Add files using upload-large-folder tool

lib/python3.12/site-packages/omegaconf/resolvers/__init__.py

@@ -0,0 +1,5 @@
+from omegaconf.resolvers import oc
+
+__all__ = [
+    "oc",
+]

lib/python3.12/site-packages/omegaconf/resolvers/oc/__init__.py

@@ -0,0 +1,113 @@
+import os
+import string
+import warnings
+from typing import Any, Optional
+
+from omegaconf import Container, Node
+from omegaconf._utils import _DEFAULT_MARKER_, _get_value
+from omegaconf.basecontainer import BaseContainer
+from omegaconf.errors import ConfigKeyError
+from omegaconf.grammar_parser import parse
+from omegaconf.resolvers.oc import dict
+
+
+def create(obj: Any, _parent_: Container) -> Any:
+    """Create a config object from `obj`, similar to `OmegaConf.create`"""
+    from omegaconf import OmegaConf
+
+    assert isinstance(_parent_, BaseContainer)
+    return OmegaConf.create(obj, parent=_parent_)
+
+
+def env(key: str, default: Any = _DEFAULT_MARKER_) -> Optional[str]:
+    """
+    :param key: Environment variable key
+    :param default: Optional default value to use in case the key environment variable is not set.
+                    If default is not a string, it is converted with str(default).
+                    None default is returned as is.
+    :return: The environment variable 'key'. If the environment variable is not set and a default is
+            provided, the default is used. If used, the default is converted to a string with str(default).
+            If the default is None, None is returned (without a string conversion).
+    """
+    try:
+        return os.environ[key]
+    except KeyError:
+        if default is not _DEFAULT_MARKER_:
+            return str(default) if default is not None else None
+        else:
+            raise KeyError(f"Environment variable '{key}' not found")
+
+
+def decode(expr: Optional[str], _parent_: Container, _node_: Node) -> Any:
+    """
+    Parse and evaluate `expr` according to the `singleElement` rule of the grammar.
+
+    If `expr` is `None`, then return `None`.
+    """
+    if expr is None:
+        return None
+
+    if not isinstance(expr, str):
+        raise TypeError(
+            f"`oc.decode` can only take strings or None as input, "
+            f"but `{expr}` is of type {type(expr).__name__}"
+        )
+
+    parse_tree = parse(expr, parser_rule="singleElement", lexer_mode="VALUE_MODE")
+    val = _parent_.resolve_parse_tree(parse_tree, node=_node_)
+    return _get_value(val)
+
+
+def deprecated(
+    key: str,
+    message: str = "'$OLD_KEY' is deprecated. Change your code and config to use '$NEW_KEY'",
+    *,
+    _parent_: Container,
+    _node_: Node,
+) -> Any:
+    from omegaconf._impl import select_node
+
+    if not isinstance(key, str):
+        raise TypeError(
+            f"oc.deprecated: interpolation key type is not a string ({type(key).__name__})"
+        )
+
+    if not isinstance(message, str):
+        raise TypeError(
+            f"oc.deprecated: interpolation message type is not a string ({type(message).__name__})"
+        )
+
+    full_key = _node_._get_full_key(key=None)
+    target_node = select_node(_parent_, key, absolute_key=True)
+    if target_node is None:
+        raise ConfigKeyError(
+            f"In oc.deprecated resolver at '{full_key}': Key not found: '{key}'"
+        )
+    new_key = target_node._get_full_key(key=None)
+    msg = string.Template(message).safe_substitute(
+        OLD_KEY=full_key,
+        NEW_KEY=new_key,
+    )
+    warnings.warn(category=UserWarning, message=msg)
+    return target_node
+
+
+def select(
+    key: str,
+    default: Any = _DEFAULT_MARKER_,
+    *,
+    _parent_: Container,
+) -> Any:
+    from omegaconf._impl import select_value
+
+    return select_value(cfg=_parent_, key=key, absolute_key=True, default=default)
+
+
+__all__ = [
+    "create",
+    "decode",
+    "deprecated",
+    "dict",
+    "env",
+    "select",
+]

lib/python3.12/site-packages/omegaconf/resolvers/oc/dict.py

@@ -0,0 +1,83 @@
+from typing import Any, List
+
+from omegaconf import AnyNode, Container, DictConfig, ListConfig
+from omegaconf._utils import Marker
+from omegaconf.basecontainer import BaseContainer
+from omegaconf.errors import ConfigKeyError
+
+_DEFAULT_SELECT_MARKER_: Any = Marker("_DEFAULT_SELECT_MARKER_")
+
+
+def keys(
+    key: str,
+    _parent_: Container,
+) -> ListConfig:
+    from omegaconf import OmegaConf
+
+    assert isinstance(_parent_, BaseContainer)
+
+    in_dict = _get_and_validate_dict_input(
+        key, parent=_parent_, resolver_name="oc.dict.keys"
+    )
+
+    ret = OmegaConf.create(list(in_dict.keys()), parent=_parent_)
+    assert isinstance(ret, ListConfig)
+    return ret
+
+
+def values(key: str, _root_: BaseContainer, _parent_: Container) -> ListConfig:
+    assert isinstance(_parent_, BaseContainer)
+    in_dict = _get_and_validate_dict_input(
+        key, parent=_parent_, resolver_name="oc.dict.values"
+    )
+
+    content = in_dict._content
+    assert isinstance(content, dict)
+
+    ret = ListConfig([])
+    if key.startswith("."):
+        key = f".{key}"  # extra dot to compensate for extra level of nesting within ret ListConfig
+    for k in content:
+        ref_node = AnyNode(f"${{{key}.{k!s}}}")
+        ret.append(ref_node)
+
+    # Finalize result by setting proper type and parent.
+    element_type: Any = in_dict._metadata.element_type
+    ret._metadata.element_type = element_type
+    ret._metadata.ref_type = List[element_type]
+    ret._set_parent(_parent_)
+
+    return ret
+
+
+def _get_and_validate_dict_input(
+    key: str,
+    parent: BaseContainer,
+    resolver_name: str,
+) -> DictConfig:
+    from omegaconf._impl import select_value
+
+    if not isinstance(key, str):
+        raise TypeError(
+            f"`{resolver_name}` requires a string as input, but obtained `{key}` "
+            f"of type: {type(key).__name__}"
+        )
+
+    in_dict = select_value(
+        parent,
+        key,
+        throw_on_missing=True,
+        absolute_key=True,
+        default=_DEFAULT_SELECT_MARKER_,
+    )
+
+    if in_dict is _DEFAULT_SELECT_MARKER_:
+        raise ConfigKeyError(f"Key not found: '{key}'")
+
+    if not isinstance(in_dict, DictConfig):
+        raise TypeError(
+            f"`{resolver_name}` cannot be applied to objects of type: "
+            f"{type(in_dict).__name__}"
+        )
+
+    return in_dict

lib/python3.12/site-packages/pygments/__init__.py

@@ -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 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+from io import StringIO, BytesIO
+
+__version__ = '2.19.2'
+__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 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 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)

lib/python3.12/site-packages/pygments/__main__.py

@@ -0,0 +1,17 @@
+"""
+    pygments.__main__
+    ~~~~~~~~~~~~~~~~~
+
+    Main entry point for ``python -m pygments``.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import sys
+import pygments.cmdline
+
+try:
+    sys.exit(pygments.cmdline.main(sys.argv))
+except KeyboardInterrupt:
+    sys.exit(1)

lib/python3.12/site-packages/pygments/cmdline.py

@@ -0,0 +1,668 @@
+"""
+    pygments.cmdline
+    ~~~~~~~~~~~~~~~~
+
+    Command line interface.
+
+    :copyright: Copyright 2006-2025 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 pygments import __version__, highlight
+from pygments.util import ClassNotFound, OptionError, docstring_headline, \
+    guess_decode, guess_decode_from_terminal, terminal_encoding, \
+    UnclosingTextIOWrapper
+from 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 pygments.lexers.special import TextLexer
+from pygments.formatters.latex import LatexEmbeddedLexer, LatexFormatter
+from pygments.formatters import get_all_formatters, get_formatter_by_name, \
+    load_formatter_from_file, get_formatter_for_filename, find_formatter_class
+from pygments.formatters.terminal import TerminalFormatter
+from pygments.formatters.terminal256 import Terminal256Formatter, TerminalTrueColorFormatter
+from pygments.filters import get_all_filters, find_filter_class
+from 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(f"Help on the {cls.name} lexer:")
+            print(dedent(cls.__doc__))
+        elif what == 'formatter':
+            cls = find_formatter_class(name)
+            print(f"Help on the {cls.name} formatter:")
+            print(dedent(cls.__doc__))
+        elif what == 'filter':
+            cls = find_filter_class(name)
+            print(f"Help on the {name} filter:")
+            print(dedent(cls.__doc__))
+        return 0
+    except (AttributeError, ValueError):
+        print(f"{what} not found!", 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(('* {}\n    {} {}').format(*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(('* {}\n    {} {}').format(*i))
+
+    elif what == 'filter':
+        print()
+        print("Filters:")
+        print("~~~~~~~~")
+
+        for name in get_all_filters():
+            cls = find_filter_class(name)
+            print("* " + name + ':')
+            print(f"    {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(f"    {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(f'Pygments version {__version__}, (c) 2006-2024 by Georg Brandl, Matthäus '
+              'Chajdas and contributors.')
+        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 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{})'.format(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

lib/python3.12/site-packages/pygments/console.py

@@ -0,0 +1,70 @@
+"""
+    pygments.console
+    ~~~~~~~~~~~~~~~~
+
+    Format colored console output.
+
+    :copyright: Copyright 2006-2025 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 dark, light in zip(dark_colors, light_colors):
+    codes[dark] = esc + "%im" % x
+    codes[light] = esc + "%im" % (60 + x)
+    x += 1
+
+del dark, light, 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)

lib/python3.12/site-packages/pygments/filter.py

@@ -0,0 +1,70 @@
+"""
+    pygments.filter
+    ~~~~~~~~~~~~~~~
+
+    Module that implements the default filter.
+
+    :copyright: Copyright 2006-2025 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(f'{self.__class__.__name__!r} used without bound function')
+        Filter.__init__(self, **options)
+
+    def filter(self, lexer, stream):
+        # pylint: disable=not-callable
+        yield from self.function(lexer, stream, self.options)

lib/python3.12/site-packages/pygments/filters/__init__.py

@@ -0,0 +1,940 @@
+"""
+    pygments.filters
+    ~~~~~~~~~~~~~~~~
+
+    Module containing filter lookup functions and default
+    filters.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.token import String, Comment, Keyword, Name, Error, Whitespace, \
+    string_to_tokentype
+from pygments.filter import Filter
+from pygments.util import get_list_opt, get_int_opt, get_bool_opt, \
+    get_choice_opt, ClassNotFound, OptionError
+from 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(f'filter {filtername!r} not found')
+
+
+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({})\b'.format('|'.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,
+}

lib/python3.12/site-packages/pygments/formatter.py

@@ -0,0 +1,129 @@
+"""
+    pygments.formatter
+    ~~~~~~~~~~~~~~~~~~
+
+    Base formatter class.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import codecs
+
+from pygments.util import get_bool_opt
+from 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)
+
+    # Allow writing Formatter[str] or Formatter[bytes]. That's equivalent to
+    # Formatter. This helps when using third-party type stubs from typeshed.
+    def __class_getitem__(cls, name):
+        return cls

lib/python3.12/site-packages/pygments/lexer.py

@@ -0,0 +1,961 @@
+"""
+    pygments.lexer
+    ~~~~~~~~~~~~~~
+
+    Base lexer classes.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+import sys
+import time
+
+from pygments.filter import apply_filters, Filter
+from pygments.filters import get_filter_by_name
+from pygments.token import Error, Text, Other, Whitespace, _TokenType
+from pygments.util import get_bool_opt, get_int_opt, get_list_opt, \
+    make_analysator, Future, guess_decode
+from 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 two additional attributes:
+
+    .. autoattribute:: url
+       :no-value:
+    .. autoattribute:: version_added
+       :no-value:
+
+    Lexers included in Pygments may have additional attributes:
+
+    .. autoattribute:: _example
+       :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. Set to an empty string to disable.
+    url = None
+
+    #: Version of Pygments in which the lexer was added.
+    version_added = None
+
+    #: Example file name. Relative to the ``tests/examplefiles`` directory.
+    #: This is used by the documentation generator to show an example.
+    _example = 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 f'<pygments.lexers.{self.__class__.__name__} with {self.options!r}>'
+        else:
+            return f'<pygments.lexers.{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 _preprocess_lexer_input(self, text):
+        """Apply preprocessing such as decoding the input, removing BOM and normalizing newlines."""
+
+        if not isinstance(text, str):
+            if self.encoding == 'guess':
+                text, _ = guess_decode(text)
+            elif self.encoding == 'chardet':
+                try:
+                    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'
+
+        return text
+
+    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.
+        """
+        text = self._preprocess_lexer_input(text)
+
+        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), \
+            f'token type must be simple type or callable, not {token!r}'
+        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, f'unknown new state {new_state!r}'
+        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, f'circular state ref {istate!r}'
+                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, f'unknown new state def {new_state!r}'
+
+    def _process_state(cls, unprocessed, processed, state):
+        """Preprocess a single state definition."""
+        assert isinstance(state, str), f"wrong state name {state!r}"
+        assert state[0] != '#', f"invalid state name {state!r}"
+        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, f"circular state reference {state!r}"
+                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, f"wrong rule def {tdef!r}"
+
+            try:
+                rex = cls._process_regex(tdef[0], rflags, state)
+            except Exception as err:
+                raise ValueError(f"uncompilable regex {tdef[0]!r} in state {state!r} of {cls!r}: {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, f"wrong state def: {new_state!r}"
+                        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 f'LexerContext({self.text!r}, {self.pos!r}, {self.stack!r})'
+
+
+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, f"wrong state def: {new_state!r}"
+                        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)

lib/python3.12/site-packages/pygments/modeline.py

@@ -0,0 +1,43 @@
+"""
+    pygments.modeline
+    ~~~~~~~~~~~~~~~~~
+
+    A simple modeline parser (based on pymodeline).
+
+    :copyright: Copyright 2006-2025 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): # noqa: E741
+    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 line in lines[-1:-max_lines-1:-1]:
+        ret = get_filetype_from_line(line)
+        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

lib/python3.12/site-packages/pygments/plugin.py

@@ -0,0 +1,72 @@
+"""
+    pygments.plugin
+    ~~~~~~~~~~~~~~~
+
+    Pygments plugin interface.
+
+    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 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+from importlib.metadata import entry_points
+
+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):
+    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()

lib/python3.12/site-packages/pygments/regexopt.py

@@ -0,0 +1,91 @@
+"""
+    pygments.regexopt
+    ~~~~~~~~~~~~~~~~~
+
+    An algorithm that generates optimized regexes for matching long lists of
+    literal strings.
+
+    :copyright: Copyright 2006-2025 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

lib/python3.12/site-packages/pygments/scanner.py

@@ -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
+        )

lib/python3.12/site-packages/pygments/sphinxext.py

@@ -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 pygments.lexers._mapping import LEXERS
+        import pygments.lexers
+        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 = pygments.lexers.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 pygments.lexers._mapping import LEXERS
+        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 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 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)

lib/python3.12/site-packages/pygments/style.py

@@ -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 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

lib/python3.12/site-packages/pygments/styles/colorful.py

@@ -0,0 +1,83 @@
+"""
+    pygments.styles.colorful
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    A colorful style, inspired by CodeRay.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String, Error, \
+     Number, Operator, Generic, Whitespace
+
+
+__all__ = ['ColorfulStyle']
+
+
+class ColorfulStyle(Style):
+    """
+    A colorful style, inspired by CodeRay.
+    """
+    name = 'colorful'
+
+    styles = {
+        Whitespace:                "#bbbbbb",
+
+        Comment:                   "#888",
+        Comment.Preproc:           "#579",
+        Comment.Special:           "bold #cc0000",
+
+        Keyword:                   "bold #080",
+        Keyword.Pseudo:            "#038",
+        Keyword.Type:              "#339",
+
+        Operator:                  "#333",
+        Operator.Word:             "bold #000",
+
+        Name.Builtin:              "#007020",
+        Name.Function:             "bold #06B",
+        Name.Class:                "bold #B06",
+        Name.Namespace:            "bold #0e84b5",
+        Name.Exception:            "bold #F00",
+        Name.Variable:             "#963",
+        Name.Variable.Instance:    "#33B",
+        Name.Variable.Class:       "#369",
+        Name.Variable.Global:      "bold #d70",
+        Name.Constant:             "bold #036",
+        Name.Label:                "bold #970",
+        Name.Entity:               "bold #800",
+        Name.Attribute:            "#00C",
+        Name.Tag:                  "#070",
+        Name.Decorator:            "bold #555",
+
+        String:                    "bg:#fff0f0",
+        String.Char:               "#04D bg:",
+        String.Doc:                "#D42 bg:",
+        String.Interpol:           "bg:#eee",
+        String.Escape:             "bold #666",
+        String.Regex:              "bg:#fff0ff #000",
+        String.Symbol:             "#A60 bg:",
+        String.Other:              "#D20",
+
+        Number:                    "bold #60E",
+        Number.Integer:            "bold #00D",
+        Number.Float:              "bold #60E",
+        Number.Hex:                "bold #058",
+        Number.Oct:                "bold #40E",
+
+        Generic.Heading:           "bold #000080",
+        Generic.Subheading:        "bold #800080",
+        Generic.Deleted:           "#A00000",
+        Generic.Inserted:          "#00A000",
+        Generic.Error:             "#FF0000",
+        Generic.Emph:              "italic",
+        Generic.Strong:            "bold",
+        Generic.EmphStrong:        "bold italic",
+        Generic.Prompt:            "bold #c65d09",
+        Generic.Output:            "#888",
+        Generic.Traceback:         "#04D",
+
+        Error:                     "#F00 bg:#FAA"
+    }

lib/python3.12/site-packages/pygments/styles/dracula.py

@@ -0,0 +1,90 @@
+"""
+    pygments.styles.dracula
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Pygments version of `Dracula` from https://github.com/dracula/dracula-theme.
+
+    Based on the Dracula Theme for pygments by Chris Bracco.
+    See https://github.com/dracula/pygments/tree/fee9ed5613d1086bc01b9d0a5a0e9867a009f571
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String, Error, Literal, \
+    Number, Operator, Other, Punctuation, Text, Generic, Whitespace
+
+
+__all__ = ['DraculaStyle']
+
+background = "#282a36"
+foreground = "#f8f8f2"
+selection = "#44475a"
+comment = "#6272a4"
+cyan = "#8be9fd"
+green = "#50fa7b"
+orange = "#ffb86c"
+pink = "#ff79c6"
+purple = "#bd93f9"
+red = "#ff5555"
+yellow = "#f1fa8c"
+
+deletion = "#8b080b"
+
+class DraculaStyle(Style):
+    name = 'dracula'
+
+    background_color = background
+    highlight_color = selection
+    line_number_color = yellow
+    line_number_background_color = selection
+    line_number_special_color = green
+    line_number_special_background_color = comment
+
+    styles = {
+        Whitespace: foreground,
+
+        Comment: comment,
+        Comment.Preproc: pink,
+
+        Generic: foreground,
+        Generic.Deleted: deletion,
+        Generic.Emph: "underline",
+        Generic.Heading: "bold",
+        Generic.Inserted: "bold",
+        Generic.Output: selection,
+        Generic.EmphStrong: "underline",
+        Generic.Subheading: "bold",
+
+        Error: foreground,
+
+        Keyword: pink,
+        Keyword.Constant: pink,
+        Keyword.Declaration: cyan + " italic",
+        Keyword.Type: cyan,
+
+        Literal: foreground,
+
+        Name: foreground,
+        Name.Attribute: green,
+        Name.Builtin: cyan + " italic",
+        Name.Builtin.Pseudo: foreground,
+        Name.Class: green,
+        Name.Function: green,
+        Name.Label: cyan + " italic",
+        Name.Tag: pink,
+        Name.Variable: cyan + " italic",
+
+        Number: orange,
+
+        Operator: pink,
+
+        Other: foreground,
+
+        Punctuation: foreground,
+
+        String: purple,
+
+        Text: foreground,
+    }

lib/python3.12/site-packages/pygments/styles/friendly.py

@@ -0,0 +1,76 @@
+"""
+    pygments.styles.friendly
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    A modern style based on the VIM pyte theme.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String, Error, \
+     Number, Operator, Generic, Whitespace
+
+
+__all__ = ['FriendlyStyle']
+
+
+class FriendlyStyle(Style):
+    """
+    A modern style based on the VIM pyte theme.
+    """
+    name = 'friendly'
+
+    background_color = "#f0f0f0"
+    line_number_color = "#666666"
+
+    styles = {
+        Whitespace:                "#bbbbbb",
+        Comment:                   "italic #60a0b0",
+        Comment.Preproc:           "noitalic #007020",
+        Comment.Special:           "noitalic bg:#fff0f0",
+
+        Keyword:                   "bold #007020",
+        Keyword.Pseudo:            "nobold",
+        Keyword.Type:              "nobold #902000",
+
+        Operator:                  "#666666",
+        Operator.Word:             "bold #007020",
+
+        Name.Builtin:              "#007020",
+        Name.Function:             "#06287e",
+        Name.Class:                "bold #0e84b5",
+        Name.Namespace:            "bold #0e84b5",
+        Name.Exception:            "#007020",
+        Name.Variable:             "#bb60d5",
+        Name.Constant:             "#60add5",
+        Name.Label:                "bold #002070",
+        Name.Entity:               "bold #d55537",
+        Name.Attribute:            "#4070a0",
+        Name.Tag:                  "bold #062873",
+        Name.Decorator:            "bold #555555",
+
+        String:                    "#4070a0",
+        String.Doc:                "italic",
+        String.Interpol:           "italic #70a0d0",
+        String.Escape:             "bold #4070a0",
+        String.Regex:              "#235388",
+        String.Symbol:             "#517918",
+        String.Other:              "#c65d09",
+        Number:                    "#40a070",
+
+        Generic.Heading:           "bold #000080",
+        Generic.Subheading:        "bold #800080",
+        Generic.Deleted:           "#A00000",
+        Generic.Inserted:          "#00A000",
+        Generic.Error:             "#FF0000",
+        Generic.Emph:              "italic",
+        Generic.Strong:            "bold",
+        Generic.EmphStrong:        "bold italic",
+        Generic.Prompt:            "bold #c65d09",
+        Generic.Output:            "#888",
+        Generic.Traceback:         "#04D",
+
+        Error:                     "border:#FF0000"
+    }

lib/python3.12/site-packages/pygments/styles/igor.py

@@ -0,0 +1,32 @@
+"""
+    pygments.styles.igor
+    ~~~~~~~~~~~~~~~~~~~~
+
+    Igor Pro default style.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String
+
+
+__all__ = ['IgorStyle']
+
+
+class IgorStyle(Style):
+    """
+    Pygments version of the official colors for Igor Pro procedures.
+    """
+
+    name = 'igor'
+
+    styles = {
+        Comment:                'italic #FF0000',
+        Keyword:                '#0000FF',
+        Name.Function:          '#C34E00',
+        Name.Decorator:         '#CC00A3',
+        Name.Class:             '#007575',
+        String:                 '#009C00'
+    }

lib/python3.12/site-packages/pygments/styles/inkpot.py

@@ -0,0 +1,72 @@
+"""
+    pygments.styles.inkpot
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    A highlighting style for Pygments, inspired by the Inkpot theme for VIM.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Text, Other, Keyword, Name, Comment, String, \
+    Error, Number, Operator, Generic, Whitespace, Punctuation
+
+
+__all__ = ['InkPotStyle']
+
+
+class InkPotStyle(Style):
+    name = 'inkpot'
+    
+    background_color = "#1e1e27"
+
+    styles = {
+        Text:                      "#cfbfad",
+        Other:                     "#cfbfad",
+        Whitespace:                "#434357",
+        Comment:                   "#cd8b00",
+        Comment.Preproc:           "#409090",
+        Comment.PreprocFile:       "bg:#404040 #ffcd8b",
+        Comment.Special:           "#808bed",
+
+        Keyword:                   "#808bed",
+        Keyword.Pseudo:            "nobold",
+        Keyword.Type:              "#ff8bff",
+
+        Operator:                  "#666666",
+
+        Punctuation:               "#cfbfad",
+
+        Name:                      "#cfbfad",
+        Name.Attribute:            "#cfbfad",
+        Name.Builtin.Pseudo:       '#ffff00',
+        Name.Builtin:              "#808bed",
+        Name.Class:                "#ff8bff",
+        Name.Constant:             "#409090",
+        Name.Decorator:            "#409090",
+        Name.Exception:            "#ff0000",
+        Name.Function:             "#c080d0",
+        Name.Label:                "#808bed",
+        Name.Namespace:            "#ff0000",
+        Name.Variable:             "#cfbfad",
+
+        String:                    "bg:#404040 #ffcd8b",
+        String.Doc:                "#808bed",
+
+        Number:                    "#f0ad6d",
+
+        Generic.Heading:           "bold #000080",
+        Generic.Subheading:        "bold #800080",
+        Generic.Deleted:           "#A00000",
+        Generic.Inserted:          "#00A000",
+        Generic.Error:             "#FF0000",
+        Generic.Emph:              "italic",
+        Generic.Strong:            "bold",
+        Generic.EmphStrong:        "bold italic",
+        Generic.Prompt:            "bold #000080",
+        Generic.Output:            "#888",
+        Generic.Traceback:         "#04D",
+
+        Error:                     "bg:#6e2e2e #ffffff"
+    }

lib/python3.12/site-packages/pygments/styles/lilypond.py

@@ -0,0 +1,62 @@
+"""
+    pygments.styles.lilypond
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    LilyPond-specific style.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Token
+
+
+__all__ = ['LilyPondStyle']
+
+
+class LilyPondStyle(Style):
+    """
+    Style for the LilyPond language.
+
+    .. versionadded:: 2.11
+    """
+
+    name = 'lilypond'
+    
+    # Don't show it in the gallery, it's intended for LilyPond
+    # input only and doesn't show good output on Python code.
+    web_style_gallery_exclude = True
+
+    styles = {
+        Token.Text: "",
+        Token.Keyword: "bold",
+        Token.Comment: "italic #A3AAB2",
+        Token.String: "#AB0909",
+        Token.String.Escape: "#C46C6C",
+        Token.String.Symbol: "noinherit",
+        Token.Pitch: "", #"#911520",
+        Token.Number: "#976806", # includes durations
+        # A bare 11 is not distinguishable from a number, so we highlight
+        # the same.
+        Token.ChordModifier: "#976806",
+        Token.Name.Lvalue: "#08547A",
+        Token.Name.BackslashReference: "#08547A",
+        Token.Name.Builtin.MusicCommand: "bold #08547A",
+        Token.Name.Builtin.PaperVariable: "bold #6C5A05",
+        Token.Name.Builtin.HeaderVariable: "bold #6C5A05",
+        Token.Name.Builtin.MusicFunction: "bold #08547A",
+        Token.Name.Builtin.Clef: "bold #08547A",
+        Token.Name.Builtin.Scale: "bold #08547A",
+        Token.Name.Builtin.RepeatType: "#08547A",
+        Token.Name.Builtin.Dynamic: "#68175A",
+        Token.Name.Builtin.Articulation: "#68175A",
+        Token.Name.Builtin.SchemeFunction: "bold #A83401",
+        Token.Name.Builtin.SchemeBuiltin: "bold",
+        Token.Name.Builtin.MarkupCommand: "bold #831E71",
+        Token.Name.Builtin.Context: "bold #038B8B",
+        Token.Name.Builtin.ContextProperty: "#038B8B",
+        Token.Name.Builtin.Grob: "bold #0C7441",
+        Token.Name.Builtin.GrobProperty: "#0C7441",
+        Token.Name.Builtin.Translator: "bold #6200A4",
+    }

lib/python3.12/site-packages/pygments/styles/murphy.py

@@ -0,0 +1,82 @@
+"""
+    pygments.styles.murphy
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Murphy's style from CodeRay.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String, Error, \
+     Number, Operator, Generic, Whitespace
+
+
+__all__ = ['MurphyStyle']
+
+
+class MurphyStyle(Style):
+    """
+    Murphy's style from CodeRay.
+    """
+    name = 'murphy'
+    
+    styles = {
+        Whitespace:                "#bbbbbb",
+        Comment:                   "#666 italic",
+        Comment.Preproc:           "#579 noitalic",
+        Comment.Special:           "#c00 bold",
+
+        Keyword:                   "bold #289",
+        Keyword.Pseudo:            "#08f",
+        Keyword.Type:              "#66f",
+
+        Operator:                  "#333",
+        Operator.Word:             "bold #000",
+
+        Name.Builtin:              "#072",
+        Name.Function:             "bold #5ed",
+        Name.Class:                "bold #e9e",
+        Name.Namespace:            "bold #0e84b5",
+        Name.Exception:            "bold #F00",
+        Name.Variable:             "#036",
+        Name.Variable.Instance:    "#aaf",
+        Name.Variable.Class:       "#ccf",
+        Name.Variable.Global:      "#f84",
+        Name.Constant:             "bold #5ed",
+        Name.Label:                "bold #970",
+        Name.Entity:               "#800",
+        Name.Attribute:            "#007",
+        Name.Tag:                  "#070",
+        Name.Decorator:            "bold #555",
+
+        String:                    "bg:#e0e0ff",
+        String.Char:               "#88F bg:",
+        String.Doc:                "#D42 bg:",
+        String.Interpol:           "bg:#eee",
+        String.Escape:             "bold #666",
+        String.Regex:              "bg:#e0e0ff #000",
+        String.Symbol:             "#fc8 bg:",
+        String.Other:              "#f88",
+
+        Number:                    "bold #60E",
+        Number.Integer:            "bold #66f",
+        Number.Float:              "bold #60E",
+        Number.Hex:                "bold #058",
+        Number.Oct:                "bold #40E",
+
+        Generic.Heading:           "bold #000080",
+        Generic.Subheading:        "bold #800080",
+        Generic.Deleted:           "#A00000",
+        Generic.Inserted:          "#00A000",
+        Generic.Error:             "#FF0000",
+        Generic.Emph:              "italic",
+        Generic.Strong:            "bold",
+        Generic.EmphStrong:        "bold italic",
+        Generic.Prompt:            "bold #c65d09",
+        Generic.Output:            "#888",
+        Generic.Traceback:         "#04D",
+
+        Error:                     "#F00 bg:#FAA"
+    }

lib/python3.12/site-packages/pygments/token.py

@@ -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',
+}

lib/python3.12/site-packages/pygments/unistring.py

@@ -0,0 +1,153 @@
+"""
+    pygments.unistring
+    ~~~~~~~~~~~~~~~~~~
+
+    Strings of all Unicode characters of a certain category.
+    Used for matching in Unicode-aware languages. Run to regenerate.
+
+    Inspired by chartypes_create.py from the MoinMoin project.
+
+    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+Cc = '\x00-\x1f\x7f-\x9f'
+
+Cf = '\xad\u0600-\u0605\u061c\u06dd\u070f\u08e2\u180e\u200b-\u200f\u202a-\u202e\u2060-\u2064\u2066-\u206f\ufeff\ufff9-\ufffb\U000110bd\U000110cd\U0001bca0-\U0001bca3\U0001d173-\U0001d17a\U000e0001\U000e0020-\U000e007f'
+
+Cn = '\u0378-\u0379\u0380-\u0383\u038b\u038d\u03a2\u0530\u0557-\u0558\u058b-\u058c\u0590\u05c8-\u05cf\u05eb-\u05ee\u05f5-\u05ff\u061d\u070e\u074b-\u074c\u07b2-\u07bf\u07fb-\u07fc\u082e-\u082f\u083f\u085c-\u085d\u085f\u086b-\u089f\u08b5\u08be-\u08d2\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09c5-\u09c6\u09c9-\u09ca\u09cf-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09ff-\u0a00\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a50\u0a52-\u0a58\u0a5d\u0a5f-\u0a65\u0a77-\u0a80\u0a84\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0acf\u0ad1-\u0adf\u0ae4-\u0ae5\u0af2-\u0af8\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34\u0b3a-\u0b3b\u0b45-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b64-\u0b65\u0b78-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bcf\u0bd1-\u0bd6\u0bd8-\u0be5\u0bfb-\u0bff\u0c0d\u0c11\u0c29\u0c3a-\u0c3c\u0c45\u0c49\u0c4e-\u0c54\u0c57\u0c5b-\u0c5f\u0c64-\u0c65\u0c70-\u0c77\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbb\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce4-\u0ce5\u0cf0\u0cf3-\u0cff\u0d04\u0d0d\u0d11\u0d45\u0d49\u0d50-\u0d53\u0d64-\u0d65\u0d80-\u0d81\u0d84\u0d97-\u0d99\u0db2\u0dbc\u0dbe-\u0dbf\u0dc7-\u0dc9\u0dcb-\u0dce\u0dd5\u0dd7\u0de0-\u0de5\u0df0-\u0df1\u0df5-\u0e00\u0e3b-\u0e3e\u0e5c-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0edb\u0ee0-\u0eff\u0f48\u0f6d-\u0f70\u0f98\u0fbd\u0fcd\u0fdb-\u0fff\u10c6\u10c8-\u10cc\u10ce-\u10cf\u1249\u124e-\u124f\u1257\u1259\u125e-\u125f\u1289\u128e-\u128f\u12b1\u12b6-\u12b7\u12bf\u12c1\u12c6-\u12c7\u12d7\u1311\u1316-\u1317\u135b-\u135c\u137d-\u137f\u139a-\u139f\u13f6-\u13f7\u13fe-\u13ff\u169d-\u169f\u16f9-\u16ff\u170d\u1715-\u171f\u1737-\u173f\u1754-\u175f\u176d\u1771\u1774-\u177f\u17de-\u17df\u17ea-\u17ef\u17fa-\u17ff\u180f\u181a-\u181f\u1879-\u187f\u18ab-\u18af\u18f6-\u18ff\u191f\u192c-\u192f\u193c-\u193f\u1941-\u1943\u196e-\u196f\u1975-\u197f\u19ac-\u19af\u19ca-\u19cf\u19db-\u19dd\u1a1c-\u1a1d\u1a5f\u1a7d-\u1a7e\u1a8a-\u1a8f\u1a9a-\u1a9f\u1aae-\u1aaf\u1abf-\u1aff\u1b4c-\u1b4f\u1b7d-\u1b7f\u1bf4-\u1bfb\u1c38-\u1c3a\u1c4a-\u1c4c\u1c89-\u1c8f\u1cbb-\u1cbc\u1cc8-\u1ccf\u1cfa-\u1cff\u1dfa\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fc5\u1fd4-\u1fd5\u1fdc\u1ff0-\u1ff1\u1ff5\u1fff\u2065\u2072-\u2073\u208f\u209d-\u209f\u20c0-\u20cf\u20f1-\u20ff\u218c-\u218f\u2427-\u243f\u244b-\u245f\u2b74-\u2b75\u2b96-\u2b97\u2bc9\u2bff\u2c2f\u2c5f\u2cf4-\u2cf8\u2d26\u2d28-\u2d2c\u2d2e-\u2d2f\u2d68-\u2d6e\u2d71-\u2d7e\u2d97-\u2d9f\u2da7\u2daf\u2db7\u2dbf\u2dc7\u2dcf\u2dd7\u2ddf\u2e4f-\u2e7f\u2e9a\u2ef4-\u2eff\u2fd6-\u2fef\u2ffc-\u2fff\u3040\u3097-\u3098\u3100-\u3104\u3130\u318f\u31bb-\u31bf\u31e4-\u31ef\u321f\u32ff\u4db6-\u4dbf\u9ff0-\u9fff\ua48d-\ua48f\ua4c7-\ua4cf\ua62c-\ua63f\ua6f8-\ua6ff\ua7ba-\ua7f6\ua82c-\ua82f\ua83a-\ua83f\ua878-\ua87f\ua8c6-\ua8cd\ua8da-\ua8df\ua954-\ua95e\ua97d-\ua97f\ua9ce\ua9da-\ua9dd\ua9ff\uaa37-\uaa3f\uaa4e-\uaa4f\uaa5a-\uaa5b\uaac3-\uaada\uaaf7-\uab00\uab07-\uab08\uab0f-\uab10\uab17-\uab1f\uab27\uab2f\uab66-\uab6f\uabee-\uabef\uabfa-\uabff\ud7a4-\ud7af\ud7c7-\ud7ca\ud7fc-\ud7ff\ufa6e-\ufa6f\ufada-\ufaff\ufb07-\ufb12\ufb18-\ufb1c\ufb37\ufb3d\ufb3f\ufb42\ufb45\ufbc2-\ufbd2\ufd40-\ufd4f\ufd90-\ufd91\ufdc8-\ufdef\ufdfe-\ufdff\ufe1a-\ufe1f\ufe53\ufe67\ufe6c-\ufe6f\ufe75\ufefd-\ufefe\uff00\uffbf-\uffc1\uffc8-\uffc9\uffd0-\uffd1\uffd8-\uffd9\uffdd-\uffdf\uffe7\uffef-\ufff8\ufffe-\uffff\U0001000c\U00010027\U0001003b\U0001003e\U0001004e-\U0001004f\U0001005e-\U0001007f\U000100fb-\U000100ff\U00010103-\U00010106\U00010134-\U00010136\U0001018f\U0001019c-\U0001019f\U000101a1-\U000101cf\U000101fe-\U0001027f\U0001029d-\U0001029f\U000102d1-\U000102df\U000102fc-\U000102ff\U00010324-\U0001032c\U0001034b-\U0001034f\U0001037b-\U0001037f\U0001039e\U000103c4-\U000103c7\U000103d6-\U000103ff\U0001049e-\U0001049f\U000104aa-\U000104af\U000104d4-\U000104d7\U000104fc-\U000104ff\U00010528-\U0001052f\U00010564-\U0001056e\U00010570-\U000105ff\U00010737-\U0001073f\U00010756-\U0001075f\U00010768-\U000107ff\U00010806-\U00010807\U00010809\U00010836\U00010839-\U0001083b\U0001083d-\U0001083e\U00010856\U0001089f-\U000108a6\U000108b0-\U000108df\U000108f3\U000108f6-\U000108fa\U0001091c-\U0001091e\U0001093a-\U0001093e\U00010940-\U0001097f\U000109b8-\U000109bb\U000109d0-\U000109d1\U00010a04\U00010a07-\U00010a0b\U00010a14\U00010a18\U00010a36-\U00010a37\U00010a3b-\U00010a3e\U00010a49-\U00010a4f\U00010a59-\U00010a5f\U00010aa0-\U00010abf\U00010ae7-\U00010aea\U00010af7-\U00010aff\U00010b36-\U00010b38\U00010b56-\U00010b57\U00010b73-\U00010b77\U00010b92-\U00010b98\U00010b9d-\U00010ba8\U00010bb0-\U00010bff\U00010c49-\U00010c7f\U00010cb3-\U00010cbf\U00010cf3-\U00010cf9\U00010d28-\U00010d2f\U00010d3a-\U00010e5f\U00010e7f-\U00010eff\U00010f28-\U00010f2f\U00010f5a-\U00010fff\U0001104e-\U00011051\U00011070-\U0001107e\U000110c2-\U000110cc\U000110ce-\U000110cf\U000110e9-\U000110ef\U000110fa-\U000110ff\U00011135\U00011147-\U0001114f\U00011177-\U0001117f\U000111ce-\U000111cf\U000111e0\U000111f5-\U000111ff\U00011212\U0001123f-\U0001127f\U00011287\U00011289\U0001128e\U0001129e\U000112aa-\U000112af\U000112eb-\U000112ef\U000112fa-\U000112ff\U00011304\U0001130d-\U0001130e\U00011311-\U00011312\U00011329\U00011331\U00011334\U0001133a\U00011345-\U00011346\U00011349-\U0001134a\U0001134e-\U0001134f\U00011351-\U00011356\U00011358-\U0001135c\U00011364-\U00011365\U0001136d-\U0001136f\U00011375-\U000113ff\U0001145a\U0001145c\U0001145f-\U0001147f\U000114c8-\U000114cf\U000114da-\U0001157f\U000115b6-\U000115b7\U000115de-\U000115ff\U00011645-\U0001164f\U0001165a-\U0001165f\U0001166d-\U0001167f\U000116b8-\U000116bf\U000116ca-\U000116ff\U0001171b-\U0001171c\U0001172c-\U0001172f\U00011740-\U000117ff\U0001183c-\U0001189f\U000118f3-\U000118fe\U00011900-\U000119ff\U00011a48-\U00011a4f\U00011a84-\U00011a85\U00011aa3-\U00011abf\U00011af9-\U00011bff\U00011c09\U00011c37\U00011c46-\U00011c4f\U00011c6d-\U00011c6f\U00011c90-\U00011c91\U00011ca8\U00011cb7-\U00011cff\U00011d07\U00011d0a\U00011d37-\U00011d39\U00011d3b\U00011d3e\U00011d48-\U00011d4f\U00011d5a-\U00011d5f\U00011d66\U00011d69\U00011d8f\U00011d92\U00011d99-\U00011d9f\U00011daa-\U00011edf\U00011ef9-\U00011fff\U0001239a-\U000123ff\U0001246f\U00012475-\U0001247f\U00012544-\U00012fff\U0001342f-\U000143ff\U00014647-\U000167ff\U00016a39-\U00016a3f\U00016a5f\U00016a6a-\U00016a6d\U00016a70-\U00016acf\U00016aee-\U00016aef\U00016af6-\U00016aff\U00016b46-\U00016b4f\U00016b5a\U00016b62\U00016b78-\U00016b7c\U00016b90-\U00016e3f\U00016e9b-\U00016eff\U00016f45-\U00016f4f\U00016f7f-\U00016f8e\U00016fa0-\U00016fdf\U00016fe2-\U00016fff\U000187f2-\U000187ff\U00018af3-\U0001afff\U0001b11f-\U0001b16f\U0001b2fc-\U0001bbff\U0001bc6b-\U0001bc6f\U0001bc7d-\U0001bc7f\U0001bc89-\U0001bc8f\U0001bc9a-\U0001bc9b\U0001bca4-\U0001cfff\U0001d0f6-\U0001d0ff\U0001d127-\U0001d128\U0001d1e9-\U0001d1ff\U0001d246-\U0001d2df\U0001d2f4-\U0001d2ff\U0001d357-\U0001d35f\U0001d379-\U0001d3ff\U0001d455\U0001d49d\U0001d4a0-\U0001d4a1\U0001d4a3-\U0001d4a4\U0001d4a7-\U0001d4a8\U0001d4ad\U0001d4ba\U0001d4bc\U0001d4c4\U0001d506\U0001d50b-\U0001d50c\U0001d515\U0001d51d\U0001d53a\U0001d53f\U0001d545\U0001d547-\U0001d549\U0001d551\U0001d6a6-\U0001d6a7\U0001d7cc-\U0001d7cd\U0001da8c-\U0001da9a\U0001daa0\U0001dab0-\U0001dfff\U0001e007\U0001e019-\U0001e01a\U0001e022\U0001e025\U0001e02b-\U0001e7ff\U0001e8c5-\U0001e8c6\U0001e8d7-\U0001e8ff\U0001e94b-\U0001e94f\U0001e95a-\U0001e95d\U0001e960-\U0001ec70\U0001ecb5-\U0001edff\U0001ee04\U0001ee20\U0001ee23\U0001ee25-\U0001ee26\U0001ee28\U0001ee33\U0001ee38\U0001ee3a\U0001ee3c-\U0001ee41\U0001ee43-\U0001ee46\U0001ee48\U0001ee4a\U0001ee4c\U0001ee50\U0001ee53\U0001ee55-\U0001ee56\U0001ee58\U0001ee5a\U0001ee5c\U0001ee5e\U0001ee60\U0001ee63\U0001ee65-\U0001ee66\U0001ee6b\U0001ee73\U0001ee78\U0001ee7d\U0001ee7f\U0001ee8a\U0001ee9c-\U0001eea0\U0001eea4\U0001eeaa\U0001eebc-\U0001eeef\U0001eef2-\U0001efff\U0001f02c-\U0001f02f\U0001f094-\U0001f09f\U0001f0af-\U0001f0b0\U0001f0c0\U0001f0d0\U0001f0f6-\U0001f0ff\U0001f10d-\U0001f10f\U0001f16c-\U0001f16f\U0001f1ad-\U0001f1e5\U0001f203-\U0001f20f\U0001f23c-\U0001f23f\U0001f249-\U0001f24f\U0001f252-\U0001f25f\U0001f266-\U0001f2ff\U0001f6d5-\U0001f6df\U0001f6ed-\U0001f6ef\U0001f6fa-\U0001f6ff\U0001f774-\U0001f77f\U0001f7d9-\U0001f7ff\U0001f80c-\U0001f80f\U0001f848-\U0001f84f\U0001f85a-\U0001f85f\U0001f888-\U0001f88f\U0001f8ae-\U0001f8ff\U0001f90c-\U0001f90f\U0001f93f\U0001f971-\U0001f972\U0001f977-\U0001f979\U0001f97b\U0001f9a3-\U0001f9af\U0001f9ba-\U0001f9bf\U0001f9c3-\U0001f9cf\U0001fa00-\U0001fa5f\U0001fa6e-\U0001ffff\U0002a6d7-\U0002a6ff\U0002b735-\U0002b73f\U0002b81e-\U0002b81f\U0002cea2-\U0002ceaf\U0002ebe1-\U0002f7ff\U0002fa1e-\U000e0000\U000e0002-\U000e001f\U000e0080-\U000e00ff\U000e01f0-\U000effff\U000ffffe-\U000fffff\U0010fffe-\U0010ffff'
+
+Co = '\ue000-\uf8ff\U000f0000-\U000ffffd\U00100000-\U0010fffd'
+
+Cs = '\ud800-\udbff\\\udc00\udc01-\udfff'
+
+Ll = 'a-z\xb5\xdf-\xf6\xf8-\xff\u0101\u0103\u0105\u0107\u0109\u010b\u010d\u010f\u0111\u0113\u0115\u0117\u0119\u011b\u011d\u011f\u0121\u0123\u0125\u0127\u0129\u012b\u012d\u012f\u0131\u0133\u0135\u0137-\u0138\u013a\u013c\u013e\u0140\u0142\u0144\u0146\u0148-\u0149\u014b\u014d\u014f\u0151\u0153\u0155\u0157\u0159\u015b\u015d\u015f\u0161\u0163\u0165\u0167\u0169\u016b\u016d\u016f\u0171\u0173\u0175\u0177\u017a\u017c\u017e-\u0180\u0183\u0185\u0188\u018c-\u018d\u0192\u0195\u0199-\u019b\u019e\u01a1\u01a3\u01a5\u01a8\u01aa-\u01ab\u01ad\u01b0\u01b4\u01b6\u01b9-\u01ba\u01bd-\u01bf\u01c6\u01c9\u01cc\u01ce\u01d0\u01d2\u01d4\u01d6\u01d8\u01da\u01dc-\u01dd\u01df\u01e1\u01e3\u01e5\u01e7\u01e9\u01eb\u01ed\u01ef-\u01f0\u01f3\u01f5\u01f9\u01fb\u01fd\u01ff\u0201\u0203\u0205\u0207\u0209\u020b\u020d\u020f\u0211\u0213\u0215\u0217\u0219\u021b\u021d\u021f\u0221\u0223\u0225\u0227\u0229\u022b\u022d\u022f\u0231\u0233-\u0239\u023c\u023f-\u0240\u0242\u0247\u0249\u024b\u024d\u024f-\u0293\u0295-\u02af\u0371\u0373\u0377\u037b-\u037d\u0390\u03ac-\u03ce\u03d0-\u03d1\u03d5-\u03d7\u03d9\u03db\u03dd\u03df\u03e1\u03e3\u03e5\u03e7\u03e9\u03eb\u03ed\u03ef-\u03f3\u03f5\u03f8\u03fb-\u03fc\u0430-\u045f\u0461\u0463\u0465\u0467\u0469\u046b\u046d\u046f\u0471\u0473\u0475\u0477\u0479\u047b\u047d\u047f\u0481\u048b\u048d\u048f\u0491\u0493\u0495\u0497\u0499\u049b\u049d\u049f\u04a1\u04a3\u04a5\u04a7\u04a9\u04ab\u04ad\u04af\u04b1\u04b3\u04b5\u04b7\u04b9\u04bb\u04bd\u04bf\u04c2\u04c4\u04c6\u04c8\u04ca\u04cc\u04ce-\u04cf\u04d1\u04d3\u04d5\u04d7\u04d9\u04db\u04dd\u04df\u04e1\u04e3\u04e5\u04e7\u04e9\u04eb\u04ed\u04ef\u04f1\u04f3\u04f5\u04f7\u04f9\u04fb\u04fd\u04ff\u0501\u0503\u0505\u0507\u0509\u050b\u050d\u050f\u0511\u0513\u0515\u0517\u0519\u051b\u051d\u051f\u0521\u0523\u0525\u0527\u0529\u052b\u052d\u052f\u0560-\u0588\u10d0-\u10fa\u10fd-\u10ff\u13f8-\u13fd\u1c80-\u1c88\u1d00-\u1d2b\u1d6b-\u1d77\u1d79-\u1d9a\u1e01\u1e03\u1e05\u1e07\u1e09\u1e0b\u1e0d\u1e0f\u1e11\u1e13\u1e15\u1e17\u1e19\u1e1b\u1e1d\u1e1f\u1e21\u1e23\u1e25\u1e27\u1e29\u1e2b\u1e2d\u1e2f\u1e31\u1e33\u1e35\u1e37\u1e39\u1e3b\u1e3d\u1e3f\u1e41\u1e43\u1e45\u1e47\u1e49\u1e4b\u1e4d\u1e4f\u1e51\u1e53\u1e55\u1e57\u1e59\u1e5b\u1e5d\u1e5f\u1e61\u1e63\u1e65\u1e67\u1e69\u1e6b\u1e6d\u1e6f\u1e71\u1e73\u1e75\u1e77\u1e79\u1e7b\u1e7d\u1e7f\u1e81\u1e83\u1e85\u1e87\u1e89\u1e8b\u1e8d\u1e8f\u1e91\u1e93\u1e95-\u1e9d\u1e9f\u1ea1\u1ea3\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u1eb9\u1ebb\u1ebd\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u1ec9\u1ecb\u1ecd\u1ecf\u1ed1\u1ed3\u1ed5\u1ed7\u1ed9\u1edb\u1edd\u1edf\u1ee1\u1ee3\u1ee5\u1ee7\u1ee9\u1eeb\u1eed\u1eef\u1ef1\u1ef3\u1ef5\u1ef7\u1ef9\u1efb\u1efd\u1eff-\u1f07\u1f10-\u1f15\u1f20-\u1f27\u1f30-\u1f37\u1f40-\u1f45\u1f50-\u1f57\u1f60-\u1f67\u1f70-\u1f7d\u1f80-\u1f87\u1f90-\u1f97\u1fa0-\u1fa7\u1fb0-\u1fb4\u1fb6-\u1fb7\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fc7\u1fd0-\u1fd3\u1fd6-\u1fd7\u1fe0-\u1fe7\u1ff2-\u1ff4\u1ff6-\u1ff7\u210a\u210e-\u210f\u2113\u212f\u2134\u2139\u213c-\u213d\u2146-\u2149\u214e\u2184\u2c30-\u2c5e\u2c61\u2c65-\u2c66\u2c68\u2c6a\u2c6c\u2c71\u2c73-\u2c74\u2c76-\u2c7b\u2c81\u2c83\u2c85\u2c87\u2c89\u2c8b\u2c8d\u2c8f\u2c91\u2c93\u2c95\u2c97\u2c99\u2c9b\u2c9d\u2c9f\u2ca1\u2ca3\u2ca5\u2ca7\u2ca9\u2cab\u2cad\u2caf\u2cb1\u2cb3\u2cb5\u2cb7\u2cb9\u2cbb\u2cbd\u2cbf\u2cc1\u2cc3\u2cc5\u2cc7\u2cc9\u2ccb\u2ccd\u2ccf\u2cd1\u2cd3\u2cd5\u2cd7\u2cd9\u2cdb\u2cdd\u2cdf\u2ce1\u2ce3-\u2ce4\u2cec\u2cee\u2cf3\u2d00-\u2d25\u2d27\u2d2d\ua641\ua643\ua645\ua647\ua649\ua64b\ua64d\ua64f\ua651\ua653\ua655\ua657\ua659\ua65b\ua65d\ua65f\ua661\ua663\ua665\ua667\ua669\ua66b\ua66d\ua681\ua683\ua685\ua687\ua689\ua68b\ua68d\ua68f\ua691\ua693\ua695\ua697\ua699\ua69b\ua723\ua725\ua727\ua729\ua72b\ua72d\ua72f-\ua731\ua733\ua735\ua737\ua739\ua73b\ua73d\ua73f\ua741\ua743\ua745\ua747\ua749\ua74b\ua74d\ua74f\ua751\ua753\ua755\ua757\ua759\ua75b\ua75d\ua75f\ua761\ua763\ua765\ua767\ua769\ua76b\ua76d\ua76f\ua771-\ua778\ua77a\ua77c\ua77f\ua781\ua783\ua785\ua787\ua78c\ua78e\ua791\ua793-\ua795\ua797\ua799\ua79b\ua79d\ua79f\ua7a1\ua7a3\ua7a5\ua7a7\ua7a9\ua7af\ua7b5\ua7b7\ua7b9\ua7fa\uab30-\uab5a\uab60-\uab65\uab70-\uabbf\ufb00-\ufb06\ufb13-\ufb17\uff41-\uff5a\U00010428-\U0001044f\U000104d8-\U000104fb\U00010cc0-\U00010cf2\U000118c0-\U000118df\U00016e60-\U00016e7f\U0001d41a-\U0001d433\U0001d44e-\U0001d454\U0001d456-\U0001d467\U0001d482-\U0001d49b\U0001d4b6-\U0001d4b9\U0001d4bb\U0001d4bd-\U0001d4c3\U0001d4c5-\U0001d4cf\U0001d4ea-\U0001d503\U0001d51e-\U0001d537\U0001d552-\U0001d56b\U0001d586-\U0001d59f\U0001d5ba-\U0001d5d3\U0001d5ee-\U0001d607\U0001d622-\U0001d63b\U0001d656-\U0001d66f\U0001d68a-\U0001d6a5\U0001d6c2-\U0001d6da\U0001d6dc-\U0001d6e1\U0001d6fc-\U0001d714\U0001d716-\U0001d71b\U0001d736-\U0001d74e\U0001d750-\U0001d755\U0001d770-\U0001d788\U0001d78a-\U0001d78f\U0001d7aa-\U0001d7c2\U0001d7c4-\U0001d7c9\U0001d7cb\U0001e922-\U0001e943'
+
+Lm = '\u02b0-\u02c1\u02c6-\u02d1\u02e0-\u02e4\u02ec\u02ee\u0374\u037a\u0559\u0640\u06e5-\u06e6\u07f4-\u07f5\u07fa\u081a\u0824\u0828\u0971\u0e46\u0ec6\u10fc\u17d7\u1843\u1aa7\u1c78-\u1c7d\u1d2c-\u1d6a\u1d78\u1d9b-\u1dbf\u2071\u207f\u2090-\u209c\u2c7c-\u2c7d\u2d6f\u2e2f\u3005\u3031-\u3035\u303b\u309d-\u309e\u30fc-\u30fe\ua015\ua4f8-\ua4fd\ua60c\ua67f\ua69c-\ua69d\ua717-\ua71f\ua770\ua788\ua7f8-\ua7f9\ua9cf\ua9e6\uaa70\uaadd\uaaf3-\uaaf4\uab5c-\uab5f\uff70\uff9e-\uff9f\U00016b40-\U00016b43\U00016f93-\U00016f9f\U00016fe0-\U00016fe1'
+
+Lo = '\xaa\xba\u01bb\u01c0-\u01c3\u0294\u05d0-\u05ea\u05ef-\u05f2\u0620-\u063f\u0641-\u064a\u066e-\u066f\u0671-\u06d3\u06d5\u06ee-\u06ef\u06fa-\u06fc\u06ff\u0710\u0712-\u072f\u074d-\u07a5\u07b1\u07ca-\u07ea\u0800-\u0815\u0840-\u0858\u0860-\u086a\u08a0-\u08b4\u08b6-\u08bd\u0904-\u0939\u093d\u0950\u0958-\u0961\u0972-\u0980\u0985-\u098c\u098f-\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09bd\u09ce\u09dc-\u09dd\u09df-\u09e1\u09f0-\u09f1\u09fc\u0a05-\u0a0a\u0a0f-\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32-\u0a33\u0a35-\u0a36\u0a38-\u0a39\u0a59-\u0a5c\u0a5e\u0a72-\u0a74\u0a85-\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2-\u0ab3\u0ab5-\u0ab9\u0abd\u0ad0\u0ae0-\u0ae1\u0af9\u0b05-\u0b0c\u0b0f-\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32-\u0b33\u0b35-\u0b39\u0b3d\u0b5c-\u0b5d\u0b5f-\u0b61\u0b71\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99-\u0b9a\u0b9c\u0b9e-\u0b9f\u0ba3-\u0ba4\u0ba8-\u0baa\u0bae-\u0bb9\u0bd0\u0c05-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c39\u0c3d\u0c58-\u0c5a\u0c60-\u0c61\u0c80\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cbd\u0cde\u0ce0-\u0ce1\u0cf1-\u0cf2\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d3a\u0d3d\u0d4e\u0d54-\u0d56\u0d5f-\u0d61\u0d7a-\u0d7f\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0e01-\u0e30\u0e32-\u0e33\u0e40-\u0e45\u0e81-\u0e82\u0e84\u0e87-\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa-\u0eab\u0ead-\u0eb0\u0eb2-\u0eb3\u0ebd\u0ec0-\u0ec4\u0edc-\u0edf\u0f00\u0f40-\u0f47\u0f49-\u0f6c\u0f88-\u0f8c\u1000-\u102a\u103f\u1050-\u1055\u105a-\u105d\u1061\u1065-\u1066\u106e-\u1070\u1075-\u1081\u108e\u1100-\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1288\u128a-\u128d\u1290-\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12d6\u12d8-\u1310\u1312-\u1315\u1318-\u135a\u1380-\u138f\u1401-\u166c\u166f-\u167f\u1681-\u169a\u16a0-\u16ea\u16f1-\u16f8\u1700-\u170c\u170e-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176c\u176e-\u1770\u1780-\u17b3\u17dc\u1820-\u1842\u1844-\u1878\u1880-\u1884\u1887-\u18a8\u18aa\u18b0-\u18f5\u1900-\u191e\u1950-\u196d\u1970-\u1974\u1980-\u19ab\u19b0-\u19c9\u1a00-\u1a16\u1a20-\u1a54\u1b05-\u1b33\u1b45-\u1b4b\u1b83-\u1ba0\u1bae-\u1baf\u1bba-\u1be5\u1c00-\u1c23\u1c4d-\u1c4f\u1c5a-\u1c77\u1ce9-\u1cec\u1cee-\u1cf1\u1cf5-\u1cf6\u2135-\u2138\u2d30-\u2d67\u2d80-\u2d96\u2da0-\u2da6\u2da8-\u2dae\u2db0-\u2db6\u2db8-\u2dbe\u2dc0-\u2dc6\u2dc8-\u2dce\u2dd0-\u2dd6\u2dd8-\u2dde\u3006\u303c\u3041-\u3096\u309f\u30a1-\u30fa\u30ff\u3105-\u312f\u3131-\u318e\u31a0-\u31ba\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fef\ua000-\ua014\ua016-\ua48c\ua4d0-\ua4f7\ua500-\ua60b\ua610-\ua61f\ua62a-\ua62b\ua66e\ua6a0-\ua6e5\ua78f\ua7f7\ua7fb-\ua801\ua803-\ua805\ua807-\ua80a\ua80c-\ua822\ua840-\ua873\ua882-\ua8b3\ua8f2-\ua8f7\ua8fb\ua8fd-\ua8fe\ua90a-\ua925\ua930-\ua946\ua960-\ua97c\ua984-\ua9b2\ua9e0-\ua9e4\ua9e7-\ua9ef\ua9fa-\ua9fe\uaa00-\uaa28\uaa40-\uaa42\uaa44-\uaa4b\uaa60-\uaa6f\uaa71-\uaa76\uaa7a\uaa7e-\uaaaf\uaab1\uaab5-\uaab6\uaab9-\uaabd\uaac0\uaac2\uaadb-\uaadc\uaae0-\uaaea\uaaf2\uab01-\uab06\uab09-\uab0e\uab11-\uab16\uab20-\uab26\uab28-\uab2e\uabc0-\uabe2\uac00-\ud7a3\ud7b0-\ud7c6\ud7cb-\ud7fb\uf900-\ufa6d\ufa70-\ufad9\ufb1d\ufb1f-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40-\ufb41\ufb43-\ufb44\ufb46-\ufbb1\ufbd3-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdfb\ufe70-\ufe74\ufe76-\ufefc\uff66-\uff6f\uff71-\uff9d\uffa0-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc\U00010000-\U0001000b\U0001000d-\U00010026\U00010028-\U0001003a\U0001003c-\U0001003d\U0001003f-\U0001004d\U00010050-\U0001005d\U00010080-\U000100fa\U00010280-\U0001029c\U000102a0-\U000102d0\U00010300-\U0001031f\U0001032d-\U00010340\U00010342-\U00010349\U00010350-\U00010375\U00010380-\U0001039d\U000103a0-\U000103c3\U000103c8-\U000103cf\U00010450-\U0001049d\U00010500-\U00010527\U00010530-\U00010563\U00010600-\U00010736\U00010740-\U00010755\U00010760-\U00010767\U00010800-\U00010805\U00010808\U0001080a-\U00010835\U00010837-\U00010838\U0001083c\U0001083f-\U00010855\U00010860-\U00010876\U00010880-\U0001089e\U000108e0-\U000108f2\U000108f4-\U000108f5\U00010900-\U00010915\U00010920-\U00010939\U00010980-\U000109b7\U000109be-\U000109bf\U00010a00\U00010a10-\U00010a13\U00010a15-\U00010a17\U00010a19-\U00010a35\U00010a60-\U00010a7c\U00010a80-\U00010a9c\U00010ac0-\U00010ac7\U00010ac9-\U00010ae4\U00010b00-\U00010b35\U00010b40-\U00010b55\U00010b60-\U00010b72\U00010b80-\U00010b91\U00010c00-\U00010c48\U00010d00-\U00010d23\U00010f00-\U00010f1c\U00010f27\U00010f30-\U00010f45\U00011003-\U00011037\U00011083-\U000110af\U000110d0-\U000110e8\U00011103-\U00011126\U00011144\U00011150-\U00011172\U00011176\U00011183-\U000111b2\U000111c1-\U000111c4\U000111da\U000111dc\U00011200-\U00011211\U00011213-\U0001122b\U00011280-\U00011286\U00011288\U0001128a-\U0001128d\U0001128f-\U0001129d\U0001129f-\U000112a8\U000112b0-\U000112de\U00011305-\U0001130c\U0001130f-\U00011310\U00011313-\U00011328\U0001132a-\U00011330\U00011332-\U00011333\U00011335-\U00011339\U0001133d\U00011350\U0001135d-\U00011361\U00011400-\U00011434\U00011447-\U0001144a\U00011480-\U000114af\U000114c4-\U000114c5\U000114c7\U00011580-\U000115ae\U000115d8-\U000115db\U00011600-\U0001162f\U00011644\U00011680-\U000116aa\U00011700-\U0001171a\U00011800-\U0001182b\U000118ff\U00011a00\U00011a0b-\U00011a32\U00011a3a\U00011a50\U00011a5c-\U00011a83\U00011a86-\U00011a89\U00011a9d\U00011ac0-\U00011af8\U00011c00-\U00011c08\U00011c0a-\U00011c2e\U00011c40\U00011c72-\U00011c8f\U00011d00-\U00011d06\U00011d08-\U00011d09\U00011d0b-\U00011d30\U00011d46\U00011d60-\U00011d65\U00011d67-\U00011d68\U00011d6a-\U00011d89\U00011d98\U00011ee0-\U00011ef2\U00012000-\U00012399\U00012480-\U00012543\U00013000-\U0001342e\U00014400-\U00014646\U00016800-\U00016a38\U00016a40-\U00016a5e\U00016ad0-\U00016aed\U00016b00-\U00016b2f\U00016b63-\U00016b77\U00016b7d-\U00016b8f\U00016f00-\U00016f44\U00016f50\U00017000-\U000187f1\U00018800-\U00018af2\U0001b000-\U0001b11e\U0001b170-\U0001b2fb\U0001bc00-\U0001bc6a\U0001bc70-\U0001bc7c\U0001bc80-\U0001bc88\U0001bc90-\U0001bc99\U0001e800-\U0001e8c4\U0001ee00-\U0001ee03\U0001ee05-\U0001ee1f\U0001ee21-\U0001ee22\U0001ee24\U0001ee27\U0001ee29-\U0001ee32\U0001ee34-\U0001ee37\U0001ee39\U0001ee3b\U0001ee42\U0001ee47\U0001ee49\U0001ee4b\U0001ee4d-\U0001ee4f\U0001ee51-\U0001ee52\U0001ee54\U0001ee57\U0001ee59\U0001ee5b\U0001ee5d\U0001ee5f\U0001ee61-\U0001ee62\U0001ee64\U0001ee67-\U0001ee6a\U0001ee6c-\U0001ee72\U0001ee74-\U0001ee77\U0001ee79-\U0001ee7c\U0001ee7e\U0001ee80-\U0001ee89\U0001ee8b-\U0001ee9b\U0001eea1-\U0001eea3\U0001eea5-\U0001eea9\U0001eeab-\U0001eebb\U00020000-\U0002a6d6\U0002a700-\U0002b734\U0002b740-\U0002b81d\U0002b820-\U0002cea1\U0002ceb0-\U0002ebe0\U0002f800-\U0002fa1d'
+
+Lt = '\u01c5\u01c8\u01cb\u01f2\u1f88-\u1f8f\u1f98-\u1f9f\u1fa8-\u1faf\u1fbc\u1fcc\u1ffc'
+
+Lu = 'A-Z\xc0-\xd6\xd8-\xde\u0100\u0102\u0104\u0106\u0108\u010a\u010c\u010e\u0110\u0112\u0114\u0116\u0118\u011a\u011c\u011e\u0120\u0122\u0124\u0126\u0128\u012a\u012c\u012e\u0130\u0132\u0134\u0136\u0139\u013b\u013d\u013f\u0141\u0143\u0145\u0147\u014a\u014c\u014e\u0150\u0152\u0154\u0156\u0158\u015a\u015c\u015e\u0160\u0162\u0164\u0166\u0168\u016a\u016c\u016e\u0170\u0172\u0174\u0176\u0178-\u0179\u017b\u017d\u0181-\u0182\u0184\u0186-\u0187\u0189-\u018b\u018e-\u0191\u0193-\u0194\u0196-\u0198\u019c-\u019d\u019f-\u01a0\u01a2\u01a4\u01a6-\u01a7\u01a9\u01ac\u01ae-\u01af\u01b1-\u01b3\u01b5\u01b7-\u01b8\u01bc\u01c4\u01c7\u01ca\u01cd\u01cf\u01d1\u01d3\u01d5\u01d7\u01d9\u01db\u01de\u01e0\u01e2\u01e4\u01e6\u01e8\u01ea\u01ec\u01ee\u01f1\u01f4\u01f6-\u01f8\u01fa\u01fc\u01fe\u0200\u0202\u0204\u0206\u0208\u020a\u020c\u020e\u0210\u0212\u0214\u0216\u0218\u021a\u021c\u021e\u0220\u0222\u0224\u0226\u0228\u022a\u022c\u022e\u0230\u0232\u023a-\u023b\u023d-\u023e\u0241\u0243-\u0246\u0248\u024a\u024c\u024e\u0370\u0372\u0376\u037f\u0386\u0388-\u038a\u038c\u038e-\u038f\u0391-\u03a1\u03a3-\u03ab\u03cf\u03d2-\u03d4\u03d8\u03da\u03dc\u03de\u03e0\u03e2\u03e4\u03e6\u03e8\u03ea\u03ec\u03ee\u03f4\u03f7\u03f9-\u03fa\u03fd-\u042f\u0460\u0462\u0464\u0466\u0468\u046a\u046c\u046e\u0470\u0472\u0474\u0476\u0478\u047a\u047c\u047e\u0480\u048a\u048c\u048e\u0490\u0492\u0494\u0496\u0498\u049a\u049c\u049e\u04a0\u04a2\u04a4\u04a6\u04a8\u04aa\u04ac\u04ae\u04b0\u04b2\u04b4\u04b6\u04b8\u04ba\u04bc\u04be\u04c0-\u04c1\u04c3\u04c5\u04c7\u04c9\u04cb\u04cd\u04d0\u04d2\u04d4\u04d6\u04d8\u04da\u04dc\u04de\u04e0\u04e2\u04e4\u04e6\u04e8\u04ea\u04ec\u04ee\u04f0\u04f2\u04f4\u04f6\u04f8\u04fa\u04fc\u04fe\u0500\u0502\u0504\u0506\u0508\u050a\u050c\u050e\u0510\u0512\u0514\u0516\u0518\u051a\u051c\u051e\u0520\u0522\u0524\u0526\u0528\u052a\u052c\u052e\u0531-\u0556\u10a0-\u10c5\u10c7\u10cd\u13a0-\u13f5\u1c90-\u1cba\u1cbd-\u1cbf\u1e00\u1e02\u1e04\u1e06\u1e08\u1e0a\u1e0c\u1e0e\u1e10\u1e12\u1e14\u1e16\u1e18\u1e1a\u1e1c\u1e1e\u1e20\u1e22\u1e24\u1e26\u1e28\u1e2a\u1e2c\u1e2e\u1e30\u1e32\u1e34\u1e36\u1e38\u1e3a\u1e3c\u1e3e\u1e40\u1e42\u1e44\u1e46\u1e48\u1e4a\u1e4c\u1e4e\u1e50\u1e52\u1e54\u1e56\u1e58\u1e5a\u1e5c\u1e5e\u1e60\u1e62\u1e64\u1e66\u1e68\u1e6a\u1e6c\u1e6e\u1e70\u1e72\u1e74\u1e76\u1e78\u1e7a\u1e7c\u1e7e\u1e80\u1e82\u1e84\u1e86\u1e88\u1e8a\u1e8c\u1e8e\u1e90\u1e92\u1e94\u1e9e\u1ea0\u1ea2\u1ea4\u1ea6\u1ea8\u1eaa\u1eac\u1eae\u1eb0\u1eb2\u1eb4\u1eb6\u1eb8\u1eba\u1ebc\u1ebe\u1ec0\u1ec2\u1ec4\u1ec6\u1ec8\u1eca\u1ecc\u1ece\u1ed0\u1ed2\u1ed4\u1ed6\u1ed8\u1eda\u1edc\u1ede\u1ee0\u1ee2\u1ee4\u1ee6\u1ee8\u1eea\u1eec\u1eee\u1ef0\u1ef2\u1ef4\u1ef6\u1ef8\u1efa\u1efc\u1efe\u1f08-\u1f0f\u1f18-\u1f1d\u1f28-\u1f2f\u1f38-\u1f3f\u1f48-\u1f4d\u1f59\u1f5b\u1f5d\u1f5f\u1f68-\u1f6f\u1fb8-\u1fbb\u1fc8-\u1fcb\u1fd8-\u1fdb\u1fe8-\u1fec\u1ff8-\u1ffb\u2102\u2107\u210b-\u210d\u2110-\u2112\u2115\u2119-\u211d\u2124\u2126\u2128\u212a-\u212d\u2130-\u2133\u213e-\u213f\u2145\u2183\u2c00-\u2c2e\u2c60\u2c62-\u2c64\u2c67\u2c69\u2c6b\u2c6d-\u2c70\u2c72\u2c75\u2c7e-\u2c80\u2c82\u2c84\u2c86\u2c88\u2c8a\u2c8c\u2c8e\u2c90\u2c92\u2c94\u2c96\u2c98\u2c9a\u2c9c\u2c9e\u2ca0\u2ca2\u2ca4\u2ca6\u2ca8\u2caa\u2cac\u2cae\u2cb0\u2cb2\u2cb4\u2cb6\u2cb8\u2cba\u2cbc\u2cbe\u2cc0\u2cc2\u2cc4\u2cc6\u2cc8\u2cca\u2ccc\u2cce\u2cd0\u2cd2\u2cd4\u2cd6\u2cd8\u2cda\u2cdc\u2cde\u2ce0\u2ce2\u2ceb\u2ced\u2cf2\ua640\ua642\ua644\ua646\ua648\ua64a\ua64c\ua64e\ua650\ua652\ua654\ua656\ua658\ua65a\ua65c\ua65e\ua660\ua662\ua664\ua666\ua668\ua66a\ua66c\ua680\ua682\ua684\ua686\ua688\ua68a\ua68c\ua68e\ua690\ua692\ua694\ua696\ua698\ua69a\ua722\ua724\ua726\ua728\ua72a\ua72c\ua72e\ua732\ua734\ua736\ua738\ua73a\ua73c\ua73e\ua740\ua742\ua744\ua746\ua748\ua74a\ua74c\ua74e\ua750\ua752\ua754\ua756\ua758\ua75a\ua75c\ua75e\ua760\ua762\ua764\ua766\ua768\ua76a\ua76c\ua76e\ua779\ua77b\ua77d-\ua77e\ua780\ua782\ua784\ua786\ua78b\ua78d\ua790\ua792\ua796\ua798\ua79a\ua79c\ua79e\ua7a0\ua7a2\ua7a4\ua7a6\ua7a8\ua7aa-\ua7ae\ua7b0-\ua7b4\ua7b6\ua7b8\uff21-\uff3a\U00010400-\U00010427\U000104b0-\U000104d3\U00010c80-\U00010cb2\U000118a0-\U000118bf\U00016e40-\U00016e5f\U0001d400-\U0001d419\U0001d434-\U0001d44d\U0001d468-\U0001d481\U0001d49c\U0001d49e-\U0001d49f\U0001d4a2\U0001d4a5-\U0001d4a6\U0001d4a9-\U0001d4ac\U0001d4ae-\U0001d4b5\U0001d4d0-\U0001d4e9\U0001d504-\U0001d505\U0001d507-\U0001d50a\U0001d50d-\U0001d514\U0001d516-\U0001d51c\U0001d538-\U0001d539\U0001d53b-\U0001d53e\U0001d540-\U0001d544\U0001d546\U0001d54a-\U0001d550\U0001d56c-\U0001d585\U0001d5a0-\U0001d5b9\U0001d5d4-\U0001d5ed\U0001d608-\U0001d621\U0001d63c-\U0001d655\U0001d670-\U0001d689\U0001d6a8-\U0001d6c0\U0001d6e2-\U0001d6fa\U0001d71c-\U0001d734\U0001d756-\U0001d76e\U0001d790-\U0001d7a8\U0001d7ca\U0001e900-\U0001e921'
+
+Mc = '\u0903\u093b\u093e-\u0940\u0949-\u094c\u094e-\u094f\u0982-\u0983\u09be-\u09c0\u09c7-\u09c8\u09cb-\u09cc\u09d7\u0a03\u0a3e-\u0a40\u0a83\u0abe-\u0ac0\u0ac9\u0acb-\u0acc\u0b02-\u0b03\u0b3e\u0b40\u0b47-\u0b48\u0b4b-\u0b4c\u0b57\u0bbe-\u0bbf\u0bc1-\u0bc2\u0bc6-\u0bc8\u0bca-\u0bcc\u0bd7\u0c01-\u0c03\u0c41-\u0c44\u0c82-\u0c83\u0cbe\u0cc0-\u0cc4\u0cc7-\u0cc8\u0cca-\u0ccb\u0cd5-\u0cd6\u0d02-\u0d03\u0d3e-\u0d40\u0d46-\u0d48\u0d4a-\u0d4c\u0d57\u0d82-\u0d83\u0dcf-\u0dd1\u0dd8-\u0ddf\u0df2-\u0df3\u0f3e-\u0f3f\u0f7f\u102b-\u102c\u1031\u1038\u103b-\u103c\u1056-\u1057\u1062-\u1064\u1067-\u106d\u1083-\u1084\u1087-\u108c\u108f\u109a-\u109c\u17b6\u17be-\u17c5\u17c7-\u17c8\u1923-\u1926\u1929-\u192b\u1930-\u1931\u1933-\u1938\u1a19-\u1a1a\u1a55\u1a57\u1a61\u1a63-\u1a64\u1a6d-\u1a72\u1b04\u1b35\u1b3b\u1b3d-\u1b41\u1b43-\u1b44\u1b82\u1ba1\u1ba6-\u1ba7\u1baa\u1be7\u1bea-\u1bec\u1bee\u1bf2-\u1bf3\u1c24-\u1c2b\u1c34-\u1c35\u1ce1\u1cf2-\u1cf3\u1cf7\u302e-\u302f\ua823-\ua824\ua827\ua880-\ua881\ua8b4-\ua8c3\ua952-\ua953\ua983\ua9b4-\ua9b5\ua9ba-\ua9bb\ua9bd-\ua9c0\uaa2f-\uaa30\uaa33-\uaa34\uaa4d\uaa7b\uaa7d\uaaeb\uaaee-\uaaef\uaaf5\uabe3-\uabe4\uabe6-\uabe7\uabe9-\uabea\uabec\U00011000\U00011002\U00011082\U000110b0-\U000110b2\U000110b7-\U000110b8\U0001112c\U00011145-\U00011146\U00011182\U000111b3-\U000111b5\U000111bf-\U000111c0\U0001122c-\U0001122e\U00011232-\U00011233\U00011235\U000112e0-\U000112e2\U00011302-\U00011303\U0001133e-\U0001133f\U00011341-\U00011344\U00011347-\U00011348\U0001134b-\U0001134d\U00011357\U00011362-\U00011363\U00011435-\U00011437\U00011440-\U00011441\U00011445\U000114b0-\U000114b2\U000114b9\U000114bb-\U000114be\U000114c1\U000115af-\U000115b1\U000115b8-\U000115bb\U000115be\U00011630-\U00011632\U0001163b-\U0001163c\U0001163e\U000116ac\U000116ae-\U000116af\U000116b6\U00011720-\U00011721\U00011726\U0001182c-\U0001182e\U00011838\U00011a39\U00011a57-\U00011a58\U00011a97\U00011c2f\U00011c3e\U00011ca9\U00011cb1\U00011cb4\U00011d8a-\U00011d8e\U00011d93-\U00011d94\U00011d96\U00011ef5-\U00011ef6\U00016f51-\U00016f7e\U0001d165-\U0001d166\U0001d16d-\U0001d172'
+
+Me = '\u0488-\u0489\u1abe\u20dd-\u20e0\u20e2-\u20e4\ua670-\ua672'
+
+Mn = '\u0300-\u036f\u0483-\u0487\u0591-\u05bd\u05bf\u05c1-\u05c2\u05c4-\u05c5\u05c7\u0610-\u061a\u064b-\u065f\u0670\u06d6-\u06dc\u06df-\u06e4\u06e7-\u06e8\u06ea-\u06ed\u0711\u0730-\u074a\u07a6-\u07b0\u07eb-\u07f3\u07fd\u0816-\u0819\u081b-\u0823\u0825-\u0827\u0829-\u082d\u0859-\u085b\u08d3-\u08e1\u08e3-\u0902\u093a\u093c\u0941-\u0948\u094d\u0951-\u0957\u0962-\u0963\u0981\u09bc\u09c1-\u09c4\u09cd\u09e2-\u09e3\u09fe\u0a01-\u0a02\u0a3c\u0a41-\u0a42\u0a47-\u0a48\u0a4b-\u0a4d\u0a51\u0a70-\u0a71\u0a75\u0a81-\u0a82\u0abc\u0ac1-\u0ac5\u0ac7-\u0ac8\u0acd\u0ae2-\u0ae3\u0afa-\u0aff\u0b01\u0b3c\u0b3f\u0b41-\u0b44\u0b4d\u0b56\u0b62-\u0b63\u0b82\u0bc0\u0bcd\u0c00\u0c04\u0c3e-\u0c40\u0c46-\u0c48\u0c4a-\u0c4d\u0c55-\u0c56\u0c62-\u0c63\u0c81\u0cbc\u0cbf\u0cc6\u0ccc-\u0ccd\u0ce2-\u0ce3\u0d00-\u0d01\u0d3b-\u0d3c\u0d41-\u0d44\u0d4d\u0d62-\u0d63\u0dca\u0dd2-\u0dd4\u0dd6\u0e31\u0e34-\u0e3a\u0e47-\u0e4e\u0eb1\u0eb4-\u0eb9\u0ebb-\u0ebc\u0ec8-\u0ecd\u0f18-\u0f19\u0f35\u0f37\u0f39\u0f71-\u0f7e\u0f80-\u0f84\u0f86-\u0f87\u0f8d-\u0f97\u0f99-\u0fbc\u0fc6\u102d-\u1030\u1032-\u1037\u1039-\u103a\u103d-\u103e\u1058-\u1059\u105e-\u1060\u1071-\u1074\u1082\u1085-\u1086\u108d\u109d\u135d-\u135f\u1712-\u1714\u1732-\u1734\u1752-\u1753\u1772-\u1773\u17b4-\u17b5\u17b7-\u17bd\u17c6\u17c9-\u17d3\u17dd\u180b-\u180d\u1885-\u1886\u18a9\u1920-\u1922\u1927-\u1928\u1932\u1939-\u193b\u1a17-\u1a18\u1a1b\u1a56\u1a58-\u1a5e\u1a60\u1a62\u1a65-\u1a6c\u1a73-\u1a7c\u1a7f\u1ab0-\u1abd\u1b00-\u1b03\u1b34\u1b36-\u1b3a\u1b3c\u1b42\u1b6b-\u1b73\u1b80-\u1b81\u1ba2-\u1ba5\u1ba8-\u1ba9\u1bab-\u1bad\u1be6\u1be8-\u1be9\u1bed\u1bef-\u1bf1\u1c2c-\u1c33\u1c36-\u1c37\u1cd0-\u1cd2\u1cd4-\u1ce0\u1ce2-\u1ce8\u1ced\u1cf4\u1cf8-\u1cf9\u1dc0-\u1df9\u1dfb-\u1dff\u20d0-\u20dc\u20e1\u20e5-\u20f0\u2cef-\u2cf1\u2d7f\u2de0-\u2dff\u302a-\u302d\u3099-\u309a\ua66f\ua674-\ua67d\ua69e-\ua69f\ua6f0-\ua6f1\ua802\ua806\ua80b\ua825-\ua826\ua8c4-\ua8c5\ua8e0-\ua8f1\ua8ff\ua926-\ua92d\ua947-\ua951\ua980-\ua982\ua9b3\ua9b6-\ua9b9\ua9bc\ua9e5\uaa29-\uaa2e\uaa31-\uaa32\uaa35-\uaa36\uaa43\uaa4c\uaa7c\uaab0\uaab2-\uaab4\uaab7-\uaab8\uaabe-\uaabf\uaac1\uaaec-\uaaed\uaaf6\uabe5\uabe8\uabed\ufb1e\ufe00-\ufe0f\ufe20-\ufe2f\U000101fd\U000102e0\U00010376-\U0001037a\U00010a01-\U00010a03\U00010a05-\U00010a06\U00010a0c-\U00010a0f\U00010a38-\U00010a3a\U00010a3f\U00010ae5-\U00010ae6\U00010d24-\U00010d27\U00010f46-\U00010f50\U00011001\U00011038-\U00011046\U0001107f-\U00011081\U000110b3-\U000110b6\U000110b9-\U000110ba\U00011100-\U00011102\U00011127-\U0001112b\U0001112d-\U00011134\U00011173\U00011180-\U00011181\U000111b6-\U000111be\U000111c9-\U000111cc\U0001122f-\U00011231\U00011234\U00011236-\U00011237\U0001123e\U000112df\U000112e3-\U000112ea\U00011300-\U00011301\U0001133b-\U0001133c\U00011340\U00011366-\U0001136c\U00011370-\U00011374\U00011438-\U0001143f\U00011442-\U00011444\U00011446\U0001145e\U000114b3-\U000114b8\U000114ba\U000114bf-\U000114c0\U000114c2-\U000114c3\U000115b2-\U000115b5\U000115bc-\U000115bd\U000115bf-\U000115c0\U000115dc-\U000115dd\U00011633-\U0001163a\U0001163d\U0001163f-\U00011640\U000116ab\U000116ad\U000116b0-\U000116b5\U000116b7\U0001171d-\U0001171f\U00011722-\U00011725\U00011727-\U0001172b\U0001182f-\U00011837\U00011839-\U0001183a\U00011a01-\U00011a0a\U00011a33-\U00011a38\U00011a3b-\U00011a3e\U00011a47\U00011a51-\U00011a56\U00011a59-\U00011a5b\U00011a8a-\U00011a96\U00011a98-\U00011a99\U00011c30-\U00011c36\U00011c38-\U00011c3d\U00011c3f\U00011c92-\U00011ca7\U00011caa-\U00011cb0\U00011cb2-\U00011cb3\U00011cb5-\U00011cb6\U00011d31-\U00011d36\U00011d3a\U00011d3c-\U00011d3d\U00011d3f-\U00011d45\U00011d47\U00011d90-\U00011d91\U00011d95\U00011d97\U00011ef3-\U00011ef4\U00016af0-\U00016af4\U00016b30-\U00016b36\U00016f8f-\U00016f92\U0001bc9d-\U0001bc9e\U0001d167-\U0001d169\U0001d17b-\U0001d182\U0001d185-\U0001d18b\U0001d1aa-\U0001d1ad\U0001d242-\U0001d244\U0001da00-\U0001da36\U0001da3b-\U0001da6c\U0001da75\U0001da84\U0001da9b-\U0001da9f\U0001daa1-\U0001daaf\U0001e000-\U0001e006\U0001e008-\U0001e018\U0001e01b-\U0001e021\U0001e023-\U0001e024\U0001e026-\U0001e02a\U0001e8d0-\U0001e8d6\U0001e944-\U0001e94a\U000e0100-\U000e01ef'
+
+Nd = '0-9\u0660-\u0669\u06f0-\u06f9\u07c0-\u07c9\u0966-\u096f\u09e6-\u09ef\u0a66-\u0a6f\u0ae6-\u0aef\u0b66-\u0b6f\u0be6-\u0bef\u0c66-\u0c6f\u0ce6-\u0cef\u0d66-\u0d6f\u0de6-\u0def\u0e50-\u0e59\u0ed0-\u0ed9\u0f20-\u0f29\u1040-\u1049\u1090-\u1099\u17e0-\u17e9\u1810-\u1819\u1946-\u194f\u19d0-\u19d9\u1a80-\u1a89\u1a90-\u1a99\u1b50-\u1b59\u1bb0-\u1bb9\u1c40-\u1c49\u1c50-\u1c59\ua620-\ua629\ua8d0-\ua8d9\ua900-\ua909\ua9d0-\ua9d9\ua9f0-\ua9f9\uaa50-\uaa59\uabf0-\uabf9\uff10-\uff19\U000104a0-\U000104a9\U00010d30-\U00010d39\U00011066-\U0001106f\U000110f0-\U000110f9\U00011136-\U0001113f\U000111d0-\U000111d9\U000112f0-\U000112f9\U00011450-\U00011459\U000114d0-\U000114d9\U00011650-\U00011659\U000116c0-\U000116c9\U00011730-\U00011739\U000118e0-\U000118e9\U00011c50-\U00011c59\U00011d50-\U00011d59\U00011da0-\U00011da9\U00016a60-\U00016a69\U00016b50-\U00016b59\U0001d7ce-\U0001d7ff\U0001e950-\U0001e959'
+
+Nl = '\u16ee-\u16f0\u2160-\u2182\u2185-\u2188\u3007\u3021-\u3029\u3038-\u303a\ua6e6-\ua6ef\U00010140-\U00010174\U00010341\U0001034a\U000103d1-\U000103d5\U00012400-\U0001246e'
+
+No = '\xb2-\xb3\xb9\xbc-\xbe\u09f4-\u09f9\u0b72-\u0b77\u0bf0-\u0bf2\u0c78-\u0c7e\u0d58-\u0d5e\u0d70-\u0d78\u0f2a-\u0f33\u1369-\u137c\u17f0-\u17f9\u19da\u2070\u2074-\u2079\u2080-\u2089\u2150-\u215f\u2189\u2460-\u249b\u24ea-\u24ff\u2776-\u2793\u2cfd\u3192-\u3195\u3220-\u3229\u3248-\u324f\u3251-\u325f\u3280-\u3289\u32b1-\u32bf\ua830-\ua835\U00010107-\U00010133\U00010175-\U00010178\U0001018a-\U0001018b\U000102e1-\U000102fb\U00010320-\U00010323\U00010858-\U0001085f\U00010879-\U0001087f\U000108a7-\U000108af\U000108fb-\U000108ff\U00010916-\U0001091b\U000109bc-\U000109bd\U000109c0-\U000109cf\U000109d2-\U000109ff\U00010a40-\U00010a48\U00010a7d-\U00010a7e\U00010a9d-\U00010a9f\U00010aeb-\U00010aef\U00010b58-\U00010b5f\U00010b78-\U00010b7f\U00010ba9-\U00010baf\U00010cfa-\U00010cff\U00010e60-\U00010e7e\U00010f1d-\U00010f26\U00010f51-\U00010f54\U00011052-\U00011065\U000111e1-\U000111f4\U0001173a-\U0001173b\U000118ea-\U000118f2\U00011c5a-\U00011c6c\U00016b5b-\U00016b61\U00016e80-\U00016e96\U0001d2e0-\U0001d2f3\U0001d360-\U0001d378\U0001e8c7-\U0001e8cf\U0001ec71-\U0001ecab\U0001ecad-\U0001ecaf\U0001ecb1-\U0001ecb4\U0001f100-\U0001f10c'
+
+Pc = '_\u203f-\u2040\u2054\ufe33-\ufe34\ufe4d-\ufe4f\uff3f'
+
+Pd = '\\-\u058a\u05be\u1400\u1806\u2010-\u2015\u2e17\u2e1a\u2e3a-\u2e3b\u2e40\u301c\u3030\u30a0\ufe31-\ufe32\ufe58\ufe63\uff0d'
+
+Pe = ')\\]}\u0f3b\u0f3d\u169c\u2046\u207e\u208e\u2309\u230b\u232a\u2769\u276b\u276d\u276f\u2771\u2773\u2775\u27c6\u27e7\u27e9\u27eb\u27ed\u27ef\u2984\u2986\u2988\u298a\u298c\u298e\u2990\u2992\u2994\u2996\u2998\u29d9\u29db\u29fd\u2e23\u2e25\u2e27\u2e29\u3009\u300b\u300d\u300f\u3011\u3015\u3017\u3019\u301b\u301e-\u301f\ufd3e\ufe18\ufe36\ufe38\ufe3a\ufe3c\ufe3e\ufe40\ufe42\ufe44\ufe48\ufe5a\ufe5c\ufe5e\uff09\uff3d\uff5d\uff60\uff63'
+
+Pf = '\xbb\u2019\u201d\u203a\u2e03\u2e05\u2e0a\u2e0d\u2e1d\u2e21'
+
+Pi = '\xab\u2018\u201b-\u201c\u201f\u2039\u2e02\u2e04\u2e09\u2e0c\u2e1c\u2e20'
+
+Po = "!-#%-'*,.-/:-;?-@\\\\\xa1\xa7\xb6-\xb7\xbf\u037e\u0387\u055a-\u055f\u0589\u05c0\u05c3\u05c6\u05f3-\u05f4\u0609-\u060a\u060c-\u060d\u061b\u061e-\u061f\u066a-\u066d\u06d4\u0700-\u070d\u07f7-\u07f9\u0830-\u083e\u085e\u0964-\u0965\u0970\u09fd\u0a76\u0af0\u0c84\u0df4\u0e4f\u0e5a-\u0e5b\u0f04-\u0f12\u0f14\u0f85\u0fd0-\u0fd4\u0fd9-\u0fda\u104a-\u104f\u10fb\u1360-\u1368\u166d-\u166e\u16eb-\u16ed\u1735-\u1736\u17d4-\u17d6\u17d8-\u17da\u1800-\u1805\u1807-\u180a\u1944-\u1945\u1a1e-\u1a1f\u1aa0-\u1aa6\u1aa8-\u1aad\u1b5a-\u1b60\u1bfc-\u1bff\u1c3b-\u1c3f\u1c7e-\u1c7f\u1cc0-\u1cc7\u1cd3\u2016-\u2017\u2020-\u2027\u2030-\u2038\u203b-\u203e\u2041-\u2043\u2047-\u2051\u2053\u2055-\u205e\u2cf9-\u2cfc\u2cfe-\u2cff\u2d70\u2e00-\u2e01\u2e06-\u2e08\u2e0b\u2e0e-\u2e16\u2e18-\u2e19\u2e1b\u2e1e-\u2e1f\u2e2a-\u2e2e\u2e30-\u2e39\u2e3c-\u2e3f\u2e41\u2e43-\u2e4e\u3001-\u3003\u303d\u30fb\ua4fe-\ua4ff\ua60d-\ua60f\ua673\ua67e\ua6f2-\ua6f7\ua874-\ua877\ua8ce-\ua8cf\ua8f8-\ua8fa\ua8fc\ua92e-\ua92f\ua95f\ua9c1-\ua9cd\ua9de-\ua9df\uaa5c-\uaa5f\uaade-\uaadf\uaaf0-\uaaf1\uabeb\ufe10-\ufe16\ufe19\ufe30\ufe45-\ufe46\ufe49-\ufe4c\ufe50-\ufe52\ufe54-\ufe57\ufe5f-\ufe61\ufe68\ufe6a-\ufe6b\uff01-\uff03\uff05-\uff07\uff0a\uff0c\uff0e-\uff0f\uff1a-\uff1b\uff1f-\uff20\uff3c\uff61\uff64-\uff65\U00010100-\U00010102\U0001039f\U000103d0\U0001056f\U00010857\U0001091f\U0001093f\U00010a50-\U00010a58\U00010a7f\U00010af0-\U00010af6\U00010b39-\U00010b3f\U00010b99-\U00010b9c\U00010f55-\U00010f59\U00011047-\U0001104d\U000110bb-\U000110bc\U000110be-\U000110c1\U00011140-\U00011143\U00011174-\U00011175\U000111c5-\U000111c8\U000111cd\U000111db\U000111dd-\U000111df\U00011238-\U0001123d\U000112a9\U0001144b-\U0001144f\U0001145b\U0001145d\U000114c6\U000115c1-\U000115d7\U00011641-\U00011643\U00011660-\U0001166c\U0001173c-\U0001173e\U0001183b\U00011a3f-\U00011a46\U00011a9a-\U00011a9c\U00011a9e-\U00011aa2\U00011c41-\U00011c45\U00011c70-\U00011c71\U00011ef7-\U00011ef8\U00012470-\U00012474\U00016a6e-\U00016a6f\U00016af5\U00016b37-\U00016b3b\U00016b44\U00016e97-\U00016e9a\U0001bc9f\U0001da87-\U0001da8b\U0001e95e-\U0001e95f"
+
+Ps = '(\\[{\u0f3a\u0f3c\u169b\u201a\u201e\u2045\u207d\u208d\u2308\u230a\u2329\u2768\u276a\u276c\u276e\u2770\u2772\u2774\u27c5\u27e6\u27e8\u27ea\u27ec\u27ee\u2983\u2985\u2987\u2989\u298b\u298d\u298f\u2991\u2993\u2995\u2997\u29d8\u29da\u29fc\u2e22\u2e24\u2e26\u2e28\u2e42\u3008\u300a\u300c\u300e\u3010\u3014\u3016\u3018\u301a\u301d\ufd3f\ufe17\ufe35\ufe37\ufe39\ufe3b\ufe3d\ufe3f\ufe41\ufe43\ufe47\ufe59\ufe5b\ufe5d\uff08\uff3b\uff5b\uff5f\uff62'
+
+Sc = '$\xa2-\xa5\u058f\u060b\u07fe-\u07ff\u09f2-\u09f3\u09fb\u0af1\u0bf9\u0e3f\u17db\u20a0-\u20bf\ua838\ufdfc\ufe69\uff04\uffe0-\uffe1\uffe5-\uffe6\U0001ecb0'
+
+Sk = '\\^`\xa8\xaf\xb4\xb8\u02c2-\u02c5\u02d2-\u02df\u02e5-\u02eb\u02ed\u02ef-\u02ff\u0375\u0384-\u0385\u1fbd\u1fbf-\u1fc1\u1fcd-\u1fcf\u1fdd-\u1fdf\u1fed-\u1fef\u1ffd-\u1ffe\u309b-\u309c\ua700-\ua716\ua720-\ua721\ua789-\ua78a\uab5b\ufbb2-\ufbc1\uff3e\uff40\uffe3\U0001f3fb-\U0001f3ff'
+
+Sm = '+<->|~\xac\xb1\xd7\xf7\u03f6\u0606-\u0608\u2044\u2052\u207a-\u207c\u208a-\u208c\u2118\u2140-\u2144\u214b\u2190-\u2194\u219a-\u219b\u21a0\u21a3\u21a6\u21ae\u21ce-\u21cf\u21d2\u21d4\u21f4-\u22ff\u2320-\u2321\u237c\u239b-\u23b3\u23dc-\u23e1\u25b7\u25c1\u25f8-\u25ff\u266f\u27c0-\u27c4\u27c7-\u27e5\u27f0-\u27ff\u2900-\u2982\u2999-\u29d7\u29dc-\u29fb\u29fe-\u2aff\u2b30-\u2b44\u2b47-\u2b4c\ufb29\ufe62\ufe64-\ufe66\uff0b\uff1c-\uff1e\uff5c\uff5e\uffe2\uffe9-\uffec\U0001d6c1\U0001d6db\U0001d6fb\U0001d715\U0001d735\U0001d74f\U0001d76f\U0001d789\U0001d7a9\U0001d7c3\U0001eef0-\U0001eef1'
+
+So = '\xa6\xa9\xae\xb0\u0482\u058d-\u058e\u060e-\u060f\u06de\u06e9\u06fd-\u06fe\u07f6\u09fa\u0b70\u0bf3-\u0bf8\u0bfa\u0c7f\u0d4f\u0d79\u0f01-\u0f03\u0f13\u0f15-\u0f17\u0f1a-\u0f1f\u0f34\u0f36\u0f38\u0fbe-\u0fc5\u0fc7-\u0fcc\u0fce-\u0fcf\u0fd5-\u0fd8\u109e-\u109f\u1390-\u1399\u1940\u19de-\u19ff\u1b61-\u1b6a\u1b74-\u1b7c\u2100-\u2101\u2103-\u2106\u2108-\u2109\u2114\u2116-\u2117\u211e-\u2123\u2125\u2127\u2129\u212e\u213a-\u213b\u214a\u214c-\u214d\u214f\u218a-\u218b\u2195-\u2199\u219c-\u219f\u21a1-\u21a2\u21a4-\u21a5\u21a7-\u21ad\u21af-\u21cd\u21d0-\u21d1\u21d3\u21d5-\u21f3\u2300-\u2307\u230c-\u231f\u2322-\u2328\u232b-\u237b\u237d-\u239a\u23b4-\u23db\u23e2-\u2426\u2440-\u244a\u249c-\u24e9\u2500-\u25b6\u25b8-\u25c0\u25c2-\u25f7\u2600-\u266e\u2670-\u2767\u2794-\u27bf\u2800-\u28ff\u2b00-\u2b2f\u2b45-\u2b46\u2b4d-\u2b73\u2b76-\u2b95\u2b98-\u2bc8\u2bca-\u2bfe\u2ce5-\u2cea\u2e80-\u2e99\u2e9b-\u2ef3\u2f00-\u2fd5\u2ff0-\u2ffb\u3004\u3012-\u3013\u3020\u3036-\u3037\u303e-\u303f\u3190-\u3191\u3196-\u319f\u31c0-\u31e3\u3200-\u321e\u322a-\u3247\u3250\u3260-\u327f\u328a-\u32b0\u32c0-\u32fe\u3300-\u33ff\u4dc0-\u4dff\ua490-\ua4c6\ua828-\ua82b\ua836-\ua837\ua839\uaa77-\uaa79\ufdfd\uffe4\uffe8\uffed-\uffee\ufffc-\ufffd\U00010137-\U0001013f\U00010179-\U00010189\U0001018c-\U0001018e\U00010190-\U0001019b\U000101a0\U000101d0-\U000101fc\U00010877-\U00010878\U00010ac8\U0001173f\U00016b3c-\U00016b3f\U00016b45\U0001bc9c\U0001d000-\U0001d0f5\U0001d100-\U0001d126\U0001d129-\U0001d164\U0001d16a-\U0001d16c\U0001d183-\U0001d184\U0001d18c-\U0001d1a9\U0001d1ae-\U0001d1e8\U0001d200-\U0001d241\U0001d245\U0001d300-\U0001d356\U0001d800-\U0001d9ff\U0001da37-\U0001da3a\U0001da6d-\U0001da74\U0001da76-\U0001da83\U0001da85-\U0001da86\U0001ecac\U0001f000-\U0001f02b\U0001f030-\U0001f093\U0001f0a0-\U0001f0ae\U0001f0b1-\U0001f0bf\U0001f0c1-\U0001f0cf\U0001f0d1-\U0001f0f5\U0001f110-\U0001f16b\U0001f170-\U0001f1ac\U0001f1e6-\U0001f202\U0001f210-\U0001f23b\U0001f240-\U0001f248\U0001f250-\U0001f251\U0001f260-\U0001f265\U0001f300-\U0001f3fa\U0001f400-\U0001f6d4\U0001f6e0-\U0001f6ec\U0001f6f0-\U0001f6f9\U0001f700-\U0001f773\U0001f780-\U0001f7d8\U0001f800-\U0001f80b\U0001f810-\U0001f847\U0001f850-\U0001f859\U0001f860-\U0001f887\U0001f890-\U0001f8ad\U0001f900-\U0001f90b\U0001f910-\U0001f93e\U0001f940-\U0001f970\U0001f973-\U0001f976\U0001f97a\U0001f97c-\U0001f9a2\U0001f9b0-\U0001f9b9\U0001f9c0-\U0001f9c2\U0001f9d0-\U0001f9ff\U0001fa60-\U0001fa6d'
+
+Zl = '\u2028'
+
+Zp = '\u2029'
+
+Zs = ' \xa0\u1680\u2000-\u200a\u202f\u205f\u3000'
+
+xid_continue = '0-9A-Z_a-z\xaa\xb5\xb7\xba\xc0-\xd6\xd8-\xf6\xf8-\u02c1\u02c6-\u02d1\u02e0-\u02e4\u02ec\u02ee\u0300-\u0374\u0376-\u0377\u037b-\u037d\u037f\u0386-\u038a\u038c\u038e-\u03a1\u03a3-\u03f5\u03f7-\u0481\u0483-\u0487\u048a-\u052f\u0531-\u0556\u0559\u0560-\u0588\u0591-\u05bd\u05bf\u05c1-\u05c2\u05c4-\u05c5\u05c7\u05d0-\u05ea\u05ef-\u05f2\u0610-\u061a\u0620-\u0669\u066e-\u06d3\u06d5-\u06dc\u06df-\u06e8\u06ea-\u06fc\u06ff\u0710-\u074a\u074d-\u07b1\u07c0-\u07f5\u07fa\u07fd\u0800-\u082d\u0840-\u085b\u0860-\u086a\u08a0-\u08b4\u08b6-\u08bd\u08d3-\u08e1\u08e3-\u0963\u0966-\u096f\u0971-\u0983\u0985-\u098c\u098f-\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09bc-\u09c4\u09c7-\u09c8\u09cb-\u09ce\u09d7\u09dc-\u09dd\u09df-\u09e3\u09e6-\u09f1\u09fc\u09fe\u0a01-\u0a03\u0a05-\u0a0a\u0a0f-\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32-\u0a33\u0a35-\u0a36\u0a38-\u0a39\u0a3c\u0a3e-\u0a42\u0a47-\u0a48\u0a4b-\u0a4d\u0a51\u0a59-\u0a5c\u0a5e\u0a66-\u0a75\u0a81-\u0a83\u0a85-\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2-\u0ab3\u0ab5-\u0ab9\u0abc-\u0ac5\u0ac7-\u0ac9\u0acb-\u0acd\u0ad0\u0ae0-\u0ae3\u0ae6-\u0aef\u0af9-\u0aff\u0b01-\u0b03\u0b05-\u0b0c\u0b0f-\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32-\u0b33\u0b35-\u0b39\u0b3c-\u0b44\u0b47-\u0b48\u0b4b-\u0b4d\u0b56-\u0b57\u0b5c-\u0b5d\u0b5f-\u0b63\u0b66-\u0b6f\u0b71\u0b82-\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99-\u0b9a\u0b9c\u0b9e-\u0b9f\u0ba3-\u0ba4\u0ba8-\u0baa\u0bae-\u0bb9\u0bbe-\u0bc2\u0bc6-\u0bc8\u0bca-\u0bcd\u0bd0\u0bd7\u0be6-\u0bef\u0c00-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c39\u0c3d-\u0c44\u0c46-\u0c48\u0c4a-\u0c4d\u0c55-\u0c56\u0c58-\u0c5a\u0c60-\u0c63\u0c66-\u0c6f\u0c80-\u0c83\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cbc-\u0cc4\u0cc6-\u0cc8\u0cca-\u0ccd\u0cd5-\u0cd6\u0cde\u0ce0-\u0ce3\u0ce6-\u0cef\u0cf1-\u0cf2\u0d00-\u0d03\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d44\u0d46-\u0d48\u0d4a-\u0d4e\u0d54-\u0d57\u0d5f-\u0d63\u0d66-\u0d6f\u0d7a-\u0d7f\u0d82-\u0d83\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0dca\u0dcf-\u0dd4\u0dd6\u0dd8-\u0ddf\u0de6-\u0def\u0df2-\u0df3\u0e01-\u0e3a\u0e40-\u0e4e\u0e50-\u0e59\u0e81-\u0e82\u0e84\u0e87-\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa-\u0eab\u0ead-\u0eb9\u0ebb-\u0ebd\u0ec0-\u0ec4\u0ec6\u0ec8-\u0ecd\u0ed0-\u0ed9\u0edc-\u0edf\u0f00\u0f18-\u0f19\u0f20-\u0f29\u0f35\u0f37\u0f39\u0f3e-\u0f47\u0f49-\u0f6c\u0f71-\u0f84\u0f86-\u0f97\u0f99-\u0fbc\u0fc6\u1000-\u1049\u1050-\u109d\u10a0-\u10c5\u10c7\u10cd\u10d0-\u10fa\u10fc-\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1288\u128a-\u128d\u1290-\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12d6\u12d8-\u1310\u1312-\u1315\u1318-\u135a\u135d-\u135f\u1369-\u1371\u1380-\u138f\u13a0-\u13f5\u13f8-\u13fd\u1401-\u166c\u166f-\u167f\u1681-\u169a\u16a0-\u16ea\u16ee-\u16f8\u1700-\u170c\u170e-\u1714\u1720-\u1734\u1740-\u1753\u1760-\u176c\u176e-\u1770\u1772-\u1773\u1780-\u17d3\u17d7\u17dc-\u17dd\u17e0-\u17e9\u180b-\u180d\u1810-\u1819\u1820-\u1878\u1880-\u18aa\u18b0-\u18f5\u1900-\u191e\u1920-\u192b\u1930-\u193b\u1946-\u196d\u1970-\u1974\u1980-\u19ab\u19b0-\u19c9\u19d0-\u19da\u1a00-\u1a1b\u1a20-\u1a5e\u1a60-\u1a7c\u1a7f-\u1a89\u1a90-\u1a99\u1aa7\u1ab0-\u1abd\u1b00-\u1b4b\u1b50-\u1b59\u1b6b-\u1b73\u1b80-\u1bf3\u1c00-\u1c37\u1c40-\u1c49\u1c4d-\u1c7d\u1c80-\u1c88\u1c90-\u1cba\u1cbd-\u1cbf\u1cd0-\u1cd2\u1cd4-\u1cf9\u1d00-\u1df9\u1dfb-\u1f15\u1f18-\u1f1d\u1f20-\u1f45\u1f48-\u1f4d\u1f50-\u1f57\u1f59\u1f5b\u1f5d\u1f5f-\u1f7d\u1f80-\u1fb4\u1fb6-\u1fbc\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fcc\u1fd0-\u1fd3\u1fd6-\u1fdb\u1fe0-\u1fec\u1ff2-\u1ff4\u1ff6-\u1ffc\u203f-\u2040\u2054\u2071\u207f\u2090-\u209c\u20d0-\u20dc\u20e1\u20e5-\u20f0\u2102\u2107\u210a-\u2113\u2115\u2118-\u211d\u2124\u2126\u2128\u212a-\u2139\u213c-\u213f\u2145-\u2149\u214e\u2160-\u2188\u2c00-\u2c2e\u2c30-\u2c5e\u2c60-\u2ce4\u2ceb-\u2cf3\u2d00-\u2d25\u2d27\u2d2d\u2d30-\u2d67\u2d6f\u2d7f-\u2d96\u2da0-\u2da6\u2da8-\u2dae\u2db0-\u2db6\u2db8-\u2dbe\u2dc0-\u2dc6\u2dc8-\u2dce\u2dd0-\u2dd6\u2dd8-\u2dde\u2de0-\u2dff\u3005-\u3007\u3021-\u302f\u3031-\u3035\u3038-\u303c\u3041-\u3096\u3099-\u309a\u309d-\u309f\u30a1-\u30fa\u30fc-\u30ff\u3105-\u312f\u3131-\u318e\u31a0-\u31ba\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fef\ua000-\ua48c\ua4d0-\ua4fd\ua500-\ua60c\ua610-\ua62b\ua640-\ua66f\ua674-\ua67d\ua67f-\ua6f1\ua717-\ua71f\ua722-\ua788\ua78b-\ua7b9\ua7f7-\ua827\ua840-\ua873\ua880-\ua8c5\ua8d0-\ua8d9\ua8e0-\ua8f7\ua8fb\ua8fd-\ua92d\ua930-\ua953\ua960-\ua97c\ua980-\ua9c0\ua9cf-\ua9d9\ua9e0-\ua9fe\uaa00-\uaa36\uaa40-\uaa4d\uaa50-\uaa59\uaa60-\uaa76\uaa7a-\uaac2\uaadb-\uaadd\uaae0-\uaaef\uaaf2-\uaaf6\uab01-\uab06\uab09-\uab0e\uab11-\uab16\uab20-\uab26\uab28-\uab2e\uab30-\uab5a\uab5c-\uab65\uab70-\uabea\uabec-\uabed\uabf0-\uabf9\uac00-\ud7a3\ud7b0-\ud7c6\ud7cb-\ud7fb\uf900-\ufa6d\ufa70-\ufad9\ufb00-\ufb06\ufb13-\ufb17\ufb1d-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40-\ufb41\ufb43-\ufb44\ufb46-\ufbb1\ufbd3-\ufc5d\ufc64-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdf9\ufe00-\ufe0f\ufe20-\ufe2f\ufe33-\ufe34\ufe4d-\ufe4f\ufe71\ufe73\ufe77\ufe79\ufe7b\ufe7d\ufe7f-\ufefc\uff10-\uff19\uff21-\uff3a\uff3f\uff41-\uff5a\uff66-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc\U00010000-\U0001000b\U0001000d-\U00010026\U00010028-\U0001003a\U0001003c-\U0001003d\U0001003f-\U0001004d\U00010050-\U0001005d\U00010080-\U000100fa\U00010140-\U00010174\U000101fd\U00010280-\U0001029c\U000102a0-\U000102d0\U000102e0\U00010300-\U0001031f\U0001032d-\U0001034a\U00010350-\U0001037a\U00010380-\U0001039d\U000103a0-\U000103c3\U000103c8-\U000103cf\U000103d1-\U000103d5\U00010400-\U0001049d\U000104a0-\U000104a9\U000104b0-\U000104d3\U000104d8-\U000104fb\U00010500-\U00010527\U00010530-\U00010563\U00010600-\U00010736\U00010740-\U00010755\U00010760-\U00010767\U00010800-\U00010805\U00010808\U0001080a-\U00010835\U00010837-\U00010838\U0001083c\U0001083f-\U00010855\U00010860-\U00010876\U00010880-\U0001089e\U000108e0-\U000108f2\U000108f4-\U000108f5\U00010900-\U00010915\U00010920-\U00010939\U00010980-\U000109b7\U000109be-\U000109bf\U00010a00-\U00010a03\U00010a05-\U00010a06\U00010a0c-\U00010a13\U00010a15-\U00010a17\U00010a19-\U00010a35\U00010a38-\U00010a3a\U00010a3f\U00010a60-\U00010a7c\U00010a80-\U00010a9c\U00010ac0-\U00010ac7\U00010ac9-\U00010ae6\U00010b00-\U00010b35\U00010b40-\U00010b55\U00010b60-\U00010b72\U00010b80-\U00010b91\U00010c00-\U00010c48\U00010c80-\U00010cb2\U00010cc0-\U00010cf2\U00010d00-\U00010d27\U00010d30-\U00010d39\U00010f00-\U00010f1c\U00010f27\U00010f30-\U00010f50\U00011000-\U00011046\U00011066-\U0001106f\U0001107f-\U000110ba\U000110d0-\U000110e8\U000110f0-\U000110f9\U00011100-\U00011134\U00011136-\U0001113f\U00011144-\U00011146\U00011150-\U00011173\U00011176\U00011180-\U000111c4\U000111c9-\U000111cc\U000111d0-\U000111da\U000111dc\U00011200-\U00011211\U00011213-\U00011237\U0001123e\U00011280-\U00011286\U00011288\U0001128a-\U0001128d\U0001128f-\U0001129d\U0001129f-\U000112a8\U000112b0-\U000112ea\U000112f0-\U000112f9\U00011300-\U00011303\U00011305-\U0001130c\U0001130f-\U00011310\U00011313-\U00011328\U0001132a-\U00011330\U00011332-\U00011333\U00011335-\U00011339\U0001133b-\U00011344\U00011347-\U00011348\U0001134b-\U0001134d\U00011350\U00011357\U0001135d-\U00011363\U00011366-\U0001136c\U00011370-\U00011374\U00011400-\U0001144a\U00011450-\U00011459\U0001145e\U00011480-\U000114c5\U000114c7\U000114d0-\U000114d9\U00011580-\U000115b5\U000115b8-\U000115c0\U000115d8-\U000115dd\U00011600-\U00011640\U00011644\U00011650-\U00011659\U00011680-\U000116b7\U000116c0-\U000116c9\U00011700-\U0001171a\U0001171d-\U0001172b\U00011730-\U00011739\U00011800-\U0001183a\U000118a0-\U000118e9\U000118ff\U00011a00-\U00011a3e\U00011a47\U00011a50-\U00011a83\U00011a86-\U00011a99\U00011a9d\U00011ac0-\U00011af8\U00011c00-\U00011c08\U00011c0a-\U00011c36\U00011c38-\U00011c40\U00011c50-\U00011c59\U00011c72-\U00011c8f\U00011c92-\U00011ca7\U00011ca9-\U00011cb6\U00011d00-\U00011d06\U00011d08-\U00011d09\U00011d0b-\U00011d36\U00011d3a\U00011d3c-\U00011d3d\U00011d3f-\U00011d47\U00011d50-\U00011d59\U00011d60-\U00011d65\U00011d67-\U00011d68\U00011d6a-\U00011d8e\U00011d90-\U00011d91\U00011d93-\U00011d98\U00011da0-\U00011da9\U00011ee0-\U00011ef6\U00012000-\U00012399\U00012400-\U0001246e\U00012480-\U00012543\U00013000-\U0001342e\U00014400-\U00014646\U00016800-\U00016a38\U00016a40-\U00016a5e\U00016a60-\U00016a69\U00016ad0-\U00016aed\U00016af0-\U00016af4\U00016b00-\U00016b36\U00016b40-\U00016b43\U00016b50-\U00016b59\U00016b63-\U00016b77\U00016b7d-\U00016b8f\U00016e40-\U00016e7f\U00016f00-\U00016f44\U00016f50-\U00016f7e\U00016f8f-\U00016f9f\U00016fe0-\U00016fe1\U00017000-\U000187f1\U00018800-\U00018af2\U0001b000-\U0001b11e\U0001b170-\U0001b2fb\U0001bc00-\U0001bc6a\U0001bc70-\U0001bc7c\U0001bc80-\U0001bc88\U0001bc90-\U0001bc99\U0001bc9d-\U0001bc9e\U0001d165-\U0001d169\U0001d16d-\U0001d172\U0001d17b-\U0001d182\U0001d185-\U0001d18b\U0001d1aa-\U0001d1ad\U0001d242-\U0001d244\U0001d400-\U0001d454\U0001d456-\U0001d49c\U0001d49e-\U0001d49f\U0001d4a2\U0001d4a5-\U0001d4a6\U0001d4a9-\U0001d4ac\U0001d4ae-\U0001d4b9\U0001d4bb\U0001d4bd-\U0001d4c3\U0001d4c5-\U0001d505\U0001d507-\U0001d50a\U0001d50d-\U0001d514\U0001d516-\U0001d51c\U0001d51e-\U0001d539\U0001d53b-\U0001d53e\U0001d540-\U0001d544\U0001d546\U0001d54a-\U0001d550\U0001d552-\U0001d6a5\U0001d6a8-\U0001d6c0\U0001d6c2-\U0001d6da\U0001d6dc-\U0001d6fa\U0001d6fc-\U0001d714\U0001d716-\U0001d734\U0001d736-\U0001d74e\U0001d750-\U0001d76e\U0001d770-\U0001d788\U0001d78a-\U0001d7a8\U0001d7aa-\U0001d7c2\U0001d7c4-\U0001d7cb\U0001d7ce-\U0001d7ff\U0001da00-\U0001da36\U0001da3b-\U0001da6c\U0001da75\U0001da84\U0001da9b-\U0001da9f\U0001daa1-\U0001daaf\U0001e000-\U0001e006\U0001e008-\U0001e018\U0001e01b-\U0001e021\U0001e023-\U0001e024\U0001e026-\U0001e02a\U0001e800-\U0001e8c4\U0001e8d0-\U0001e8d6\U0001e900-\U0001e94a\U0001e950-\U0001e959\U0001ee00-\U0001ee03\U0001ee05-\U0001ee1f\U0001ee21-\U0001ee22\U0001ee24\U0001ee27\U0001ee29-\U0001ee32\U0001ee34-\U0001ee37\U0001ee39\U0001ee3b\U0001ee42\U0001ee47\U0001ee49\U0001ee4b\U0001ee4d-\U0001ee4f\U0001ee51-\U0001ee52\U0001ee54\U0001ee57\U0001ee59\U0001ee5b\U0001ee5d\U0001ee5f\U0001ee61-\U0001ee62\U0001ee64\U0001ee67-\U0001ee6a\U0001ee6c-\U0001ee72\U0001ee74-\U0001ee77\U0001ee79-\U0001ee7c\U0001ee7e\U0001ee80-\U0001ee89\U0001ee8b-\U0001ee9b\U0001eea1-\U0001eea3\U0001eea5-\U0001eea9\U0001eeab-\U0001eebb\U00020000-\U0002a6d6\U0002a700-\U0002b734\U0002b740-\U0002b81d\U0002b820-\U0002cea1\U0002ceb0-\U0002ebe0\U0002f800-\U0002fa1d\U000e0100-\U000e01ef'
+
+xid_start = 'A-Z_a-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\u02c1\u02c6-\u02d1\u02e0-\u02e4\u02ec\u02ee\u0370-\u0374\u0376-\u0377\u037b-\u037d\u037f\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03a3-\u03f5\u03f7-\u0481\u048a-\u052f\u0531-\u0556\u0559\u0560-\u0588\u05d0-\u05ea\u05ef-\u05f2\u0620-\u064a\u066e-\u066f\u0671-\u06d3\u06d5\u06e5-\u06e6\u06ee-\u06ef\u06fa-\u06fc\u06ff\u0710\u0712-\u072f\u074d-\u07a5\u07b1\u07ca-\u07ea\u07f4-\u07f5\u07fa\u0800-\u0815\u081a\u0824\u0828\u0840-\u0858\u0860-\u086a\u08a0-\u08b4\u08b6-\u08bd\u0904-\u0939\u093d\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098c\u098f-\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09bd\u09ce\u09dc-\u09dd\u09df-\u09e1\u09f0-\u09f1\u09fc\u0a05-\u0a0a\u0a0f-\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32-\u0a33\u0a35-\u0a36\u0a38-\u0a39\u0a59-\u0a5c\u0a5e\u0a72-\u0a74\u0a85-\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2-\u0ab3\u0ab5-\u0ab9\u0abd\u0ad0\u0ae0-\u0ae1\u0af9\u0b05-\u0b0c\u0b0f-\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32-\u0b33\u0b35-\u0b39\u0b3d\u0b5c-\u0b5d\u0b5f-\u0b61\u0b71\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99-\u0b9a\u0b9c\u0b9e-\u0b9f\u0ba3-\u0ba4\u0ba8-\u0baa\u0bae-\u0bb9\u0bd0\u0c05-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c39\u0c3d\u0c58-\u0c5a\u0c60-\u0c61\u0c80\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cbd\u0cde\u0ce0-\u0ce1\u0cf1-\u0cf2\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d3a\u0d3d\u0d4e\u0d54-\u0d56\u0d5f-\u0d61\u0d7a-\u0d7f\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0e01-\u0e30\u0e32\u0e40-\u0e46\u0e81-\u0e82\u0e84\u0e87-\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa-\u0eab\u0ead-\u0eb0\u0eb2\u0ebd\u0ec0-\u0ec4\u0ec6\u0edc-\u0edf\u0f00\u0f40-\u0f47\u0f49-\u0f6c\u0f88-\u0f8c\u1000-\u102a\u103f\u1050-\u1055\u105a-\u105d\u1061\u1065-\u1066\u106e-\u1070\u1075-\u1081\u108e\u10a0-\u10c5\u10c7\u10cd\u10d0-\u10fa\u10fc-\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1288\u128a-\u128d\u1290-\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12d6\u12d8-\u1310\u1312-\u1315\u1318-\u135a\u1380-\u138f\u13a0-\u13f5\u13f8-\u13fd\u1401-\u166c\u166f-\u167f\u1681-\u169a\u16a0-\u16ea\u16ee-\u16f8\u1700-\u170c\u170e-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176c\u176e-\u1770\u1780-\u17b3\u17d7\u17dc\u1820-\u1878\u1880-\u18a8\u18aa\u18b0-\u18f5\u1900-\u191e\u1950-\u196d\u1970-\u1974\u1980-\u19ab\u19b0-\u19c9\u1a00-\u1a16\u1a20-\u1a54\u1aa7\u1b05-\u1b33\u1b45-\u1b4b\u1b83-\u1ba0\u1bae-\u1baf\u1bba-\u1be5\u1c00-\u1c23\u1c4d-\u1c4f\u1c5a-\u1c7d\u1c80-\u1c88\u1c90-\u1cba\u1cbd-\u1cbf\u1ce9-\u1cec\u1cee-\u1cf1\u1cf5-\u1cf6\u1d00-\u1dbf\u1e00-\u1f15\u1f18-\u1f1d\u1f20-\u1f45\u1f48-\u1f4d\u1f50-\u1f57\u1f59\u1f5b\u1f5d\u1f5f-\u1f7d\u1f80-\u1fb4\u1fb6-\u1fbc\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fcc\u1fd0-\u1fd3\u1fd6-\u1fdb\u1fe0-\u1fec\u1ff2-\u1ff4\u1ff6-\u1ffc\u2071\u207f\u2090-\u209c\u2102\u2107\u210a-\u2113\u2115\u2118-\u211d\u2124\u2126\u2128\u212a-\u2139\u213c-\u213f\u2145-\u2149\u214e\u2160-\u2188\u2c00-\u2c2e\u2c30-\u2c5e\u2c60-\u2ce4\u2ceb-\u2cee\u2cf2-\u2cf3\u2d00-\u2d25\u2d27\u2d2d\u2d30-\u2d67\u2d6f\u2d80-\u2d96\u2da0-\u2da6\u2da8-\u2dae\u2db0-\u2db6\u2db8-\u2dbe\u2dc0-\u2dc6\u2dc8-\u2dce\u2dd0-\u2dd6\u2dd8-\u2dde\u3005-\u3007\u3021-\u3029\u3031-\u3035\u3038-\u303c\u3041-\u3096\u309d-\u309f\u30a1-\u30fa\u30fc-\u30ff\u3105-\u312f\u3131-\u318e\u31a0-\u31ba\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fef\ua000-\ua48c\ua4d0-\ua4fd\ua500-\ua60c\ua610-\ua61f\ua62a-\ua62b\ua640-\ua66e\ua67f-\ua69d\ua6a0-\ua6ef\ua717-\ua71f\ua722-\ua788\ua78b-\ua7b9\ua7f7-\ua801\ua803-\ua805\ua807-\ua80a\ua80c-\ua822\ua840-\ua873\ua882-\ua8b3\ua8f2-\ua8f7\ua8fb\ua8fd-\ua8fe\ua90a-\ua925\ua930-\ua946\ua960-\ua97c\ua984-\ua9b2\ua9cf\ua9e0-\ua9e4\ua9e6-\ua9ef\ua9fa-\ua9fe\uaa00-\uaa28\uaa40-\uaa42\uaa44-\uaa4b\uaa60-\uaa76\uaa7a\uaa7e-\uaaaf\uaab1\uaab5-\uaab6\uaab9-\uaabd\uaac0\uaac2\uaadb-\uaadd\uaae0-\uaaea\uaaf2-\uaaf4\uab01-\uab06\uab09-\uab0e\uab11-\uab16\uab20-\uab26\uab28-\uab2e\uab30-\uab5a\uab5c-\uab65\uab70-\uabe2\uac00-\ud7a3\ud7b0-\ud7c6\ud7cb-\ud7fb\uf900-\ufa6d\ufa70-\ufad9\ufb00-\ufb06\ufb13-\ufb17\ufb1d\ufb1f-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40-\ufb41\ufb43-\ufb44\ufb46-\ufbb1\ufbd3-\ufc5d\ufc64-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdf9\ufe71\ufe73\ufe77\ufe79\ufe7b\ufe7d\ufe7f-\ufefc\uff21-\uff3a\uff41-\uff5a\uff66-\uff9d\uffa0-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc\U00010000-\U0001000b\U0001000d-\U00010026\U00010028-\U0001003a\U0001003c-\U0001003d\U0001003f-\U0001004d\U00010050-\U0001005d\U00010080-\U000100fa\U00010140-\U00010174\U00010280-\U0001029c\U000102a0-\U000102d0\U00010300-\U0001031f\U0001032d-\U0001034a\U00010350-\U00010375\U00010380-\U0001039d\U000103a0-\U000103c3\U000103c8-\U000103cf\U000103d1-\U000103d5\U00010400-\U0001049d\U000104b0-\U000104d3\U000104d8-\U000104fb\U00010500-\U00010527\U00010530-\U00010563\U00010600-\U00010736\U00010740-\U00010755\U00010760-\U00010767\U00010800-\U00010805\U00010808\U0001080a-\U00010835\U00010837-\U00010838\U0001083c\U0001083f-\U00010855\U00010860-\U00010876\U00010880-\U0001089e\U000108e0-\U000108f2\U000108f4-\U000108f5\U00010900-\U00010915\U00010920-\U00010939\U00010980-\U000109b7\U000109be-\U000109bf\U00010a00\U00010a10-\U00010a13\U00010a15-\U00010a17\U00010a19-\U00010a35\U00010a60-\U00010a7c\U00010a80-\U00010a9c\U00010ac0-\U00010ac7\U00010ac9-\U00010ae4\U00010b00-\U00010b35\U00010b40-\U00010b55\U00010b60-\U00010b72\U00010b80-\U00010b91\U00010c00-\U00010c48\U00010c80-\U00010cb2\U00010cc0-\U00010cf2\U00010d00-\U00010d23\U00010f00-\U00010f1c\U00010f27\U00010f30-\U00010f45\U00011003-\U00011037\U00011083-\U000110af\U000110d0-\U000110e8\U00011103-\U00011126\U00011144\U00011150-\U00011172\U00011176\U00011183-\U000111b2\U000111c1-\U000111c4\U000111da\U000111dc\U00011200-\U00011211\U00011213-\U0001122b\U00011280-\U00011286\U00011288\U0001128a-\U0001128d\U0001128f-\U0001129d\U0001129f-\U000112a8\U000112b0-\U000112de\U00011305-\U0001130c\U0001130f-\U00011310\U00011313-\U00011328\U0001132a-\U00011330\U00011332-\U00011333\U00011335-\U00011339\U0001133d\U00011350\U0001135d-\U00011361\U00011400-\U00011434\U00011447-\U0001144a\U00011480-\U000114af\U000114c4-\U000114c5\U000114c7\U00011580-\U000115ae\U000115d8-\U000115db\U00011600-\U0001162f\U00011644\U00011680-\U000116aa\U00011700-\U0001171a\U00011800-\U0001182b\U000118a0-\U000118df\U000118ff\U00011a00\U00011a0b-\U00011a32\U00011a3a\U00011a50\U00011a5c-\U00011a83\U00011a86-\U00011a89\U00011a9d\U00011ac0-\U00011af8\U00011c00-\U00011c08\U00011c0a-\U00011c2e\U00011c40\U00011c72-\U00011c8f\U00011d00-\U00011d06\U00011d08-\U00011d09\U00011d0b-\U00011d30\U00011d46\U00011d60-\U00011d65\U00011d67-\U00011d68\U00011d6a-\U00011d89\U00011d98\U00011ee0-\U00011ef2\U00012000-\U00012399\U00012400-\U0001246e\U00012480-\U00012543\U00013000-\U0001342e\U00014400-\U00014646\U00016800-\U00016a38\U00016a40-\U00016a5e\U00016ad0-\U00016aed\U00016b00-\U00016b2f\U00016b40-\U00016b43\U00016b63-\U00016b77\U00016b7d-\U00016b8f\U00016e40-\U00016e7f\U00016f00-\U00016f44\U00016f50\U00016f93-\U00016f9f\U00016fe0-\U00016fe1\U00017000-\U000187f1\U00018800-\U00018af2\U0001b000-\U0001b11e\U0001b170-\U0001b2fb\U0001bc00-\U0001bc6a\U0001bc70-\U0001bc7c\U0001bc80-\U0001bc88\U0001bc90-\U0001bc99\U0001d400-\U0001d454\U0001d456-\U0001d49c\U0001d49e-\U0001d49f\U0001d4a2\U0001d4a5-\U0001d4a6\U0001d4a9-\U0001d4ac\U0001d4ae-\U0001d4b9\U0001d4bb\U0001d4bd-\U0001d4c3\U0001d4c5-\U0001d505\U0001d507-\U0001d50a\U0001d50d-\U0001d514\U0001d516-\U0001d51c\U0001d51e-\U0001d539\U0001d53b-\U0001d53e\U0001d540-\U0001d544\U0001d546\U0001d54a-\U0001d550\U0001d552-\U0001d6a5\U0001d6a8-\U0001d6c0\U0001d6c2-\U0001d6da\U0001d6dc-\U0001d6fa\U0001d6fc-\U0001d714\U0001d716-\U0001d734\U0001d736-\U0001d74e\U0001d750-\U0001d76e\U0001d770-\U0001d788\U0001d78a-\U0001d7a8\U0001d7aa-\U0001d7c2\U0001d7c4-\U0001d7cb\U0001e800-\U0001e8c4\U0001e900-\U0001e943\U0001ee00-\U0001ee03\U0001ee05-\U0001ee1f\U0001ee21-\U0001ee22\U0001ee24\U0001ee27\U0001ee29-\U0001ee32\U0001ee34-\U0001ee37\U0001ee39\U0001ee3b\U0001ee42\U0001ee47\U0001ee49\U0001ee4b\U0001ee4d-\U0001ee4f\U0001ee51-\U0001ee52\U0001ee54\U0001ee57\U0001ee59\U0001ee5b\U0001ee5d\U0001ee5f\U0001ee61-\U0001ee62\U0001ee64\U0001ee67-\U0001ee6a\U0001ee6c-\U0001ee72\U0001ee74-\U0001ee77\U0001ee79-\U0001ee7c\U0001ee7e\U0001ee80-\U0001ee89\U0001ee8b-\U0001ee9b\U0001eea1-\U0001eea3\U0001eea5-\U0001eea9\U0001eeab-\U0001eebb\U00020000-\U0002a6d6\U0002a700-\U0002b734\U0002b740-\U0002b81d\U0002b820-\U0002cea1\U0002ceb0-\U0002ebe0\U0002f800-\U0002fa1d'
+
+cats = ['Cc', 'Cf', 'Cn', 'Co', 'Cs', 'Ll', 'Lm', 'Lo', 'Lt', 'Lu', 'Mc', 'Me', 'Mn', 'Nd', 'Nl', 'No', 'Pc', 'Pd', 'Pe', 'Pf', 'Pi', 'Po', 'Ps', 'Sc', 'Sk', 'Sm', 'So', 'Zl', 'Zp', 'Zs']
+
+# Generated from unidata 11.0.0
+
+def combine(*args):
+    return ''.join(globals()[cat] for cat in args)
+
+
+def allexcept(*args):
+    newcats = cats[:]
+    for arg in args:
+        newcats.remove(arg)
+    return ''.join(globals()[cat] for cat in newcats)
+
+
+def _handle_runs(char_list):  # pragma: no cover
+    buf = []
+    for c in char_list:
+        if len(c) == 1:
+            if buf and buf[-1][1] == chr(ord(c)-1):
+                buf[-1] = (buf[-1][0], c)
+            else:
+                buf.append((c, c))
+        else:
+            buf.append((c, c))
+    for a, b in buf:
+        if a == b:
+            yield a
+        else:
+            yield f'{a}-{b}'
+
+
+if __name__ == '__main__':  # pragma: no cover
+    import unicodedata
+
+    categories = {'xid_start': [], 'xid_continue': []}
+
+    with open(__file__, encoding='utf-8') as fp:
+        content = fp.read()
+
+    header = content[:content.find('Cc =')]
+    footer = content[content.find("def combine("):]
+
+    for code in range(0x110000):
+        c = chr(code)
+        cat = unicodedata.category(c)
+        if ord(c) == 0xdc00:
+            # Hack to avoid combining this combining with the preceding high
+            # surrogate, 0xdbff, when doing a repr.
+            c = '\\' + c
+        elif ord(c) in (0x2d, 0x5b, 0x5c, 0x5d, 0x5e):
+            # Escape regex metachars.
+            c = '\\' + c
+        categories.setdefault(cat, []).append(c)
+        # XID_START and XID_CONTINUE are special categories used for matching
+        # identifiers in Python 3.
+        if c.isidentifier():
+            categories['xid_start'].append(c)
+        if ('a' + c).isidentifier():
+            categories['xid_continue'].append(c)
+
+    with open(__file__, 'w', encoding='utf-8') as fp:
+        fp.write(header)
+
+        for cat in sorted(categories):
+            val = ''.join(_handle_runs(categories[cat]))
+            fp.write(f'{cat} = {val!a}\n\n')
+
+        cats = sorted(categories)
+        cats.remove('xid_start')
+        cats.remove('xid_continue')
+        fp.write(f'cats = {cats!r}\n\n')
+
+        fp.write(f'# Generated from unidata {unicodedata.unidata_version}\n\n')
+
+        fp.write(footer)

lib/python3.12/site-packages/pygments/util.py

@@ -0,0 +1,324 @@
+"""
+    pygments.util
+    ~~~~~~~~~~~~~
+
+    Utility functions.
+
+    :copyright: Copyright 2006-2025 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 {} must be one of {}'.format(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(f'Invalid type {string!r} for option {optname}; use '
+                          '1/0, yes/no, true/false, on/off')
+    elif string.lower() in ('1', 'yes', 'true', 'on'):
+        return True
+    elif string.lower() in ('0', 'no', 'false', 'off'):
+        return False
+    else:
+        raise OptionError(f'Invalid value {string!r} for option {optname}; use '
+                          '1/0, yes/no, true/false, on/off')
+
+
+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(f'Invalid type {string!r} for option {optname}; you '
+                          'must give an integer value')
+    except ValueError:
+        raise OptionError(f'Invalid value {string!r} for option {optname}; you '
+                          'must give an integer value')
+
+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(f'Invalid type {val!r} for option {optname}; you '
+                          'must give a list value')
+
+
+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 ``'^$'``)
+    """
+    index = text.find('\n')
+    if index >= 0:
+        first_line = text[:index].lower()
+    else:
+        first_line = text.lower()
+    if first_line.startswith('#!'):
+        try:
+            found = [x for x in split_path_re.split(first_line[2:].strip())
+                     if x and not x.startswith('-')][-1]
+        except IndexError:
+            return False
+        regex = re.compile(rf'^{regex}(\.(exe|cmd|bat|bin))?$', 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()