source lines are broken using ``<br>`` tags.
After calling `wrap()`, the `format()` method also adds the "line numbers"
and/or "full document" wrappers if the respective options are set. Then, all
HTML yielded by the wrapped generator is output.
"""
name = 'HTML'
aliases = ['html']
filenames = ['*.html', '*.htm']
def __init__(self, **options):
Formatter.__init__(self, **options)
self.title = self._decodeifneeded(self.title)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.noclasses = get_bool_opt(options, 'noclasses', False)
self.classprefix = options.get('classprefix', '')
self.cssclass = self._decodeifneeded(options.get('cssclass', 'highlight'))
self.cssstyles = self._decodeifneeded(options.get('cssstyles', ''))
self.prestyles = self._decodeifneeded(options.get('prestyles', ''))
self.cssfile = self._decodeifneeded(options.get('cssfile', ''))
self.noclobber_cssfile = get_bool_opt(options, 'noclobber_cssfile', False)
self.tagsfile = self._decodeifneeded(options.get('tagsfile', ''))
self.tagurlformat = self._decodeifneeded(options.get('tagurlformat', ''))
self.filename = self._decodeifneeded(options.get('filename', ''))
self.wrapcode = get_bool_opt(options, 'wrapcode', False)
self.span_element_openers = {}
self.debug_token_types = get_bool_opt(options, 'debug_token_types', False)
if self.tagsfile:
if not ctags:
raise RuntimeError('The "ctags" package must to be installed '
'to be able to use the "tagsfile" feature.')
self._ctags = ctags.CTags(self.tagsfile)
linenos = options.get('linenos', False)
if linenos == 'inline':
self.linenos = 2
elif linenos:
# compatibility with <= 0.7
self.linenos = 1
else:
self.linenos = 0
self.linenostart = abs(get_int_opt(options, 'linenostart', 1))
self.linenostep = abs(get_int_opt(options, 'linenostep', 1))
self.linenospecial = abs(get_int_opt(options, 'linenospecial', 0))
self.nobackground = get_bool_opt(options, 'nobackground', False)
self.lineseparator = options.get('lineseparator', '\n')
self.lineanchors = options.get('lineanchors', '')
self.linespans = options.get('linespans', '')
self.anchorlinenos = get_bool_opt(options, 'anchorlinenos', False)
self.hl_lines = set()
for lineno in get_list_opt(options, 'hl_lines', []):
try:
self.hl_lines.add(int(lineno))
except ValueError:
pass
self._create_stylesheet()
def _get_css_class(self, ttype):
"""Return the css class of this token type prefixed with
the classprefix option."""
ttypeclass = _get_ttype_class(ttype)
if ttypeclass:
return self.classprefix + ttypeclass
return ''
def _get_css_classes(self, ttype):
"""Return the CSS classes of this token type prefixed with the classprefix option."""
cls = self._get_css_class(ttype)
while ttype not in STANDARD_TYPES:
ttype = ttype.parent
cls = self._get_css_class(ttype) + ' ' + cls
return cls or ''
def _get_css_inline_styles(self, ttype):
"""Return the inline CSS styles for this token type."""
cclass = self.ttype2class.get(ttype)
while cclass is None:
ttype = ttype.parent
cclass = self.ttype2class.get(ttype)
return cclass or ''
def _create_stylesheet(self):
t2c = self.ttype2class = {Token: ''}
c2s = self.class2style = {}
for ttype, ndef in self.style:
name = self._get_css_class(ttype)
style = ''
if ndef['color']:
style += 'color: %s; ' % webify(ndef['color'])
if ndef['bold']:
style += 'font-weight: bold; '
if ndef['italic']:
style += 'font-style: italic; '
if ndef['underline']:
style += 'text-decoration: underline; '
if ndef['bgcolor']:
style += 'background-color: %s; ' % webify(ndef['bgcolor'])
if ndef['border']:
style += 'border: 1px solid %s; ' % webify(ndef['border'])
if style:
t2c[ttype] = name
# save len(ttype) to enable ordering the styles by
# hierarchy (necessary for CSS cascading rules!)
c2s[name] = (style[:-2], ttype, len(ttype))
def get_style_defs(self, arg=None):
"""
Return CSS style definitions for the classes produced by the current
highlighting style. ``arg`` can be a string or list of selectors to
insert before the token type classes.
"""
style_lines = []
style_lines.extend(self.get_linenos_style_defs())
style_lines.extend(self.get_background_style_defs(arg))
style_lines.extend(self.get_token_style_defs(arg))
return '\n'.join(style_lines)
def get_token_style_defs(self, arg=None):
prefix = self.get_css_prefix(arg)
styles = [
(level, ttype, cls, style)
for cls, (style, ttype, level) in self.class2style.items()
if cls and style
]
styles.sort()
lines = [
'%s { %s } /* %s */' % (prefix(cls), style, repr(ttype)[6:])
for (level, ttype, cls, style) in styles
]
return lines
def get_background_style_defs(self, arg=None):
prefix = self.get_css_prefix(arg)
bg_color = self.style.background_color
hl_color = self.style.highlight_color
lines = []
if arg and not self.nobackground and bg_color is not None:
text_style = ''
if Text in self.ttype2class:
text_style = ' ' + self.class2style[self.ttype2class[Text]][0]
lines.insert(
0, '%s{ background: %s;%s }' % (
prefix(''), bg_color, text_style
)
)
if hl_color is not None:
lines.insert(
0, '%s { background-color: %s }' % (prefix('hll'), hl_color)
)
return lines
def get_linenos_style_defs(self):
lines = [
'pre { %s }' % self._pre_style,
'td.linenos .normal { %s }' % self._linenos_style,
'span.linenos { %s }' % self._linenos_style,
'td.linenos .special { %s }' % self._linenos_special_style,
'span.linenos.special { %s }' % self._linenos_special_style,
]
return lines
def get_css_prefix(self, arg):
if arg is None:
arg = ('cssclass' in self.options and '.'+self.cssclass or '')
if isinstance(arg, str):
args = [arg]
else:
args = list(arg)
def prefix(cls):
if cls:
cls = '.' + cls
tmp = []
for arg in args:
tmp.append((arg and arg + ' ' or '') + cls)
return ', '.join(tmp)
return prefix
@property
def _pre_style(self):
return 'line-height: 125%;'
@property
def _linenos_style(self):
return 'color: %s; background-color: %s; padding-left: 5px; padding-right: 5px;' % (
self.style.line_number_color,
self.style.line_number_background_color
)
@property
def _linenos_special_style(self):
return 'color: %s; background-color: %s; padding-left: 5px; padding-right: 5px;' % (
self.style.line_number_special_color,
self.style.line_number_special_background_color
)
def _decodeifneeded(self, value):
if isinstance(value, bytes):
if self.encoding:
return value.decode(self.encoding)
return value.decode()
return value
def _wrap_full(self, inner, outfile):
if self.cssfile:
if os.path.isabs(self.cssfile):
# it's an absolute filename
cssfilename = self.cssfile
else:
try:
filename = outfile.name
if not filename or filename[0] == '<':
# pseudo files, e.g. name == '<fdopen>'
raise AttributeError
cssfilename = os.path.join(os.path.dirname(filename),
self.cssfile)
except AttributeError:
print('Note: Cannot determine output file name, '
'using current directory as base for the CSS file name',
file=sys.stderr)
cssfilename = self.cssfile
# write CSS file only if noclobber_cssfile isn't given as an option.
try:
if not os.path.exists(cssfilename) or not self.noclobber_cssfile:
with open(cssfilename, "w", encoding="utf-8") as cf:
cf.write(CSSFILE_TEMPLATE %
{'styledefs': self.get_style_defs('body')})
except OSError as err:
err.strerror = 'Error writing CSS file: ' + err.strerror
raise
yield 0, (DOC_HEADER_EXTERNALCSS %
dict(title=self.title,
cssfile=self.cssfile,
encoding=self.encoding))
else:
yield 0, (DOC_HEADER %
dict(title=self.title,
styledefs=self.get_style_defs('body'),
encoding=self.encoding))
yield from inner
yield 0, DOC_FOOTER
def _wrap_tablelinenos(self, inner):
dummyoutfile = StringIO()
lncount = 0
for t, line in inner:
if t:
lncount += 1
dummyoutfile.write(line)
fl = self.linenostart
mw = len(str(lncount + fl - 1))
sp = self.linenospecial
st = self.linenostep
anchor_name = self.lineanchors or self.linespans
aln = self.anchorlinenos
nocls = self.noclasses
lines = []
for i in range(fl, fl+lncount):
print_line = i % st == 0
special_line = sp and i % sp == 0
if print_line:
line = '%*d' % (mw, i)
if aln:
line = '<a href="#%s-%d">%s</a>' % (anchor_name, i, line)
else:
line = ' ' * mw
if nocls:
if special_line:
style = ' style="%s"' % self._linenos_special_style
else:
style = ' style="%s"' % self._linenos_style
else:
if special_line:
style = ' class="special"'
else:
style = ' class="normal"'
if style:
line = '<span%s>%s</span>' % (style, line)
lines.append(line)
ls = '\n'.join(lines)
# If a filename was specified, we can't put it into the code table as it
# would misalign the line numbers. Hence we emit a separate row for it.
filename_tr = ""
if self.filename:
filename_tr = (
'<tr><th colspan="2" class="filename">'
'<span class="filename">' + self.filename + '</span>'
'</th></tr>')
# in case you wonder about the seemingly redundant <div> here: since the
# content in the other cell also is wrapped in a div, some browsers in
# some configurations seem to mess up the formatting...
yield 0, (f'<table class="{self.cssclass}table">' + filename_tr +
'<tr><td class="linenos"><div class="linenodiv"><pre>' +
ls + '</pre></div></td><td class="code">')
yield 0, '<div>'
yield 0, dummyoutfile.getvalue()
yield 0, '</div>'
yield 0, '</td></tr></table>'
def _wrap_inlinelinenos(self, inner):
# need a list of lines since we need the width of a single number :(
inner_lines = list(inner)
sp = self.linenospecial
st = self.linenostep
num = self.linenostart
mw = len(str(len(inner_lines) + num - 1))
anchor_name = self.lineanchors or self.linespans
aln = self.anchorlinenos
nocls = self.noclasses
for _, inner_line in inner_lines:
print_line = num % st == 0
special_line = sp and num % sp == 0
if print_line:
line = '%*d' % (mw, num)
else:
line = ' ' * mw
if nocls:
if special_line:
style = ' style="%s"' % self._linenos_special_style
else:
style = ' style="%s"' % self._linenos_style
else:
if special_line:
style = ' class="linenos special"'
else:
style = ' class="linenos"'
if style:
linenos = '<span%s>%s</span>' % (style, line)
else:
linenos = line
if aln:
yield 1, ('<a href="#%s-%d">%s</a>' % (anchor_name, num, linenos) +
inner_line)
else:
yield 1, linenos + inner_line
num += 1
def _wrap_lineanchors(self, inner):
s = self.lineanchors
# subtract 1 since we have to increment i *before* yielding
i = self.linenostart - 1
for t, line in inner:
if t:
i += 1
href = "" if self.linenos else ' href="#%s-%d"' % (s, i)
yield 1, '<a id="%s-%d" name="%s-%d"%s></a>' % (s, i, s, i, href) + line
else:
yield 0, line
def _wrap_linespans(self, inner):
s = self.linespans
i = self.linenostart - 1
for t, line in inner:
if t:
i += 1
yield 1, '<span id="%s-%d">%s</span>' % (s, i, line)
else:
yield 0, line
def _wrap_div(self, inner):
style = []
if (self.noclasses and not self.nobackground and
self.style.background_color is not None):
style.append('background: %s' % (self.style.background_color,))
if self.cssstyles:
style.append(self.cssstyles)
style = '; '.join(style)
yield 0, ('<div' + (self.cssclass and ' class="%s"' % self.cssclass) +
(style and (' style="%s"' % style)) + '>')
yield from inner
yield 0, '</div>\n'
def _wrap_pre(self, inner):
style = []
if self.prestyles:
style.append(self.prestyles)
if self.noclasses:
style.append(self._pre_style)
style = '; '.join(style)
if self.filename and self.linenos != 1:
yield 0, ('<span class="filename">' + self.filename + '</span>')
# the empty span here is to keep leading empty lines from being
# ignored by HTML parsers
yield 0, ('<pre' + (style and ' style="%s"' % style) + '><span></span>')
yield from inner
yield 0, '</pre>'
def _wrap_code(self, inner):
yield 0, '<code>'
yield from inner
yield 0, '</code>'
@functools.lru_cache(maxsize=100)
def _translate_parts(self, value):
"""HTML-escape a value and split it by newlines."""
return value.translate(_escape_html_table).split('\n')
def _format_lines(self, tokensource):
"""
Just format the tokens, without any wrapping tags.
Yield individual lines.
"""
nocls = self.noclasses
lsep = self.lineseparator
tagsfile = self.tagsfile
lspan = ''
line = []
for ttype, value in tokensource:
try:
cspan = self.span_element_openers[ttype]
except KeyError:
title = ' title="%s"' % '.'.join(ttype) if self.debug_token_types else ''
if nocls:
css_style = self._get_css_inline_styles(ttype)
if css_style:
css_style = self.class2style[css_style][0]
cspan = '<span style="%s"%s>' % (css_style, title)
else:
cspan = ''
else:
css_class = self._get_css_classes(ttype)
if css_class:
cspan = '<span class="%s"%s>' % (css_class, title)
else:
cspan = ''
self.span_element_openers[ttype] = cspan
parts = self._translate_parts(value)
if tagsfile and ttype in Token.Name:
filename, linenumber = self._lookup_ctag(value)
if linenumber:
base, filename = os.path.split(filename)
if base:
base += '/'
filename, extension = os.path.splitext(filename)
url = self.tagurlformat % {'path': base, 'fname': filename,
'fext': extension}
parts[0] = "<a href=\"%s#%s-%d\">%s" % \
(url, self.lineanchors, linenumber, parts[0])
parts[-1] = parts[-1] + "</a>"
# for all but the last line
for part in parts[:-1]:
if line:
# Also check for part being non-empty, so we avoid creating
# empty <span> tags
if lspan != cspan and part:
line.extend(((lspan and '</span>'), cspan, part,
(cspan and '</span>'), lsep))
else: # both are the same, or the current part was empty
line.extend((part, (lspan and '</span>'), lsep))
yield 1, ''.join(line)
line = []
elif part:
yield 1, ''.join((cspan, part, (cspan and '</span>'), lsep))
else:
yield 1, lsep
# for the last line
if line and parts[-1]:
if lspan != cspan:
line.extend(((lspan and '</span>'), cspan, parts[-1]))
lspan = cspan
else:
line.append(parts[-1])
elif parts[-1]:
line = [cspan, parts[-1]]
lspan = cspan
# else we neither have to open a new span nor set lspan
if line:
line.extend(((lspan and '</span>'), lsep))
yield 1, ''.join(line)
def _lookup_ctag(self, token):
entry = ctags.TagEntry()
if self._ctags.find(entry, token.encode(), 0):
return entry['file'], entry['lineNumber']
else:
return None, None
def _highlight_lines(self, tokensource):
"""
Highlighted the lines specified in the `hl_lines` option by
post-processing the token stream coming from `_format_lines`.
"""
hls = self.hl_lines
for i, (t, value) in enumerate(tokensource):
if t != 1:
yield t, value
if i + 1 in hls: # i + 1 because Python indexes start at 0
if self.noclasses:
style = ''
if self.style.highlight_color is not None:
style = (' style="background-color: %s"' %
(self.style.highlight_color,))
yield 1, '<span%s>%s</span>' % (style, value)
else:
yield 1, '<span class="hll">%s</span>' % value
else:
yield 1, value
def wrap(self, source):
"""
Wrap the ``source``, which is a generator yielding
individual lines, in custom generators. See docstring
for `format`. Can be overridden.
"""
output = source
if self.wrapcode:
output = self._wrap_code(output)
output = self._wrap_pre(output)
return output
def format_unencoded(self, tokensource, outfile):
"""
The formatting process uses several nested generators; which of
them are used is determined by the user's options.
Each generator should take at least one argument, ``inner``,
and wrap the pieces of text generated by this.
Always yield 2-tuples: (code, text). If "code" is 1, the text
is part of the original tokensource being highlighted, if it's
0, the text is some piece of wrapping. This makes it possible to
use several different wrappers that process the original source
linewise, e.g. line number generators.
"""
source = self._format_lines(tokensource)
# As a special case, we wrap line numbers before line highlighting
# so the line numbers get wrapped in the highlighting tag.
if not self.nowrap and self.linenos == 2:
source = self._wrap_inlinelinenos(source)
if self.hl_lines:
source = self._highlight_lines(source)
if not self.nowrap:
if self.lineanchors:
source = self._wrap_lineanchors(source)
if self.linespans:
source = self._wrap_linespans(source)
source = self.wrap(source)
if self.linenos == 1:
source = self._wrap_tablelinenos(source)
source = self._wrap_div(source)
if self.full:
source = self._wrap_full(source, outfile)
for t, piece in source:
outfile.write(piece)

View file

@ -0,0 +1,645 @@
"""
pygments.formatters.img
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for Pixmap output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import sys
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.util import get_bool_opt, get_int_opt, get_list_opt, \
get_choice_opt
import subprocess
# Import this carefully
try:
from PIL import Image, ImageDraw, ImageFont
pil_available = True
except ImportError:
pil_available = False
try:
import _winreg
except ImportError:
try:
import winreg as _winreg
except ImportError:
_winreg = None
__all__ = ['ImageFormatter', 'GifImageFormatter', 'JpgImageFormatter',
'BmpImageFormatter']
# For some unknown reason every font calls it something different
STYLES = {
'NORMAL': ['', 'Roman', 'Book', 'Normal', 'Regular', 'Medium'],
'ITALIC': ['Oblique', 'Italic'],
'BOLD': ['Bold'],
'BOLDITALIC': ['Bold Oblique', 'Bold Italic'],
}
# A sane default for modern systems
DEFAULT_FONT_NAME_NIX = 'DejaVu Sans Mono'
DEFAULT_FONT_NAME_WIN = 'Courier New'
DEFAULT_FONT_NAME_MAC = 'Menlo'
class PilNotAvailable(ImportError):
"""When Python imaging library is not available"""
class FontNotFound(Exception):
"""When there are no usable fonts specified"""
class FontManager:
"""
Manages a set of fonts: normal, italic, bold, etc...
"""
def __init__(self, font_name, font_size=14):
self.font_name = font_name
self.font_size = font_size
self.fonts = {}
self.encoding = None
if sys.platform.startswith('win'):
if not font_name:
self.font_name = DEFAULT_FONT_NAME_WIN
self._create_win()
elif sys.platform.startswith('darwin'):
if not font_name:
self.font_name = DEFAULT_FONT_NAME_MAC
self._create_mac()
else:
if not font_name:
self.font_name = DEFAULT_FONT_NAME_NIX
self._create_nix()
def _get_nix_font_path(self, name, style):
proc = subprocess.Popen(['fc-list', "%s:style=%s" % (name, style), 'file'],
stdout=subprocess.PIPE, stderr=None)
stdout, _ = proc.communicate()
if proc.returncode == 0:
lines = stdout.splitlines()
for line in lines:
if line.startswith(b'Fontconfig warning:'):
continue
path = line.decode().strip().strip(':')
if path:
return path
return None
def _create_nix(self):
for name in STYLES['NORMAL']:
path = self._get_nix_font_path(self.font_name, name)
if path is not None:
self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size)
break
else:
raise FontNotFound('No usable fonts named: "%s"' %
self.font_name)
for style in ('ITALIC', 'BOLD', 'BOLDITALIC'):
for stylename in STYLES[style]:
path = self._get_nix_font_path(self.font_name, stylename)
if path is not None:
self.fonts[style] = ImageFont.truetype(path, self.font_size)
break
else:
if style == 'BOLDITALIC':
self.fonts[style] = self.fonts['BOLD']
else:
self.fonts[style] = self.fonts['NORMAL']
def _get_mac_font_path(self, font_map, name, style):
return font_map.get((name + ' ' + style).strip().lower())
def _create_mac(self):
font_map = {}
for font_dir in (os.path.join(os.getenv("HOME"), 'Library/Fonts/'),
'/Library/Fonts/', '/System/Library/Fonts/'):
font_map.update(
(os.path.splitext(f)[0].lower(), os.path.join(font_dir, f))
for f in os.listdir(font_dir)
if f.lower().endswith(('ttf', 'ttc')))
for name in STYLES['NORMAL']:
path = self._get_mac_font_path(font_map, self.font_name, name)
if path is not None:
self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size)
break
else:
raise FontNotFound('No usable fonts named: "%s"' %
self.font_name)
for style in ('ITALIC', 'BOLD', 'BOLDITALIC'):
for stylename in STYLES[style]:
path = self._get_mac_font_path(font_map, self.font_name, stylename)
if path is not None:
self.fonts[style] = ImageFont.truetype(path, self.font_size)
break
else:
if style == 'BOLDITALIC':
self.fonts[style] = self.fonts['BOLD']
else:
self.fonts[style] = self.fonts['NORMAL']
def _lookup_win(self, key, basename, styles, fail=False):
for suffix in ('', ' (TrueType)'):
for style in styles:
try:
valname = '%s%s%s' % (basename, style and ' '+style, suffix)
val, _ = _winreg.QueryValueEx(key, valname)
return val
except OSError:
continue
else:
if fail:
raise FontNotFound('Font %s (%s) not found in registry' %
(basename, styles[0]))
return None
def _create_win(self):
lookuperror = None
keynames = [ (_winreg.HKEY_CURRENT_USER, r'Software\Microsoft\Windows NT\CurrentVersion\Fonts'),
(_winreg.HKEY_CURRENT_USER, r'Software\Microsoft\Windows\CurrentVersion\Fonts'),
(_winreg.HKEY_LOCAL_MACHINE, r'Software\Microsoft\Windows NT\CurrentVersion\Fonts'),
(_winreg.HKEY_LOCAL_MACHINE, r'Software\Microsoft\Windows\CurrentVersion\Fonts') ]
for keyname in keynames:
try:
key = _winreg.OpenKey(*keyname)
try:
path = self._lookup_win(key, self.font_name, STYLES['NORMAL'], True)
self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size)
for style in ('ITALIC', 'BOLD', 'BOLDITALIC'):
path = self._lookup_win(key, self.font_name, STYLES[style])
if path:
self.fonts[style] = ImageFont.truetype(path, self.font_size)
else:
if style == 'BOLDITALIC':
self.fonts[style] = self.fonts['BOLD']
else:
self.fonts[style] = self.fonts['NORMAL']
return
except FontNotFound as err:
lookuperror = err
finally:
_winreg.CloseKey(key)
except OSError:
pass
else:
# If we get here, we checked all registry keys and had no luck
# We can be in one of two situations now:
# * All key lookups failed. In this case lookuperror is None and we
# will raise a generic error
# * At least one lookup failed with a FontNotFound error. In this
# case, we will raise that as a more specific error
if lookuperror:
raise lookuperror
raise FontNotFound('Can\'t open Windows font registry key')
def get_char_size(self):
"""
Get the character size.
"""
return self.get_text_size('M')
def get_text_size(self, text):
"""
Get the text size (width, height).
"""
font = self.fonts['NORMAL']
if hasattr(font, 'getbbox'): # Pillow >= 9.2.0
return font.getbbox(text)[2:4]
else:
return font.getsize(text)
def get_font(self, bold, oblique):
"""
Get the font based on bold and italic flags.
"""
if bold and oblique:
return self.fonts['BOLDITALIC']
elif bold:
return self.fonts['BOLD']
elif oblique:
return self.fonts['ITALIC']
else:
return self.fonts['NORMAL']
class ImageFormatter(Formatter):
"""
Create a PNG image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
.. versionadded:: 0.10
Additional options accepted:
`image_format`
An image format to output to that is recognised by PIL, these include:
* "PNG" (default)
* "JPEG"
* "BMP"
* "GIF"
`line_pad`
The extra spacing (in pixels) between each line of text.
Default: 2
`font_name`
The font name to be used as the base font from which others, such as
bold and italic fonts will be generated. This really should be a
monospace font to look sane.
Default: "Courier New" on Windows, "Menlo" on Mac OS, and
"DejaVu Sans Mono" on \\*nix
`font_size`
The font size in points to be used.
Default: 14
`image_pad`
The padding, in pixels to be used at each edge of the resulting image.
Default: 10
`line_numbers`
Whether line numbers should be shown: True/False
Default: True
`line_number_start`
The line number of the first line.
Default: 1
`line_number_step`
The step used when printing line numbers.
Default: 1
`line_number_bg`
The background colour (in "#123456" format) of the line number bar, or
None to use the style background color.
Default: "#eed"
`line_number_fg`
The text color of the line numbers (in "#123456"-like format).
Default: "#886"
`line_number_chars`
The number of columns of line numbers allowable in the line number
margin.
Default: 2
`line_number_bold`
Whether line numbers will be bold: True/False
Default: False
`line_number_italic`
Whether line numbers will be italicized: True/False
Default: False
`line_number_separator`
Whether a line will be drawn between the line number area and the
source code area: True/False
Default: True
`line_number_pad`
The horizontal padding (in pixels) between the line number margin, and
the source code area.
Default: 6
`hl_lines`
Specify a list of lines to be highlighted.
.. versionadded:: 1.2
Default: empty list
`hl_color`
Specify the color for highlighting lines.
.. versionadded:: 1.2
Default: highlight color of the selected style
"""
# Required by the pygments mapper
name = 'img'
aliases = ['img', 'IMG', 'png']
filenames = ['*.png']
unicodeoutput = False
default_image_format = 'png'
def __init__(self, **options):
"""
See the class docstring for explanation of options.
"""
if not pil_available:
raise PilNotAvailable(
'Python Imaging Library is required for this formatter')
Formatter.__init__(self, **options)
self.encoding = 'latin1' # let pygments.format() do the right thing
# Read the style
self.styles = dict(self.style)
if self.style.background_color is None:
self.background_color = '#fff'
else:
self.background_color = self.style.background_color
# Image options
self.image_format = get_choice_opt(
options, 'image_format', ['png', 'jpeg', 'gif', 'bmp'],
self.default_image_format, normcase=True)
self.image_pad = get_int_opt(options, 'image_pad', 10)
self.line_pad = get_int_opt(options, 'line_pad', 2)
# The fonts
fontsize = get_int_opt(options, 'font_size', 14)
self.fonts = FontManager(options.get('font_name', ''), fontsize)
self.fontw, self.fonth = self.fonts.get_char_size()
# Line number options
self.line_number_fg = options.get('line_number_fg', '#886')
self.line_number_bg = options.get('line_number_bg', '#eed')
self.line_number_chars = get_int_opt(options,
'line_number_chars', 2)
self.line_number_bold = get_bool_opt(options,
'line_number_bold', False)
self.line_number_italic = get_bool_opt(options,
'line_number_italic', False)
self.line_number_pad = get_int_opt(options, 'line_number_pad', 6)
self.line_numbers = get_bool_opt(options, 'line_numbers', True)
self.line_number_separator = get_bool_opt(options,
'line_number_separator', True)
self.line_number_step = get_int_opt(options, 'line_number_step', 1)
self.line_number_start = get_int_opt(options, 'line_number_start', 1)
if self.line_numbers:
self.line_number_width = (self.fontw * self.line_number_chars +
self.line_number_pad * 2)
else:
self.line_number_width = 0
self.hl_lines = []
hl_lines_str = get_list_opt(options, 'hl_lines', [])
for line in hl_lines_str:
try:
self.hl_lines.append(int(line))
except ValueError:
pass
self.hl_color = options.get('hl_color',
self.style.highlight_color) or '#f90'
self.drawables = []
def get_style_defs(self, arg=''):
raise NotImplementedError('The -S option is meaningless for the image '
'formatter. Use -O style=<stylename> instead.')
def _get_line_height(self):
"""
Get the height of a line.
"""
return self.fonth + self.line_pad
def _get_line_y(self, lineno):
"""
Get the Y coordinate of a line number.
"""
return lineno * self._get_line_height() + self.image_pad
def _get_char_width(self):
"""
Get the width of a character.
"""
return self.fontw
def _get_char_x(self, linelength):
"""
Get the X coordinate of a character position.
"""
return linelength + self.image_pad + self.line_number_width
def _get_text_pos(self, linelength, lineno):
"""
Get the actual position for a character and line position.
"""
return self._get_char_x(linelength), self._get_line_y(lineno)
def _get_linenumber_pos(self, lineno):
"""
Get the actual position for the start of a line number.
"""
return (self.image_pad, self._get_line_y(lineno))
def _get_text_color(self, style):
"""
Get the correct color for the token from the style.
"""
if style['color'] is not None:
fill = '#' + style['color']
else:
fill = '#000'
return fill
def _get_text_bg_color(self, style):
"""
Get the correct background color for the token from the style.
"""
if style['bgcolor'] is not None:
bg_color = '#' + style['bgcolor']
else:
bg_color = None
return bg_color
def _get_style_font(self, style):
"""
Get the correct font for the style.
"""
return self.fonts.get_font(style['bold'], style['italic'])
def _get_image_size(self, maxlinelength, maxlineno):
"""
Get the required image size.
"""
return (self._get_char_x(maxlinelength) + self.image_pad,
self._get_line_y(maxlineno + 0) + self.image_pad)
def _draw_linenumber(self, posno, lineno):
"""
Remember a line number drawable to paint later.
"""
self._draw_text(
self._get_linenumber_pos(posno),
str(lineno).rjust(self.line_number_chars),
font=self.fonts.get_font(self.line_number_bold,
self.line_number_italic),
text_fg=self.line_number_fg,
text_bg=None,
)
def _draw_text(self, pos, text, font, text_fg, text_bg):
"""
Remember a single drawable tuple to paint later.
"""
self.drawables.append((pos, text, font, text_fg, text_bg))
def _create_drawables(self, tokensource):
"""
Create drawables for the token content.
"""
lineno = charno = maxcharno = 0
maxlinelength = linelength = 0
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
style = self.styles[ttype]
# TODO: make sure tab expansion happens earlier in the chain. It
# really ought to be done on the input, as to do it right here is
# quite complex.
value = value.expandtabs(4)
lines = value.splitlines(True)
# print lines
for i, line in enumerate(lines):
temp = line.rstrip('\n')
if temp:
self._draw_text(
self._get_text_pos(linelength, lineno),
temp,
font = self._get_style_font(style),
text_fg = self._get_text_color(style),
text_bg = self._get_text_bg_color(style),
)
temp_width, _ = self.fonts.get_text_size(temp)
linelength += temp_width
maxlinelength = max(maxlinelength, linelength)
charno += len(temp)
maxcharno = max(maxcharno, charno)
if line.endswith('\n'):
# add a line for each extra line in the value
linelength = 0
charno = 0
lineno += 1
self.maxlinelength = maxlinelength
self.maxcharno = maxcharno
self.maxlineno = lineno
def _draw_line_numbers(self):
"""
Create drawables for the line numbers.
"""
if not self.line_numbers:
return
for p in range(self.maxlineno):
n = p + self.line_number_start
if (n % self.line_number_step) == 0:
self._draw_linenumber(p, n)
def _paint_line_number_bg(self, im):
"""
Paint the line number background on the image.
"""
if not self.line_numbers:
return
if self.line_number_fg is None:
return
draw = ImageDraw.Draw(im)
recth = im.size[-1]
rectw = self.image_pad + self.line_number_width - self.line_number_pad
draw.rectangle([(0, 0), (rectw, recth)],
fill=self.line_number_bg)
if self.line_number_separator:
draw.line([(rectw, 0), (rectw, recth)], fill=self.line_number_fg)
del draw
def format(self, tokensource, outfile):
"""
Format ``tokensource``, an iterable of ``(tokentype, tokenstring)``
tuples and write it into ``outfile``.
This implementation calculates where it should draw each token on the
pixmap, then calculates the required pixmap size and draws the items.
"""
self._create_drawables(tokensource)
self._draw_line_numbers()
im = Image.new(
'RGB',
self._get_image_size(self.maxlinelength, self.maxlineno),
self.background_color
)
self._paint_line_number_bg(im)
draw = ImageDraw.Draw(im)
# Highlight
if self.hl_lines:
x = self.image_pad + self.line_number_width - self.line_number_pad + 1
recth = self._get_line_height()
rectw = im.size[0] - x
for linenumber in self.hl_lines:
y = self._get_line_y(linenumber - 1)
draw.rectangle([(x, y), (x + rectw, y + recth)],
fill=self.hl_color)
for pos, value, font, text_fg, text_bg in self.drawables:
if text_bg:
text_size = draw.textsize(text=value, font=font)
draw.rectangle([pos[0], pos[1], pos[0] + text_size[0], pos[1] + text_size[1]], fill=text_bg)
draw.text(pos, value, font=font, fill=text_fg)
im.save(outfile, self.image_format.upper())
# Add one formatter per format, so that the "-f gif" option gives the correct result
# when used in pygmentize.
class GifImageFormatter(ImageFormatter):
"""
Create a GIF image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
.. versionadded:: 1.0
"""
name = 'img_gif'
aliases = ['gif']
filenames = ['*.gif']
default_image_format = 'gif'
class JpgImageFormatter(ImageFormatter):
"""
Create a JPEG image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
.. versionadded:: 1.0
"""
name = 'img_jpg'
aliases = ['jpg', 'jpeg']
filenames = ['*.jpg']
default_image_format = 'jpeg'
class BmpImageFormatter(ImageFormatter):
"""
Create a bitmap image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
.. versionadded:: 1.0
"""
name = 'img_bmp'
aliases = ['bmp', 'bitmap']
filenames = ['*.bmp']
default_image_format = 'bmp'

View file

@ -0,0 +1,154 @@
"""
pygments.formatters.irc
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for IRC output
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.token import Keyword, Name, Comment, String, Error, \
Number, Operator, Generic, Token, Whitespace
from pip._vendor.pygments.util import get_choice_opt
__all__ = ['IRCFormatter']
#: Map token types to a tuple of color values for light and dark
#: backgrounds.
IRC_COLORS = {
Token: ('', ''),
Whitespace: ('gray', 'brightblack'),
Comment: ('gray', 'brightblack'),
Comment.Preproc: ('cyan', 'brightcyan'),
Keyword: ('blue', 'brightblue'),
Keyword.Type: ('cyan', 'brightcyan'),
Operator.Word: ('magenta', 'brightcyan'),
Name.Builtin: ('cyan', 'brightcyan'),
Name.Function: ('green', 'brightgreen'),
Name.Namespace: ('_cyan_', '_brightcyan_'),
Name.Class: ('_green_', '_brightgreen_'),
Name.Exception: ('cyan', 'brightcyan'),
Name.Decorator: ('brightblack', 'gray'),
Name.Variable: ('red', 'brightred'),
Name.Constant: ('red', 'brightred'),
Name.Attribute: ('cyan', 'brightcyan'),
Name.Tag: ('brightblue', 'brightblue'),
String: ('yellow', 'yellow'),
Number: ('blue', 'brightblue'),
Generic.Deleted: ('brightred', 'brightred'),
Generic.Inserted: ('green', 'brightgreen'),
Generic.Heading: ('**', '**'),
Generic.Subheading: ('*magenta*', '*brightmagenta*'),
Generic.Error: ('brightred', 'brightred'),
Error: ('_brightred_', '_brightred_'),
}
IRC_COLOR_MAP = {
'white': 0,
'black': 1,
'blue': 2,
'brightgreen': 3,
'brightred': 4,
'yellow': 5,
'magenta': 6,
'orange': 7,
'green': 7, #compat w/ ansi
'brightyellow': 8,
'lightgreen': 9,
'brightcyan': 9, # compat w/ ansi
'cyan': 10,
'lightblue': 11,
'red': 11, # compat w/ ansi
'brightblue': 12,
'brightmagenta': 13,
'brightblack': 14,
'gray': 15,
}
def ircformat(color, text):
if len(color) < 1:
return text
add = sub = ''
if '_' in color: # italic
add += '\x1D'
sub = '\x1D' + sub
color = color.strip('_')
if '*' in color: # bold
add += '\x02'
sub = '\x02' + sub
color = color.strip('*')
# underline (\x1F) not supported
# backgrounds (\x03FF,BB) not supported
if len(color) > 0: # actual color - may have issues with ircformat("red", "blah")+"10" type stuff
add += '\x03' + str(IRC_COLOR_MAP[color]).zfill(2)
sub = '\x03' + sub
return add + text + sub
return '<'+add+'>'+text+'</'+sub+'>'
class IRCFormatter(Formatter):
r"""
Format tokens with IRC color sequences
The `get_style_defs()` method doesn't do anything special since there is
no support for common styles.
Options accepted:
`bg`
Set to ``"light"`` or ``"dark"`` depending on the terminal's background
(default: ``"light"``).
`colorscheme`
A dictionary mapping token types to (lightbg, darkbg) color names or
``None`` (default: ``None`` = use builtin colorscheme).
`linenos`
Set to ``True`` to have line numbers in the output as well
(default: ``False`` = no line numbers).
"""
name = 'IRC'
aliases = ['irc', 'IRC']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.darkbg = get_choice_opt(options, 'bg',
['light', 'dark'], 'light') == 'dark'
self.colorscheme = options.get('colorscheme', None) or IRC_COLORS
self.linenos = options.get('linenos', False)
self._lineno = 0
def _write_lineno(self, outfile):
if self.linenos:
self._lineno += 1
outfile.write("%04d: " % self._lineno)
def format_unencoded(self, tokensource, outfile):
self._write_lineno(outfile)
for ttype, value in tokensource:
color = self.colorscheme.get(ttype)
while color is None:
ttype = ttype[:-1]
color = self.colorscheme.get(ttype)
if color:
color = color[self.darkbg]
spl = value.split('\n')
for line in spl[:-1]:
if line:
outfile.write(ircformat(color, line))
outfile.write('\n')
self._write_lineno(outfile)
if spl[-1]:
outfile.write(ircformat(color, spl[-1]))
else:
outfile.write(value)

View file

@ -0,0 +1,521 @@
"""
pygments.formatters.latex
~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for LaTeX fancyvrb output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from io import StringIO
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.lexer import Lexer, do_insertions
from pip._vendor.pygments.token import Token, STANDARD_TYPES
from pip._vendor.pygments.util import get_bool_opt, get_int_opt
__all__ = ['LatexFormatter']
def escape_tex(text, commandprefix):
return text.replace('\\', '\x00'). \
replace('{', '\x01'). \
replace('}', '\x02'). \
replace('\x00', r'\%sZbs{}' % commandprefix). \
replace('\x01', r'\%sZob{}' % commandprefix). \
replace('\x02', r'\%sZcb{}' % commandprefix). \
replace('^', r'\%sZca{}' % commandprefix). \
replace('_', r'\%sZus{}' % commandprefix). \
replace('&', r'\%sZam{}' % commandprefix). \
replace('<', r'\%sZlt{}' % commandprefix). \
replace('>', r'\%sZgt{}' % commandprefix). \
replace('#', r'\%sZsh{}' % commandprefix). \
replace('%', r'\%sZpc{}' % commandprefix). \
replace('$', r'\%sZdl{}' % commandprefix). \
replace('-', r'\%sZhy{}' % commandprefix). \
replace("'", r'\%sZsq{}' % commandprefix). \
replace('"', r'\%sZdq{}' % commandprefix). \
replace('~', r'\%sZti{}' % commandprefix)
DOC_TEMPLATE = r'''
\documentclass{%(docclass)s}
\usepackage{fancyvrb}
\usepackage{color}
\usepackage[%(encoding)s]{inputenc}
%(preamble)s
%(styledefs)s
\begin{document}
\section*{%(title)s}
%(code)s
\end{document}
'''
## Small explanation of the mess below :)
#
# The previous version of the LaTeX formatter just assigned a command to
# each token type defined in the current style. That obviously is
# problematic if the highlighted code is produced for a different style
# than the style commands themselves.
#
# This version works much like the HTML formatter which assigns multiple
# CSS classes to each <span> tag, from the most specific to the least
# specific token type, thus falling back to the parent token type if one
# is not defined. Here, the classes are there too and use the same short
# forms given in token.STANDARD_TYPES.
#
# Highlighted code now only uses one custom command, which by default is
# \PY and selectable by the commandprefix option (and in addition the
# escapes \PYZat, \PYZlb and \PYZrb which haven't been renamed for
# backwards compatibility purposes).
#
# \PY has two arguments: the classes, separated by +, and the text to
# render in that style. The classes are resolved into the respective
# style commands by magic, which serves to ignore unknown classes.
#
# The magic macros are:
# * \PY@it, \PY@bf, etc. are unconditionally wrapped around the text
# to render in \PY@do. Their definition determines the style.
# * \PY@reset resets \PY@it etc. to do nothing.
# * \PY@toks parses the list of classes, using magic inspired by the
# keyval package (but modified to use plusses instead of commas
# because fancyvrb redefines commas inside its environments).
# * \PY@tok processes one class, calling the \PY@tok@classname command
# if it exists.
# * \PY@tok@classname sets the \PY@it etc. to reflect the chosen style
# for its class.
# * \PY resets the style, parses the classnames and then calls \PY@do.
#
# Tip: to read this code, print it out in substituted form using e.g.
# >>> print STYLE_TEMPLATE % {'cp': 'PY'}
STYLE_TEMPLATE = r'''
\makeatletter
\def\%(cp)s@reset{\let\%(cp)s@it=\relax \let\%(cp)s@bf=\relax%%
\let\%(cp)s@ul=\relax \let\%(cp)s@tc=\relax%%
\let\%(cp)s@bc=\relax \let\%(cp)s@ff=\relax}
\def\%(cp)s@tok#1{\csname %(cp)s@tok@#1\endcsname}
\def\%(cp)s@toks#1+{\ifx\relax#1\empty\else%%
\%(cp)s@tok{#1}\expandafter\%(cp)s@toks\fi}
\def\%(cp)s@do#1{\%(cp)s@bc{\%(cp)s@tc{\%(cp)s@ul{%%
\%(cp)s@it{\%(cp)s@bf{\%(cp)s@ff{#1}}}}}}}
\def\%(cp)s#1#2{\%(cp)s@reset\%(cp)s@toks#1+\relax+\%(cp)s@do{#2}}
%(styles)s
\def\%(cp)sZbs{\char`\\}
\def\%(cp)sZus{\char`\_}
\def\%(cp)sZob{\char`\{}
\def\%(cp)sZcb{\char`\}}
\def\%(cp)sZca{\char`\^}
\def\%(cp)sZam{\char`\&}
\def\%(cp)sZlt{\char`\<}
\def\%(cp)sZgt{\char`\>}
\def\%(cp)sZsh{\char`\#}
\def\%(cp)sZpc{\char`\%%}
\def\%(cp)sZdl{\char`\$}
\def\%(cp)sZhy{\char`\-}
\def\%(cp)sZsq{\char`\'}
\def\%(cp)sZdq{\char`\"}
\def\%(cp)sZti{\char`\~}
%% for compatibility with earlier versions
\def\%(cp)sZat{@}
\def\%(cp)sZlb{[}
\def\%(cp)sZrb{]}
\makeatother
'''
def _get_ttype_name(ttype):
fname = STANDARD_TYPES.get(ttype)
if fname:
return fname
aname = ''
while fname is None:
aname = ttype[-1] + aname
ttype = ttype.parent
fname = STANDARD_TYPES.get(ttype)
return fname + aname
class LatexFormatter(Formatter):
r"""
Format tokens as LaTeX code. This needs the `fancyvrb` and `color`
standard packages.
Without the `full` option, code is formatted as one ``Verbatim``
environment, like this:
.. sourcecode:: latex
\begin{Verbatim}[commandchars=\\\{\}]
\PY{k}{def }\PY{n+nf}{foo}(\PY{n}{bar}):
\PY{k}{pass}
\end{Verbatim}
Wrapping can be disabled using the `nowrap` option.
The special command used here (``\PY``) and all the other macros it needs
are output by the `get_style_defs` method.
With the `full` option, a complete LaTeX document is output, including
the command definitions in the preamble.
The `get_style_defs()` method of a `LatexFormatter` returns a string
containing ``\def`` commands defining the macros needed inside the
``Verbatim`` environments.
Additional options accepted:
`nowrap`
If set to ``True``, don't wrap the tokens at all, not even inside a
``\begin{Verbatim}`` environment. This disables most other options
(default: ``False``).
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`full`
Tells the formatter to output a "full" document, i.e. a complete
self-contained document (default: ``False``).
`title`
If `full` is true, the title that should be used to caption the
document (default: ``''``).
`docclass`
If the `full` option is enabled, this is the document class to use
(default: ``'article'``).
`preamble`
If the `full` option is enabled, this can be further preamble commands,
e.g. ``\usepackage`` (default: ``''``).
`linenos`
If set to ``True``, output line numbers (default: ``False``).
`linenostart`
The line number for the first line (default: ``1``).
`linenostep`
If set to a number n > 1, only every nth line number is printed.
`verboptions`
Additional options given to the Verbatim environment (see the *fancyvrb*
docs for possible values) (default: ``''``).
`commandprefix`
The LaTeX commands used to produce colored output are constructed
using this prefix and some letters (default: ``'PY'``).
.. versionadded:: 0.7
.. versionchanged:: 0.10
The default is now ``'PY'`` instead of ``'C'``.
`texcomments`
If set to ``True``, enables LaTeX comment lines. That is, LaTex markup
in comment tokens is not escaped so that LaTeX can render it (default:
``False``).
.. versionadded:: 1.2
`mathescape`
If set to ``True``, enables LaTeX math mode escape in comments. That
is, ``'$...$'`` inside a comment will trigger math mode (default:
``False``).
.. versionadded:: 1.2
`escapeinside`
If set to a string of length 2, enables escaping to LaTeX. Text
delimited by these 2 characters is read as LaTeX code and
typeset accordingly. It has no effect in string literals. It has
no effect in comments if `texcomments` or `mathescape` is
set. (default: ``''``).
.. versionadded:: 2.0
`envname`
Allows you to pick an alternative environment name replacing Verbatim.
The alternate environment still has to support Verbatim's option syntax.
(default: ``'Verbatim'``).
.. versionadded:: 2.0
"""
name = 'LaTeX'
aliases = ['latex', 'tex']
filenames = ['*.tex']
def __init__(self, **options):
Formatter.__init__(self, **options)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.docclass = options.get('docclass', 'article')
self.preamble = options.get('preamble', '')
self.linenos = get_bool_opt(options, 'linenos', False)
self.linenostart = abs(get_int_opt(options, 'linenostart', 1))
self.linenostep = abs(get_int_opt(options, 'linenostep', 1))
self.verboptions = options.get('verboptions', '')
self.nobackground = get_bool_opt(options, 'nobackground', False)
self.commandprefix = options.get('commandprefix', 'PY')
self.texcomments = get_bool_opt(options, 'texcomments', False)
self.mathescape = get_bool_opt(options, 'mathescape', False)
self.escapeinside = options.get('escapeinside', '')
if len(self.escapeinside) == 2:
self.left = self.escapeinside[0]
self.right = self.escapeinside[1]
else:
self.escapeinside = ''
self.envname = options.get('envname', 'Verbatim')
self._create_stylesheet()
def _create_stylesheet(self):
t2n = self.ttype2name = {Token: ''}
c2d = self.cmd2def = {}
cp = self.commandprefix
def rgbcolor(col):
if col:
return ','.join(['%.2f' % (int(col[i] + col[i + 1], 16) / 255.0)
for i in (0, 2, 4)])
else:
return '1,1,1'
for ttype, ndef in self.style:
name = _get_ttype_name(ttype)
cmndef = ''
if ndef['bold']:
cmndef += r'\let\$$@bf=\textbf'
if ndef['italic']:
cmndef += r'\let\$$@it=\textit'
if ndef['underline']:
cmndef += r'\let\$$@ul=\underline'
if ndef['roman']:
cmndef += r'\let\$$@ff=\textrm'
if ndef['sans']:
cmndef += r'\let\$$@ff=\textsf'
if ndef['mono']:
cmndef += r'\let\$$@ff=\textsf'
if ndef['color']:
cmndef += (r'\def\$$@tc##1{\textcolor[rgb]{%s}{##1}}' %
rgbcolor(ndef['color']))
if ndef['border']:
cmndef += (r'\def\$$@bc##1{{\setlength{\fboxsep}{\string -\fboxrule}'
r'\fcolorbox[rgb]{%s}{%s}{\strut ##1}}}' %
(rgbcolor(ndef['border']),
rgbcolor(ndef['bgcolor'])))
elif ndef['bgcolor']:
cmndef += (r'\def\$$@bc##1{{\setlength{\fboxsep}{0pt}'
r'\colorbox[rgb]{%s}{\strut ##1}}}' %
rgbcolor(ndef['bgcolor']))
if cmndef == '':
continue
cmndef = cmndef.replace('$$', cp)
t2n[ttype] = name
c2d[name] = cmndef
def get_style_defs(self, arg=''):
"""
Return the command sequences needed to define the commands
used to format text in the verbatim environment. ``arg`` is ignored.
"""
cp = self.commandprefix
styles = []
for name, definition in self.cmd2def.items():
styles.append(r'\@namedef{%s@tok@%s}{%s}' % (cp, name, definition))
return STYLE_TEMPLATE % {'cp': self.commandprefix,
'styles': '\n'.join(styles)}
def format_unencoded(self, tokensource, outfile):
# TODO: add support for background colors
t2n = self.ttype2name
cp = self.commandprefix
if self.full:
realoutfile = outfile
outfile = StringIO()
if not self.nowrap:
outfile.write('\\begin{' + self.envname + '}[commandchars=\\\\\\{\\}')
if self.linenos:
start, step = self.linenostart, self.linenostep
outfile.write(',numbers=left' +
(start and ',firstnumber=%d' % start or '') +
(step and ',stepnumber=%d' % step or ''))
if self.mathescape or self.texcomments or self.escapeinside:
outfile.write(',codes={\\catcode`\\$=3\\catcode`\\^=7'
'\\catcode`\\_=8\\relax}')
if self.verboptions:
outfile.write(',' + self.verboptions)
outfile.write(']\n')
for ttype, value in tokensource:
if ttype in Token.Comment:
if self.texcomments:
# Try to guess comment starting lexeme and escape it ...
start = value[0:1]
for i in range(1, len(value)):
if start[0] != value[i]:
break
start += value[i]
value = value[len(start):]
start = escape_tex(start, cp)
# ... but do not escape inside comment.
value = start + value
elif self.mathescape:
# Only escape parts not inside a math environment.
parts = value.split('$')
in_math = False
for i, part in enumerate(parts):
if not in_math:
parts[i] = escape_tex(part, cp)
in_math = not in_math
value = '$'.join(parts)
elif self.escapeinside:
text = value
value = ''
while text:
a, sep1, text = text.partition(self.left)
if sep1:
b, sep2, text = text.partition(self.right)
if sep2:
value += escape_tex(a, cp) + b
else:
value += escape_tex(a + sep1 + b, cp)
else:
value += escape_tex(a, cp)
else:
value = escape_tex(value, cp)
elif ttype not in Token.Escape:
value = escape_tex(value, cp)
styles = []
while ttype is not Token:
try:
styles.append(t2n[ttype])
except KeyError:
# not in current style
styles.append(_get_ttype_name(ttype))
ttype = ttype.parent
styleval = '+'.join(reversed(styles))
if styleval:
spl = value.split('\n')
for line in spl[:-1]:
if line:
outfile.write("\\%s{%s}{%s}" % (cp, styleval, line))
outfile.write('\n')
if spl[-1]:
outfile.write("\\%s{%s}{%s}" % (cp, styleval, spl[-1]))
else:
outfile.write(value)
if not self.nowrap:
outfile.write('\\end{' + self.envname + '}\n')
if self.full:
encoding = self.encoding or 'utf8'
# map known existings encodings from LaTeX distribution
encoding = {
'utf_8': 'utf8',
'latin_1': 'latin1',
'iso_8859_1': 'latin1',
}.get(encoding.replace('-', '_'), encoding)
realoutfile.write(DOC_TEMPLATE %
dict(docclass = self.docclass,
preamble = self.preamble,
title = self.title,
encoding = encoding,
styledefs = self.get_style_defs(),
code = outfile.getvalue()))
class LatexEmbeddedLexer(Lexer):
"""
This lexer takes one lexer as argument, the lexer for the language
being formatted, and the left and right delimiters for escaped text.
First everything is scanned using the language lexer to obtain
strings and comments. All other consecutive tokens are merged and
the resulting text is scanned for escaped segments, which are given
the Token.Escape type. Finally text that is not escaped is scanned
again with the language lexer.
"""
def __init__(self, left, right, lang, **options):
self.left = left
self.right = right
self.lang = lang
Lexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
# find and remove all the escape tokens (replace with an empty string)
# this is very similar to DelegatingLexer.get_tokens_unprocessed.
buffered = ''
insertions = []
insertion_buf = []
for i, t, v in self._find_safe_escape_tokens(text):
if t is None:
if insertion_buf:
insertions.append((len(buffered), insertion_buf))
insertion_buf = []
buffered += v
else:
insertion_buf.append((i, t, v))
if insertion_buf:
insertions.append((len(buffered), insertion_buf))
return do_insertions(insertions,
self.lang.get_tokens_unprocessed(buffered))
def _find_safe_escape_tokens(self, text):
""" find escape tokens that are not in strings or comments """
for i, t, v in self._filter_to(
self.lang.get_tokens_unprocessed(text),
lambda t: t in Token.Comment or t in Token.String
):
if t is None:
for i2, t2, v2 in self._find_escape_tokens(v):
yield i + i2, t2, v2
else:
yield i, None, v
def _filter_to(self, it, pred):
""" Keep only the tokens that match `pred`, merge the others together """
buf = ''
idx = 0
for i, t, v in it:
if pred(t):
if buf:
yield idx, None, buf
buf = ''
yield i, t, v
else:
if not buf:
idx = i
buf += v
if buf:
yield idx, None, buf
def _find_escape_tokens(self, text):
""" Find escape tokens within text, give token=None otherwise """
index = 0
while text:
a, sep1, text = text.partition(self.left)
if a:
yield index, None, a
index += len(a)
if sep1:
b, sep2, text = text.partition(self.right)
if sep2:
yield index + len(sep1), Token.Escape, b
index += len(sep1) + len(b) + len(sep2)
else:
yield index, Token.Error, sep1
index += len(sep1)
text = b

View file

@ -0,0 +1,161 @@
"""
pygments.formatters.other
~~~~~~~~~~~~~~~~~~~~~~~~~
Other formatters: NullFormatter, RawTokenFormatter.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.util import get_choice_opt
from pip._vendor.pygments.token import Token
from pip._vendor.pygments.console import colorize
__all__ = ['NullFormatter', 'RawTokenFormatter', 'TestcaseFormatter']
class NullFormatter(Formatter):
"""
Output the text unchanged without any formatting.
"""
name = 'Text only'
aliases = ['text', 'null']
filenames = ['*.txt']
def format(self, tokensource, outfile):
enc = self.encoding
for ttype, value in tokensource:
if enc:
outfile.write(value.encode(enc))
else:
outfile.write(value)
class RawTokenFormatter(Formatter):
r"""
Format tokens as a raw representation for storing token streams.
The format is ``tokentype<TAB>repr(tokenstring)\n``. The output can later
be converted to a token stream with the `RawTokenLexer`, described in the
:doc:`lexer list <lexers>`.
Only two options are accepted:
`compress`
If set to ``'gz'`` or ``'bz2'``, compress the output with the given
compression algorithm after encoding (default: ``''``).
`error_color`
If set to a color name, highlight error tokens using that color. If
set but with no value, defaults to ``'red'``.
.. versionadded:: 0.11
"""
name = 'Raw tokens'
aliases = ['raw', 'tokens']
filenames = ['*.raw']
unicodeoutput = False
def __init__(self, **options):
Formatter.__init__(self, **options)
# We ignore self.encoding if it is set, since it gets set for lexer
# and formatter if given with -Oencoding on the command line.
# The RawTokenFormatter outputs only ASCII. Override here.
self.encoding = 'ascii' # let pygments.format() do the right thing
self.compress = get_choice_opt(options, 'compress',
['', 'none', 'gz', 'bz2'], '')
self.error_color = options.get('error_color', None)
if self.error_color is True:
self.error_color = 'red'
if self.error_color is not None:
try:
colorize(self.error_color, '')
except KeyError:
raise ValueError("Invalid color %r specified" %
self.error_color)
def format(self, tokensource, outfile):
try:
outfile.write(b'')
except TypeError:
raise TypeError('The raw tokens formatter needs a binary '
'output file')
if self.compress == 'gz':
import gzip
outfile = gzip.GzipFile('', 'wb', 9, outfile)
write = outfile.write
flush = outfile.close
elif self.compress == 'bz2':
import bz2
compressor = bz2.BZ2Compressor(9)
def write(text):
outfile.write(compressor.compress(text))
def flush():
outfile.write(compressor.flush())
outfile.flush()
else:
write = outfile.write
flush = outfile.flush
if self.error_color:
for ttype, value in tokensource:
line = b"%r\t%r\n" % (ttype, value)
if ttype is Token.Error:
write(colorize(self.error_color, line))
else:
write(line)
else:
for ttype, value in tokensource:
write(b"%r\t%r\n" % (ttype, value))
flush()
TESTCASE_BEFORE = '''\
def testNeedsName(lexer):
fragment = %r
tokens = [
'''
TESTCASE_AFTER = '''\
]
assert list(lexer.get_tokens(fragment)) == tokens
'''
class TestcaseFormatter(Formatter):
"""
Format tokens as appropriate for a new testcase.
.. versionadded:: 2.0
"""
name = 'Testcase'
aliases = ['testcase']
def __init__(self, **options):
Formatter.__init__(self, **options)
if self.encoding is not None and self.encoding != 'utf-8':
raise ValueError("Only None and utf-8 are allowed encodings.")
def format(self, tokensource, outfile):
indentation = ' ' * 12
rawbuf = []
outbuf = []
for ttype, value in tokensource:
rawbuf.append(value)
outbuf.append('%s(%s, %r),\n' % (indentation, ttype, value))
before = TESTCASE_BEFORE % (''.join(rawbuf),)
during = ''.join(outbuf)
after = TESTCASE_AFTER
if self.encoding is None:
outfile.write(before + during + after)
else:
outfile.write(before.encode('utf-8'))
outfile.write(during.encode('utf-8'))
outfile.write(after.encode('utf-8'))
outfile.flush()

View file

@ -0,0 +1,83 @@
"""
pygments.formatters.pangomarkup
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for Pango markup output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
__all__ = ['PangoMarkupFormatter']
_escape_table = {
ord('&'): '&amp;',
ord('<'): '&lt;',
}
def escape_special_chars(text, table=_escape_table):
"""Escape & and < for Pango Markup."""
return text.translate(table)
class PangoMarkupFormatter(Formatter):
"""
Format tokens as Pango Markup code. It can then be rendered to an SVG.
.. versionadded:: 2.9
"""
name = 'Pango Markup'
aliases = ['pango', 'pangomarkup']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.styles = {}
for token, style in self.style:
start = ''
end = ''
if style['color']:
start += '<span fgcolor="#%s">' % style['color']
end = '</span>' + end
if style['bold']:
start += '<b>'
end = '</b>' + end
if style['italic']:
start += '<i>'
end = '</i>' + end
if style['underline']:
start += '<u>'
end = '</u>' + end
self.styles[token] = (start, end)
def format_unencoded(self, tokensource, outfile):
lastval = ''
lasttype = None
outfile.write('<tt>')
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
if ttype == lasttype:
lastval += escape_special_chars(value)
else:
if lastval:
stylebegin, styleend = self.styles[lasttype]
outfile.write(stylebegin + lastval + styleend)
lastval = escape_special_chars(value)
lasttype = ttype
if lastval:
stylebegin, styleend = self.styles[lasttype]
outfile.write(stylebegin + lastval + styleend)
outfile.write('</tt>')

View file

@ -0,0 +1,146 @@
"""
pygments.formatters.rtf
~~~~~~~~~~~~~~~~~~~~~~~
A formatter that generates RTF files.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.util import get_int_opt, surrogatepair
__all__ = ['RtfFormatter']
class RtfFormatter(Formatter):
"""
Format tokens as RTF markup. This formatter automatically outputs full RTF
documents with color information and other useful stuff. Perfect for Copy and
Paste into Microsoft(R) Word(R) documents.
Please note that ``encoding`` and ``outencoding`` options are ignored.
The RTF format is ASCII natively, but handles unicode characters correctly
thanks to escape sequences.
.. versionadded:: 0.6
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`fontface`
The used font family, for example ``Bitstream Vera Sans``. Defaults to
some generic font which is supposed to have fixed width.
`fontsize`
Size of the font used. Size is specified in half points. The
default is 24 half-points, giving a size 12 font.
.. versionadded:: 2.0
"""
name = 'RTF'
aliases = ['rtf']
filenames = ['*.rtf']
def __init__(self, **options):
r"""
Additional options accepted:
``fontface``
Name of the font used. Could for example be ``'Courier New'``
to further specify the default which is ``'\fmodern'``. The RTF
specification claims that ``\fmodern`` are "Fixed-pitch serif
and sans serif fonts". Hope every RTF implementation thinks
the same about modern...
"""
Formatter.__init__(self, **options)
self.fontface = options.get('fontface') or ''
self.fontsize = get_int_opt(options, 'fontsize', 0)
def _escape(self, text):
return text.replace('\\', '\\\\') \
.replace('{', '\\{') \
.replace('}', '\\}')
def _escape_text(self, text):
# empty strings, should give a small performance improvement
if not text:
return ''
# escape text
text = self._escape(text)
buf = []
for c in text:
cn = ord(c)
if cn < (2**7):
# ASCII character
buf.append(str(c))
elif (2**7) <= cn < (2**16):
# single unicode escape sequence
buf.append('{\\u%d}' % cn)
elif (2**16) <= cn:
# RTF limits unicode to 16 bits.
# Force surrogate pairs
buf.append('{\\u%d}{\\u%d}' % surrogatepair(cn))
return ''.join(buf).replace('\n', '\\par\n')
def format_unencoded(self, tokensource, outfile):
# rtf 1.8 header
outfile.write('{\\rtf1\\ansi\\uc0\\deff0'
'{\\fonttbl{\\f0\\fmodern\\fprq1\\fcharset0%s;}}'
'{\\colortbl;' % (self.fontface and
' ' + self._escape(self.fontface) or
''))
# convert colors and save them in a mapping to access them later.
color_mapping = {}
offset = 1
for _, style in self.style:
for color in style['color'], style['bgcolor'], style['border']:
if color and color not in color_mapping:
color_mapping[color] = offset
outfile.write('\\red%d\\green%d\\blue%d;' % (
int(color[0:2], 16),
int(color[2:4], 16),
int(color[4:6], 16)
))
offset += 1
outfile.write('}\\f0 ')
if self.fontsize:
outfile.write('\\fs%d' % self.fontsize)
# highlight stream
for ttype, value in tokensource:
while not self.style.styles_token(ttype) and ttype.parent:
ttype = ttype.parent
style = self.style.style_for_token(ttype)
buf = []
if style['bgcolor']:
buf.append('\\cb%d' % color_mapping[style['bgcolor']])
if style['color']:
buf.append('\\cf%d' % color_mapping[style['color']])
if style['bold']:
buf.append('\\b')
if style['italic']:
buf.append('\\i')
if style['underline']:
buf.append('\\ul')
if style['border']:
buf.append('\\chbrdr\\chcfpat%d' %
color_mapping[style['border']])
start = ''.join(buf)
if start:
outfile.write('{%s ' % start)
outfile.write(self._escape_text(value))
if start:
outfile.write('}')
outfile.write('}')

View file

@ -0,0 +1,188 @@
"""
pygments.formatters.svg
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for SVG output.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.token import Comment
from pip._vendor.pygments.util import get_bool_opt, get_int_opt
__all__ = ['SvgFormatter']
def escape_html(text):
"""Escape &, <, > as well as single and double quotes for HTML."""
return text.replace('&', '&amp;'). \
replace('<', '&lt;'). \
replace('>', '&gt;'). \
replace('"', '&quot;'). \
replace("'", '&#39;')
class2style = {}
class SvgFormatter(Formatter):
"""
Format tokens as an SVG graphics file. This formatter is still experimental.
Each line of code is a ``<text>`` element with explicit ``x`` and ``y``
coordinates containing ``<tspan>`` elements with the individual token styles.
By default, this formatter outputs a full SVG document including doctype
declaration and the ``<svg>`` root element.
.. versionadded:: 0.9
Additional options accepted:
`nowrap`
Don't wrap the SVG ``<text>`` elements in ``<svg><g>`` elements and
don't add a XML declaration and a doctype. If true, the `fontfamily`
and `fontsize` options are ignored. Defaults to ``False``.
`fontfamily`
The value to give the wrapping ``<g>`` element's ``font-family``
attribute, defaults to ``"monospace"``.
`fontsize`
The value to give the wrapping ``<g>`` element's ``font-size``
attribute, defaults to ``"14px"``.
`linenos`
If ``True``, add line numbers (default: ``False``).
`linenostart`
The line number for the first line (default: ``1``).
`linenostep`
If set to a number n > 1, only every nth line number is printed.
`linenowidth`
Maximum width devoted to line numbers (default: ``3*ystep``, sufficient
for up to 4-digit line numbers. Increase width for longer code blocks).
`xoffset`
Starting offset in X direction, defaults to ``0``.
`yoffset`
Starting offset in Y direction, defaults to the font size if it is given
in pixels, or ``20`` else. (This is necessary since text coordinates
refer to the text baseline, not the top edge.)
`ystep`
Offset to add to the Y coordinate for each subsequent line. This should
roughly be the text size plus 5. It defaults to that value if the text
size is given in pixels, or ``25`` else.
`spacehack`
Convert spaces in the source to ``&#160;``, which are non-breaking
spaces. SVG provides the ``xml:space`` attribute to control how
whitespace inside tags is handled, in theory, the ``preserve`` value
could be used to keep all whitespace as-is. However, many current SVG
viewers don't obey that rule, so this option is provided as a workaround
and defaults to ``True``.
"""
name = 'SVG'
aliases = ['svg']
filenames = ['*.svg']
def __init__(self, **options):
Formatter.__init__(self, **options)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.fontfamily = options.get('fontfamily', 'monospace')
self.fontsize = options.get('fontsize', '14px')
self.xoffset = get_int_opt(options, 'xoffset', 0)
fs = self.fontsize.strip()
if fs.endswith('px'): fs = fs[:-2].strip()
try:
int_fs = int(fs)
except:
int_fs = 20
self.yoffset = get_int_opt(options, 'yoffset', int_fs)
self.ystep = get_int_opt(options, 'ystep', int_fs + 5)
self.spacehack = get_bool_opt(options, 'spacehack', True)
self.linenos = get_bool_opt(options,'linenos',False)
self.linenostart = get_int_opt(options,'linenostart',1)
self.linenostep = get_int_opt(options,'linenostep',1)
self.linenowidth = get_int_opt(options,'linenowidth', 3*self.ystep)
self._stylecache = {}
def format_unencoded(self, tokensource, outfile):
"""
Format ``tokensource``, an iterable of ``(tokentype, tokenstring)``
tuples and write it into ``outfile``.
For our implementation we put all lines in their own 'line group'.
"""
x = self.xoffset
y = self.yoffset
if not self.nowrap:
if self.encoding:
outfile.write('<?xml version="1.0" encoding="%s"?>\n' %
self.encoding)
else:
outfile.write('<?xml version="1.0"?>\n')
outfile.write('<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN" '
'"http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/'
'svg10.dtd">\n')
outfile.write('<svg xmlns="http://www.w3.org/2000/svg">\n')
outfile.write('<g font-family="%s" font-size="%s">\n' %
(self.fontfamily, self.fontsize))
counter = self.linenostart
counter_step = self.linenostep
counter_style = self._get_style(Comment)
line_x = x
if self.linenos:
if counter % counter_step == 0:
outfile.write('<text x="%s" y="%s" %s text-anchor="end">%s</text>' %
(x+self.linenowidth,y,counter_style,counter))
line_x += self.linenowidth + self.ystep
counter += 1
outfile.write('<text x="%s" y="%s" xml:space="preserve">' % (line_x, y))
for ttype, value in tokensource:
style = self._get_style(ttype)
tspan = style and '<tspan' + style + '>' or ''
tspanend = tspan and '</tspan>' or ''
value = escape_html(value)
if self.spacehack:
value = value.expandtabs().replace(' ', '&#160;')
parts = value.split('\n')
for part in parts[:-1]:
outfile.write(tspan + part + tspanend)
y += self.ystep
outfile.write('</text>\n')
if self.linenos and counter % counter_step == 0:
outfile.write('<text x="%s" y="%s" text-anchor="end" %s>%s</text>' %
(x+self.linenowidth,y,counter_style,counter))
counter += 1
outfile.write('<text x="%s" y="%s" ' 'xml:space="preserve">' % (line_x,y))
outfile.write(tspan + parts[-1] + tspanend)
outfile.write('</text>')
if not self.nowrap:
outfile.write('</g></svg>\n')
def _get_style(self, tokentype):
if tokentype in self._stylecache:
return self._stylecache[tokentype]
otokentype = tokentype
while not self.style.styles_token(tokentype):
tokentype = tokentype.parent
value = self.style.style_for_token(tokentype)
result = ''
if value['color']:
result = ' fill="#' + value['color'] + '"'
if value['bold']:
result += ' font-weight="bold"'
if value['italic']:
result += ' font-style="italic"'
self._stylecache[otokentype] = result
return result

View file

@ -0,0 +1,127 @@
"""
pygments.formatters.terminal
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for terminal output with ANSI sequences.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.token import Keyword, Name, Comment, String, Error, \
Number, Operator, Generic, Token, Whitespace
from pip._vendor.pygments.console import ansiformat
from pip._vendor.pygments.util import get_choice_opt
__all__ = ['TerminalFormatter']
#: Map token types to a tuple of color values for light and dark
#: backgrounds.
TERMINAL_COLORS = {
Token: ('', ''),
Whitespace: ('gray', 'brightblack'),
Comment: ('gray', 'brightblack'),
Comment.Preproc: ('cyan', 'brightcyan'),
Keyword: ('blue', 'brightblue'),
Keyword.Type: ('cyan', 'brightcyan'),
Operator.Word: ('magenta', 'brightmagenta'),
Name.Builtin: ('cyan', 'brightcyan'),
Name.Function: ('green', 'brightgreen'),
Name.Namespace: ('_cyan_', '_brightcyan_'),
Name.Class: ('_green_', '_brightgreen_'),
Name.Exception: ('cyan', 'brightcyan'),
Name.Decorator: ('brightblack', 'gray'),
Name.Variable: ('red', 'brightred'),
Name.Constant: ('red', 'brightred'),
Name.Attribute: ('cyan', 'brightcyan'),
Name.Tag: ('brightblue', 'brightblue'),
String: ('yellow', 'yellow'),
Number: ('blue', 'brightblue'),
Generic.Deleted: ('brightred', 'brightred'),
Generic.Inserted: ('green', 'brightgreen'),
Generic.Heading: ('**', '**'),
Generic.Subheading: ('*magenta*', '*brightmagenta*'),
Generic.Prompt: ('**', '**'),
Generic.Error: ('brightred', 'brightred'),
Error: ('_brightred_', '_brightred_'),
}
class TerminalFormatter(Formatter):
r"""
Format tokens with ANSI color sequences, for output in a text console.
Color sequences are terminated at newlines, so that paging the output
works correctly.
The `get_style_defs()` method doesn't do anything special since there is
no support for common styles.
Options accepted:
`bg`
Set to ``"light"`` or ``"dark"`` depending on the terminal's background
(default: ``"light"``).
`colorscheme`
A dictionary mapping token types to (lightbg, darkbg) color names or
``None`` (default: ``None`` = use builtin colorscheme).
`linenos`
Set to ``True`` to have line numbers on the terminal output as well
(default: ``False`` = no line numbers).
"""
name = 'Terminal'
aliases = ['terminal', 'console']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.darkbg = get_choice_opt(options, 'bg',
['light', 'dark'], 'light') == 'dark'
self.colorscheme = options.get('colorscheme', None) or TERMINAL_COLORS
self.linenos = options.get('linenos', False)
self._lineno = 0
def format(self, tokensource, outfile):
return Formatter.format(self, tokensource, outfile)
def _write_lineno(self, outfile):
self._lineno += 1
outfile.write("%s%04d: " % (self._lineno != 1 and '\n' or '', self._lineno))
def _get_color(self, ttype):
# self.colorscheme is a dict containing usually generic types, so we
# have to walk the tree of dots. The base Token type must be a key,
# even if it's empty string, as in the default above.
colors = self.colorscheme.get(ttype)
while colors is None:
ttype = ttype.parent
colors = self.colorscheme.get(ttype)
return colors[self.darkbg]
def format_unencoded(self, tokensource, outfile):
if self.linenos:
self._write_lineno(outfile)
for ttype, value in tokensource:
color = self._get_color(ttype)
for line in value.splitlines(True):
if color:
outfile.write(ansiformat(color, line.rstrip('\n')))
else:
outfile.write(line.rstrip('\n'))
if line.endswith('\n'):
if self.linenos:
self._write_lineno(outfile)
else:
outfile.write('\n')
if self.linenos:
outfile.write("\n")

View file

@ -0,0 +1,338 @@
"""
pygments.formatters.terminal256
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for 256-color terminal output with ANSI sequences.
RGB-to-XTERM color conversion routines adapted from xterm256-conv
tool (http://frexx.de/xterm-256-notes/data/xterm256-conv2.tar.bz2)
by Wolfgang Frisch.
Formatter version 1.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
# TODO:
# - Options to map style's bold/underline/italic/border attributes
# to some ANSI attrbutes (something like 'italic=underline')
# - An option to output "style RGB to xterm RGB/index" conversion table
# - An option to indicate that we are running in "reverse background"
# xterm. This means that default colors are white-on-black, not
# black-on-while, so colors like "white background" need to be converted
# to "white background, black foreground", etc...
from pip._vendor.pygments.formatter import Formatter
from pip._vendor.pygments.console import codes
from pip._vendor.pygments.style import ansicolors
__all__ = ['Terminal256Formatter', 'TerminalTrueColorFormatter']
class EscapeSequence:
def __init__(self, fg=None, bg=None, bold=False, underline=False, italic=False):
self.fg = fg
self.bg = bg
self.bold = bold
self.underline = underline
self.italic = italic
def escape(self, attrs):
if len(attrs):
return "\x1b[" + ";".join(attrs) + "m"
return ""
def color_string(self):
attrs = []
if self.fg is not None:
if self.fg in ansicolors:
esc = codes[self.fg.replace('ansi','')]
if ';01m' in esc:
self.bold = True
# extract fg color code.
attrs.append(esc[2:4])
else:
attrs.extend(("38", "5", "%i" % self.fg))
if self.bg is not None:
if self.bg in ansicolors:
esc = codes[self.bg.replace('ansi','')]
# extract fg color code, add 10 for bg.
attrs.append(str(int(esc[2:4])+10))
else:
attrs.extend(("48", "5", "%i" % self.bg))
if self.bold:
attrs.append("01")
if self.underline:
attrs.append("04")
if self.italic:
attrs.append("03")
return self.escape(attrs)
def true_color_string(self):
attrs = []
if self.fg:
attrs.extend(("38", "2", str(self.fg[0]), str(self.fg[1]), str(self.fg[2])))
if self.bg:
attrs.extend(("48", "2", str(self.bg[0]), str(self.bg[1]), str(self.bg[2])))
if self.bold:
attrs.append("01")
if self.underline:
attrs.append("04")
if self.italic:
attrs.append("03")
return self.escape(attrs)
def reset_string(self):
attrs = []
if self.fg is not None:
attrs.append("39")
if self.bg is not None:
attrs.append("49")
if self.bold or self.underline or self.italic:
attrs.append("00")
return self.escape(attrs)
class Terminal256Formatter(Formatter):
"""
Format tokens with ANSI color sequences, for output in a 256-color
terminal or console. Like in `TerminalFormatter` color sequences
are terminated at newlines, so that paging the output works correctly.
The formatter takes colors from a style defined by the `style` option
and converts them to nearest ANSI 256-color escape sequences. Bold and
underline attributes from the style are preserved (and displayed).
.. versionadded:: 0.9
.. versionchanged:: 2.2
If the used style defines foreground colors in the form ``#ansi*``, then
`Terminal256Formatter` will map these to non extended foreground color.
See :ref:`AnsiTerminalStyle` for more information.
.. versionchanged:: 2.4
The ANSI color names have been updated with names that are easier to
understand and align with colornames of other projects and terminals.
See :ref:`this table <new-ansi-color-names>` for more information.
Options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`linenos`
Set to ``True`` to have line numbers on the terminal output as well
(default: ``False`` = no line numbers).
"""
name = 'Terminal256'
aliases = ['terminal256', 'console256', '256']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.xterm_colors = []
self.best_match = {}
self.style_string = {}
self.usebold = 'nobold' not in options
self.useunderline = 'nounderline' not in options
self.useitalic = 'noitalic' not in options
self._build_color_table() # build an RGB-to-256 color conversion table
self._setup_styles() # convert selected style's colors to term. colors
self.linenos = options.get('linenos', False)
self._lineno = 0
def _build_color_table(self):
# colors 0..15: 16 basic colors
self.xterm_colors.append((0x00, 0x00, 0x00)) # 0
self.xterm_colors.append((0xcd, 0x00, 0x00)) # 1
self.xterm_colors.append((0x00, 0xcd, 0x00)) # 2
self.xterm_colors.append((0xcd, 0xcd, 0x00)) # 3
self.xterm_colors.append((0x00, 0x00, 0xee)) # 4
self.xterm_colors.append((0xcd, 0x00, 0xcd)) # 5
self.xterm_colors.append((0x00, 0xcd, 0xcd)) # 6
self.xterm_colors.append((0xe5, 0xe5, 0xe5)) # 7
self.xterm_colors.append((0x7f, 0x7f, 0x7f)) # 8
self.xterm_colors.append((0xff, 0x00, 0x00)) # 9
self.xterm_colors.append((0x00, 0xff, 0x00)) # 10
self.xterm_colors.append((0xff, 0xff, 0x00)) # 11
self.xterm_colors.append((0x5c, 0x5c, 0xff)) # 12
self.xterm_colors.append((0xff, 0x00, 0xff)) # 13
self.xterm_colors.append((0x00, 0xff, 0xff)) # 14
self.xterm_colors.append((0xff, 0xff, 0xff)) # 15
# colors 16..232: the 6x6x6 color cube
valuerange = (0x00, 0x5f, 0x87, 0xaf, 0xd7, 0xff)
for i in range(217):
r = valuerange[(i // 36) % 6]
g = valuerange[(i // 6) % 6]
b = valuerange[i % 6]
self.xterm_colors.append((r, g, b))
# colors 233..253: grayscale
for i in range(1, 22):
v = 8 + i * 10
self.xterm_colors.append((v, v, v))
def _closest_color(self, r, g, b):
distance = 257*257*3 # "infinity" (>distance from #000000 to #ffffff)
match = 0
for i in range(0, 254):
values = self.xterm_colors[i]
rd = r - values[0]
gd = g - values[1]
bd = b - values[2]
d = rd*rd + gd*gd + bd*bd
if d < distance:
match = i
distance = d
return match
def _color_index(self, color):
index = self.best_match.get(color, None)
if color in ansicolors:
# strip the `ansi/#ansi` part and look up code
index = color
self.best_match[color] = index
if index is None:
try:
rgb = int(str(color), 16)
except ValueError:
rgb = 0
r = (rgb >> 16) & 0xff
g = (rgb >> 8) & 0xff
b = rgb & 0xff
index = self._closest_color(r, g, b)
self.best_match[color] = index
return index
def _setup_styles(self):
for ttype, ndef in self.style:
escape = EscapeSequence()
# get foreground from ansicolor if set
if ndef['ansicolor']:
escape.fg = self._color_index(ndef['ansicolor'])
elif ndef['color']:
escape.fg = self._color_index(ndef['color'])
if ndef['bgansicolor']:
escape.bg = self._color_index(ndef['bgansicolor'])
elif ndef['bgcolor']:
escape.bg = self._color_index(ndef['bgcolor'])
if self.usebold and ndef['bold']:
escape.bold = True
if self.useunderline and ndef['underline']:
escape.underline = True
if self.useitalic and ndef['italic']:
escape.italic = True
self.style_string[str(ttype)] = (escape.color_string(),
escape.reset_string())
def _write_lineno(self, outfile):
self._lineno += 1
outfile.write("%s%04d: " % (self._lineno != 1 and '\n' or '', self._lineno))
def format(self, tokensource, outfile):
return Formatter.format(self, tokensource, outfile)
def format_unencoded(self, tokensource, outfile):
if self.linenos:
self._write_lineno(outfile)
for ttype, value in tokensource:
not_found = True
while ttype and not_found:
try:
# outfile.write( "<" + str(ttype) + ">" )
on, off = self.style_string[str(ttype)]
# Like TerminalFormatter, add "reset colors" escape sequence
# on newline.
spl = value.split('\n')
for line in spl[:-1]:
if line:
outfile.write(on + line + off)
if self.linenos:
self._write_lineno(outfile)
else:
outfile.write('\n')
if spl[-1]:
outfile.write(on + spl[-1] + off)
not_found = False
# outfile.write( '#' + str(ttype) + '#' )
except KeyError:
# ottype = ttype
ttype = ttype.parent
# outfile.write( '!' + str(ottype) + '->' + str(ttype) + '!' )
if not_found:
outfile.write(value)
if self.linenos:
outfile.write("\n")
class TerminalTrueColorFormatter(Terminal256Formatter):
r"""
Format tokens with ANSI color sequences, for output in a true-color
terminal or console. Like in `TerminalFormatter` color sequences
are terminated at newlines, so that paging the output works correctly.
.. versionadded:: 2.1
Options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
"""
name = 'TerminalTrueColor'
aliases = ['terminal16m', 'console16m', '16m']
filenames = []
def _build_color_table(self):
pass
def _color_tuple(self, color):
try:
rgb = int(str(color), 16)
except ValueError:
return None
r = (rgb >> 16) & 0xff
g = (rgb >> 8) & 0xff
b = rgb & 0xff
return (r, g, b)
def _setup_styles(self):
for ttype, ndef in self.style:
escape = EscapeSequence()
if ndef['color']:
escape.fg = self._color_tuple(ndef['color'])
if ndef['bgcolor']:
escape.bg = self._color_tuple(ndef['bgcolor'])
if self.usebold and ndef['bold']:
escape.bold = True
if self.useunderline and ndef['underline']:
escape.underline = True
if self.useitalic and ndef['italic']:
escape.italic = True
self.style_string[str(ttype)] = (escape.true_color_string(),
escape.reset_string())

View file

@ -0,0 +1,943 @@
"""
pygments.lexer
~~~~~~~~~~~~~~
Base lexer classes.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
import sys
import time
from pip._vendor.pygments.filter import apply_filters, Filter
from pip._vendor.pygments.filters import get_filter_by_name
from pip._vendor.pygments.token import Error, Text, Other, Whitespace, _TokenType
from pip._vendor.pygments.util import get_bool_opt, get_int_opt, get_list_opt, \
make_analysator, Future, guess_decode
from pip._vendor.pygments.regexopt import regex_opt
__all__ = ['Lexer', 'RegexLexer', 'ExtendedRegexLexer', 'DelegatingLexer',
'LexerContext', 'include', 'inherit', 'bygroups', 'using', 'this',
'default', 'words', 'line_re']
line_re = re.compile('.*?\n')
_encoding_map = [(b'\xef\xbb\xbf', 'utf-8'),
(b'\xff\xfe\0\0', 'utf-32'),
(b'\0\0\xfe\xff', 'utf-32be'),
(b'\xff\xfe', 'utf-16'),
(b'\xfe\xff', 'utf-16be')]
_default_analyse = staticmethod(lambda x: 0.0)
class LexerMeta(type):
"""
This metaclass automagically converts ``analyse_text`` methods into
static methods which always return float values.
"""
def __new__(mcs, name, bases, d):
if 'analyse_text' in d:
d['analyse_text'] = make_analysator(d['analyse_text'])
return type.__new__(mcs, name, bases, d)
class Lexer(metaclass=LexerMeta):
"""
Lexer for a specific language.
See also :doc:`lexerdevelopment`, a high-level guide to writing
lexers.
Lexer classes have attributes used for choosing the most appropriate
lexer based on various criteria.
.. autoattribute:: name
:no-value:
.. autoattribute:: aliases
:no-value:
.. autoattribute:: filenames
:no-value:
.. autoattribute:: alias_filenames
.. autoattribute:: mimetypes
:no-value:
.. autoattribute:: priority
Lexers included in Pygments should have an additional attribute:
.. autoattribute:: url
:no-value:
You can pass options to the constructor. The basic options recognized
by all lexers and processed by the base `Lexer` class are:
``stripnl``
Strip leading and trailing newlines from the input (default: True).
``stripall``
Strip all leading and trailing whitespace from the input
(default: False).
``ensurenl``
Make sure that the input ends with a newline (default: True). This
is required for some lexers that consume input linewise.
.. versionadded:: 1.3
``tabsize``
If given and greater than 0, expand tabs in the input (default: 0).
``encoding``
If given, must be an encoding name. This encoding will be used to
convert the input string to Unicode, if it is not already a Unicode
string (default: ``'guess'``, which uses a simple UTF-8 / Locale /
Latin1 detection. Can also be ``'chardet'`` to use the chardet
library, if it is installed.
``inencoding``
Overrides the ``encoding`` if given.
"""
#: Full name of the lexer, in human-readable form
name = None
#: A list of short, unique identifiers that can be used to look
#: up the lexer from a list, e.g., using `get_lexer_by_name()`.
aliases = []
#: A list of `fnmatch` patterns that match filenames which contain
#: content for this lexer. The patterns in this list should be unique among
#: all lexers.
filenames = []
#: A list of `fnmatch` patterns that match filenames which may or may not
#: contain content for this lexer. This list is used by the
#: :func:`.guess_lexer_for_filename()` function, to determine which lexers
#: are then included in guessing the correct one. That means that
#: e.g. every lexer for HTML and a template language should include
#: ``\*.html`` in this list.
alias_filenames = []
#: A list of MIME types for content that can be lexed with this lexer.
mimetypes = []
#: Priority, should multiple lexers match and no content is provided
priority = 0
#: URL of the language specification/definition. Used in the Pygments
#: documentation.
url = None
def __init__(self, **options):
"""
This constructor takes arbitrary options as keyword arguments.
Every subclass must first process its own options and then call
the `Lexer` constructor, since it processes the basic
options like `stripnl`.
An example looks like this:
.. sourcecode:: python
def __init__(self, **options):
self.compress = options.get('compress', '')
Lexer.__init__(self, **options)
As these options must all be specifiable as strings (due to the
command line usage), there are various utility functions
available to help with that, see `Utilities`_.
"""
self.options = options
self.stripnl = get_bool_opt(options, 'stripnl', True)
self.stripall = get_bool_opt(options, 'stripall', False)
self.ensurenl = get_bool_opt(options, 'ensurenl', True)
self.tabsize = get_int_opt(options, 'tabsize', 0)
self.encoding = options.get('encoding', 'guess')
self.encoding = options.get('inencoding') or self.encoding
self.filters = []
for filter_ in get_list_opt(options, 'filters', ()):
self.add_filter(filter_)
def __repr__(self):
if self.options:
return '<pygments.lexers.%s with %r>' % (self.__class__.__name__,
self.options)
else:
return '<pygments.lexers.%s>' % self.__class__.__name__
def add_filter(self, filter_, **options):
"""
Add a new stream filter to this lexer.
"""
if not isinstance(filter_, Filter):
filter_ = get_filter_by_name(filter_, **options)
self.filters.append(filter_)
def analyse_text(text):
"""
A static method which is called for lexer guessing.
It should analyse the text and return a float in the range
from ``0.0`` to ``1.0``. If it returns ``0.0``, the lexer
will not be selected as the most probable one, if it returns
``1.0``, it will be selected immediately. This is used by
`guess_lexer`.
The `LexerMeta` metaclass automatically wraps this function so
that it works like a static method (no ``self`` or ``cls``
parameter) and the return value is automatically converted to
`float`. If the return value is an object that is boolean `False`
it's the same as if the return values was ``0.0``.
"""
def get_tokens(self, text, unfiltered=False):
"""
This method is the basic interface of a lexer. It is called by
the `highlight()` function. It must process the text and return an
iterable of ``(tokentype, value)`` pairs from `text`.
Normally, you don't need to override this method. The default
implementation processes the options recognized by all lexers
(`stripnl`, `stripall` and so on), and then yields all tokens
from `get_tokens_unprocessed()`, with the ``index`` dropped.
If `unfiltered` is set to `True`, the filtering mechanism is
bypassed even if filters are defined.
"""
if not isinstance(text, str):
if self.encoding == 'guess':
text, _ = guess_decode(text)
elif self.encoding == 'chardet':
try:
from pip._vendor import chardet
except ImportError as e:
raise ImportError('To enable chardet encoding guessing, '
'please install the chardet library '
'from http://chardet.feedparser.org/') from e
# check for BOM first
decoded = None
for bom, encoding in _encoding_map:
if text.startswith(bom):
decoded = text[len(bom):].decode(encoding, 'replace')
break
# no BOM found, so use chardet
if decoded is None:
enc = chardet.detect(text[:1024]) # Guess using first 1KB
decoded = text.decode(enc.get('encoding') or 'utf-8',
'replace')
text = decoded
else:
text = text.decode(self.encoding)
if text.startswith('\ufeff'):
text = text[len('\ufeff'):]
else:
if text.startswith('\ufeff'):
text = text[len('\ufeff'):]
# text now *is* a unicode string
text = text.replace('\r\n', '\n')
text = text.replace('\r', '\n')
if self.stripall:
text = text.strip()
elif self.stripnl:
text = text.strip('\n')
if self.tabsize > 0:
text = text.expandtabs(self.tabsize)
if self.ensurenl and not text.endswith('\n'):
text += '\n'
def streamer():
for _, t, v in self.get_tokens_unprocessed(text):
yield t, v
stream = streamer()
if not unfiltered:
stream = apply_filters(stream, self.filters, self)
return stream
def get_tokens_unprocessed(self, text):
"""
This method should process the text and return an iterable of
``(index, tokentype, value)`` tuples where ``index`` is the starting
position of the token within the input text.
It must be overridden by subclasses. It is recommended to
implement it as a generator to maximize effectiveness.
"""
raise NotImplementedError
class DelegatingLexer(Lexer):
"""
This lexer takes two lexer as arguments. A root lexer and
a language lexer. First everything is scanned using the language
lexer, afterwards all ``Other`` tokens are lexed using the root
lexer.
The lexers from the ``template`` lexer package use this base lexer.
"""
def __init__(self, _root_lexer, _language_lexer, _needle=Other, **options):
self.root_lexer = _root_lexer(**options)
self.language_lexer = _language_lexer(**options)
self.needle = _needle
Lexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
buffered = ''
insertions = []
lng_buffer = []
for i, t, v in self.language_lexer.get_tokens_unprocessed(text):
if t is self.needle:
if lng_buffer:
insertions.append((len(buffered), lng_buffer))
lng_buffer = []
buffered += v
else:
lng_buffer.append((i, t, v))
if lng_buffer:
insertions.append((len(buffered), lng_buffer))
return do_insertions(insertions,
self.root_lexer.get_tokens_unprocessed(buffered))
# ------------------------------------------------------------------------------
# RegexLexer and ExtendedRegexLexer
#
class include(str): # pylint: disable=invalid-name
"""
Indicates that a state should include rules from another state.
"""
pass
class _inherit:
"""
Indicates the a state should inherit from its superclass.
"""
def __repr__(self):
return 'inherit'
inherit = _inherit() # pylint: disable=invalid-name
class combined(tuple): # pylint: disable=invalid-name
"""
Indicates a state combined from multiple states.
"""
def __new__(cls, *args):
return tuple.__new__(cls, args)
def __init__(self, *args):
# tuple.__init__ doesn't do anything
pass
class _PseudoMatch:
"""
A pseudo match object constructed from a string.
"""
def __init__(self, start, text):
self._text = text
self._start = start
def start(self, arg=None):
return self._start
def end(self, arg=None):
return self._start + len(self._text)
def group(self, arg=None):
if arg:
raise IndexError('No such group')
return self._text
def groups(self):
return (self._text,)
def groupdict(self):
return {}
def bygroups(*args):
"""
Callback that yields multiple actions for each group in the match.
"""
def callback(lexer, match, ctx=None):
for i, action in enumerate(args):
if action is None:
continue
elif type(action) is _TokenType:
data = match.group(i + 1)
if data:
yield match.start(i + 1), action, data
else:
data = match.group(i + 1)
if data is not None:
if ctx:
ctx.pos = match.start(i + 1)
for item in action(lexer,
_PseudoMatch(match.start(i + 1), data), ctx):
if item:
yield item
if ctx:
ctx.pos = match.end()
return callback
class _This:
"""
Special singleton used for indicating the caller class.
Used by ``using``.
"""
this = _This()
def using(_other, **kwargs):
"""
Callback that processes the match with a different lexer.
The keyword arguments are forwarded to the lexer, except `state` which
is handled separately.
`state` specifies the state that the new lexer will start in, and can
be an enumerable such as ('root', 'inline', 'string') or a simple
string which is assumed to be on top of the root state.
Note: For that to work, `_other` must not be an `ExtendedRegexLexer`.
"""
gt_kwargs = {}
if 'state' in kwargs:
s = kwargs.pop('state')
if isinstance(s, (list, tuple)):
gt_kwargs['stack'] = s
else:
gt_kwargs['stack'] = ('root', s)
if _other is this:
def callback(lexer, match, ctx=None):
# if keyword arguments are given the callback
# function has to create a new lexer instance
if kwargs:
# XXX: cache that somehow
kwargs.update(lexer.options)
lx = lexer.__class__(**kwargs)
else:
lx = lexer
s = match.start()
for i, t, v in lx.get_tokens_unprocessed(match.group(), **gt_kwargs):
yield i + s, t, v
if ctx:
ctx.pos = match.end()
else:
def callback(lexer, match, ctx=None):
# XXX: cache that somehow
kwargs.update(lexer.options)
lx = _other(**kwargs)
s = match.start()
for i, t, v in lx.get_tokens_unprocessed(match.group(), **gt_kwargs):
yield i + s, t, v
if ctx:
ctx.pos = match.end()
return callback
class default:
"""
Indicates a state or state action (e.g. #pop) to apply.
For example default('#pop') is equivalent to ('', Token, '#pop')
Note that state tuples may be used as well.
.. versionadded:: 2.0
"""
def __init__(self, state):
self.state = state
class words(Future):
"""
Indicates a list of literal words that is transformed into an optimized
regex that matches any of the words.
.. versionadded:: 2.0
"""
def __init__(self, words, prefix='', suffix=''):
self.words = words
self.prefix = prefix
self.suffix = suffix
def get(self):
return regex_opt(self.words, prefix=self.prefix, suffix=self.suffix)
class RegexLexerMeta(LexerMeta):
"""
Metaclass for RegexLexer, creates the self._tokens attribute from
self.tokens on the first instantiation.
"""
def _process_regex(cls, regex, rflags, state):
"""Preprocess the regular expression component of a token definition."""
if isinstance(regex, Future):
regex = regex.get()
return re.compile(regex, rflags).match
def _process_token(cls, token):
"""Preprocess the token component of a token definition."""
assert type(token) is _TokenType or callable(token), \
'token type must be simple type or callable, not %r' % (token,)
return token
def _process_new_state(cls, new_state, unprocessed, processed):
"""Preprocess the state transition action of a token definition."""
if isinstance(new_state, str):
# an existing state
if new_state == '#pop':
return -1
elif new_state in unprocessed:
return (new_state,)
elif new_state == '#push':
return new_state
elif new_state[:5] == '#pop:':
return -int(new_state[5:])
else:
assert False, 'unknown new state %r' % new_state
elif isinstance(new_state, combined):
# combine a new state from existing ones
tmp_state = '_tmp_%d' % cls._tmpname
cls._tmpname += 1
itokens = []
for istate in new_state:
assert istate != new_state, 'circular state ref %r' % istate
itokens.extend(cls._process_state(unprocessed,
processed, istate))
processed[tmp_state] = itokens
return (tmp_state,)
elif isinstance(new_state, tuple):
# push more than one state
for istate in new_state:
assert (istate in unprocessed or
istate in ('#pop', '#push')), \
'unknown new state ' + istate
return new_state
else:
assert False, 'unknown new state def %r' % new_state
def _process_state(cls, unprocessed, processed, state):
"""Preprocess a single state definition."""
assert type(state) is str, "wrong state name %r" % state
assert state[0] != '#', "invalid state name %r" % state
if state in processed:
return processed[state]
tokens = processed[state] = []
rflags = cls.flags
for tdef in unprocessed[state]:
if isinstance(tdef, include):
# it's a state reference
assert tdef != state, "circular state reference %r" % state
tokens.extend(cls._process_state(unprocessed, processed,
str(tdef)))
continue
if isinstance(tdef, _inherit):
# should be processed already, but may not in the case of:
# 1. the state has no counterpart in any parent
# 2. the state includes more than one 'inherit'
continue
if isinstance(tdef, default):
new_state = cls._process_new_state(tdef.state, unprocessed, processed)
tokens.append((re.compile('').match, None, new_state))
continue
assert type(tdef) is tuple, "wrong rule def %r" % tdef
try:
rex = cls._process_regex(tdef[0], rflags, state)
except Exception as err:
raise ValueError("uncompilable regex %r in state %r of %r: %s" %
(tdef[0], state, cls, err)) from err
token = cls._process_token(tdef[1])
if len(tdef) == 2:
new_state = None
else:
new_state = cls._process_new_state(tdef[2],
unprocessed, processed)
tokens.append((rex, token, new_state))
return tokens
def process_tokendef(cls, name, tokendefs=None):
"""Preprocess a dictionary of token definitions."""
processed = cls._all_tokens[name] = {}
tokendefs = tokendefs or cls.tokens[name]
for state in list(tokendefs):
cls._process_state(tokendefs, processed, state)
return processed
def get_tokendefs(cls):
"""
Merge tokens from superclasses in MRO order, returning a single tokendef
dictionary.
Any state that is not defined by a subclass will be inherited
automatically. States that *are* defined by subclasses will, by
default, override that state in the superclass. If a subclass wishes to
inherit definitions from a superclass, it can use the special value
"inherit", which will cause the superclass' state definition to be
included at that point in the state.
"""
tokens = {}
inheritable = {}
for c in cls.__mro__:
toks = c.__dict__.get('tokens', {})
for state, items in toks.items():
curitems = tokens.get(state)
if curitems is None:
# N.b. because this is assigned by reference, sufficiently
# deep hierarchies are processed incrementally (e.g. for
# A(B), B(C), C(RegexLexer), B will be premodified so X(B)
# will not see any inherits in B).
tokens[state] = items
try:
inherit_ndx = items.index(inherit)
except ValueError:
continue
inheritable[state] = inherit_ndx
continue
inherit_ndx = inheritable.pop(state, None)
if inherit_ndx is None:
continue
# Replace the "inherit" value with the items
curitems[inherit_ndx:inherit_ndx+1] = items
try:
# N.b. this is the index in items (that is, the superclass
# copy), so offset required when storing below.
new_inh_ndx = items.index(inherit)
except ValueError:
pass
else:
inheritable[state] = inherit_ndx + new_inh_ndx
return tokens
def __call__(cls, *args, **kwds):
"""Instantiate cls after preprocessing its token definitions."""
if '_tokens' not in cls.__dict__:
cls._all_tokens = {}
cls._tmpname = 0
if hasattr(cls, 'token_variants') and cls.token_variants:
# don't process yet
pass
else:
cls._tokens = cls.process_tokendef('', cls.get_tokendefs())
return type.__call__(cls, *args, **kwds)
class RegexLexer(Lexer, metaclass=RegexLexerMeta):
"""
Base for simple stateful regular expression-based lexers.
Simplifies the lexing process so that you need only
provide a list of states and regular expressions.
"""
#: Flags for compiling the regular expressions.
#: Defaults to MULTILINE.
flags = re.MULTILINE
#: At all time there is a stack of states. Initially, the stack contains
#: a single state 'root'. The top of the stack is called "the current state".
#:
#: Dict of ``{'state': [(regex, tokentype, new_state), ...], ...}``
#:
#: ``new_state`` can be omitted to signify no state transition.
#: If ``new_state`` is a string, it is pushed on the stack. This ensure
#: the new current state is ``new_state``.
#: If ``new_state`` is a tuple of strings, all of those strings are pushed
#: on the stack and the current state will be the last element of the list.
#: ``new_state`` can also be ``combined('state1', 'state2', ...)``
#: to signify a new, anonymous state combined from the rules of two
#: or more existing ones.
#: Furthermore, it can be '#pop' to signify going back one step in
#: the state stack, or '#push' to push the current state on the stack
#: again. Note that if you push while in a combined state, the combined
#: state itself is pushed, and not only the state in which the rule is
#: defined.
#:
#: The tuple can also be replaced with ``include('state')``, in which
#: case the rules from the state named by the string are included in the
#: current one.
tokens = {}
def get_tokens_unprocessed(self, text, stack=('root',)):
"""
Split ``text`` into (tokentype, text) pairs.
``stack`` is the initial stack (default: ``['root']``)
"""
pos = 0
tokendefs = self._tokens
statestack = list(stack)
statetokens = tokendefs[statestack[-1]]
while 1:
for rexmatch, action, new_state in statetokens:
m = rexmatch(text, pos)
if m:
if action is not None:
if type(action) is _TokenType:
yield pos, action, m.group()
else:
yield from action(self, m)
pos = m.end()
if new_state is not None:
# state transition
if isinstance(new_state, tuple):
for state in new_state:
if state == '#pop':
if len(statestack) > 1:
statestack.pop()
elif state == '#push':
statestack.append(statestack[-1])
else:
statestack.append(state)
elif isinstance(new_state, int):
# pop, but keep at least one state on the stack
# (random code leading to unexpected pops should
# not allow exceptions)
if abs(new_state) >= len(statestack):
del statestack[1:]
else:
del statestack[new_state:]
elif new_state == '#push':
statestack.append(statestack[-1])
else:
assert False, "wrong state def: %r" % new_state
statetokens = tokendefs[statestack[-1]]
break
else:
# We are here only if all state tokens have been considered
# and there was not a match on any of them.
try:
if text[pos] == '\n':
# at EOL, reset state to "root"
statestack = ['root']
statetokens = tokendefs['root']
yield pos, Whitespace, '\n'
pos += 1
continue
yield pos, Error, text[pos]
pos += 1
except IndexError:
break
class LexerContext:
"""
A helper object that holds lexer position data.
"""
def __init__(self, text, pos, stack=None, end=None):
self.text = text
self.pos = pos
self.end = end or len(text) # end=0 not supported ;-)
self.stack = stack or ['root']
def __repr__(self):
return 'LexerContext(%r, %r, %r)' % (
self.text, self.pos, self.stack)
class ExtendedRegexLexer(RegexLexer):
"""
A RegexLexer that uses a context object to store its state.
"""
def get_tokens_unprocessed(self, text=None, context=None):
"""
Split ``text`` into (tokentype, text) pairs.
If ``context`` is given, use this lexer context instead.
"""
tokendefs = self._tokens
if not context:
ctx = LexerContext(text, 0)
statetokens = tokendefs['root']
else:
ctx = context
statetokens = tokendefs[ctx.stack[-1]]
text = ctx.text
while 1:
for rexmatch, action, new_state in statetokens:
m = rexmatch(text, ctx.pos, ctx.end)
if m:
if action is not None:
if type(action) is _TokenType:
yield ctx.pos, action, m.group()
ctx.pos = m.end()
else:
yield from action(self, m, ctx)
if not new_state:
# altered the state stack?
statetokens = tokendefs[ctx.stack[-1]]
# CAUTION: callback must set ctx.pos!
if new_state is not None:
# state transition
if isinstance(new_state, tuple):
for state in new_state:
if state == '#pop':
if len(ctx.stack) > 1:
ctx.stack.pop()
elif state == '#push':
ctx.stack.append(ctx.stack[-1])
else:
ctx.stack.append(state)
elif isinstance(new_state, int):
# see RegexLexer for why this check is made
if abs(new_state) >= len(ctx.stack):
del ctx.stack[1:]
else:
del ctx.stack[new_state:]
elif new_state == '#push':
ctx.stack.append(ctx.stack[-1])
else:
assert False, "wrong state def: %r" % new_state
statetokens = tokendefs[ctx.stack[-1]]
break
else:
try:
if ctx.pos >= ctx.end:
break
if text[ctx.pos] == '\n':
# at EOL, reset state to "root"
ctx.stack = ['root']
statetokens = tokendefs['root']
yield ctx.pos, Text, '\n'
ctx.pos += 1
continue
yield ctx.pos, Error, text[ctx.pos]
ctx.pos += 1
except IndexError:
break
def do_insertions(insertions, tokens):
"""
Helper for lexers which must combine the results of several
sublexers.
``insertions`` is a list of ``(index, itokens)`` pairs.
Each ``itokens`` iterable should be inserted at position
``index`` into the token stream given by the ``tokens``
argument.
The result is a combined token stream.
TODO: clean up the code here.
"""
insertions = iter(insertions)
try:
index, itokens = next(insertions)
except StopIteration:
# no insertions
yield from tokens
return
realpos = None
insleft = True
# iterate over the token stream where we want to insert
# the tokens from the insertion list.
for i, t, v in tokens:
# first iteration. store the position of first item
if realpos is None:
realpos = i
oldi = 0
while insleft and i + len(v) >= index:
tmpval = v[oldi:index - i]
if tmpval:
yield realpos, t, tmpval
realpos += len(tmpval)
for it_index, it_token, it_value in itokens:
yield realpos, it_token, it_value
realpos += len(it_value)
oldi = index - i
try:
index, itokens = next(insertions)
except StopIteration:
insleft = False
break # not strictly necessary
if oldi < len(v):
yield realpos, t, v[oldi:]
realpos += len(v) - oldi
# leftover tokens
while insleft:
# no normal tokens, set realpos to zero
realpos = realpos or 0
for p, t, v in itokens:
yield realpos, t, v
realpos += len(v)
try:
index, itokens = next(insertions)
except StopIteration:
insleft = False
break # not strictly necessary
class ProfilingRegexLexerMeta(RegexLexerMeta):
"""Metaclass for ProfilingRegexLexer, collects regex timing info."""
def _process_regex(cls, regex, rflags, state):
if isinstance(regex, words):
rex = regex_opt(regex.words, prefix=regex.prefix,
suffix=regex.suffix)
else:
rex = regex
compiled = re.compile(rex, rflags)
def match_func(text, pos, endpos=sys.maxsize):
info = cls._prof_data[-1].setdefault((state, rex), [0, 0.0])
t0 = time.time()
res = compiled.match(text, pos, endpos)
t1 = time.time()
info[0] += 1
info[1] += t1 - t0
return res
return match_func
class ProfilingRegexLexer(RegexLexer, metaclass=ProfilingRegexLexerMeta):
"""Drop-in replacement for RegexLexer that does profiling of its regexes."""
_prof_data = []
_prof_sort_index = 4 # defaults to time per call
def get_tokens_unprocessed(self, text, stack=('root',)):
# this needs to be a stack, since using(this) will produce nested calls
self.__class__._prof_data.append({})
yield from RegexLexer.get_tokens_unprocessed(self, text, stack)
rawdata = self.__class__._prof_data.pop()
data = sorted(((s, repr(r).strip('u\'').replace('\\\\', '\\')[:65],
n, 1000 * t, 1000 * t / n)
for ((s, r), (n, t)) in rawdata.items()),
key=lambda x: x[self._prof_sort_index],
reverse=True)
sum_total = sum(x[3] for x in data)
print()
print('Profiling result for %s lexing %d chars in %.3f ms' %
(self.__class__.__name__, len(text), sum_total))
print('=' * 110)
print('%-20s %-64s ncalls tottime percall' % ('state', 'regex'))
print('-' * 110)
for d in data:
print('%-20s %-65s %5d %8.4f %8.4f' % d)
print('=' * 110)

View file

@ -0,0 +1,362 @@
"""
pygments.lexers
~~~~~~~~~~~~~~~
Pygments lexers.
:copyright: Copyright 2006-2023 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 pip._vendor.pygments.lexers._mapping import LEXERS
from pip._vendor.pygments.modeline import get_filetype_from_buffer
from pip._vendor.pygments.plugin import find_plugin_lexers
from pip._vendor.pygments.util import ClassNotFound, guess_decode
COMPAT = {
'Python3Lexer': 'PythonLexer',
'Python3TracebackLexer': 'PythonTracebackLexer',
}
__all__ = ['get_lexer_by_name', 'get_lexer_for_filename', 'find_lexer_class',
'guess_lexer', 'load_lexer_from_file'] + list(LEXERS) + list(COMPAT)
_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(plugins=True):
"""Return a generator of tuples in the form ``(name, aliases,
filenames, mimetypes)`` of all know lexers.
If *plugins* is true (the default), plugin lexers supplied by entrypoints
are also returned. Otherwise, only builtin ones are considered.
"""
for item in LEXERS.values():
yield item[1:]
if plugins:
for lexer in find_plugin_lexers():
yield lexer.name, lexer.aliases, lexer.filenames, lexer.mimetypes
def find_lexer_class(name):
"""
Return the `Lexer` subclass that with the *name* attribute as given by
the *name* argument.
"""
if name in _lexer_cache:
return _lexer_cache[name]
# lookup builtin lexers
for module_name, lname, aliases, _, _ in LEXERS.values():
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 find_lexer_class_by_name(_alias):
"""
Return the `Lexer` subclass that has `alias` in its aliases list, without
instantiating it.
Like `get_lexer_by_name`, but does not instantiate the class.
Will raise :exc:`pygments.util.ClassNotFound` if no lexer with that alias is
found.
.. versionadded:: 2.2
"""
if not _alias:
raise ClassNotFound('no lexer for alias %r found' % _alias)
# lookup builtin lexers
for module_name, name, aliases, _, _ in LEXERS.values():
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 get_lexer_by_name(_alias, **options):
"""
Return an instance of a `Lexer` subclass that has `alias` in its
aliases list. The lexer is given the `options` at its
instantiation.
Will raise :exc:`pygments.util.ClassNotFound` if no lexer with that alias is
found.
"""
if not _alias:
raise ClassNotFound('no lexer for alias %r found' % _alias)
# lookup builtin lexers
for module_name, name, aliases, _, _ in LEXERS.values():
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 load_lexer_from_file(filename, lexername="CustomLexer", **options):
"""Load a lexer from a file.
This method expects a file located relative to the current working
directory, which contains a Lexer class. By default, it expects the
Lexer to be name CustomLexer; you can specify your own class name
as the second argument to this function.
Users should be very careful with the input, because this method
is equivalent to running eval on the input file.
Raises ClassNotFound if there are any problems importing the Lexer.
.. versionadded:: 2.2
"""
try:
# This empty dict will contain the namespace for the exec'd file
custom_namespace = {}
with open(filename, 'rb') as f:
exec(f.read(), custom_namespace)
# Retrieve the class `lexername` from that namespace
if lexername not in custom_namespace:
raise ClassNotFound('no valid %s class found in %s' %
(lexername, filename))
lexer_class = custom_namespace[lexername]
# And finally instantiate it with the options
return lexer_class(**options)
except OSError as err:
raise ClassNotFound('cannot read %s: %s' % (filename, err))
except ClassNotFound:
raise
except Exception as err:
raise ClassNotFound('error when loading custom lexer: %s' % err)
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]
def get_lexer_for_filename(_fn, code=None, **options):
"""Get a lexer for a filename.
Return a `Lexer` subclass instance that has a filename pattern
matching `fn`. The lexer is given the `options` at its
instantiation.
Raise :exc:`pygments.util.ClassNotFound` if no lexer for that filename
is found.
If multiple lexers match the filename pattern, use their ``analyse_text()``
methods to figure out which one is more appropriate.
"""
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):
"""
Return a `Lexer` subclass instance that has `mime` in its mimetype
list. The lexer is given the `options` at its instantiation.
Will raise :exc:`pygments.util.ClassNotFound` if not lexer for that mimetype
is found.
"""
for modname, name, _, _, mimetypes in LEXERS.values():
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:
yield from find_plugin_lexers()
def guess_lexer_for_filename(_fn, _text, **options):
"""
As :func:`guess_lexer()`, but only lexers which have a pattern in `filenames`
or `alias_filenames` that matches `filename` are taken into consideration.
:exc:`pygments.util.ClassNotFound` is raised if no lexer thinks it can
handle the content.
"""
fn = basename(_fn)
primary = {}
matching_lexers = set()
for lexer in _iter_lexerclasses():
for filename in lexer.filenames:
if _fn_matches(fn, filename):
matching_lexers.add(lexer)
primary[lexer] = True
for filename in lexer.alias_filenames:
if _fn_matches(fn, filename):
matching_lexers.add(lexer)
primary[lexer] = False
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))
def type_sort(t):
# sort by:
# - analyse score
# - is primary filename pattern?
# - priority
# - last resort: class name
return (t[0], primary[t[1]], t[1].priority, t[1].__name__)
result.sort(key=type_sort)
return result[-1][1](**options)
def guess_lexer(_text, **options):
"""
Return a `Lexer` subclass instance that's guessed from the text in
`text`. For that, the :meth:`.analyse_text()` method of every known lexer
class is called with the text as argument, and the lexer which returned the
highest value will be instantiated and returned.
:exc:`pygments.util.ClassNotFound` is raised if no lexer thinks it can
handle the content.
"""
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)
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
if name in COMPAT:
return getattr(self, COMPAT[name])
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

View file

@ -0,0 +1,559 @@
# Automatically generated by scripts/gen_mapfiles.py.
# DO NOT EDIT BY HAND; run `tox -e mapfiles` instead.
LEXERS = {
'ABAPLexer': ('pip._vendor.pygments.lexers.business', 'ABAP', ('abap',), ('*.abap', '*.ABAP'), ('text/x-abap',)),
'AMDGPULexer': ('pip._vendor.pygments.lexers.amdgpu', 'AMDGPU', ('amdgpu',), ('*.isa',), ()),
'APLLexer': ('pip._vendor.pygments.lexers.apl', 'APL', ('apl',), ('*.apl', '*.aplf', '*.aplo', '*.apln', '*.aplc', '*.apli', '*.dyalog'), ()),
'AbnfLexer': ('pip._vendor.pygments.lexers.grammar_notation', 'ABNF', ('abnf',), ('*.abnf',), ('text/x-abnf',)),
'ActionScript3Lexer': ('pip._vendor.pygments.lexers.actionscript', 'ActionScript 3', ('actionscript3', 'as3'), ('*.as',), ('application/x-actionscript3', 'text/x-actionscript3', 'text/actionscript3')),
'ActionScriptLexer': ('pip._vendor.pygments.lexers.actionscript', 'ActionScript', ('actionscript', 'as'), ('*.as',), ('application/x-actionscript', 'text/x-actionscript', 'text/actionscript')),
'AdaLexer': ('pip._vendor.pygments.lexers.ada', 'Ada', ('ada', 'ada95', 'ada2005'), ('*.adb', '*.ads', '*.ada'), ('text/x-ada',)),
'AdlLexer': ('pip._vendor.pygments.lexers.archetype', 'ADL', ('adl',), ('*.adl', '*.adls', '*.adlf', '*.adlx'), ()),
'AgdaLexer': ('pip._vendor.pygments.lexers.haskell', 'Agda', ('agda',), ('*.agda',), ('text/x-agda',)),
'AheuiLexer': ('pip._vendor.pygments.lexers.esoteric', 'Aheui', ('aheui',), ('*.aheui',), ()),
'AlloyLexer': ('pip._vendor.pygments.lexers.dsls', 'Alloy', ('alloy',), ('*.als',), ('text/x-alloy',)),
'AmbientTalkLexer': ('pip._vendor.pygments.lexers.ambient', 'AmbientTalk', ('ambienttalk', 'ambienttalk/2', 'at'), ('*.at',), ('text/x-ambienttalk',)),
'AmplLexer': ('pip._vendor.pygments.lexers.ampl', 'Ampl', ('ampl',), ('*.run',), ()),
'Angular2HtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML + Angular2', ('html+ng2',), ('*.ng2',), ()),
'Angular2Lexer': ('pip._vendor.pygments.lexers.templates', 'Angular2', ('ng2',), (), ()),
'AntlrActionScriptLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With ActionScript Target', ('antlr-actionscript', 'antlr-as'), ('*.G', '*.g'), ()),
'AntlrCSharpLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With C# Target', ('antlr-csharp', 'antlr-c#'), ('*.G', '*.g'), ()),
'AntlrCppLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With CPP Target', ('antlr-cpp',), ('*.G', '*.g'), ()),
'AntlrJavaLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With Java Target', ('antlr-java',), ('*.G', '*.g'), ()),
'AntlrLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR', ('antlr',), (), ()),
'AntlrObjectiveCLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With ObjectiveC Target', ('antlr-objc',), ('*.G', '*.g'), ()),
'AntlrPerlLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With Perl Target', ('antlr-perl',), ('*.G', '*.g'), ()),
'AntlrPythonLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With Python Target', ('antlr-python',), ('*.G', '*.g'), ()),
'AntlrRubyLexer': ('pip._vendor.pygments.lexers.parsers', 'ANTLR With Ruby Target', ('antlr-ruby', 'antlr-rb'), ('*.G', '*.g'), ()),
'ApacheConfLexer': ('pip._vendor.pygments.lexers.configs', 'ApacheConf', ('apacheconf', 'aconf', 'apache'), ('.htaccess', 'apache.conf', 'apache2.conf'), ('text/x-apacheconf',)),
'AppleScriptLexer': ('pip._vendor.pygments.lexers.scripting', 'AppleScript', ('applescript',), ('*.applescript',), ()),
'ArduinoLexer': ('pip._vendor.pygments.lexers.c_like', 'Arduino', ('arduino',), ('*.ino',), ('text/x-arduino',)),
'ArrowLexer': ('pip._vendor.pygments.lexers.arrow', 'Arrow', ('arrow',), ('*.arw',), ()),
'ArturoLexer': ('pip._vendor.pygments.lexers.arturo', 'Arturo', ('arturo', 'art'), ('*.art',), ()),
'AscLexer': ('pip._vendor.pygments.lexers.asc', 'ASCII armored', ('asc', 'pem'), ('*.asc', '*.pem', 'id_dsa', 'id_ecdsa', 'id_ecdsa_sk', 'id_ed25519', 'id_ed25519_sk', 'id_rsa'), ('application/pgp-keys', 'application/pgp-encrypted', 'application/pgp-signature')),
'AspectJLexer': ('pip._vendor.pygments.lexers.jvm', 'AspectJ', ('aspectj',), ('*.aj',), ('text/x-aspectj',)),
'AsymptoteLexer': ('pip._vendor.pygments.lexers.graphics', 'Asymptote', ('asymptote', 'asy'), ('*.asy',), ('text/x-asymptote',)),
'AugeasLexer': ('pip._vendor.pygments.lexers.configs', 'Augeas', ('augeas',), ('*.aug',), ()),
'AutoItLexer': ('pip._vendor.pygments.lexers.automation', 'AutoIt', ('autoit',), ('*.au3',), ('text/x-autoit',)),
'AutohotkeyLexer': ('pip._vendor.pygments.lexers.automation', 'autohotkey', ('autohotkey', 'ahk'), ('*.ahk', '*.ahkl'), ('text/x-autohotkey',)),
'AwkLexer': ('pip._vendor.pygments.lexers.textedit', 'Awk', ('awk', 'gawk', 'mawk', 'nawk'), ('*.awk',), ('application/x-awk',)),
'BBCBasicLexer': ('pip._vendor.pygments.lexers.basic', 'BBC Basic', ('bbcbasic',), ('*.bbc',), ()),
'BBCodeLexer': ('pip._vendor.pygments.lexers.markup', 'BBCode', ('bbcode',), (), ('text/x-bbcode',)),
'BCLexer': ('pip._vendor.pygments.lexers.algebra', 'BC', ('bc',), ('*.bc',), ()),
'BSTLexer': ('pip._vendor.pygments.lexers.bibtex', 'BST', ('bst', 'bst-pybtex'), ('*.bst',), ()),
'BareLexer': ('pip._vendor.pygments.lexers.bare', 'BARE', ('bare',), ('*.bare',), ()),
'BaseMakefileLexer': ('pip._vendor.pygments.lexers.make', 'Base Makefile', ('basemake',), (), ()),
'BashLexer': ('pip._vendor.pygments.lexers.shell', 'Bash', ('bash', 'sh', 'ksh', 'zsh', 'shell'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass', '*.exheres-0', '*.exlib', '*.zsh', '.bashrc', 'bashrc', '.bash_*', 'bash_*', 'zshrc', '.zshrc', '.kshrc', 'kshrc', 'PKGBUILD'), ('application/x-sh', 'application/x-shellscript', 'text/x-shellscript')),
'BashSessionLexer': ('pip._vendor.pygments.lexers.shell', 'Bash Session', ('console', 'shell-session'), ('*.sh-session', '*.shell-session'), ('application/x-shell-session', 'application/x-sh-session')),
'BatchLexer': ('pip._vendor.pygments.lexers.shell', 'Batchfile', ('batch', 'bat', 'dosbatch', 'winbatch'), ('*.bat', '*.cmd'), ('application/x-dos-batch',)),
'BddLexer': ('pip._vendor.pygments.lexers.bdd', 'Bdd', ('bdd',), ('*.feature',), ('text/x-bdd',)),
'BefungeLexer': ('pip._vendor.pygments.lexers.esoteric', 'Befunge', ('befunge',), ('*.befunge',), ('application/x-befunge',)),
'BerryLexer': ('pip._vendor.pygments.lexers.berry', 'Berry', ('berry', 'be'), ('*.be',), ('text/x-berry', 'application/x-berry')),
'BibTeXLexer': ('pip._vendor.pygments.lexers.bibtex', 'BibTeX', ('bibtex', 'bib'), ('*.bib',), ('text/x-bibtex',)),
'BlitzBasicLexer': ('pip._vendor.pygments.lexers.basic', 'BlitzBasic', ('blitzbasic', 'b3d', 'bplus'), ('*.bb', '*.decls'), ('text/x-bb',)),
'BlitzMaxLexer': ('pip._vendor.pygments.lexers.basic', 'BlitzMax', ('blitzmax', 'bmax'), ('*.bmx',), ('text/x-bmx',)),
'BnfLexer': ('pip._vendor.pygments.lexers.grammar_notation', 'BNF', ('bnf',), ('*.bnf',), ('text/x-bnf',)),
'BoaLexer': ('pip._vendor.pygments.lexers.boa', 'Boa', ('boa',), ('*.boa',), ()),
'BooLexer': ('pip._vendor.pygments.lexers.dotnet', 'Boo', ('boo',), ('*.boo',), ('text/x-boo',)),
'BoogieLexer': ('pip._vendor.pygments.lexers.verification', 'Boogie', ('boogie',), ('*.bpl',), ()),
'BrainfuckLexer': ('pip._vendor.pygments.lexers.esoteric', 'Brainfuck', ('brainfuck', 'bf'), ('*.bf', '*.b'), ('application/x-brainfuck',)),
'BugsLexer': ('pip._vendor.pygments.lexers.modeling', 'BUGS', ('bugs', 'winbugs', 'openbugs'), ('*.bug',), ()),
'CAmkESLexer': ('pip._vendor.pygments.lexers.esoteric', 'CAmkES', ('camkes', 'idl4'), ('*.camkes', '*.idl4'), ()),
'CLexer': ('pip._vendor.pygments.lexers.c_cpp', 'C', ('c',), ('*.c', '*.h', '*.idc', '*.x[bp]m'), ('text/x-chdr', 'text/x-csrc', 'image/x-xbitmap', 'image/x-xpixmap')),
'CMakeLexer': ('pip._vendor.pygments.lexers.make', 'CMake', ('cmake',), ('*.cmake', 'CMakeLists.txt'), ('text/x-cmake',)),
'CObjdumpLexer': ('pip._vendor.pygments.lexers.asm', 'c-objdump', ('c-objdump',), ('*.c-objdump',), ('text/x-c-objdump',)),
'CPSALexer': ('pip._vendor.pygments.lexers.lisp', 'CPSA', ('cpsa',), ('*.cpsa',), ()),
'CSSUL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'CSS+UL4', ('css+ul4',), ('*.cssul4',), ()),
'CSharpAspxLexer': ('pip._vendor.pygments.lexers.dotnet', 'aspx-cs', ('aspx-cs',), ('*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd'), ()),
'CSharpLexer': ('pip._vendor.pygments.lexers.dotnet', 'C#', ('csharp', 'c#', 'cs'), ('*.cs',), ('text/x-csharp',)),
'Ca65Lexer': ('pip._vendor.pygments.lexers.asm', 'ca65 assembler', ('ca65',), ('*.s',), ()),
'CadlLexer': ('pip._vendor.pygments.lexers.archetype', 'cADL', ('cadl',), ('*.cadl',), ()),
'CapDLLexer': ('pip._vendor.pygments.lexers.esoteric', 'CapDL', ('capdl',), ('*.cdl',), ()),
'CapnProtoLexer': ('pip._vendor.pygments.lexers.capnproto', "Cap'n Proto", ('capnp',), ('*.capnp',), ()),
'CarbonLexer': ('pip._vendor.pygments.lexers.carbon', 'Carbon', ('carbon',), ('*.carbon',), ('text/x-carbon',)),
'CbmBasicV2Lexer': ('pip._vendor.pygments.lexers.basic', 'CBM BASIC V2', ('cbmbas',), ('*.bas',), ()),
'CddlLexer': ('pip._vendor.pygments.lexers.cddl', 'CDDL', ('cddl',), ('*.cddl',), ('text/x-cddl',)),
'CeylonLexer': ('pip._vendor.pygments.lexers.jvm', 'Ceylon', ('ceylon',), ('*.ceylon',), ('text/x-ceylon',)),
'Cfengine3Lexer': ('pip._vendor.pygments.lexers.configs', 'CFEngine3', ('cfengine3', 'cf3'), ('*.cf',), ()),
'ChaiscriptLexer': ('pip._vendor.pygments.lexers.scripting', 'ChaiScript', ('chaiscript', 'chai'), ('*.chai',), ('text/x-chaiscript', 'application/x-chaiscript')),
'ChapelLexer': ('pip._vendor.pygments.lexers.chapel', 'Chapel', ('chapel', 'chpl'), ('*.chpl',), ()),
'CharmciLexer': ('pip._vendor.pygments.lexers.c_like', 'Charmci', ('charmci',), ('*.ci',), ()),
'CheetahHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Cheetah', ('html+cheetah', 'html+spitfire', 'htmlcheetah'), (), ('text/html+cheetah', 'text/html+spitfire')),
'CheetahJavascriptLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Cheetah', ('javascript+cheetah', 'js+cheetah', 'javascript+spitfire', 'js+spitfire'), (), ('application/x-javascript+cheetah', 'text/x-javascript+cheetah', 'text/javascript+cheetah', 'application/x-javascript+spitfire', 'text/x-javascript+spitfire', 'text/javascript+spitfire')),
'CheetahLexer': ('pip._vendor.pygments.lexers.templates', 'Cheetah', ('cheetah', 'spitfire'), ('*.tmpl', '*.spt'), ('application/x-cheetah', 'application/x-spitfire')),
'CheetahXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Cheetah', ('xml+cheetah', 'xml+spitfire'), (), ('application/xml+cheetah', 'application/xml+spitfire')),
'CirruLexer': ('pip._vendor.pygments.lexers.webmisc', 'Cirru', ('cirru',), ('*.cirru',), ('text/x-cirru',)),
'ClayLexer': ('pip._vendor.pygments.lexers.c_like', 'Clay', ('clay',), ('*.clay',), ('text/x-clay',)),
'CleanLexer': ('pip._vendor.pygments.lexers.clean', 'Clean', ('clean',), ('*.icl', '*.dcl'), ()),
'ClojureLexer': ('pip._vendor.pygments.lexers.jvm', 'Clojure', ('clojure', 'clj'), ('*.clj', '*.cljc'), ('text/x-clojure', 'application/x-clojure')),
'ClojureScriptLexer': ('pip._vendor.pygments.lexers.jvm', 'ClojureScript', ('clojurescript', 'cljs'), ('*.cljs',), ('text/x-clojurescript', 'application/x-clojurescript')),
'CobolFreeformatLexer': ('pip._vendor.pygments.lexers.business', 'COBOLFree', ('cobolfree',), ('*.cbl', '*.CBL'), ()),
'CobolLexer': ('pip._vendor.pygments.lexers.business', 'COBOL', ('cobol',), ('*.cob', '*.COB', '*.cpy', '*.CPY'), ('text/x-cobol',)),
'CoffeeScriptLexer': ('pip._vendor.pygments.lexers.javascript', 'CoffeeScript', ('coffeescript', 'coffee-script', 'coffee'), ('*.coffee',), ('text/coffeescript',)),
'ColdfusionCFCLexer': ('pip._vendor.pygments.lexers.templates', 'Coldfusion CFC', ('cfc',), ('*.cfc',), ()),
'ColdfusionHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'Coldfusion HTML', ('cfm',), ('*.cfm', '*.cfml'), ('application/x-coldfusion',)),
'ColdfusionLexer': ('pip._vendor.pygments.lexers.templates', 'cfstatement', ('cfs',), (), ()),
'Comal80Lexer': ('pip._vendor.pygments.lexers.comal', 'COMAL-80', ('comal', 'comal80'), ('*.cml', '*.comal'), ()),
'CommonLispLexer': ('pip._vendor.pygments.lexers.lisp', 'Common Lisp', ('common-lisp', 'cl', 'lisp'), ('*.cl', '*.lisp'), ('text/x-common-lisp',)),
'ComponentPascalLexer': ('pip._vendor.pygments.lexers.oberon', 'Component Pascal', ('componentpascal', 'cp'), ('*.cp', '*.cps'), ('text/x-component-pascal',)),
'CoqLexer': ('pip._vendor.pygments.lexers.theorem', 'Coq', ('coq',), ('*.v',), ('text/x-coq',)),
'CplintLexer': ('pip._vendor.pygments.lexers.cplint', 'cplint', ('cplint',), ('*.ecl', '*.prolog', '*.pro', '*.pl', '*.P', '*.lpad', '*.cpl'), ('text/x-cplint',)),
'CppLexer': ('pip._vendor.pygments.lexers.c_cpp', 'C++', ('cpp', 'c++'), ('*.cpp', '*.hpp', '*.c++', '*.h++', '*.cc', '*.hh', '*.cxx', '*.hxx', '*.C', '*.H', '*.cp', '*.CPP', '*.tpp'), ('text/x-c++hdr', 'text/x-c++src')),
'CppObjdumpLexer': ('pip._vendor.pygments.lexers.asm', 'cpp-objdump', ('cpp-objdump', 'c++-objdumb', 'cxx-objdump'), ('*.cpp-objdump', '*.c++-objdump', '*.cxx-objdump'), ('text/x-cpp-objdump',)),
'CrmshLexer': ('pip._vendor.pygments.lexers.dsls', 'Crmsh', ('crmsh', 'pcmk'), ('*.crmsh', '*.pcmk'), ()),
'CrocLexer': ('pip._vendor.pygments.lexers.d', 'Croc', ('croc',), ('*.croc',), ('text/x-crocsrc',)),
'CryptolLexer': ('pip._vendor.pygments.lexers.haskell', 'Cryptol', ('cryptol', 'cry'), ('*.cry',), ('text/x-cryptol',)),
'CrystalLexer': ('pip._vendor.pygments.lexers.crystal', 'Crystal', ('cr', 'crystal'), ('*.cr',), ('text/x-crystal',)),
'CsoundDocumentLexer': ('pip._vendor.pygments.lexers.csound', 'Csound Document', ('csound-document', 'csound-csd'), ('*.csd',), ()),
'CsoundOrchestraLexer': ('pip._vendor.pygments.lexers.csound', 'Csound Orchestra', ('csound', 'csound-orc'), ('*.orc', '*.udo'), ()),
'CsoundScoreLexer': ('pip._vendor.pygments.lexers.csound', 'Csound Score', ('csound-score', 'csound-sco'), ('*.sco',), ()),
'CssDjangoLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Django/Jinja', ('css+django', 'css+jinja'), ('*.css.j2', '*.css.jinja2'), ('text/css+django', 'text/css+jinja')),
'CssErbLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Ruby', ('css+ruby', 'css+erb'), (), ('text/css+ruby',)),
'CssGenshiLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Genshi Text', ('css+genshitext', 'css+genshi'), (), ('text/css+genshi',)),
'CssLexer': ('pip._vendor.pygments.lexers.css', 'CSS', ('css',), ('*.css',), ('text/css',)),
'CssPhpLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+PHP', ('css+php',), (), ('text/css+php',)),
'CssSmartyLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Smarty', ('css+smarty',), (), ('text/css+smarty',)),
'CudaLexer': ('pip._vendor.pygments.lexers.c_like', 'CUDA', ('cuda', 'cu'), ('*.cu', '*.cuh'), ('text/x-cuda',)),
'CypherLexer': ('pip._vendor.pygments.lexers.graph', 'Cypher', ('cypher',), ('*.cyp', '*.cypher'), ()),
'CythonLexer': ('pip._vendor.pygments.lexers.python', 'Cython', ('cython', 'pyx', 'pyrex'), ('*.pyx', '*.pxd', '*.pxi'), ('text/x-cython', 'application/x-cython')),
'DLexer': ('pip._vendor.pygments.lexers.d', 'D', ('d',), ('*.d', '*.di'), ('text/x-dsrc',)),
'DObjdumpLexer': ('pip._vendor.pygments.lexers.asm', 'd-objdump', ('d-objdump',), ('*.d-objdump',), ('text/x-d-objdump',)),
'DarcsPatchLexer': ('pip._vendor.pygments.lexers.diff', 'Darcs Patch', ('dpatch',), ('*.dpatch', '*.darcspatch'), ()),
'DartLexer': ('pip._vendor.pygments.lexers.javascript', 'Dart', ('dart',), ('*.dart',), ('text/x-dart',)),
'Dasm16Lexer': ('pip._vendor.pygments.lexers.asm', 'DASM16', ('dasm16',), ('*.dasm16', '*.dasm'), ('text/x-dasm16',)),
'DaxLexer': ('pip._vendor.pygments.lexers.dax', 'Dax', ('dax',), ('*.dax',), ()),
'DebianControlLexer': ('pip._vendor.pygments.lexers.installers', 'Debian Control file', ('debcontrol', 'control'), ('control',), ()),
'DelphiLexer': ('pip._vendor.pygments.lexers.pascal', 'Delphi', ('delphi', 'pas', 'pascal', 'objectpascal'), ('*.pas', '*.dpr'), ('text/x-pascal',)),
'DevicetreeLexer': ('pip._vendor.pygments.lexers.devicetree', 'Devicetree', ('devicetree', 'dts'), ('*.dts', '*.dtsi'), ('text/x-c',)),
'DgLexer': ('pip._vendor.pygments.lexers.python', 'dg', ('dg',), ('*.dg',), ('text/x-dg',)),
'DiffLexer': ('pip._vendor.pygments.lexers.diff', 'Diff', ('diff', 'udiff'), ('*.diff', '*.patch'), ('text/x-diff', 'text/x-patch')),
'DjangoLexer': ('pip._vendor.pygments.lexers.templates', 'Django/Jinja', ('django', 'jinja'), (), ('application/x-django-templating', 'application/x-jinja')),
'DockerLexer': ('pip._vendor.pygments.lexers.configs', 'Docker', ('docker', 'dockerfile'), ('Dockerfile', '*.docker'), ('text/x-dockerfile-config',)),
'DtdLexer': ('pip._vendor.pygments.lexers.html', 'DTD', ('dtd',), ('*.dtd',), ('application/xml-dtd',)),
'DuelLexer': ('pip._vendor.pygments.lexers.webmisc', 'Duel', ('duel', 'jbst', 'jsonml+bst'), ('*.duel', '*.jbst'), ('text/x-duel', 'text/x-jbst')),
'DylanConsoleLexer': ('pip._vendor.pygments.lexers.dylan', 'Dylan session', ('dylan-console', 'dylan-repl'), ('*.dylan-console',), ('text/x-dylan-console',)),
'DylanLexer': ('pip._vendor.pygments.lexers.dylan', 'Dylan', ('dylan',), ('*.dylan', '*.dyl', '*.intr'), ('text/x-dylan',)),
'DylanLidLexer': ('pip._vendor.pygments.lexers.dylan', 'DylanLID', ('dylan-lid', 'lid'), ('*.lid', '*.hdp'), ('text/x-dylan-lid',)),
'ECLLexer': ('pip._vendor.pygments.lexers.ecl', 'ECL', ('ecl',), ('*.ecl',), ('application/x-ecl',)),
'ECLexer': ('pip._vendor.pygments.lexers.c_like', 'eC', ('ec',), ('*.ec', '*.eh'), ('text/x-echdr', 'text/x-ecsrc')),
'EarlGreyLexer': ('pip._vendor.pygments.lexers.javascript', 'Earl Grey', ('earl-grey', 'earlgrey', 'eg'), ('*.eg',), ('text/x-earl-grey',)),
'EasytrieveLexer': ('pip._vendor.pygments.lexers.scripting', 'Easytrieve', ('easytrieve',), ('*.ezt', '*.mac'), ('text/x-easytrieve',)),
'EbnfLexer': ('pip._vendor.pygments.lexers.parsers', 'EBNF', ('ebnf',), ('*.ebnf',), ('text/x-ebnf',)),
'EiffelLexer': ('pip._vendor.pygments.lexers.eiffel', 'Eiffel', ('eiffel',), ('*.e',), ('text/x-eiffel',)),
'ElixirConsoleLexer': ('pip._vendor.pygments.lexers.erlang', 'Elixir iex session', ('iex',), (), ('text/x-elixir-shellsession',)),
'ElixirLexer': ('pip._vendor.pygments.lexers.erlang', 'Elixir', ('elixir', 'ex', 'exs'), ('*.ex', '*.eex', '*.exs', '*.leex'), ('text/x-elixir',)),
'ElmLexer': ('pip._vendor.pygments.lexers.elm', 'Elm', ('elm',), ('*.elm',), ('text/x-elm',)),
'ElpiLexer': ('pip._vendor.pygments.lexers.elpi', 'Elpi', ('elpi',), ('*.elpi',), ('text/x-elpi',)),
'EmacsLispLexer': ('pip._vendor.pygments.lexers.lisp', 'EmacsLisp', ('emacs-lisp', 'elisp', 'emacs'), ('*.el',), ('text/x-elisp', 'application/x-elisp')),
'EmailLexer': ('pip._vendor.pygments.lexers.email', 'E-mail', ('email', 'eml'), ('*.eml',), ('message/rfc822',)),
'ErbLexer': ('pip._vendor.pygments.lexers.templates', 'ERB', ('erb',), (), ('application/x-ruby-templating',)),
'ErlangLexer': ('pip._vendor.pygments.lexers.erlang', 'Erlang', ('erlang',), ('*.erl', '*.hrl', '*.es', '*.escript'), ('text/x-erlang',)),
'ErlangShellLexer': ('pip._vendor.pygments.lexers.erlang', 'Erlang erl session', ('erl',), ('*.erl-sh',), ('text/x-erl-shellsession',)),
'EvoqueHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Evoque', ('html+evoque',), ('*.html',), ('text/html+evoque',)),
'EvoqueLexer': ('pip._vendor.pygments.lexers.templates', 'Evoque', ('evoque',), ('*.evoque',), ('application/x-evoque',)),
'EvoqueXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Evoque', ('xml+evoque',), ('*.xml',), ('application/xml+evoque',)),
'ExeclineLexer': ('pip._vendor.pygments.lexers.shell', 'execline', ('execline',), ('*.exec',), ()),
'EzhilLexer': ('pip._vendor.pygments.lexers.ezhil', 'Ezhil', ('ezhil',), ('*.n',), ('text/x-ezhil',)),
'FSharpLexer': ('pip._vendor.pygments.lexers.dotnet', 'F#', ('fsharp', 'f#'), ('*.fs', '*.fsi', '*.fsx'), ('text/x-fsharp',)),
'FStarLexer': ('pip._vendor.pygments.lexers.ml', 'FStar', ('fstar',), ('*.fst', '*.fsti'), ('text/x-fstar',)),
'FactorLexer': ('pip._vendor.pygments.lexers.factor', 'Factor', ('factor',), ('*.factor',), ('text/x-factor',)),
'FancyLexer': ('pip._vendor.pygments.lexers.ruby', 'Fancy', ('fancy', 'fy'), ('*.fy', '*.fancypack'), ('text/x-fancysrc',)),
'FantomLexer': ('pip._vendor.pygments.lexers.fantom', 'Fantom', ('fan',), ('*.fan',), ('application/x-fantom',)),
'FelixLexer': ('pip._vendor.pygments.lexers.felix', 'Felix', ('felix', 'flx'), ('*.flx', '*.flxh'), ('text/x-felix',)),
'FennelLexer': ('pip._vendor.pygments.lexers.lisp', 'Fennel', ('fennel', 'fnl'), ('*.fnl',), ()),
'FiftLexer': ('pip._vendor.pygments.lexers.fift', 'Fift', ('fift', 'fif'), ('*.fif',), ()),
'FishShellLexer': ('pip._vendor.pygments.lexers.shell', 'Fish', ('fish', 'fishshell'), ('*.fish', '*.load'), ('application/x-fish',)),
'FlatlineLexer': ('pip._vendor.pygments.lexers.dsls', 'Flatline', ('flatline',), (), ('text/x-flatline',)),
'FloScriptLexer': ('pip._vendor.pygments.lexers.floscript', 'FloScript', ('floscript', 'flo'), ('*.flo',), ()),
'ForthLexer': ('pip._vendor.pygments.lexers.forth', 'Forth', ('forth',), ('*.frt', '*.fs'), ('application/x-forth',)),
'FortranFixedLexer': ('pip._vendor.pygments.lexers.fortran', 'FortranFixed', ('fortranfixed',), ('*.f', '*.F'), ()),
'FortranLexer': ('pip._vendor.pygments.lexers.fortran', 'Fortran', ('fortran', 'f90'), ('*.f03', '*.f90', '*.F03', '*.F90'), ('text/x-fortran',)),
'FoxProLexer': ('pip._vendor.pygments.lexers.foxpro', 'FoxPro', ('foxpro', 'vfp', 'clipper', 'xbase'), ('*.PRG', '*.prg'), ()),
'FreeFemLexer': ('pip._vendor.pygments.lexers.freefem', 'Freefem', ('freefem',), ('*.edp',), ('text/x-freefem',)),
'FuncLexer': ('pip._vendor.pygments.lexers.func', 'FunC', ('func', 'fc'), ('*.fc', '*.func'), ()),
'FutharkLexer': ('pip._vendor.pygments.lexers.futhark', 'Futhark', ('futhark',), ('*.fut',), ('text/x-futhark',)),
'GAPConsoleLexer': ('pip._vendor.pygments.lexers.algebra', 'GAP session', ('gap-console', 'gap-repl'), ('*.tst',), ()),
'GAPLexer': ('pip._vendor.pygments.lexers.algebra', 'GAP', ('gap',), ('*.g', '*.gd', '*.gi', '*.gap'), ()),
'GDScriptLexer': ('pip._vendor.pygments.lexers.gdscript', 'GDScript', ('gdscript', 'gd'), ('*.gd',), ('text/x-gdscript', 'application/x-gdscript')),
'GLShaderLexer': ('pip._vendor.pygments.lexers.graphics', 'GLSL', ('glsl',), ('*.vert', '*.frag', '*.geo'), ('text/x-glslsrc',)),
'GSQLLexer': ('pip._vendor.pygments.lexers.gsql', 'GSQL', ('gsql',), ('*.gsql',), ()),
'GasLexer': ('pip._vendor.pygments.lexers.asm', 'GAS', ('gas', 'asm'), ('*.s', '*.S'), ('text/x-gas',)),
'GcodeLexer': ('pip._vendor.pygments.lexers.gcodelexer', 'g-code', ('gcode',), ('*.gcode',), ()),
'GenshiLexer': ('pip._vendor.pygments.lexers.templates', 'Genshi', ('genshi', 'kid', 'xml+genshi', 'xml+kid'), ('*.kid',), ('application/x-genshi', 'application/x-kid')),
'GenshiTextLexer': ('pip._vendor.pygments.lexers.templates', 'Genshi Text', ('genshitext',), (), ('application/x-genshi-text', 'text/x-genshi')),
'GettextLexer': ('pip._vendor.pygments.lexers.textfmts', 'Gettext Catalog', ('pot', 'po'), ('*.pot', '*.po'), ('application/x-gettext', 'text/x-gettext', 'text/gettext')),
'GherkinLexer': ('pip._vendor.pygments.lexers.testing', 'Gherkin', ('gherkin', 'cucumber'), ('*.feature',), ('text/x-gherkin',)),
'GnuplotLexer': ('pip._vendor.pygments.lexers.graphics', 'Gnuplot', ('gnuplot',), ('*.plot', '*.plt'), ('text/x-gnuplot',)),
'GoLexer': ('pip._vendor.pygments.lexers.go', 'Go', ('go', 'golang'), ('*.go',), ('text/x-gosrc',)),
'GoloLexer': ('pip._vendor.pygments.lexers.jvm', 'Golo', ('golo',), ('*.golo',), ()),
'GoodDataCLLexer': ('pip._vendor.pygments.lexers.business', 'GoodData-CL', ('gooddata-cl',), ('*.gdc',), ('text/x-gooddata-cl',)),
'GosuLexer': ('pip._vendor.pygments.lexers.jvm', 'Gosu', ('gosu',), ('*.gs', '*.gsx', '*.gsp', '*.vark'), ('text/x-gosu',)),
'GosuTemplateLexer': ('pip._vendor.pygments.lexers.jvm', 'Gosu Template', ('gst',), ('*.gst',), ('text/x-gosu-template',)),
'GraphvizLexer': ('pip._vendor.pygments.lexers.graphviz', 'Graphviz', ('graphviz', 'dot'), ('*.gv', '*.dot'), ('text/x-graphviz', 'text/vnd.graphviz')),
'GroffLexer': ('pip._vendor.pygments.lexers.markup', 'Groff', ('groff', 'nroff', 'man'), ('*.[1-9]', '*.man', '*.1p', '*.3pm'), ('application/x-troff', 'text/troff')),
'GroovyLexer': ('pip._vendor.pygments.lexers.jvm', 'Groovy', ('groovy',), ('*.groovy', '*.gradle'), ('text/x-groovy',)),
'HLSLShaderLexer': ('pip._vendor.pygments.lexers.graphics', 'HLSL', ('hlsl',), ('*.hlsl', '*.hlsli'), ('text/x-hlsl',)),
'HTMLUL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'HTML+UL4', ('html+ul4',), ('*.htmlul4',), ()),
'HamlLexer': ('pip._vendor.pygments.lexers.html', 'Haml', ('haml',), ('*.haml',), ('text/x-haml',)),
'HandlebarsHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Handlebars', ('html+handlebars',), ('*.handlebars', '*.hbs'), ('text/html+handlebars', 'text/x-handlebars-template')),
'HandlebarsLexer': ('pip._vendor.pygments.lexers.templates', 'Handlebars', ('handlebars',), (), ()),
'HaskellLexer': ('pip._vendor.pygments.lexers.haskell', 'Haskell', ('haskell', 'hs'), ('*.hs',), ('text/x-haskell',)),
'HaxeLexer': ('pip._vendor.pygments.lexers.haxe', 'Haxe', ('haxe', 'hxsl', 'hx'), ('*.hx', '*.hxsl'), ('text/haxe', 'text/x-haxe', 'text/x-hx')),
'HexdumpLexer': ('pip._vendor.pygments.lexers.hexdump', 'Hexdump', ('hexdump',), (), ()),
'HsailLexer': ('pip._vendor.pygments.lexers.asm', 'HSAIL', ('hsail', 'hsa'), ('*.hsail',), ('text/x-hsail',)),
'HspecLexer': ('pip._vendor.pygments.lexers.haskell', 'Hspec', ('hspec',), ('*Spec.hs',), ()),
'HtmlDjangoLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Django/Jinja', ('html+django', 'html+jinja', 'htmldjango'), ('*.html.j2', '*.htm.j2', '*.xhtml.j2', '*.html.jinja2', '*.htm.jinja2', '*.xhtml.jinja2'), ('text/html+django', 'text/html+jinja')),
'HtmlGenshiLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Genshi', ('html+genshi', 'html+kid'), (), ('text/html+genshi',)),
'HtmlLexer': ('pip._vendor.pygments.lexers.html', 'HTML', ('html',), ('*.html', '*.htm', '*.xhtml', '*.xslt'), ('text/html', 'application/xhtml+xml')),
'HtmlPhpLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+PHP', ('html+php',), ('*.phtml',), ('application/x-php', 'application/x-httpd-php', 'application/x-httpd-php3', 'application/x-httpd-php4', 'application/x-httpd-php5')),
'HtmlSmartyLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Smarty', ('html+smarty',), (), ('text/html+smarty',)),
'HttpLexer': ('pip._vendor.pygments.lexers.textfmts', 'HTTP', ('http',), (), ()),
'HxmlLexer': ('pip._vendor.pygments.lexers.haxe', 'Hxml', ('haxeml', 'hxml'), ('*.hxml',), ()),
'HyLexer': ('pip._vendor.pygments.lexers.lisp', 'Hy', ('hylang',), ('*.hy',), ('text/x-hy', 'application/x-hy')),
'HybrisLexer': ('pip._vendor.pygments.lexers.scripting', 'Hybris', ('hybris', 'hy'), ('*.hy', '*.hyb'), ('text/x-hybris', 'application/x-hybris')),
'IDLLexer': ('pip._vendor.pygments.lexers.idl', 'IDL', ('idl',), ('*.pro',), ('text/idl',)),
'IconLexer': ('pip._vendor.pygments.lexers.unicon', 'Icon', ('icon',), ('*.icon', '*.ICON'), ()),
'IdrisLexer': ('pip._vendor.pygments.lexers.haskell', 'Idris', ('idris', 'idr'), ('*.idr',), ('text/x-idris',)),
'IgorLexer': ('pip._vendor.pygments.lexers.igor', 'Igor', ('igor', 'igorpro'), ('*.ipf',), ('text/ipf',)),
'Inform6Lexer': ('pip._vendor.pygments.lexers.int_fiction', 'Inform 6', ('inform6', 'i6'), ('*.inf',), ()),
'Inform6TemplateLexer': ('pip._vendor.pygments.lexers.int_fiction', 'Inform 6 template', ('i6t',), ('*.i6t',), ()),
'Inform7Lexer': ('pip._vendor.pygments.lexers.int_fiction', 'Inform 7', ('inform7', 'i7'), ('*.ni', '*.i7x'), ()),
'IniLexer': ('pip._vendor.pygments.lexers.configs', 'INI', ('ini', 'cfg', 'dosini'), ('*.ini', '*.cfg', '*.inf', '.editorconfig', '*.service', '*.socket', '*.device', '*.mount', '*.automount', '*.swap', '*.target', '*.path', '*.timer', '*.slice', '*.scope'), ('text/x-ini', 'text/inf')),
'IoLexer': ('pip._vendor.pygments.lexers.iolang', 'Io', ('io',), ('*.io',), ('text/x-iosrc',)),
'IokeLexer': ('pip._vendor.pygments.lexers.jvm', 'Ioke', ('ioke', 'ik'), ('*.ik',), ('text/x-iokesrc',)),
'IrcLogsLexer': ('pip._vendor.pygments.lexers.textfmts', 'IRC logs', ('irc',), ('*.weechatlog',), ('text/x-irclog',)),
'IsabelleLexer': ('pip._vendor.pygments.lexers.theorem', 'Isabelle', ('isabelle',), ('*.thy',), ('text/x-isabelle',)),
'JLexer': ('pip._vendor.pygments.lexers.j', 'J', ('j',), ('*.ijs',), ('text/x-j',)),
'JMESPathLexer': ('pip._vendor.pygments.lexers.jmespath', 'JMESPath', ('jmespath', 'jp'), ('*.jp',), ()),
'JSLTLexer': ('pip._vendor.pygments.lexers.jslt', 'JSLT', ('jslt',), ('*.jslt',), ('text/x-jslt',)),
'JagsLexer': ('pip._vendor.pygments.lexers.modeling', 'JAGS', ('jags',), ('*.jag', '*.bug'), ()),
'JasminLexer': ('pip._vendor.pygments.lexers.jvm', 'Jasmin', ('jasmin', 'jasminxt'), ('*.j',), ()),
'JavaLexer': ('pip._vendor.pygments.lexers.jvm', 'Java', ('java',), ('*.java',), ('text/x-java',)),
'JavascriptDjangoLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Django/Jinja', ('javascript+django', 'js+django', 'javascript+jinja', 'js+jinja'), ('*.js.j2', '*.js.jinja2'), ('application/x-javascript+django', 'application/x-javascript+jinja', 'text/x-javascript+django', 'text/x-javascript+jinja', 'text/javascript+django', 'text/javascript+jinja')),
'JavascriptErbLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Ruby', ('javascript+ruby', 'js+ruby', 'javascript+erb', 'js+erb'), (), ('application/x-javascript+ruby', 'text/x-javascript+ruby', 'text/javascript+ruby')),
'JavascriptGenshiLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Genshi Text', ('js+genshitext', 'js+genshi', 'javascript+genshitext', 'javascript+genshi'), (), ('application/x-javascript+genshi', 'text/x-javascript+genshi', 'text/javascript+genshi')),
'JavascriptLexer': ('pip._vendor.pygments.lexers.javascript', 'JavaScript', ('javascript', 'js'), ('*.js', '*.jsm', '*.mjs', '*.cjs'), ('application/javascript', 'application/x-javascript', 'text/x-javascript', 'text/javascript')),
'JavascriptPhpLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+PHP', ('javascript+php', 'js+php'), (), ('application/x-javascript+php', 'text/x-javascript+php', 'text/javascript+php')),
'JavascriptSmartyLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Smarty', ('javascript+smarty', 'js+smarty'), (), ('application/x-javascript+smarty', 'text/x-javascript+smarty', 'text/javascript+smarty')),
'JavascriptUL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'Javascript+UL4', ('js+ul4',), ('*.jsul4',), ()),
'JclLexer': ('pip._vendor.pygments.lexers.scripting', 'JCL', ('jcl',), ('*.jcl',), ('text/x-jcl',)),
'JsgfLexer': ('pip._vendor.pygments.lexers.grammar_notation', 'JSGF', ('jsgf',), ('*.jsgf',), ('application/jsgf', 'application/x-jsgf', 'text/jsgf')),
'JsonBareObjectLexer': ('pip._vendor.pygments.lexers.data', 'JSONBareObject', (), (), ()),
'JsonLdLexer': ('pip._vendor.pygments.lexers.data', 'JSON-LD', ('jsonld', 'json-ld'), ('*.jsonld',), ('application/ld+json',)),
'JsonLexer': ('pip._vendor.pygments.lexers.data', 'JSON', ('json', 'json-object'), ('*.json', 'Pipfile.lock'), ('application/json', 'application/json-object')),
'JsonnetLexer': ('pip._vendor.pygments.lexers.jsonnet', 'Jsonnet', ('jsonnet',), ('*.jsonnet', '*.libsonnet'), ()),
'JspLexer': ('pip._vendor.pygments.lexers.templates', 'Java Server Page', ('jsp',), ('*.jsp',), ('application/x-jsp',)),
'JuliaConsoleLexer': ('pip._vendor.pygments.lexers.julia', 'Julia console', ('jlcon', 'julia-repl'), (), ()),
'JuliaLexer': ('pip._vendor.pygments.lexers.julia', 'Julia', ('julia', 'jl'), ('*.jl',), ('text/x-julia', 'application/x-julia')),
'JuttleLexer': ('pip._vendor.pygments.lexers.javascript', 'Juttle', ('juttle',), ('*.juttle',), ('application/juttle', 'application/x-juttle', 'text/x-juttle', 'text/juttle')),
'KLexer': ('pip._vendor.pygments.lexers.q', 'K', ('k',), ('*.k',), ()),
'KalLexer': ('pip._vendor.pygments.lexers.javascript', 'Kal', ('kal',), ('*.kal',), ('text/kal', 'application/kal')),
'KconfigLexer': ('pip._vendor.pygments.lexers.configs', 'Kconfig', ('kconfig', 'menuconfig', 'linux-config', 'kernel-config'), ('Kconfig*', '*Config.in*', 'external.in*', 'standard-modules.in'), ('text/x-kconfig',)),
'KernelLogLexer': ('pip._vendor.pygments.lexers.textfmts', 'Kernel log', ('kmsg', 'dmesg'), ('*.kmsg', '*.dmesg'), ()),
'KokaLexer': ('pip._vendor.pygments.lexers.haskell', 'Koka', ('koka',), ('*.kk', '*.kki'), ('text/x-koka',)),
'KotlinLexer': ('pip._vendor.pygments.lexers.jvm', 'Kotlin', ('kotlin',), ('*.kt', '*.kts'), ('text/x-kotlin',)),
'KuinLexer': ('pip._vendor.pygments.lexers.kuin', 'Kuin', ('kuin',), ('*.kn',), ()),
'LSLLexer': ('pip._vendor.pygments.lexers.scripting', 'LSL', ('lsl',), ('*.lsl',), ('text/x-lsl',)),
'LassoCssLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Lasso', ('css+lasso',), (), ('text/css+lasso',)),
'LassoHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Lasso', ('html+lasso',), (), ('text/html+lasso', 'application/x-httpd-lasso', 'application/x-httpd-lasso[89]')),
'LassoJavascriptLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Lasso', ('javascript+lasso', 'js+lasso'), (), ('application/x-javascript+lasso', 'text/x-javascript+lasso', 'text/javascript+lasso')),
'LassoLexer': ('pip._vendor.pygments.lexers.javascript', 'Lasso', ('lasso', 'lassoscript'), ('*.lasso', '*.lasso[89]'), ('text/x-lasso',)),
'LassoXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Lasso', ('xml+lasso',), (), ('application/xml+lasso',)),
'LeanLexer': ('pip._vendor.pygments.lexers.theorem', 'Lean', ('lean',), ('*.lean',), ('text/x-lean',)),
'LessCssLexer': ('pip._vendor.pygments.lexers.css', 'LessCss', ('less',), ('*.less',), ('text/x-less-css',)),
'LighttpdConfLexer': ('pip._vendor.pygments.lexers.configs', 'Lighttpd configuration file', ('lighttpd', 'lighty'), ('lighttpd.conf',), ('text/x-lighttpd-conf',)),
'LilyPondLexer': ('pip._vendor.pygments.lexers.lilypond', 'LilyPond', ('lilypond',), ('*.ly',), ()),
'LimboLexer': ('pip._vendor.pygments.lexers.inferno', 'Limbo', ('limbo',), ('*.b',), ('text/limbo',)),
'LiquidLexer': ('pip._vendor.pygments.lexers.templates', 'liquid', ('liquid',), ('*.liquid',), ()),
'LiterateAgdaLexer': ('pip._vendor.pygments.lexers.haskell', 'Literate Agda', ('literate-agda', 'lagda'), ('*.lagda',), ('text/x-literate-agda',)),
'LiterateCryptolLexer': ('pip._vendor.pygments.lexers.haskell', 'Literate Cryptol', ('literate-cryptol', 'lcryptol', 'lcry'), ('*.lcry',), ('text/x-literate-cryptol',)),
'LiterateHaskellLexer': ('pip._vendor.pygments.lexers.haskell', 'Literate Haskell', ('literate-haskell', 'lhaskell', 'lhs'), ('*.lhs',), ('text/x-literate-haskell',)),
'LiterateIdrisLexer': ('pip._vendor.pygments.lexers.haskell', 'Literate Idris', ('literate-idris', 'lidris', 'lidr'), ('*.lidr',), ('text/x-literate-idris',)),
'LiveScriptLexer': ('pip._vendor.pygments.lexers.javascript', 'LiveScript', ('livescript', 'live-script'), ('*.ls',), ('text/livescript',)),
'LlvmLexer': ('pip._vendor.pygments.lexers.asm', 'LLVM', ('llvm',), ('*.ll',), ('text/x-llvm',)),
'LlvmMirBodyLexer': ('pip._vendor.pygments.lexers.asm', 'LLVM-MIR Body', ('llvm-mir-body',), (), ()),
'LlvmMirLexer': ('pip._vendor.pygments.lexers.asm', 'LLVM-MIR', ('llvm-mir',), ('*.mir',), ()),
'LogosLexer': ('pip._vendor.pygments.lexers.objective', 'Logos', ('logos',), ('*.x', '*.xi', '*.xm', '*.xmi'), ('text/x-logos',)),
'LogtalkLexer': ('pip._vendor.pygments.lexers.prolog', 'Logtalk', ('logtalk',), ('*.lgt', '*.logtalk'), ('text/x-logtalk',)),
'LuaLexer': ('pip._vendor.pygments.lexers.scripting', 'Lua', ('lua',), ('*.lua', '*.wlua'), ('text/x-lua', 'application/x-lua')),
'MCFunctionLexer': ('pip._vendor.pygments.lexers.minecraft', 'MCFunction', ('mcfunction', 'mcf'), ('*.mcfunction',), ('text/mcfunction',)),
'MCSchemaLexer': ('pip._vendor.pygments.lexers.minecraft', 'MCSchema', ('mcschema',), ('*.mcschema',), ('text/mcschema',)),
'MIMELexer': ('pip._vendor.pygments.lexers.mime', 'MIME', ('mime',), (), ('multipart/mixed', 'multipart/related', 'multipart/alternative')),
'MIPSLexer': ('pip._vendor.pygments.lexers.mips', 'MIPS', ('mips',), ('*.mips', '*.MIPS'), ()),
'MOOCodeLexer': ('pip._vendor.pygments.lexers.scripting', 'MOOCode', ('moocode', 'moo'), ('*.moo',), ('text/x-moocode',)),
'MSDOSSessionLexer': ('pip._vendor.pygments.lexers.shell', 'MSDOS Session', ('doscon',), (), ()),
'Macaulay2Lexer': ('pip._vendor.pygments.lexers.macaulay2', 'Macaulay2', ('macaulay2',), ('*.m2',), ()),
'MakefileLexer': ('pip._vendor.pygments.lexers.make', 'Makefile', ('make', 'makefile', 'mf', 'bsdmake'), ('*.mak', '*.mk', 'Makefile', 'makefile', 'Makefile.*', 'GNUmakefile'), ('text/x-makefile',)),
'MakoCssLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Mako', ('css+mako',), (), ('text/css+mako',)),
'MakoHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Mako', ('html+mako',), (), ('text/html+mako',)),
'MakoJavascriptLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Mako', ('javascript+mako', 'js+mako'), (), ('application/x-javascript+mako', 'text/x-javascript+mako', 'text/javascript+mako')),
'MakoLexer': ('pip._vendor.pygments.lexers.templates', 'Mako', ('mako',), ('*.mao',), ('application/x-mako',)),
'MakoXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Mako', ('xml+mako',), (), ('application/xml+mako',)),
'MaqlLexer': ('pip._vendor.pygments.lexers.business', 'MAQL', ('maql',), ('*.maql',), ('text/x-gooddata-maql', 'application/x-gooddata-maql')),
'MarkdownLexer': ('pip._vendor.pygments.lexers.markup', 'Markdown', ('markdown', 'md'), ('*.md', '*.markdown'), ('text/x-markdown',)),
'MaskLexer': ('pip._vendor.pygments.lexers.javascript', 'Mask', ('mask',), ('*.mask',), ('text/x-mask',)),
'MasonLexer': ('pip._vendor.pygments.lexers.templates', 'Mason', ('mason',), ('*.m', '*.mhtml', '*.mc', '*.mi', 'autohandler', 'dhandler'), ('application/x-mason',)),
'MathematicaLexer': ('pip._vendor.pygments.lexers.algebra', 'Mathematica', ('mathematica', 'mma', 'nb'), ('*.nb', '*.cdf', '*.nbp', '*.ma'), ('application/mathematica', 'application/vnd.wolfram.mathematica', 'application/vnd.wolfram.mathematica.package', 'application/vnd.wolfram.cdf')),
'MatlabLexer': ('pip._vendor.pygments.lexers.matlab', 'Matlab', ('matlab',), ('*.m',), ('text/matlab',)),
'MatlabSessionLexer': ('pip._vendor.pygments.lexers.matlab', 'Matlab session', ('matlabsession',), (), ()),
'MaximaLexer': ('pip._vendor.pygments.lexers.maxima', 'Maxima', ('maxima', 'macsyma'), ('*.mac', '*.max'), ()),
'MesonLexer': ('pip._vendor.pygments.lexers.meson', 'Meson', ('meson', 'meson.build'), ('meson.build', 'meson_options.txt'), ('text/x-meson',)),
'MiniDLexer': ('pip._vendor.pygments.lexers.d', 'MiniD', ('minid',), (), ('text/x-minidsrc',)),
'MiniScriptLexer': ('pip._vendor.pygments.lexers.scripting', 'MiniScript', ('miniscript', 'ms'), ('*.ms',), ('text/x-minicript', 'application/x-miniscript')),
'ModelicaLexer': ('pip._vendor.pygments.lexers.modeling', 'Modelica', ('modelica',), ('*.mo',), ('text/x-modelica',)),
'Modula2Lexer': ('pip._vendor.pygments.lexers.modula2', 'Modula-2', ('modula2', 'm2'), ('*.def', '*.mod'), ('text/x-modula2',)),
'MoinWikiLexer': ('pip._vendor.pygments.lexers.markup', 'MoinMoin/Trac Wiki markup', ('trac-wiki', 'moin'), (), ('text/x-trac-wiki',)),
'MonkeyLexer': ('pip._vendor.pygments.lexers.basic', 'Monkey', ('monkey',), ('*.monkey',), ('text/x-monkey',)),
'MonteLexer': ('pip._vendor.pygments.lexers.monte', 'Monte', ('monte',), ('*.mt',), ()),
'MoonScriptLexer': ('pip._vendor.pygments.lexers.scripting', 'MoonScript', ('moonscript', 'moon'), ('*.moon',), ('text/x-moonscript', 'application/x-moonscript')),
'MoselLexer': ('pip._vendor.pygments.lexers.mosel', 'Mosel', ('mosel',), ('*.mos',), ()),
'MozPreprocCssLexer': ('pip._vendor.pygments.lexers.markup', 'CSS+mozpreproc', ('css+mozpreproc',), ('*.css.in',), ()),
'MozPreprocHashLexer': ('pip._vendor.pygments.lexers.markup', 'mozhashpreproc', ('mozhashpreproc',), (), ()),
'MozPreprocJavascriptLexer': ('pip._vendor.pygments.lexers.markup', 'Javascript+mozpreproc', ('javascript+mozpreproc',), ('*.js.in',), ()),
'MozPreprocPercentLexer': ('pip._vendor.pygments.lexers.markup', 'mozpercentpreproc', ('mozpercentpreproc',), (), ()),
'MozPreprocXulLexer': ('pip._vendor.pygments.lexers.markup', 'XUL+mozpreproc', ('xul+mozpreproc',), ('*.xul.in',), ()),
'MqlLexer': ('pip._vendor.pygments.lexers.c_like', 'MQL', ('mql', 'mq4', 'mq5', 'mql4', 'mql5'), ('*.mq4', '*.mq5', '*.mqh'), ('text/x-mql',)),
'MscgenLexer': ('pip._vendor.pygments.lexers.dsls', 'Mscgen', ('mscgen', 'msc'), ('*.msc',), ()),
'MuPADLexer': ('pip._vendor.pygments.lexers.algebra', 'MuPAD', ('mupad',), ('*.mu',), ()),
'MxmlLexer': ('pip._vendor.pygments.lexers.actionscript', 'MXML', ('mxml',), ('*.mxml',), ()),
'MySqlLexer': ('pip._vendor.pygments.lexers.sql', 'MySQL', ('mysql',), (), ('text/x-mysql',)),
'MyghtyCssLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Myghty', ('css+myghty',), (), ('text/css+myghty',)),
'MyghtyHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Myghty', ('html+myghty',), (), ('text/html+myghty',)),
'MyghtyJavascriptLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Myghty', ('javascript+myghty', 'js+myghty'), (), ('application/x-javascript+myghty', 'text/x-javascript+myghty', 'text/javascript+mygthy')),
'MyghtyLexer': ('pip._vendor.pygments.lexers.templates', 'Myghty', ('myghty',), ('*.myt', 'autodelegate'), ('application/x-myghty',)),
'MyghtyXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Myghty', ('xml+myghty',), (), ('application/xml+myghty',)),
'NCLLexer': ('pip._vendor.pygments.lexers.ncl', 'NCL', ('ncl',), ('*.ncl',), ('text/ncl',)),
'NSISLexer': ('pip._vendor.pygments.lexers.installers', 'NSIS', ('nsis', 'nsi', 'nsh'), ('*.nsi', '*.nsh'), ('text/x-nsis',)),
'NasmLexer': ('pip._vendor.pygments.lexers.asm', 'NASM', ('nasm',), ('*.asm', '*.ASM', '*.nasm'), ('text/x-nasm',)),
'NasmObjdumpLexer': ('pip._vendor.pygments.lexers.asm', 'objdump-nasm', ('objdump-nasm',), ('*.objdump-intel',), ('text/x-nasm-objdump',)),
'NemerleLexer': ('pip._vendor.pygments.lexers.dotnet', 'Nemerle', ('nemerle',), ('*.n',), ('text/x-nemerle',)),
'NesCLexer': ('pip._vendor.pygments.lexers.c_like', 'nesC', ('nesc',), ('*.nc',), ('text/x-nescsrc',)),
'NestedTextLexer': ('pip._vendor.pygments.lexers.configs', 'NestedText', ('nestedtext', 'nt'), ('*.nt',), ()),
'NewLispLexer': ('pip._vendor.pygments.lexers.lisp', 'NewLisp', ('newlisp',), ('*.lsp', '*.nl', '*.kif'), ('text/x-newlisp', 'application/x-newlisp')),
'NewspeakLexer': ('pip._vendor.pygments.lexers.smalltalk', 'Newspeak', ('newspeak',), ('*.ns2',), ('text/x-newspeak',)),
'NginxConfLexer': ('pip._vendor.pygments.lexers.configs', 'Nginx configuration file', ('nginx',), ('nginx.conf',), ('text/x-nginx-conf',)),
'NimrodLexer': ('pip._vendor.pygments.lexers.nimrod', 'Nimrod', ('nimrod', 'nim'), ('*.nim', '*.nimrod'), ('text/x-nim',)),
'NitLexer': ('pip._vendor.pygments.lexers.nit', 'Nit', ('nit',), ('*.nit',), ()),
'NixLexer': ('pip._vendor.pygments.lexers.nix', 'Nix', ('nixos', 'nix'), ('*.nix',), ('text/x-nix',)),
'NodeConsoleLexer': ('pip._vendor.pygments.lexers.javascript', 'Node.js REPL console session', ('nodejsrepl',), (), ('text/x-nodejsrepl',)),
'NotmuchLexer': ('pip._vendor.pygments.lexers.textfmts', 'Notmuch', ('notmuch',), (), ()),
'NuSMVLexer': ('pip._vendor.pygments.lexers.smv', 'NuSMV', ('nusmv',), ('*.smv',), ()),
'NumPyLexer': ('pip._vendor.pygments.lexers.python', 'NumPy', ('numpy',), (), ()),
'ObjdumpLexer': ('pip._vendor.pygments.lexers.asm', 'objdump', ('objdump',), ('*.objdump',), ('text/x-objdump',)),
'ObjectiveCLexer': ('pip._vendor.pygments.lexers.objective', 'Objective-C', ('objective-c', 'objectivec', 'obj-c', 'objc'), ('*.m', '*.h'), ('text/x-objective-c',)),
'ObjectiveCppLexer': ('pip._vendor.pygments.lexers.objective', 'Objective-C++', ('objective-c++', 'objectivec++', 'obj-c++', 'objc++'), ('*.mm', '*.hh'), ('text/x-objective-c++',)),
'ObjectiveJLexer': ('pip._vendor.pygments.lexers.javascript', 'Objective-J', ('objective-j', 'objectivej', 'obj-j', 'objj'), ('*.j',), ('text/x-objective-j',)),
'OcamlLexer': ('pip._vendor.pygments.lexers.ml', 'OCaml', ('ocaml',), ('*.ml', '*.mli', '*.mll', '*.mly'), ('text/x-ocaml',)),
'OctaveLexer': ('pip._vendor.pygments.lexers.matlab', 'Octave', ('octave',), ('*.m',), ('text/octave',)),
'OdinLexer': ('pip._vendor.pygments.lexers.archetype', 'ODIN', ('odin',), ('*.odin',), ('text/odin',)),
'OmgIdlLexer': ('pip._vendor.pygments.lexers.c_like', 'OMG Interface Definition Language', ('omg-idl',), ('*.idl', '*.pidl'), ()),
'OocLexer': ('pip._vendor.pygments.lexers.ooc', 'Ooc', ('ooc',), ('*.ooc',), ('text/x-ooc',)),
'OpaLexer': ('pip._vendor.pygments.lexers.ml', 'Opa', ('opa',), ('*.opa',), ('text/x-opa',)),
'OpenEdgeLexer': ('pip._vendor.pygments.lexers.business', 'OpenEdge ABL', ('openedge', 'abl', 'progress'), ('*.p', '*.cls'), ('text/x-openedge', 'application/x-openedge')),
'OutputLexer': ('pip._vendor.pygments.lexers.special', 'Text output', ('output',), (), ()),
'PacmanConfLexer': ('pip._vendor.pygments.lexers.configs', 'PacmanConf', ('pacmanconf',), ('pacman.conf',), ()),
'PanLexer': ('pip._vendor.pygments.lexers.dsls', 'Pan', ('pan',), ('*.pan',), ()),
'ParaSailLexer': ('pip._vendor.pygments.lexers.parasail', 'ParaSail', ('parasail',), ('*.psi', '*.psl'), ('text/x-parasail',)),
'PawnLexer': ('pip._vendor.pygments.lexers.pawn', 'Pawn', ('pawn',), ('*.p', '*.pwn', '*.inc'), ('text/x-pawn',)),
'PegLexer': ('pip._vendor.pygments.lexers.grammar_notation', 'PEG', ('peg',), ('*.peg',), ('text/x-peg',)),
'Perl6Lexer': ('pip._vendor.pygments.lexers.perl', 'Perl6', ('perl6', 'pl6', 'raku'), ('*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', '*.6pm', '*.p6m', '*.pm6', '*.t', '*.raku', '*.rakumod', '*.rakutest', '*.rakudoc'), ('text/x-perl6', 'application/x-perl6')),
'PerlLexer': ('pip._vendor.pygments.lexers.perl', 'Perl', ('perl', 'pl'), ('*.pl', '*.pm', '*.t', '*.perl'), ('text/x-perl', 'application/x-perl')),
'PhixLexer': ('pip._vendor.pygments.lexers.phix', 'Phix', ('phix',), ('*.exw',), ('text/x-phix',)),
'PhpLexer': ('pip._vendor.pygments.lexers.php', 'PHP', ('php', 'php3', 'php4', 'php5'), ('*.php', '*.php[345]', '*.inc'), ('text/x-php',)),
'PigLexer': ('pip._vendor.pygments.lexers.jvm', 'Pig', ('pig',), ('*.pig',), ('text/x-pig',)),
'PikeLexer': ('pip._vendor.pygments.lexers.c_like', 'Pike', ('pike',), ('*.pike', '*.pmod'), ('text/x-pike',)),
'PkgConfigLexer': ('pip._vendor.pygments.lexers.configs', 'PkgConfig', ('pkgconfig',), ('*.pc',), ()),
'PlPgsqlLexer': ('pip._vendor.pygments.lexers.sql', 'PL/pgSQL', ('plpgsql',), (), ('text/x-plpgsql',)),
'PointlessLexer': ('pip._vendor.pygments.lexers.pointless', 'Pointless', ('pointless',), ('*.ptls',), ()),
'PonyLexer': ('pip._vendor.pygments.lexers.pony', 'Pony', ('pony',), ('*.pony',), ()),
'PortugolLexer': ('pip._vendor.pygments.lexers.pascal', 'Portugol', ('portugol',), ('*.alg', '*.portugol'), ()),
'PostScriptLexer': ('pip._vendor.pygments.lexers.graphics', 'PostScript', ('postscript', 'postscr'), ('*.ps', '*.eps'), ('application/postscript',)),
'PostgresConsoleLexer': ('pip._vendor.pygments.lexers.sql', 'PostgreSQL console (psql)', ('psql', 'postgresql-console', 'postgres-console'), (), ('text/x-postgresql-psql',)),
'PostgresExplainLexer': ('pip._vendor.pygments.lexers.sql', 'PostgreSQL EXPLAIN dialect', ('postgres-explain',), ('*.explain',), ('text/x-postgresql-explain',)),
'PostgresLexer': ('pip._vendor.pygments.lexers.sql', 'PostgreSQL SQL dialect', ('postgresql', 'postgres'), (), ('text/x-postgresql',)),
'PovrayLexer': ('pip._vendor.pygments.lexers.graphics', 'POVRay', ('pov',), ('*.pov', '*.inc'), ('text/x-povray',)),
'PowerShellLexer': ('pip._vendor.pygments.lexers.shell', 'PowerShell', ('powershell', 'pwsh', 'posh', 'ps1', 'psm1'), ('*.ps1', '*.psm1'), ('text/x-powershell',)),
'PowerShellSessionLexer': ('pip._vendor.pygments.lexers.shell', 'PowerShell Session', ('pwsh-session', 'ps1con'), (), ()),
'PraatLexer': ('pip._vendor.pygments.lexers.praat', 'Praat', ('praat',), ('*.praat', '*.proc', '*.psc'), ()),
'ProcfileLexer': ('pip._vendor.pygments.lexers.procfile', 'Procfile', ('procfile',), ('Procfile',), ()),
'PrologLexer': ('pip._vendor.pygments.lexers.prolog', 'Prolog', ('prolog',), ('*.ecl', '*.prolog', '*.pro', '*.pl'), ('text/x-prolog',)),
'PromQLLexer': ('pip._vendor.pygments.lexers.promql', 'PromQL', ('promql',), ('*.promql',), ()),
'PropertiesLexer': ('pip._vendor.pygments.lexers.configs', 'Properties', ('properties', 'jproperties'), ('*.properties',), ('text/x-java-properties',)),
'ProtoBufLexer': ('pip._vendor.pygments.lexers.dsls', 'Protocol Buffer', ('protobuf', 'proto'), ('*.proto',), ()),
'PsyshConsoleLexer': ('pip._vendor.pygments.lexers.php', 'PsySH console session for PHP', ('psysh',), (), ()),
'PugLexer': ('pip._vendor.pygments.lexers.html', 'Pug', ('pug', 'jade'), ('*.pug', '*.jade'), ('text/x-pug', 'text/x-jade')),
'PuppetLexer': ('pip._vendor.pygments.lexers.dsls', 'Puppet', ('puppet',), ('*.pp',), ()),
'PyPyLogLexer': ('pip._vendor.pygments.lexers.console', 'PyPy Log', ('pypylog', 'pypy'), ('*.pypylog',), ('application/x-pypylog',)),
'Python2Lexer': ('pip._vendor.pygments.lexers.python', 'Python 2.x', ('python2', 'py2'), (), ('text/x-python2', 'application/x-python2')),
'Python2TracebackLexer': ('pip._vendor.pygments.lexers.python', 'Python 2.x Traceback', ('py2tb',), ('*.py2tb',), ('text/x-python2-traceback',)),
'PythonConsoleLexer': ('pip._vendor.pygments.lexers.python', 'Python console session', ('pycon',), (), ('text/x-python-doctest',)),
'PythonLexer': ('pip._vendor.pygments.lexers.python', 'Python', ('python', 'py', 'sage', 'python3', 'py3'), ('*.py', '*.pyw', '*.pyi', '*.jy', '*.sage', '*.sc', 'SConstruct', 'SConscript', '*.bzl', 'BUCK', 'BUILD', 'BUILD.bazel', 'WORKSPACE', '*.tac'), ('text/x-python', 'application/x-python', 'text/x-python3', 'application/x-python3')),
'PythonTracebackLexer': ('pip._vendor.pygments.lexers.python', 'Python Traceback', ('pytb', 'py3tb'), ('*.pytb', '*.py3tb'), ('text/x-python-traceback', 'text/x-python3-traceback')),
'PythonUL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'Python+UL4', ('py+ul4',), ('*.pyul4',), ()),
'QBasicLexer': ('pip._vendor.pygments.lexers.basic', 'QBasic', ('qbasic', 'basic'), ('*.BAS', '*.bas'), ('text/basic',)),
'QLexer': ('pip._vendor.pygments.lexers.q', 'Q', ('q',), ('*.q',), ()),
'QVToLexer': ('pip._vendor.pygments.lexers.qvt', 'QVTO', ('qvto', 'qvt'), ('*.qvto',), ()),
'QlikLexer': ('pip._vendor.pygments.lexers.qlik', 'Qlik', ('qlik', 'qlikview', 'qliksense', 'qlikscript'), ('*.qvs', '*.qvw'), ()),
'QmlLexer': ('pip._vendor.pygments.lexers.webmisc', 'QML', ('qml', 'qbs'), ('*.qml', '*.qbs'), ('application/x-qml', 'application/x-qt.qbs+qml')),
'RConsoleLexer': ('pip._vendor.pygments.lexers.r', 'RConsole', ('rconsole', 'rout'), ('*.Rout',), ()),
'RNCCompactLexer': ('pip._vendor.pygments.lexers.rnc', 'Relax-NG Compact', ('rng-compact', 'rnc'), ('*.rnc',), ()),
'RPMSpecLexer': ('pip._vendor.pygments.lexers.installers', 'RPMSpec', ('spec',), ('*.spec',), ('text/x-rpm-spec',)),
'RacketLexer': ('pip._vendor.pygments.lexers.lisp', 'Racket', ('racket', 'rkt'), ('*.rkt', '*.rktd', '*.rktl'), ('text/x-racket', 'application/x-racket')),
'RagelCLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel in C Host', ('ragel-c',), ('*.rl',), ()),
'RagelCppLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel in CPP Host', ('ragel-cpp',), ('*.rl',), ()),
'RagelDLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel in D Host', ('ragel-d',), ('*.rl',), ()),
'RagelEmbeddedLexer': ('pip._vendor.pygments.lexers.parsers', 'Embedded Ragel', ('ragel-em',), ('*.rl',), ()),
'RagelJavaLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel in Java Host', ('ragel-java',), ('*.rl',), ()),
'RagelLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel', ('ragel',), (), ()),
'RagelObjectiveCLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel in Objective C Host', ('ragel-objc',), ('*.rl',), ()),
'RagelRubyLexer': ('pip._vendor.pygments.lexers.parsers', 'Ragel in Ruby Host', ('ragel-ruby', 'ragel-rb'), ('*.rl',), ()),
'RawTokenLexer': ('pip._vendor.pygments.lexers.special', 'Raw token data', (), (), ('application/x-pygments-tokens',)),
'RdLexer': ('pip._vendor.pygments.lexers.r', 'Rd', ('rd',), ('*.Rd',), ('text/x-r-doc',)),
'ReasonLexer': ('pip._vendor.pygments.lexers.ml', 'ReasonML', ('reasonml', 'reason'), ('*.re', '*.rei'), ('text/x-reasonml',)),
'RebolLexer': ('pip._vendor.pygments.lexers.rebol', 'REBOL', ('rebol',), ('*.r', '*.r3', '*.reb'), ('text/x-rebol',)),
'RedLexer': ('pip._vendor.pygments.lexers.rebol', 'Red', ('red', 'red/system'), ('*.red', '*.reds'), ('text/x-red', 'text/x-red-system')),
'RedcodeLexer': ('pip._vendor.pygments.lexers.esoteric', 'Redcode', ('redcode',), ('*.cw',), ()),
'RegeditLexer': ('pip._vendor.pygments.lexers.configs', 'reg', ('registry',), ('*.reg',), ('text/x-windows-registry',)),
'ResourceLexer': ('pip._vendor.pygments.lexers.resource', 'ResourceBundle', ('resourcebundle', 'resource'), (), ()),
'RexxLexer': ('pip._vendor.pygments.lexers.scripting', 'Rexx', ('rexx', 'arexx'), ('*.rexx', '*.rex', '*.rx', '*.arexx'), ('text/x-rexx',)),
'RhtmlLexer': ('pip._vendor.pygments.lexers.templates', 'RHTML', ('rhtml', 'html+erb', 'html+ruby'), ('*.rhtml',), ('text/html+ruby',)),
'RideLexer': ('pip._vendor.pygments.lexers.ride', 'Ride', ('ride',), ('*.ride',), ('text/x-ride',)),
'RitaLexer': ('pip._vendor.pygments.lexers.rita', 'Rita', ('rita',), ('*.rita',), ('text/rita',)),
'RoboconfGraphLexer': ('pip._vendor.pygments.lexers.roboconf', 'Roboconf Graph', ('roboconf-graph',), ('*.graph',), ()),
'RoboconfInstancesLexer': ('pip._vendor.pygments.lexers.roboconf', 'Roboconf Instances', ('roboconf-instances',), ('*.instances',), ()),
'RobotFrameworkLexer': ('pip._vendor.pygments.lexers.robotframework', 'RobotFramework', ('robotframework',), ('*.robot', '*.resource'), ('text/x-robotframework',)),
'RqlLexer': ('pip._vendor.pygments.lexers.sql', 'RQL', ('rql',), ('*.rql',), ('text/x-rql',)),
'RslLexer': ('pip._vendor.pygments.lexers.dsls', 'RSL', ('rsl',), ('*.rsl',), ('text/rsl',)),
'RstLexer': ('pip._vendor.pygments.lexers.markup', 'reStructuredText', ('restructuredtext', 'rst', 'rest'), ('*.rst', '*.rest'), ('text/x-rst', 'text/prs.fallenstein.rst')),
'RtsLexer': ('pip._vendor.pygments.lexers.trafficscript', 'TrafficScript', ('trafficscript', 'rts'), ('*.rts',), ()),
'RubyConsoleLexer': ('pip._vendor.pygments.lexers.ruby', 'Ruby irb session', ('rbcon', 'irb'), (), ('text/x-ruby-shellsession',)),
'RubyLexer': ('pip._vendor.pygments.lexers.ruby', 'Ruby', ('ruby', 'rb', 'duby'), ('*.rb', '*.rbw', 'Rakefile', '*.rake', '*.gemspec', '*.rbx', '*.duby', 'Gemfile', 'Vagrantfile'), ('text/x-ruby', 'application/x-ruby')),
'RustLexer': ('pip._vendor.pygments.lexers.rust', 'Rust', ('rust', 'rs'), ('*.rs', '*.rs.in'), ('text/rust', 'text/x-rust')),
'SASLexer': ('pip._vendor.pygments.lexers.sas', 'SAS', ('sas',), ('*.SAS', '*.sas'), ('text/x-sas', 'text/sas', 'application/x-sas')),
'SLexer': ('pip._vendor.pygments.lexers.r', 'S', ('splus', 's', 'r'), ('*.S', '*.R', '.Rhistory', '.Rprofile', '.Renviron'), ('text/S-plus', 'text/S', 'text/x-r-source', 'text/x-r', 'text/x-R', 'text/x-r-history', 'text/x-r-profile')),
'SMLLexer': ('pip._vendor.pygments.lexers.ml', 'Standard ML', ('sml',), ('*.sml', '*.sig', '*.fun'), ('text/x-standardml', 'application/x-standardml')),
'SNBTLexer': ('pip._vendor.pygments.lexers.minecraft', 'SNBT', ('snbt',), ('*.snbt',), ('text/snbt',)),
'SarlLexer': ('pip._vendor.pygments.lexers.jvm', 'SARL', ('sarl',), ('*.sarl',), ('text/x-sarl',)),
'SassLexer': ('pip._vendor.pygments.lexers.css', 'Sass', ('sass',), ('*.sass',), ('text/x-sass',)),
'SaviLexer': ('pip._vendor.pygments.lexers.savi', 'Savi', ('savi',), ('*.savi',), ()),
'ScalaLexer': ('pip._vendor.pygments.lexers.jvm', 'Scala', ('scala',), ('*.scala',), ('text/x-scala',)),
'ScamlLexer': ('pip._vendor.pygments.lexers.html', 'Scaml', ('scaml',), ('*.scaml',), ('text/x-scaml',)),
'ScdocLexer': ('pip._vendor.pygments.lexers.scdoc', 'scdoc', ('scdoc', 'scd'), ('*.scd', '*.scdoc'), ()),
'SchemeLexer': ('pip._vendor.pygments.lexers.lisp', 'Scheme', ('scheme', 'scm'), ('*.scm', '*.ss'), ('text/x-scheme', 'application/x-scheme')),
'ScilabLexer': ('pip._vendor.pygments.lexers.matlab', 'Scilab', ('scilab',), ('*.sci', '*.sce', '*.tst'), ('text/scilab',)),
'ScssLexer': ('pip._vendor.pygments.lexers.css', 'SCSS', ('scss',), ('*.scss',), ('text/x-scss',)),
'SedLexer': ('pip._vendor.pygments.lexers.textedit', 'Sed', ('sed', 'gsed', 'ssed'), ('*.sed', '*.[gs]sed'), ('text/x-sed',)),
'ShExCLexer': ('pip._vendor.pygments.lexers.rdf', 'ShExC', ('shexc', 'shex'), ('*.shex',), ('text/shex',)),
'ShenLexer': ('pip._vendor.pygments.lexers.lisp', 'Shen', ('shen',), ('*.shen',), ('text/x-shen', 'application/x-shen')),
'SieveLexer': ('pip._vendor.pygments.lexers.sieve', 'Sieve', ('sieve',), ('*.siv', '*.sieve'), ()),
'SilverLexer': ('pip._vendor.pygments.lexers.verification', 'Silver', ('silver',), ('*.sil', '*.vpr'), ()),
'SingularityLexer': ('pip._vendor.pygments.lexers.configs', 'Singularity', ('singularity',), ('*.def', 'Singularity'), ()),
'SlashLexer': ('pip._vendor.pygments.lexers.slash', 'Slash', ('slash',), ('*.sla',), ()),
'SlimLexer': ('pip._vendor.pygments.lexers.webmisc', 'Slim', ('slim',), ('*.slim',), ('text/x-slim',)),
'SlurmBashLexer': ('pip._vendor.pygments.lexers.shell', 'Slurm', ('slurm', 'sbatch'), ('*.sl',), ()),
'SmaliLexer': ('pip._vendor.pygments.lexers.dalvik', 'Smali', ('smali',), ('*.smali',), ('text/smali',)),
'SmalltalkLexer': ('pip._vendor.pygments.lexers.smalltalk', 'Smalltalk', ('smalltalk', 'squeak', 'st'), ('*.st',), ('text/x-smalltalk',)),
'SmartGameFormatLexer': ('pip._vendor.pygments.lexers.sgf', 'SmartGameFormat', ('sgf',), ('*.sgf',), ()),
'SmartyLexer': ('pip._vendor.pygments.lexers.templates', 'Smarty', ('smarty',), ('*.tpl',), ('application/x-smarty',)),
'SmithyLexer': ('pip._vendor.pygments.lexers.smithy', 'Smithy', ('smithy',), ('*.smithy',), ()),
'SnobolLexer': ('pip._vendor.pygments.lexers.snobol', 'Snobol', ('snobol',), ('*.snobol',), ('text/x-snobol',)),
'SnowballLexer': ('pip._vendor.pygments.lexers.dsls', 'Snowball', ('snowball',), ('*.sbl',), ()),
'SolidityLexer': ('pip._vendor.pygments.lexers.solidity', 'Solidity', ('solidity',), ('*.sol',), ()),
'SophiaLexer': ('pip._vendor.pygments.lexers.sophia', 'Sophia', ('sophia',), ('*.aes',), ()),
'SourcePawnLexer': ('pip._vendor.pygments.lexers.pawn', 'SourcePawn', ('sp',), ('*.sp',), ('text/x-sourcepawn',)),
'SourcesListLexer': ('pip._vendor.pygments.lexers.installers', 'Debian Sourcelist', ('debsources', 'sourceslist', 'sources.list'), ('sources.list',), ()),
'SparqlLexer': ('pip._vendor.pygments.lexers.rdf', 'SPARQL', ('sparql',), ('*.rq', '*.sparql'), ('application/sparql-query',)),
'SpiceLexer': ('pip._vendor.pygments.lexers.spice', 'Spice', ('spice', 'spicelang'), ('*.spice',), ('text/x-spice',)),
'SqlJinjaLexer': ('pip._vendor.pygments.lexers.templates', 'SQL+Jinja', ('sql+jinja',), ('*.sql', '*.sql.j2', '*.sql.jinja2'), ()),
'SqlLexer': ('pip._vendor.pygments.lexers.sql', 'SQL', ('sql',), ('*.sql',), ('text/x-sql',)),
'SqliteConsoleLexer': ('pip._vendor.pygments.lexers.sql', 'sqlite3con', ('sqlite3',), ('*.sqlite3-console',), ('text/x-sqlite3-console',)),
'SquidConfLexer': ('pip._vendor.pygments.lexers.configs', 'SquidConf', ('squidconf', 'squid.conf', 'squid'), ('squid.conf',), ('text/x-squidconf',)),
'SrcinfoLexer': ('pip._vendor.pygments.lexers.srcinfo', 'Srcinfo', ('srcinfo',), ('.SRCINFO',), ()),
'SspLexer': ('pip._vendor.pygments.lexers.templates', 'Scalate Server Page', ('ssp',), ('*.ssp',), ('application/x-ssp',)),
'StanLexer': ('pip._vendor.pygments.lexers.modeling', 'Stan', ('stan',), ('*.stan',), ()),
'StataLexer': ('pip._vendor.pygments.lexers.stata', 'Stata', ('stata', 'do'), ('*.do', '*.ado'), ('text/x-stata', 'text/stata', 'application/x-stata')),
'SuperColliderLexer': ('pip._vendor.pygments.lexers.supercollider', 'SuperCollider', ('supercollider', 'sc'), ('*.sc', '*.scd'), ('application/supercollider', 'text/supercollider')),
'SwiftLexer': ('pip._vendor.pygments.lexers.objective', 'Swift', ('swift',), ('*.swift',), ('text/x-swift',)),
'SwigLexer': ('pip._vendor.pygments.lexers.c_like', 'SWIG', ('swig',), ('*.swg', '*.i'), ('text/swig',)),
'SystemVerilogLexer': ('pip._vendor.pygments.lexers.hdl', 'systemverilog', ('systemverilog', 'sv'), ('*.sv', '*.svh'), ('text/x-systemverilog',)),
'TAPLexer': ('pip._vendor.pygments.lexers.testing', 'TAP', ('tap',), ('*.tap',), ()),
'TNTLexer': ('pip._vendor.pygments.lexers.tnt', 'Typographic Number Theory', ('tnt',), ('*.tnt',), ()),
'TOMLLexer': ('pip._vendor.pygments.lexers.configs', 'TOML', ('toml',), ('*.toml', 'Pipfile', 'poetry.lock'), ()),
'Tads3Lexer': ('pip._vendor.pygments.lexers.int_fiction', 'TADS 3', ('tads3',), ('*.t',), ()),
'TalLexer': ('pip._vendor.pygments.lexers.tal', 'Tal', ('tal', 'uxntal'), ('*.tal',), ('text/x-uxntal',)),
'TasmLexer': ('pip._vendor.pygments.lexers.asm', 'TASM', ('tasm',), ('*.asm', '*.ASM', '*.tasm'), ('text/x-tasm',)),
'TclLexer': ('pip._vendor.pygments.lexers.tcl', 'Tcl', ('tcl',), ('*.tcl', '*.rvt'), ('text/x-tcl', 'text/x-script.tcl', 'application/x-tcl')),
'TcshLexer': ('pip._vendor.pygments.lexers.shell', 'Tcsh', ('tcsh', 'csh'), ('*.tcsh', '*.csh'), ('application/x-csh',)),
'TcshSessionLexer': ('pip._vendor.pygments.lexers.shell', 'Tcsh Session', ('tcshcon',), (), ()),
'TeaTemplateLexer': ('pip._vendor.pygments.lexers.templates', 'Tea', ('tea',), ('*.tea',), ('text/x-tea',)),
'TealLexer': ('pip._vendor.pygments.lexers.teal', 'teal', ('teal',), ('*.teal',), ()),
'TeraTermLexer': ('pip._vendor.pygments.lexers.teraterm', 'Tera Term macro', ('teratermmacro', 'teraterm', 'ttl'), ('*.ttl',), ('text/x-teratermmacro',)),
'TermcapLexer': ('pip._vendor.pygments.lexers.configs', 'Termcap', ('termcap',), ('termcap', 'termcap.src'), ()),
'TerminfoLexer': ('pip._vendor.pygments.lexers.configs', 'Terminfo', ('terminfo',), ('terminfo', 'terminfo.src'), ()),
'TerraformLexer': ('pip._vendor.pygments.lexers.configs', 'Terraform', ('terraform', 'tf', 'hcl'), ('*.tf', '*.hcl'), ('application/x-tf', 'application/x-terraform')),
'TexLexer': ('pip._vendor.pygments.lexers.markup', 'TeX', ('tex', 'latex'), ('*.tex', '*.aux', '*.toc'), ('text/x-tex', 'text/x-latex')),
'TextLexer': ('pip._vendor.pygments.lexers.special', 'Text only', ('text',), ('*.txt',), ('text/plain',)),
'ThingsDBLexer': ('pip._vendor.pygments.lexers.thingsdb', 'ThingsDB', ('ti', 'thingsdb'), ('*.ti',), ()),
'ThriftLexer': ('pip._vendor.pygments.lexers.dsls', 'Thrift', ('thrift',), ('*.thrift',), ('application/x-thrift',)),
'TiddlyWiki5Lexer': ('pip._vendor.pygments.lexers.markup', 'tiddler', ('tid',), ('*.tid',), ('text/vnd.tiddlywiki',)),
'TlbLexer': ('pip._vendor.pygments.lexers.tlb', 'Tl-b', ('tlb',), ('*.tlb',), ()),
'TodotxtLexer': ('pip._vendor.pygments.lexers.textfmts', 'Todotxt', ('todotxt',), ('todo.txt', '*.todotxt'), ('text/x-todo',)),
'TransactSqlLexer': ('pip._vendor.pygments.lexers.sql', 'Transact-SQL', ('tsql', 't-sql'), ('*.sql',), ('text/x-tsql',)),
'TreetopLexer': ('pip._vendor.pygments.lexers.parsers', 'Treetop', ('treetop',), ('*.treetop', '*.tt'), ()),
'TurtleLexer': ('pip._vendor.pygments.lexers.rdf', 'Turtle', ('turtle',), ('*.ttl',), ('text/turtle', 'application/x-turtle')),
'TwigHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Twig', ('html+twig',), ('*.twig',), ('text/html+twig',)),
'TwigLexer': ('pip._vendor.pygments.lexers.templates', 'Twig', ('twig',), (), ('application/x-twig',)),
'TypeScriptLexer': ('pip._vendor.pygments.lexers.javascript', 'TypeScript', ('typescript', 'ts'), ('*.ts',), ('application/x-typescript', 'text/x-typescript')),
'TypoScriptCssDataLexer': ('pip._vendor.pygments.lexers.typoscript', 'TypoScriptCssData', ('typoscriptcssdata',), (), ()),
'TypoScriptHtmlDataLexer': ('pip._vendor.pygments.lexers.typoscript', 'TypoScriptHtmlData', ('typoscripthtmldata',), (), ()),
'TypoScriptLexer': ('pip._vendor.pygments.lexers.typoscript', 'TypoScript', ('typoscript',), ('*.typoscript',), ('text/x-typoscript',)),
'UL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'UL4', ('ul4',), ('*.ul4',), ()),
'UcodeLexer': ('pip._vendor.pygments.lexers.unicon', 'ucode', ('ucode',), ('*.u', '*.u1', '*.u2'), ()),
'UniconLexer': ('pip._vendor.pygments.lexers.unicon', 'Unicon', ('unicon',), ('*.icn',), ('text/unicon',)),
'UnixConfigLexer': ('pip._vendor.pygments.lexers.configs', 'Unix/Linux config files', ('unixconfig', 'linuxconfig'), (), ()),
'UrbiscriptLexer': ('pip._vendor.pygments.lexers.urbi', 'UrbiScript', ('urbiscript',), ('*.u',), ('application/x-urbiscript',)),
'UsdLexer': ('pip._vendor.pygments.lexers.usd', 'USD', ('usd', 'usda'), ('*.usd', '*.usda'), ()),
'VBScriptLexer': ('pip._vendor.pygments.lexers.basic', 'VBScript', ('vbscript',), ('*.vbs', '*.VBS'), ()),
'VCLLexer': ('pip._vendor.pygments.lexers.varnish', 'VCL', ('vcl',), ('*.vcl',), ('text/x-vclsrc',)),
'VCLSnippetLexer': ('pip._vendor.pygments.lexers.varnish', 'VCLSnippets', ('vclsnippets', 'vclsnippet'), (), ('text/x-vclsnippet',)),
'VCTreeStatusLexer': ('pip._vendor.pygments.lexers.console', 'VCTreeStatus', ('vctreestatus',), (), ()),
'VGLLexer': ('pip._vendor.pygments.lexers.dsls', 'VGL', ('vgl',), ('*.rpf',), ()),
'ValaLexer': ('pip._vendor.pygments.lexers.c_like', 'Vala', ('vala', 'vapi'), ('*.vala', '*.vapi'), ('text/x-vala',)),
'VbNetAspxLexer': ('pip._vendor.pygments.lexers.dotnet', 'aspx-vb', ('aspx-vb',), ('*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd'), ()),
'VbNetLexer': ('pip._vendor.pygments.lexers.dotnet', 'VB.net', ('vb.net', 'vbnet', 'lobas', 'oobas', 'sobas'), ('*.vb', '*.bas'), ('text/x-vbnet', 'text/x-vba')),
'VelocityHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Velocity', ('html+velocity',), (), ('text/html+velocity',)),
'VelocityLexer': ('pip._vendor.pygments.lexers.templates', 'Velocity', ('velocity',), ('*.vm', '*.fhtml'), ()),
'VelocityXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Velocity', ('xml+velocity',), (), ('application/xml+velocity',)),
'VerilogLexer': ('pip._vendor.pygments.lexers.hdl', 'verilog', ('verilog', 'v'), ('*.v',), ('text/x-verilog',)),
'VhdlLexer': ('pip._vendor.pygments.lexers.hdl', 'vhdl', ('vhdl',), ('*.vhdl', '*.vhd'), ('text/x-vhdl',)),
'VimLexer': ('pip._vendor.pygments.lexers.textedit', 'VimL', ('vim',), ('*.vim', '.vimrc', '.exrc', '.gvimrc', '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc'), ('text/x-vim',)),
'WDiffLexer': ('pip._vendor.pygments.lexers.diff', 'WDiff', ('wdiff',), ('*.wdiff',), ()),
'WatLexer': ('pip._vendor.pygments.lexers.webassembly', 'WebAssembly', ('wast', 'wat'), ('*.wat', '*.wast'), ()),
'WebIDLLexer': ('pip._vendor.pygments.lexers.webidl', 'Web IDL', ('webidl',), ('*.webidl',), ()),
'WgslLexer': ('pip._vendor.pygments.lexers.wgsl', 'WebGPU Shading Language', ('wgsl',), ('*.wgsl',), ('text/wgsl',)),
'WhileyLexer': ('pip._vendor.pygments.lexers.whiley', 'Whiley', ('whiley',), ('*.whiley',), ('text/x-whiley',)),
'WikitextLexer': ('pip._vendor.pygments.lexers.markup', 'Wikitext', ('wikitext', 'mediawiki'), (), ('text/x-wiki',)),
'WoWTocLexer': ('pip._vendor.pygments.lexers.wowtoc', 'World of Warcraft TOC', ('wowtoc',), ('*.toc',), ()),
'WrenLexer': ('pip._vendor.pygments.lexers.wren', 'Wren', ('wren',), ('*.wren',), ()),
'X10Lexer': ('pip._vendor.pygments.lexers.x10', 'X10', ('x10', 'xten'), ('*.x10',), ('text/x-x10',)),
'XMLUL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'XML+UL4', ('xml+ul4',), ('*.xmlul4',), ()),
'XQueryLexer': ('pip._vendor.pygments.lexers.webmisc', 'XQuery', ('xquery', 'xqy', 'xq', 'xql', 'xqm'), ('*.xqy', '*.xquery', '*.xq', '*.xql', '*.xqm'), ('text/xquery', 'application/xquery')),
'XmlDjangoLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Django/Jinja', ('xml+django', 'xml+jinja'), ('*.xml.j2', '*.xml.jinja2'), ('application/xml+django', 'application/xml+jinja')),
'XmlErbLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Ruby', ('xml+ruby', 'xml+erb'), (), ('application/xml+ruby',)),
'XmlLexer': ('pip._vendor.pygments.lexers.html', 'XML', ('xml',), ('*.xml', '*.xsl', '*.rss', '*.xslt', '*.xsd', '*.wsdl', '*.wsf'), ('text/xml', 'application/xml', 'image/svg+xml', 'application/rss+xml', 'application/atom+xml')),
'XmlPhpLexer': ('pip._vendor.pygments.lexers.templates', 'XML+PHP', ('xml+php',), (), ('application/xml+php',)),
'XmlSmartyLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Smarty', ('xml+smarty',), (), ('application/xml+smarty',)),
'XorgLexer': ('pip._vendor.pygments.lexers.xorg', 'Xorg', ('xorg.conf',), ('xorg.conf',), ()),
'XppLexer': ('pip._vendor.pygments.lexers.dotnet', 'X++', ('xpp', 'x++'), ('*.xpp',), ()),
'XsltLexer': ('pip._vendor.pygments.lexers.html', 'XSLT', ('xslt',), ('*.xsl', '*.xslt', '*.xpl'), ('application/xsl+xml', 'application/xslt+xml')),
'XtendLexer': ('pip._vendor.pygments.lexers.jvm', 'Xtend', ('xtend',), ('*.xtend',), ('text/x-xtend',)),
'XtlangLexer': ('pip._vendor.pygments.lexers.lisp', 'xtlang', ('extempore',), ('*.xtm',), ()),
'YamlJinjaLexer': ('pip._vendor.pygments.lexers.templates', 'YAML+Jinja', ('yaml+jinja', 'salt', 'sls'), ('*.sls', '*.yaml.j2', '*.yml.j2', '*.yaml.jinja2', '*.yml.jinja2'), ('text/x-yaml+jinja', 'text/x-sls')),
'YamlLexer': ('pip._vendor.pygments.lexers.data', 'YAML', ('yaml',), ('*.yaml', '*.yml'), ('text/x-yaml',)),
'YangLexer': ('pip._vendor.pygments.lexers.yang', 'YANG', ('yang',), ('*.yang',), ('application/yang',)),
'ZeekLexer': ('pip._vendor.pygments.lexers.dsls', 'Zeek', ('zeek', 'bro'), ('*.zeek', '*.bro'), ()),
'ZephirLexer': ('pip._vendor.pygments.lexers.php', 'Zephir', ('zephir',), ('*.zep',), ()),
'ZigLexer': ('pip._vendor.pygments.lexers.zig', 'Zig', ('zig',), ('*.zig',), ('text/zig',)),
'apdlexer': ('pip._vendor.pygments.lexers.apdlexer', 'ANSYS parametric design language', ('ansys', 'apdl'), ('*.ans',), ()),
}

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,43 @@
"""
pygments.modeline
~~~~~~~~~~~~~~~~~
A simple modeline parser (based on pymodeline).
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
__all__ = ['get_filetype_from_buffer']
modeline_re = re.compile(r'''
(?: vi | vim | ex ) (?: [<=>]? \d* )? :
.* (?: ft | filetype | syn | syntax ) = ( [^:\s]+ )
''', re.VERBOSE)
def get_filetype_from_line(l):
m = modeline_re.search(l)
if m:
return m.group(1)
def get_filetype_from_buffer(buf, max_lines=5):
"""
Scan the buffer for modelines and return filetype if one is found.
"""
lines = buf.splitlines()
for l in lines[-1:-max_lines-1:-1]:
ret = get_filetype_from_line(l)
if ret:
return ret
for i in range(max_lines, -1, -1):
if i < len(lines):
ret = get_filetype_from_line(lines[i])
if ret:
return ret
return None

View file

@ -0,0 +1,88 @@
"""
pygments.plugin
~~~~~~~~~~~~~~~
Pygments plugin interface. By default, this tries to use
``importlib.metadata``, which is in the Python standard
library since Python 3.8, or its ``importlib_metadata``
backport for earlier versions of Python. It falls back on
``pkg_resources`` if not found. Finally, if ``pkg_resources``
is not found either, no plugins are loaded at all.
lexer plugins::
[pygments.lexers]
yourlexer = yourmodule:YourLexer
formatter plugins::
[pygments.formatters]
yourformatter = yourformatter:YourFormatter
/.ext = yourformatter:YourFormatter
As you can see, you can define extensions for the formatter
with a leading slash.
syntax plugins::
[pygments.styles]
yourstyle = yourstyle:YourStyle
filter plugin::
[pygments.filter]
yourfilter = yourfilter:YourFilter
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
LEXER_ENTRY_POINT = 'pygments.lexers'
FORMATTER_ENTRY_POINT = 'pygments.formatters'
STYLE_ENTRY_POINT = 'pygments.styles'
FILTER_ENTRY_POINT = 'pygments.filters'
def iter_entry_points(group_name):
try:
from importlib.metadata import entry_points
except ImportError:
try:
from importlib_metadata import entry_points
except ImportError:
try:
from pip._vendor.pkg_resources import iter_entry_points
except (ImportError, OSError):
return []
else:
return iter_entry_points(group_name)
groups = entry_points()
if hasattr(groups, 'select'):
# New interface in Python 3.10 and newer versions of the
# importlib_metadata backport.
return groups.select(group=group_name)
else:
# Older interface, deprecated in Python 3.10 and recent
# importlib_metadata, but we need it in Python 3.8 and 3.9.
return groups.get(group_name, [])
def find_plugin_lexers():
for entrypoint in iter_entry_points(LEXER_ENTRY_POINT):
yield entrypoint.load()
def find_plugin_formatters():
for entrypoint in iter_entry_points(FORMATTER_ENTRY_POINT):
yield entrypoint.name, entrypoint.load()
def find_plugin_styles():
for entrypoint in iter_entry_points(STYLE_ENTRY_POINT):
yield entrypoint.name, entrypoint.load()
def find_plugin_filters():
for entrypoint in iter_entry_points(FILTER_ENTRY_POINT):
yield entrypoint.name, entrypoint.load()

View file

@ -0,0 +1,91 @@
"""
pygments.regexopt
~~~~~~~~~~~~~~~~~
An algorithm that generates optimized regexes for matching long lists of
literal strings.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from re import escape
from os.path import commonprefix
from itertools import groupby
from operator import itemgetter
CS_ESCAPE = re.compile(r'[\[\^\\\-\]]')
FIRST_ELEMENT = itemgetter(0)
def make_charset(letters):
return '[' + CS_ESCAPE.sub(lambda m: '\\' + m.group(), ''.join(letters)) + ']'
def regex_opt_inner(strings, open_paren):
"""Return a regex that matches any string in the sorted list of strings."""
close_paren = open_paren and ')' or ''
# print strings, repr(open_paren)
if not strings:
# print '-> nothing left'
return ''
first = strings[0]
if len(strings) == 1:
# print '-> only 1 string'
return open_paren + escape(first) + close_paren
if not first:
# print '-> first string empty'
return open_paren + regex_opt_inner(strings[1:], '(?:') \
+ '?' + close_paren
if len(first) == 1:
# multiple one-char strings? make a charset
oneletter = []
rest = []
for s in strings:
if len(s) == 1:
oneletter.append(s)
else:
rest.append(s)
if len(oneletter) > 1: # do we have more than one oneletter string?
if rest:
# print '-> 1-character + rest'
return open_paren + regex_opt_inner(rest, '') + '|' \
+ make_charset(oneletter) + close_paren
# print '-> only 1-character'
return open_paren + make_charset(oneletter) + close_paren
prefix = commonprefix(strings)
if prefix:
plen = len(prefix)
# we have a prefix for all strings
# print '-> prefix:', prefix
return open_paren + escape(prefix) \
+ regex_opt_inner([s[plen:] for s in strings], '(?:') \
+ close_paren
# is there a suffix?
strings_rev = [s[::-1] for s in strings]
suffix = commonprefix(strings_rev)
if suffix:
slen = len(suffix)
# print '-> suffix:', suffix[::-1]
return open_paren \
+ regex_opt_inner(sorted(s[:-slen] for s in strings), '(?:') \
+ escape(suffix[::-1]) + close_paren
# recurse on common 1-string prefixes
# print '-> last resort'
return open_paren + \
'|'.join(regex_opt_inner(list(group[1]), '')
for group in groupby(strings, lambda s: s[0] == first[0])) \
+ close_paren
def regex_opt(strings, prefix='', suffix=''):
"""Return a compiled regex that matches any string in the given list.
The strings to match must be literal strings, not regexes. They will be
regex-escaped.
*prefix* and *suffix* are pre- and appended to the final regex.
"""
strings = sorted(strings)
return prefix + regex_opt_inner(strings, '(') + suffix

View file

@ -0,0 +1,104 @@
"""
pygments.scanner
~~~~~~~~~~~~~~~~
This library implements a regex based scanner. Some languages
like Pascal are easy to parse but have some keywords that
depend on the context. Because of this it's impossible to lex
that just by using a regular expression lexer like the
`RegexLexer`.
Have a look at the `DelphiLexer` to get an idea of how to use
this scanner.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
class EndOfText(RuntimeError):
"""
Raise if end of text is reached and the user
tried to call a match function.
"""
class Scanner:
"""
Simple scanner
All method patterns are regular expression strings (not
compiled expressions!)
"""
def __init__(self, text, flags=0):
"""
:param text: The text which should be scanned
:param flags: default regular expression flags
"""
self.data = text
self.data_length = len(text)
self.start_pos = 0
self.pos = 0
self.flags = flags
self.last = None
self.match = None
self._re_cache = {}
def eos(self):
"""`True` if the scanner reached the end of text."""
return self.pos >= self.data_length
eos = property(eos, eos.__doc__)
def check(self, pattern):
"""
Apply `pattern` on the current position and return
the match object. (Doesn't touch pos). Use this for
lookahead.
"""
if self.eos:
raise EndOfText()
if pattern not in self._re_cache:
self._re_cache[pattern] = re.compile(pattern, self.flags)
return self._re_cache[pattern].match(self.data, self.pos)
def test(self, pattern):
"""Apply a pattern on the current position and check
if it patches. Doesn't touch pos.
"""
return self.check(pattern) is not None
def scan(self, pattern):
"""
Scan the text for the given pattern and update pos/match
and related fields. The return value is a boolean that
indicates if the pattern matched. The matched value is
stored on the instance as ``match``, the last value is
stored as ``last``. ``start_pos`` is the position of the
pointer before the pattern was matched, ``pos`` is the
end position.
"""
if self.eos:
raise EndOfText()
if pattern not in self._re_cache:
self._re_cache[pattern] = re.compile(pattern, self.flags)
self.last = self.match
m = self._re_cache[pattern].match(self.data, self.pos)
if m is None:
return False
self.start_pos = m.start()
self.pos = m.end()
self.match = m.group()
return True
def get_char(self):
"""Scan exactly one char."""
self.scan('.')
def __repr__(self):
return '<%s %d/%d>' % (
self.__class__.__name__,
self.pos,
self.data_length
)

View file

@ -0,0 +1,217 @@
"""
pygments.sphinxext
~~~~~~~~~~~~~~~~~~
Sphinx extension to generate automatic documentation of lexers,
formatters and filters.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
from docutils import nodes
from docutils.statemachine import ViewList
from docutils.parsers.rst import Directive
from sphinx.util.nodes import nested_parse_with_titles
MODULEDOC = '''
.. module:: %s
%s
%s
'''
LEXERDOC = '''
.. class:: %s
:Short names: %s
:Filenames: %s
:MIME types: %s
%s
'''
FMTERDOC = '''
.. class:: %s
:Short names: %s
:Filenames: %s
%s
'''
FILTERDOC = '''
.. class:: %s
:Name: %s
%s
'''
class PygmentsDoc(Directive):
"""
A directive to collect all lexers/formatters/filters and generate
autoclass directives for them.
"""
has_content = False
required_arguments = 1
optional_arguments = 0
final_argument_whitespace = False
option_spec = {}
def run(self):
self.filenames = set()
if self.arguments[0] == 'lexers':
out = self.document_lexers()
elif self.arguments[0] == 'formatters':
out = self.document_formatters()
elif self.arguments[0] == 'filters':
out = self.document_filters()
elif self.arguments[0] == 'lexers_overview':
out = self.document_lexers_overview()
else:
raise Exception('invalid argument for "pygmentsdoc" directive')
node = nodes.compound()
vl = ViewList(out.split('\n'), source='')
nested_parse_with_titles(self.state, vl, node)
for fn in self.filenames:
self.state.document.settings.record_dependencies.add(fn)
return node.children
def document_lexers_overview(self):
"""Generate a tabular overview of all lexers.
The columns are the lexer name, the extensions handled by this lexer
(or "None"), the aliases and a link to the lexer class."""
from pip._vendor.pygments.lexers._mapping import LEXERS
from pip._vendor.pygments.lexers import find_lexer_class
out = []
table = []
def format_link(name, url):
if url:
return f'`{name} <{url}>`_'
return name
for classname, data in sorted(LEXERS.items(), key=lambda x: x[1][1].lower()):
lexer_cls = find_lexer_class(data[1])
extensions = lexer_cls.filenames + lexer_cls.alias_filenames
table.append({
'name': format_link(data[1], lexer_cls.url),
'extensions': ', '.join(extensions).replace('*', '\\*').replace('_', '\\') or 'None',
'aliases': ', '.join(data[2]),
'class': f'{data[0]}.{classname}'
})
column_names = ['name', 'extensions', 'aliases', 'class']
column_lengths = [max([len(row[column]) for row in table if row[column]])
for column in column_names]
def write_row(*columns):
"""Format a table row"""
out = []
for l, c in zip(column_lengths, columns):
if c:
out.append(c.ljust(l))
else:
out.append(' '*l)
return ' '.join(out)
def write_seperator():
"""Write a table separator row"""
sep = ['='*c for c in column_lengths]
return write_row(*sep)
out.append(write_seperator())
out.append(write_row('Name', 'Extension(s)', 'Short name(s)', 'Lexer class'))
out.append(write_seperator())
for row in table:
out.append(write_row(
row['name'],
row['extensions'],
row['aliases'],
f':class:`~{row["class"]}`'))
out.append(write_seperator())
return '\n'.join(out)
def document_lexers(self):
from pip._vendor.pygments.lexers._mapping import LEXERS
out = []
modules = {}
moduledocstrings = {}
for classname, data in sorted(LEXERS.items(), key=lambda x: x[0]):
module = data[0]
mod = __import__(module, None, None, [classname])
self.filenames.add(mod.__file__)
cls = getattr(mod, classname)
if not cls.__doc__:
print("Warning: %s does not have a docstring." % classname)
docstring = cls.__doc__
if isinstance(docstring, bytes):
docstring = docstring.decode('utf8')
modules.setdefault(module, []).append((
classname,
', '.join(data[2]) or 'None',
', '.join(data[3]).replace('*', '\\*').replace('_', '\\') or 'None',
', '.join(data[4]) or 'None',
docstring))
if module not in moduledocstrings:
moddoc = mod.__doc__
if isinstance(moddoc, bytes):
moddoc = moddoc.decode('utf8')
moduledocstrings[module] = moddoc
for module, lexers in sorted(modules.items(), key=lambda x: x[0]):
if moduledocstrings[module] is None:
raise Exception("Missing docstring for %s" % (module,))
heading = moduledocstrings[module].splitlines()[4].strip().rstrip('.')
out.append(MODULEDOC % (module, heading, '-'*len(heading)))
for data in lexers:
out.append(LEXERDOC % data)
return ''.join(out)
def document_formatters(self):
from pip._vendor.pygments.formatters import FORMATTERS
out = []
for classname, data in sorted(FORMATTERS.items(), key=lambda x: x[0]):
module = data[0]
mod = __import__(module, None, None, [classname])
self.filenames.add(mod.__file__)
cls = getattr(mod, classname)
docstring = cls.__doc__
if isinstance(docstring, bytes):
docstring = docstring.decode('utf8')
heading = cls.__name__
out.append(FMTERDOC % (heading, ', '.join(data[2]) or 'None',
', '.join(data[3]).replace('*', '\\*') or 'None',
docstring))
return ''.join(out)
def document_filters(self):
from pip._vendor.pygments.filters import FILTERS
out = []
for name, cls in FILTERS.items():
self.filenames.add(sys.modules[cls.__module__].__file__)
docstring = cls.__doc__
if isinstance(docstring, bytes):
docstring = docstring.decode('utf8')
out.append(FILTERDOC % (cls.__name__, name, docstring))
return ''.join(out)
def setup(app):
app.add_directive('pygmentsdoc', PygmentsDoc)

View file

@ -0,0 +1,197 @@
"""
pygments.style
~~~~~~~~~~~~~~
Basic style object.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.token import Token, STANDARD_TYPES
# Default mapping of ansixxx to RGB colors.
_ansimap = {
# dark
'ansiblack': '000000',
'ansired': '7f0000',
'ansigreen': '007f00',
'ansiyellow': '7f7fe0',
'ansiblue': '00007f',
'ansimagenta': '7f007f',
'ansicyan': '007f7f',
'ansigray': 'e5e5e5',
# normal
'ansibrightblack': '555555',
'ansibrightred': 'ff0000',
'ansibrightgreen': '00ff00',
'ansibrightyellow': 'ffff00',
'ansibrightblue': '0000ff',
'ansibrightmagenta': 'ff00ff',
'ansibrightcyan': '00ffff',
'ansiwhite': 'ffffff',
}
# mapping of deprecated #ansixxx colors to new color names
_deprecated_ansicolors = {
# dark
'#ansiblack': 'ansiblack',
'#ansidarkred': 'ansired',
'#ansidarkgreen': 'ansigreen',
'#ansibrown': 'ansiyellow',
'#ansidarkblue': 'ansiblue',
'#ansipurple': 'ansimagenta',
'#ansiteal': 'ansicyan',
'#ansilightgray': 'ansigray',
# normal
'#ansidarkgray': 'ansibrightblack',
'#ansired': 'ansibrightred',
'#ansigreen': 'ansibrightgreen',
'#ansiyellow': 'ansibrightyellow',
'#ansiblue': 'ansibrightblue',
'#ansifuchsia': 'ansibrightmagenta',
'#ansiturquoise': 'ansibrightcyan',
'#ansiwhite': 'ansiwhite',
}
ansicolors = set(_ansimap)
class StyleMeta(type):
def __new__(mcs, name, bases, dct):
obj = type.__new__(mcs, name, bases, dct)
for token in STANDARD_TYPES:
if token not in obj.styles:
obj.styles[token] = ''
def colorformat(text):
if text in ansicolors:
return text
if text[0:1] == '#':
col = text[1:]
if len(col) == 6:
return col
elif len(col) == 3:
return col[0] * 2 + col[1] * 2 + col[2] * 2
elif text == '':
return ''
elif text.startswith('var') or text.startswith('calc'):
return text
assert False, "wrong color format %r" % text
_styles = obj._styles = {}
for ttype in obj.styles:
for token in ttype.split():
if token in _styles:
continue
ndef = _styles.get(token.parent, None)
styledefs = obj.styles.get(token, '').split()
if not ndef or token is None:
ndef = ['', 0, 0, 0, '', '', 0, 0, 0]
elif 'noinherit' in styledefs and token is not Token:
ndef = _styles[Token][:]
else:
ndef = ndef[:]
_styles[token] = ndef
for styledef in obj.styles.get(token, '').split():
if styledef == 'noinherit':
pass
elif styledef == 'bold':
ndef[1] = 1
elif styledef == 'nobold':
ndef[1] = 0
elif styledef == 'italic':
ndef[2] = 1
elif styledef == 'noitalic':
ndef[2] = 0
elif styledef == 'underline':
ndef[3] = 1
elif styledef == 'nounderline':
ndef[3] = 0
elif styledef[:3] == 'bg:':
ndef[4] = colorformat(styledef[3:])
elif styledef[:7] == 'border:':
ndef[5] = colorformat(styledef[7:])
elif styledef == 'roman':
ndef[6] = 1
elif styledef == 'sans':
ndef[7] = 1
elif styledef == 'mono':
ndef[8] = 1
else:
ndef[0] = colorformat(styledef)
return obj
def style_for_token(cls, token):
t = cls._styles[token]
ansicolor = bgansicolor = None
color = t[0]
if color in _deprecated_ansicolors:
color = _deprecated_ansicolors[color]
if color in ansicolors:
ansicolor = color
color = _ansimap[color]
bgcolor = t[4]
if bgcolor in _deprecated_ansicolors:
bgcolor = _deprecated_ansicolors[bgcolor]
if bgcolor in ansicolors:
bgansicolor = bgcolor
bgcolor = _ansimap[bgcolor]
return {
'color': color or None,
'bold': bool(t[1]),
'italic': bool(t[2]),
'underline': bool(t[3]),
'bgcolor': bgcolor or None,
'border': t[5] or None,
'roman': bool(t[6]) or None,
'sans': bool(t[7]) or None,
'mono': bool(t[8]) or None,
'ansicolor': ansicolor,
'bgansicolor': bgansicolor,
}
def list_styles(cls):
return list(cls)
def styles_token(cls, ttype):
return ttype in cls._styles
def __iter__(cls):
for token in cls._styles:
yield token, cls.style_for_token(token)
def __len__(cls):
return len(cls._styles)
class Style(metaclass=StyleMeta):
#: overall background color (``None`` means transparent)
background_color = '#ffffff'
#: highlight background color
highlight_color = '#ffffcc'
#: line number font color
line_number_color = 'inherit'
#: line number background color
line_number_background_color = 'transparent'
#: special line number font color
line_number_special_color = '#000000'
#: special line number background color
line_number_special_background_color = '#ffffc0'
#: Style definitions for individual token types.
styles = {}
# Attribute for lexers defined within Pygments. If set
# to True, the style is not shown in the style gallery
# on the website. This is intended for language-specific
# styles.
web_style_gallery_exclude = False

View file

@ -0,0 +1,103 @@
"""
pygments.styles
~~~~~~~~~~~~~~~
Contains built-in styles.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pip._vendor.pygments.plugin import find_plugin_styles
from pip._vendor.pygments.util import ClassNotFound
#: A dictionary of built-in styles, mapping style names to
#: ``'submodule::classname'`` strings.
STYLE_MAP = {
'default': 'default::DefaultStyle',
'emacs': 'emacs::EmacsStyle',
'friendly': 'friendly::FriendlyStyle',
'friendly_grayscale': 'friendly_grayscale::FriendlyGrayscaleStyle',
'colorful': 'colorful::ColorfulStyle',
'autumn': 'autumn::AutumnStyle',
'murphy': 'murphy::MurphyStyle',
'manni': 'manni::ManniStyle',
'material': 'material::MaterialStyle',
'monokai': 'monokai::MonokaiStyle',
'perldoc': 'perldoc::PerldocStyle',
'pastie': 'pastie::PastieStyle',
'borland': 'borland::BorlandStyle',
'trac': 'trac::TracStyle',
'native': 'native::NativeStyle',
'fruity': 'fruity::FruityStyle',
'bw': 'bw::BlackWhiteStyle',
'vim': 'vim::VimStyle',
'vs': 'vs::VisualStudioStyle',
'tango': 'tango::TangoStyle',
'rrt': 'rrt::RrtStyle',
'xcode': 'xcode::XcodeStyle',
'igor': 'igor::IgorStyle',
'paraiso-light': 'paraiso_light::ParaisoLightStyle',
'paraiso-dark': 'paraiso_dark::ParaisoDarkStyle',
'lovelace': 'lovelace::LovelaceStyle',
'algol': 'algol::AlgolStyle',
'algol_nu': 'algol_nu::Algol_NuStyle',
'arduino': 'arduino::ArduinoStyle',
'rainbow_dash': 'rainbow_dash::RainbowDashStyle',
'abap': 'abap::AbapStyle',
'solarized-dark': 'solarized::SolarizedDarkStyle',
'solarized-light': 'solarized::SolarizedLightStyle',
'sas': 'sas::SasStyle',
'staroffice' : 'staroffice::StarofficeStyle',
'stata': 'stata_light::StataLightStyle',
'stata-light': 'stata_light::StataLightStyle',
'stata-dark': 'stata_dark::StataDarkStyle',
'inkpot': 'inkpot::InkPotStyle',
'zenburn': 'zenburn::ZenburnStyle',
'gruvbox-dark': 'gruvbox::GruvboxDarkStyle',
'gruvbox-light': 'gruvbox::GruvboxLightStyle',
'dracula': 'dracula::DraculaStyle',
'one-dark': 'onedark::OneDarkStyle',
'lilypond' : 'lilypond::LilyPondStyle',
'nord': 'nord::NordStyle',
'nord-darker': 'nord::NordDarkerStyle',
'github-dark': 'gh_dark::GhDarkStyle'
}
def get_style_by_name(name):
"""
Return a style class by its short name. The names of the builtin styles
are listed in :data:`pygments.styles.STYLE_MAP`.
Will raise :exc:`pygments.util.ClassNotFound` if no style of that name is
found.
"""
if name in STYLE_MAP:
mod, cls = STYLE_MAP[name].split('::')
builtin = "yes"
else:
for found_name, style in find_plugin_styles():
if name == found_name:
return style
# perhaps it got dropped into our styles package
builtin = ""
mod = name
cls = name.title() + "Style"
try:
mod = __import__('pygments.styles.' + mod, None, None, [cls])
except ImportError:
raise ClassNotFound("Could not find style module %r" % mod +
(builtin and ", though it should be builtin") + ".")
try:
return getattr(mod, cls)
except AttributeError:
raise ClassNotFound("Could not find style class %r in style module." % cls)
def get_all_styles():
"""Return a generator for all styles by name, both builtin and plugin."""
yield from STYLE_MAP
for name, _ in find_plugin_styles():
yield name

View file

@ -0,0 +1,213 @@
"""
pygments.token
~~~~~~~~~~~~~~
Basic token types and the standard tokens.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
class _TokenType(tuple):
parent = None
def split(self):
buf = []
node = self
while node is not None:
buf.append(node)
node = node.parent
buf.reverse()
return buf
def __init__(self, *args):
# no need to call super.__init__
self.subtypes = set()
def __contains__(self, val):
return self is val or (
type(val) is self.__class__ and
val[:len(self)] == self
)
def __getattr__(self, val):
if not val or not val[0].isupper():
return tuple.__getattribute__(self, val)
new = _TokenType(self + (val,))
setattr(self, val, new)
self.subtypes.add(new)
new.parent = self
return new
def __repr__(self):
return 'Token' + (self and '.' or '') + '.'.join(self)
def __copy__(self):
# These instances are supposed to be singletons
return self
def __deepcopy__(self, memo):
# These instances are supposed to be singletons
return self
Token = _TokenType()
# Special token types
Text = Token.Text
Whitespace = Text.Whitespace
Escape = Token.Escape
Error = Token.Error
# Text that doesn't belong to this lexer (e.g. HTML in PHP)
Other = Token.Other
# Common token types for source code
Keyword = Token.Keyword
Name = Token.Name
Literal = Token.Literal
String = Literal.String
Number = Literal.Number
Punctuation = Token.Punctuation
Operator = Token.Operator
Comment = Token.Comment
# Generic types for non-source code
Generic = Token.Generic
# String and some others are not direct children of Token.
# alias them:
Token.Token = Token
Token.String = String
Token.Number = Number
def is_token_subtype(ttype, other):
"""
Return True if ``ttype`` is a subtype of ``other``.
exists for backwards compatibility. use ``ttype in other`` now.
"""
return ttype in other
def string_to_tokentype(s):
"""
Convert a string into a token type::
>>> string_to_token('String.Double')
Token.Literal.String.Double
>>> string_to_token('Token.Literal.Number')
Token.Literal.Number
>>> string_to_token('')
Token
Tokens that are already tokens are returned unchanged:
>>> string_to_token(String)
Token.Literal.String
"""
if isinstance(s, _TokenType):
return s
if not s:
return Token
node = Token
for item in s.split('.'):
node = getattr(node, item)
return node
# Map standard token types to short names, used in CSS class naming.
# If you add a new item, please be sure to run this file to perform
# a consistency check for duplicate values.
STANDARD_TYPES = {
Token: '',
Text: '',
Whitespace: 'w',
Escape: 'esc',
Error: 'err',
Other: 'x',
Keyword: 'k',
Keyword.Constant: 'kc',
Keyword.Declaration: 'kd',
Keyword.Namespace: 'kn',
Keyword.Pseudo: 'kp',
Keyword.Reserved: 'kr',
Keyword.Type: 'kt',
Name: 'n',
Name.Attribute: 'na',
Name.Builtin: 'nb',
Name.Builtin.Pseudo: 'bp',
Name.Class: 'nc',
Name.Constant: 'no',
Name.Decorator: 'nd',
Name.Entity: 'ni',
Name.Exception: 'ne',
Name.Function: 'nf',
Name.Function.Magic: 'fm',
Name.Property: 'py',
Name.Label: 'nl',
Name.Namespace: 'nn',
Name.Other: 'nx',
Name.Tag: 'nt',
Name.Variable: 'nv',
Name.Variable.Class: 'vc',
Name.Variable.Global: 'vg',
Name.Variable.Instance: 'vi',
Name.Variable.Magic: 'vm',
Literal: 'l',
Literal.Date: 'ld',
String: 's',
String.Affix: 'sa',
String.Backtick: 'sb',
String.Char: 'sc',
String.Delimiter: 'dl',
String.Doc: 'sd',
String.Double: 's2',
String.Escape: 'se',
String.Heredoc: 'sh',
String.Interpol: 'si',
String.Other: 'sx',
String.Regex: 'sr',
String.Single: 's1',
String.Symbol: 'ss',
Number: 'm',
Number.Bin: 'mb',
Number.Float: 'mf',
Number.Hex: 'mh',
Number.Integer: 'mi',
Number.Integer.Long: 'il',
Number.Oct: 'mo',
Operator: 'o',
Operator.Word: 'ow',
Punctuation: 'p',
Punctuation.Marker: 'pm',
Comment: 'c',
Comment.Hashbang: 'ch',
Comment.Multiline: 'cm',
Comment.Preproc: 'cp',
Comment.PreprocFile: 'cpf',
Comment.Single: 'c1',
Comment.Special: 'cs',
Generic: 'g',
Generic.Deleted: 'gd',
Generic.Emph: 'ge',
Generic.Error: 'gr',
Generic.Heading: 'gh',
Generic.Inserted: 'gi',
Generic.Output: 'go',
Generic.Prompt: 'gp',
Generic.Strong: 'gs',
Generic.Subheading: 'gu',
Generic.Traceback: 'gt',
}

File diff suppressed because one or more lines are too long

View file

@ -0,0 +1,330 @@
"""
pygments.util
~~~~~~~~~~~~~
Utility functions.
:copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from io import TextIOWrapper
split_path_re = re.compile(r'[/\\ ]')
doctype_lookup_re = re.compile(r'''
<!DOCTYPE\s+(
[a-zA-Z_][a-zA-Z0-9]*
(?: \s+ # optional in HTML5
[a-zA-Z_][a-zA-Z0-9]*\s+
"[^"]*")?
)
[^>]*>
''', re.DOTALL | re.MULTILINE | re.VERBOSE)
tag_re = re.compile(r'<(.+?)(\s.*?)?>.*?</.+?>',
re.IGNORECASE | re.DOTALL | re.MULTILINE)
xml_decl_re = re.compile(r'\s*<\?xml[^>]*\?>', re.I)
class ClassNotFound(ValueError):
"""Raised if one of the lookup functions didn't find a matching class."""
class OptionError(Exception):
"""
This exception will be raised by all option processing functions if
the type or value of the argument is not correct.
"""
def get_choice_opt(options, optname, allowed, default=None, normcase=False):
"""
If the key `optname` from the dictionary is not in the sequence
`allowed`, raise an error, otherwise return it.
"""
string = options.get(optname, default)
if normcase:
string = string.lower()
if string not in allowed:
raise OptionError('Value for option %s must be one of %s' %
(optname, ', '.join(map(str, allowed))))
return string
def get_bool_opt(options, optname, default=None):
"""
Intuitively, this is `options.get(optname, default)`, but restricted to
Boolean value. The Booleans can be represented as string, in order to accept
Boolean value from the command line arguments. If the key `optname` is
present in the dictionary `options` and is not associated with a Boolean,
raise an `OptionError`. If it is absent, `default` is returned instead.
The valid string values for ``True`` are ``1``, ``yes``, ``true`` and
``on``, the ones for ``False`` are ``0``, ``no``, ``false`` and ``off``
(matched case-insensitively).
"""
string = options.get(optname, default)
if isinstance(string, bool):
return string
elif isinstance(string, int):
return bool(string)
elif not isinstance(string, str):
raise OptionError('Invalid type %r for option %s; use '
'1/0, yes/no, true/false, on/off' % (
string, optname))
elif string.lower() in ('1', 'yes', 'true', 'on'):
return True
elif string.lower() in ('0', 'no', 'false', 'off'):
return False
else:
raise OptionError('Invalid value %r for option %s; use '
'1/0, yes/no, true/false, on/off' % (
string, optname))
def get_int_opt(options, optname, default=None):
"""As :func:`get_bool_opt`, but interpret the value as an integer."""
string = options.get(optname, default)
try:
return int(string)
except TypeError:
raise OptionError('Invalid type %r for option %s; you '
'must give an integer value' % (
string, optname))
except ValueError:
raise OptionError('Invalid value %r for option %s; you '
'must give an integer value' % (
string, optname))
def get_list_opt(options, optname, default=None):
"""
If the key `optname` from the dictionary `options` is a string,
split it at whitespace and return it. If it is already a list
or a tuple, it is returned as a list.
"""
val = options.get(optname, default)
if isinstance(val, str):
return val.split()
elif isinstance(val, (list, tuple)):
return list(val)
else:
raise OptionError('Invalid type %r for option %s; you '
'must give a list value' % (
val, optname))
def docstring_headline(obj):
if not obj.__doc__:
return ''
res = []
for line in obj.__doc__.strip().splitlines():
if line.strip():
res.append(" " + line.strip())
else:
break
return ''.join(res).lstrip()
def make_analysator(f):
"""Return a static text analyser function that returns float values."""
def text_analyse(text):
try:
rv = f(text)
except Exception:
return 0.0
if not rv:
return 0.0
try:
return min(1.0, max(0.0, float(rv)))
except (ValueError, TypeError):
return 0.0
text_analyse.__doc__ = f.__doc__
return staticmethod(text_analyse)
def shebang_matches(text, regex):
r"""Check if the given regular expression matches the last part of the
shebang if one exists.
>>> from pygments.util import shebang_matches
>>> shebang_matches('#!/usr/bin/env python', r'python(2\.\d)?')
True
>>> shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?')
True
>>> shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?')
False
>>> shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?')
False
>>> shebang_matches('#!/usr/bin/startsomethingwith python',
... r'python(2\.\d)?')
True
It also checks for common windows executable file extensions::
>>> shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?')
True
Parameters (``'-f'`` or ``'--foo'`` are ignored so ``'perl'`` does
the same as ``'perl -e'``)
Note that this method automatically searches the whole string (eg:
the regular expression is wrapped in ``'^$'``)
"""
index = text.find('\n')
if index >= 0:
first_line = text[:index].lower()
else:
first_line = text.lower()
if first_line.startswith('#!'):
try:
found = [x for x in split_path_re.split(first_line[2:].strip())
if x and not x.startswith('-')][-1]
except IndexError:
return False
regex = re.compile(r'^%s(\.(exe|cmd|bat|bin))?$' % regex, re.IGNORECASE)
if regex.search(found) is not None:
return True
return False
def doctype_matches(text, regex):
"""Check if the doctype matches a regular expression (if present).
Note that this method only checks the first part of a DOCTYPE.
eg: 'html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"'
"""
m = doctype_lookup_re.search(text)
if m is None:
return False
doctype = m.group(1)
return re.compile(regex, re.I).match(doctype.strip()) is not None
def html_doctype_matches(text):
"""Check if the file looks like it has a html doctype."""
return doctype_matches(text, r'html')
_looks_like_xml_cache = {}
def looks_like_xml(text):
"""Check if a doctype exists or if we have some tags."""
if xml_decl_re.match(text):
return True
key = hash(text)
try:
return _looks_like_xml_cache[key]
except KeyError:
m = doctype_lookup_re.search(text)
if m is not None:
return True
rv = tag_re.search(text[:1000]) is not None
_looks_like_xml_cache[key] = rv
return rv
def surrogatepair(c):
"""Given a unicode character code with length greater than 16 bits,
return the two 16 bit surrogate pair.
"""
# From example D28 of:
# http://www.unicode.org/book/ch03.pdf
return (0xd7c0 + (c >> 10), (0xdc00 + (c & 0x3ff)))
def format_lines(var_name, seq, raw=False, indent_level=0):
"""Formats a sequence of strings for output."""
lines = []
base_indent = ' ' * indent_level * 4
inner_indent = ' ' * (indent_level + 1) * 4
lines.append(base_indent + var_name + ' = (')
if raw:
# These should be preformatted reprs of, say, tuples.
for i in seq:
lines.append(inner_indent + i + ',')
else:
for i in seq:
# Force use of single quotes
r = repr(i + '"')
lines.append(inner_indent + r[:-2] + r[-1] + ',')
lines.append(base_indent + ')')
return '\n'.join(lines)
def duplicates_removed(it, already_seen=()):
"""
Returns a list with duplicates removed from the iterable `it`.
Order is preserved.
"""
lst = []
seen = set()
for i in it:
if i in seen or i in already_seen:
continue
lst.append(i)
seen.add(i)
return lst
class Future:
"""Generic class to defer some work.
Handled specially in RegexLexerMeta, to support regex string construction at
first use.
"""
def get(self):
raise NotImplementedError
def guess_decode(text):
"""Decode *text* with guessed encoding.
First try UTF-8; this should fail for non-UTF-8 encodings.
Then try the preferred locale encoding.
Fall back to latin-1, which always works.
"""
try:
text = text.decode('utf-8')
return text, 'utf-8'
except UnicodeDecodeError:
try:
import locale
prefencoding = locale.getpreferredencoding()
text = text.decode()
return text, prefencoding
except (UnicodeDecodeError, LookupError):
text = text.decode('latin1')
return text, 'latin1'
def guess_decode_from_terminal(text, term):
"""Decode *text* coming from terminal *term*.
First try the terminal encoding, if given.
Then try UTF-8. Then try the preferred locale encoding.
Fall back to latin-1, which always works.
"""
if getattr(term, 'encoding', None):
try:
text = text.decode(term.encoding)
except UnicodeDecodeError:
pass
else:
return text, term.encoding
return guess_decode(text)
def terminal_encoding(term):
"""Return our best guess of encoding for the given *term*."""
if getattr(term, 'encoding', None):
return term.encoding
import locale
return locale.getpreferredencoding()
class UnclosingTextIOWrapper(TextIOWrapper):
# Don't close underlying buffer on destruction.
def close(self):
self.flush()