Загрузить файлы в «venv/Lib/site-packages/pip/_vendor/pygments»

This commit is contained in:
2026-07-02 19:25:21 +00:00
parent 3213c46f80
commit ab9b9ee191
5 changed files with 921 additions and 0 deletions

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 2006-2025 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 +1,247 @@
"""
pygments.sphinxext
~~~~~~~~~~~~~~~~~~
Sphinx extension to generate automatic documentation of lexers,
formatters and filters.
:copyright: Copyright 2006-2025 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
%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 length, col in zip(column_lengths, columns):
if col:
out.append(col.ljust(length))
else:
out.append(' '*length)
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
from pip._vendor import pygments
import inspect
import pathlib
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(f"Warning: {classname} does not have a docstring.")
docstring = cls.__doc__
if isinstance(docstring, bytes):
docstring = docstring.decode('utf8')
example_file = getattr(cls, '_example', None)
if example_file:
p = pathlib.Path(inspect.getabsfile(pygments)).parent.parent /\
'tests' / 'examplefiles' / example_file
content = p.read_text(encoding='utf-8')
if not content:
raise Exception(
f"Empty example file '{example_file}' for lexer "
f"{classname}")
if data[2]:
lexer_name = data[2][0]
docstring += '\n\n .. admonition:: Example\n'
docstring += f'\n .. code-block:: {lexer_name}\n\n'
for line in content.splitlines():
docstring += f' {line}\n'
if cls.version_added:
version_line = f'.. versionadded:: {cls.version_added}'
else:
version_line = ''
modules.setdefault(module, []).append((
classname,
', '.join(data[2]) or 'None',
', '.join(data[3]).replace('*', '\\*').replace('_', '\\') or 'None',
', '.join(data[4]) or 'None',
docstring,
version_line))
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(f"Missing docstring for {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 +1,203 @@
"""
pygments.style
~~~~~~~~~~~~~~
Basic style object.
:copyright: Copyright 2006-2025 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, f"wrong color format {text!r}"
_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 = {}
#: user-friendly style name (used when selecting the style, so this
# should be all-lowercase, no spaces, hyphens)
name = 'unnamed'
aliases = []
# 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 +1,214 @@
"""
pygments.token
~~~~~~~~~~~~~~
Basic token types and the standard tokens.
:copyright: Copyright 2006-2025 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.EmphStrong: 'ges',
Generic.Traceback: 'gt',
}

File diff suppressed because one or more lines are too long