import sys
from typing import Optional, Tuple

if sys.version_info >= (3, 8):
    from typing import Literal
else:
    from pip._vendor.typing_extensions import Literal  # pragma: no cover


from ._loop import loop_last
from .console import Console, ConsoleOptions, RenderableType, RenderResult
from .control import Control
from .segment import ControlType, Segment
from .style import StyleType
from .text import Text

VerticalOverflowMethod = Literal["crop", "ellipsis", "visible"]


class LiveRender:
    """Creates a renderable that may be updated.

    Args:
        renderable (RenderableType): Any renderable object.
        style (StyleType, optional): An optional style to apply to the renderable. Defaults to "".
    """

    def __init__(
        self,
        renderable: RenderableType,
        style: StyleType = "",
        vertical_overflow: VerticalOverflowMethod = "ellipsis",
    ) -> None:
        self.renderable = renderable
        self.style = style
        self.vertical_overflow = vertical_overflow
        self._shape: Optional[Tuple[int, int]] = None

    def set_renderable(self, renderable: RenderableType) -> None:
        """Set a new renderable.

        Args:
            renderable (RenderableType): Any renderable object, including str.
        """
        self.renderable = renderable

    def position_cursor(self) -> Control:
        """Get control codes to move cursor to beginning of live render.

        Returns:
            Control: A control instance that may be printed.
        """
        if self._shape is not None:
            _, height = self._shape
            return Control(
                ControlType.CARRIAGE_RETURN,
                (ControlType.ERASE_IN_LINE, 2),
                *(
                    (
                        (ControlType.CURSOR_UP, 1),
                        (ControlType.ERASE_IN_LINE, 2),
                    )
                    * (height - 1)
                )
            )
        return Control()

    def restore_cursor(self) -> Control:
        """Get control codes to clear the render and restore the cursor to its previous position.

        Returns:
            Control: A Control instance that may be printed.
        """
        if self._shape is not None:
            _, height = self._shape
            return Control(
                ControlType.CARRIAGE_RETURN,
                *((ControlType.CURSOR_UP, 1), (ControlType.ERASE_IN_LINE, 2)) * height
            )
        return Control()

    def __rich_console__(
        self, console: Console, options: ConsoleOptions
    ) -> RenderResult:
        renderable = self.renderable
        style = console.get_style(self.style)
        lines = console.render_lines(renderable, options, style=style, pad=False)
        shape = Segment.get_shape(lines)

        _, height = shape
        if height > options.size.height:
            if self.vertical_overflow == "crop":
                lines = lines[: options.size.height]
                shape = Segment.get_shape(lines)
            elif self.vertical_overflow == "ellipsis":
                lines = lines[: (options.size.height - 1)]
                overflow_text = Text(
                    "...",
                    overflow="crop",
                    justify="center",
                    end="",
                    style="live.ellipsis",
                )
                lines.append(list(console.render(overflow_text)))
                shape = Segment.get_shape(lines)
        self._shape = shape

        new_line = Segment.line()
        for last, line in loop_last(lines):
            yield from line
            if not last:
                yield new_line

"""
    pygments.lexer
    ~~~~~~~~~~~~~~

    Base lexer classes.

    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
import sys
import time

from pip._vendor.pygments.filter import apply_filters, Filter
from pip._vendor.pygments.filters import get_filter_by_name
from pip._vendor.pygments.token import Error, Text, Other, Whitespace, _TokenType
from pip._vendor.pygments.util import get_bool_opt, get_int_opt, get_list_opt, \
    make_analysator, Future, guess_decode
from pip._vendor.pygments.regexopt import regex_opt

__all__ = ['Lexer', 'RegexLexer', 'ExtendedRegexLexer', 'DelegatingLexer',
           'LexerContext', 'include', 'inherit', 'bygroups', 'using', 'this',
           'default', 'words', 'line_re']

line_re = re.compile('.*?\n')

_encoding_map = [(b'\xef\xbb\xbf', 'utf-8'),
                 (b'\xff\xfe\0\0', 'utf-32'),
                 (b'\0\0\xfe\xff', 'utf-32be'),
                 (b'\xff\xfe', 'utf-16'),
                 (b'\xfe\xff', 'utf-16be')]

_default_analyse = staticmethod(lambda x: 0.0)


class LexerMeta(type):
    """
    This metaclass automagically converts ``analyse_text`` methods into
    static methods which always return float values.
    """

    def __new__(mcs, name, bases, d):
        if 'analyse_text' in d:
            d['analyse_text'] = make_analysator(d['analyse_text'])
        return type.__new__(mcs, name, bases, d)


class Lexer(metaclass=LexerMeta):
    """
    Lexer for a specific language.

    See also :doc:`lexerdevelopment`, a high-level guide to writing
    lexers.

    Lexer classes have attributes used for choosing the most appropriate
    lexer based on various criteria.

    .. autoattribute:: name
       :no-value:
    .. autoattribute:: aliases
       :no-value:
    .. autoattribute:: filenames
       :no-value:
    .. autoattribute:: alias_filenames
    .. autoattribute:: mimetypes
       :no-value:
    .. autoattribute:: priority

    Lexers included in Pygments should have 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:
                    # pip vendoring note: this code is not reachable by pip,
                    # removed import of chardet to make it clear.
                    raise ImportError('chardet is not vendored by pip')
                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)

from collections.abc import Mapping
from typing import TYPE_CHECKING, Any, Optional, Tuple

from .highlighter import ReprHighlighter
from .panel import Panel
from .pretty import Pretty
from .table import Table
from .text import Text, TextType

if TYPE_CHECKING:
    from .console import ConsoleRenderable


def render_scope(
    scope: "Mapping[str, Any]",
    *,
    title: Optional[TextType] = None,
    sort_keys: bool = True,
    indent_guides: bool = False,
    max_length: Optional[int] = None,
    max_string: Optional[int] = None,
) -> "ConsoleRenderable":
    """Render python variables in a given scope.

    Args:
        scope (Mapping): A mapping containing variable names and values.
        title (str, optional): Optional title. Defaults to None.
        sort_keys (bool, optional): Enable sorting of items. Defaults to True.
        indent_guides (bool, optional): Enable indentation guides. Defaults to False.
        max_length (int, optional): Maximum length of containers before abbreviating, or None for no abbreviation.
            Defaults to None.
        max_string (int, optional): Maximum length of string before truncating, or None to disable. Defaults to None.

    Returns:
        ConsoleRenderable: A renderable object.
    """
    highlighter = ReprHighlighter()
    items_table = Table.grid(padding=(0, 1), expand=False)
    items_table.add_column(justify="right")

    def sort_items(item: Tuple[str, Any]) -> Tuple[bool, str]:
        """Sort special variables first, then alphabetically."""
        key, _ = item
        return (not key.startswith("__"), key.lower())

    items = sorted(scope.items(), key=sort_items) if sort_keys else scope.items()
    for key, value in items:
        key_text = Text.assemble(
            (key, "scope.key.special" if key.startswith("__") else "scope.key"),
            (" =", "scope.equals"),
        )
        items_table.add_row(
            key_text,
            Pretty(
                value,
                highlighter=highlighter,
                indent_guides=indent_guides,
                max_length=max_length,
                max_string=max_string,
            ),
        )
    return Panel.fit(
        items_table,
        title=title,
        border_style="scope.border",
        padding=(0, 1),
    )


if __name__ == "__main__":  # pragma: no cover
    from pip._vendor.rich import print

    print()

    def test(foo: float, bar: float) -> None:
        list_of_things = [1, 2, 3, None, 4, True, False, "Hello World"]
        dict_of_things = {
            "version": "1.1",
            "method": "confirmFruitPurchase",
            "params": [["apple", "orange", "mangoes", "pomelo"], 1.123],
            "id": "194521489",
        }
        print(render_scope(locals(), title="[i]locals", sort_keys=False))

    test(20.3423, 3.1427)
    print()

# -*- coding: utf-8 -*-
#
# Copyright (C) 2012-2023 The Python Software Foundation.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
"""
Implementation of a flexible versioning scheme providing support for PEP-440,
setuptools-compatible and semantic versioning.
"""

import logging
import re

from .compat import string_types
from .util import parse_requirement

__all__ = ['NormalizedVersion', 'NormalizedMatcher',
           'LegacyVersion', 'LegacyMatcher',
           'SemanticVersion', 'SemanticMatcher',
           'UnsupportedVersionError', 'get_scheme']

logger = logging.getLogger(__name__)


class UnsupportedVersionError(ValueError):
    """This is an unsupported version."""
    pass


class Version(object):
    def __init__(self, s):
        self._string = s = s.strip()
        self._parts = parts = self.parse(s)
        assert isinstance(parts, tuple)
        assert len(parts) > 0

    def parse(self, s):
        raise NotImplementedError('please implement in a subclass')

    def _check_compatible(self, other):
        if type(self) != type(other):
            raise TypeError('cannot compare %r and %r' % (self, other))

    def __eq__(self, other):
        self._check_compatible(other)
        return self._parts == other._parts

    def __ne__(self, other):
        return not self.__eq__(other)

    def __lt__(self, other):
        self._check_compatible(other)
        return self._parts < other._parts

    def __gt__(self, other):
        return not (self.__lt__(other) or self.__eq__(other))

    def __le__(self, other):
        return self.__lt__(other) or self.__eq__(other)

    def __ge__(self, other):
        return self.__gt__(other) or self.__eq__(other)

    # See http://docs.python.org/reference/datamodel#object.__hash__
    def __hash__(self):
        return hash(self._parts)

    def __repr__(self):
        return "%s('%s')" % (self.__class__.__name__, self._string)

    def __str__(self):
        return self._string

    @property
    def is_prerelease(self):
        raise NotImplementedError('Please implement in subclasses.')


class Matcher(object):
    version_class = None

    # value is either a callable or the name of a method
    _operators = {
        '<': lambda v, c, p: v < c,
        '>': lambda v, c, p: v > c,
        '<=': lambda v, c, p: v == c or v < c,
        '>=': lambda v, c, p: v == c or v > c,
        '==': lambda v, c, p: v == c,
        '===': lambda v, c, p: v == c,
        # by default, compatible => >=.
        '~=': lambda v, c, p: v == c or v > c,
        '!=': lambda v, c, p: v != c,
    }

    # this is a method only to support alternative implementations
    # via overriding
    def parse_requirement(self, s):
        return parse_requirement(s)

    def __init__(self, s):
        if self.version_class is None:
            raise ValueError('Please specify a version class')
        self._string = s = s.strip()
        r = self.parse_requirement(s)
        if not r:
            raise ValueError('Not valid: %r' % s)
        self.name = r.name
        self.key = self.name.lower()    # for case-insensitive comparisons
        clist = []
        if r.constraints:
            # import pdb; pdb.set_trace()
            for op, s in r.constraints:
                if s.endswith('.*'):
                    if op not in ('==', '!='):
                        raise ValueError('\'.*\' not allowed for '
                                         '%r constraints' % op)
                    # Could be a partial version (e.g. for '2.*') which
                    # won't parse as a version, so keep it as a string
                    vn, prefix = s[:-2], True
                    # Just to check that vn is a valid version
                    self.version_class(vn)
                else:
                    # Should parse as a version, so we can create an
                    # instance for the comparison
                    vn, prefix = self.version_class(s), False
                clist.append((op, vn, prefix))
        self._parts = tuple(clist)

    def match(self, version):
        """
        Check if the provided version matches the constraints.

        :param version: The version to match against this instance.
        :type version: String or :class:`Version` instance.
        """
        if isinstance(version, string_types):
            version = self.version_class(version)
        for operator, constraint, prefix in self._parts:
            f = self._operators.get(operator)
            if isinstance(f, string_types):
                f = getattr(self, f)
            if not f:
                msg = ('%r not implemented '
                       'for %s' % (operator, self.__class__.__name__))
                raise NotImplementedError(msg)
            if not f(version, constraint, prefix):
                return False
        return True

    @property
    def exact_version(self):
        result = None
        if len(self._parts) == 1 and self._parts[0][0] in ('==', '==='):
            result = self._parts[0][1]
        return result

    def _check_compatible(self, other):
        if type(self) != type(other) or self.name != other.name:
            raise TypeError('cannot compare %s and %s' % (self, other))

    def __eq__(self, other):
        self._check_compatible(other)
        return self.key == other.key and self._parts == other._parts

    def __ne__(self, other):
        return not self.__eq__(other)

    # See http://docs.python.org/reference/datamodel#object.__hash__
    def __hash__(self):
        return hash(self.key) + hash(self._parts)

    def __repr__(self):
        return "%s(%r)" % (self.__class__.__name__, self._string)

    def __str__(self):
        return self._string


PEP440_VERSION_RE = re.compile(r'^v?(\d+!)?(\d+(\.\d+)*)((a|alpha|b|beta|c|rc|pre|preview)(\d+)?)?'
                               r'(\.(post|r|rev)(\d+)?)?([._-]?(dev)(\d+)?)?'
                               r'(\+([a-zA-Z\d]+(\.[a-zA-Z\d]+)?))?$', re.I)


def _pep_440_key(s):
    s = s.strip()
    m = PEP440_VERSION_RE.match(s)
    if not m:
        raise UnsupportedVersionError('Not a valid version: %s' % s)
    groups = m.groups()
    nums = tuple(int(v) for v in groups[1].split('.'))
    while len(nums) > 1 and nums[-1] == 0:
        nums = nums[:-1]

    if not groups[0]:
        epoch = 0
    else:
        epoch = int(groups[0][:-1])
    pre = groups[4:6]
    post = groups[7:9]
    dev = groups[10:12]
    local = groups[13]
    if pre == (None, None):
        pre = ()
    else:
        if pre[1] is None:
            pre = pre[0], 0
        else:
            pre = pre[0], int(pre[1])
    if post == (None, None):
        post = ()
    else:
        if post[1] is None:
            post = post[0], 0
        else:
            post = post[0], int(post[1])
    if dev == (None, None):
        dev = ()
    else:
        if dev[1] is None:
            dev = dev[0], 0
        else:
            dev = dev[0], int(dev[1])
    if local is None:
        local = ()
    else:
        parts = []
        for part in local.split('.'):
            # to ensure that numeric compares as > lexicographic, avoid
            # comparing them directly, but encode a tuple which ensures
            # correct sorting
            if part.isdigit():
                part = (1, int(part))
            else:
                part = (0, part)
            parts.append(part)
        local = tuple(parts)
    if not pre:
        # either before pre-release, or final release and after
        if not post and dev:
            # before pre-release
            pre = ('a', -1)     # to sort before a0
        else:
            pre = ('z',)        # to sort after all pre-releases
    # now look at the state of post and dev.
    if not post:
        post = ('_',)   # sort before 'a'
    if not dev:
        dev = ('final',)

    return epoch, nums, pre, post, dev, local


_normalized_key = _pep_440_key


class NormalizedVersion(Version):
    """A rational version.

    Good:
        1.2         # equivalent to "1.2.0"
        1.2.0
        1.2a1
        1.2.3a2
        1.2.3b1
        1.2.3c1
        1.2.3.4
        TODO: fill this out

    Bad:
        1           # minimum two numbers
        1.2a        # release level must have a release serial
        1.2.3b
    """
    def parse(self, s):
        result = _normalized_key(s)
        # _normalized_key loses trailing zeroes in the release
        # clause, since that's needed to ensure that X.Y == X.Y.0 == X.Y.0.0
        # However, PEP 440 prefix matching needs it: for example,
        # (~= 1.4.5.0) matches differently to (~= 1.4.5.0.0).
        m = PEP440_VERSION_RE.match(s)      # must succeed
        groups = m.groups()
        self._release_clause = tuple(int(v) for v in groups[1].split('.'))
        return result

    PREREL_TAGS = set(['a', 'b', 'c', 'rc', 'dev'])

    @property
    def is_prerelease(self):
        return any(t[0] in self.PREREL_TAGS for t in self._parts if t)


def _match_prefix(x, y):
    x = str(x)
    y = str(y)
    if x == y:
        return True
    if not x.startswith(y):
        return False
    n = len(y)
    return x[n] == '.'


class NormalizedMatcher(Matcher):
    version_class = NormalizedVersion

    # value is either a callable or the name of a method
    _operators = {
        '~=': '_match_compatible',
        '<': '_match_lt',
        '>': '_match_gt',
        '<=': '_match_le',
        '>=': '_match_ge',
        '==': '_match_eq',
        '===': '_match_arbitrary',
        '!=': '_match_ne',
    }

    def _adjust_local(self, version, constraint, prefix):
        if prefix:
            strip_local = '+' not in constraint and version._parts[-1]
        else:
            # both constraint and version are
            # NormalizedVersion instances.
            # If constraint does not have a local component,
            # ensure the version doesn't, either.
            strip_local = not constraint._parts[-1] and version._parts[-1]
        if strip_local:
            s = version._string.split('+', 1)[0]
            version = self.version_class(s)
        return version, constraint

    def _match_lt(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        if version >= constraint:
            return False
        release_clause = constraint._release_clause
        pfx = '.'.join([str(i) for i in release_clause])
        return not _match_prefix(version, pfx)

    def _match_gt(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        if version <= constraint:
            return False
        release_clause = constraint._release_clause
        pfx = '.'.join([str(i) for i in release_clause])
        return not _match_prefix(version, pfx)

    def _match_le(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        return version <= constraint

    def _match_ge(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        return version >= constraint

    def _match_eq(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        if not prefix:
            result = (version == constraint)
        else:
            result = _match_prefix(version, constraint)
        return result

    def _match_arbitrary(self, version, constraint, prefix):
        return str(version) == str(constraint)

    def _match_ne(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        if not prefix:
            result = (version != constraint)
        else:
            result = not _match_prefix(version, constraint)
        return result

    def _match_compatible(self, version, constraint, prefix):
        version, constraint = self._adjust_local(version, constraint, prefix)
        if version == constraint:
            return True
        if version < constraint:
            return False
#        if not prefix:
#            return True
        release_clause = constraint._release_clause
        if len(release_clause) > 1:
            release_clause = release_clause[:-1]
        pfx = '.'.join([str(i) for i in release_clause])
        return _match_prefix(version, pfx)


_REPLACEMENTS = (
    (re.compile('[.+-]$'), ''),                     # remove trailing puncts
    (re.compile(r'^[.](\d)'), r'0.\1'),             # .N -> 0.N at start
    (re.compile('^[.-]'), ''),                      # remove leading puncts
    (re.compile(r'^\((.*)\)$'), r'\1'),             # remove parentheses
    (re.compile(r'^v(ersion)?\s*(\d+)'), r'\2'),    # remove leading v(ersion)
    (re.compile(r'^r(ev)?\s*(\d+)'), r'\2'),        # remove leading v(ersion)
    (re.compile('[.]{2,}'), '.'),                   # multiple runs of '.'
    (re.compile(r'\b(alfa|apha)\b'), 'alpha'),      # misspelt alpha
    (re.compile(r'\b(pre-alpha|prealpha)\b'),
        'pre.alpha'),                               # standardise
    (re.compile(r'\(beta\)$'), 'beta'),             # remove parentheses
)

_SUFFIX_REPLACEMENTS = (
    (re.compile('^[:~._+-]+'), ''),                   # remove leading puncts
    (re.compile('[,*")([\\]]'), ''),                  # remove unwanted chars
    (re.compile('[~:+_ -]'), '.'),                    # replace illegal chars
    (re.compile('[.]{2,}'), '.'),                   # multiple runs of '.'
    (re.compile(r'\.$'), ''),                       # trailing '.'
)

_NUMERIC_PREFIX = re.compile(r'(\d+(\.\d+)*)')


def _suggest_semantic_version(s):
    """
    Try to suggest a semantic form for a version for which
    _suggest_normalized_version couldn't come up with anything.
    """
    result = s.strip().lower()
    for pat, repl in _REPLACEMENTS:
        result = pat.sub(repl, result)
    if not result:
        result = '0.0.0'

    # Now look for numeric prefix, and separate it out from
    # the rest.
    # import pdb; pdb.set_trace()
    m = _NUMERIC_PREFIX.match(result)
    if not m:
        prefix = '0.0.0'
        suffix = result
    else:
        prefix = m.groups()[0].split('.')
        prefix = [int(i) for i in prefix]
        while len(prefix) < 3:
            prefix.append(0)
        if len(prefix) == 3:
            suffix = result[m.end():]
        else:
            suffix = '.'.join([str(i) for i in prefix[3:]]) + result[m.end():]
            prefix = prefix[:3]
        prefix = '.'.join([str(i) for i in prefix])
        suffix = suffix.strip()
    if suffix:
        # import pdb; pdb.set_trace()
        # massage the suffix.
        for pat, repl in _SUFFIX_REPLACEMENTS:
            suffix = pat.sub(repl, suffix)

    if not suffix:
        result = prefix
    else:
        sep = '-' if 'dev' in suffix else '+'
        result = prefix + sep + suffix
    if not is_semver(result):
        result = None
    return result


def _suggest_normalized_version(s):
    """Suggest a normalized version close to the given version string.

    If you have a version string that isn't rational (i.e. NormalizedVersion
    doesn't like it) then you might be able to get an equivalent (or close)
    rational version from this function.

    This does a number of simple normalizations to the given string, based
    on observation of versions currently in use on PyPI. Given a dump of
    those version during PyCon 2009, 4287 of them:
    - 2312 (53.93%) match NormalizedVersion without change
      with the automatic suggestion
    - 3474 (81.04%) match when using this suggestion method

    @param s {str} An irrational version string.
    @returns A rational version string, or None, if couldn't determine one.
    """
    try:
        _normalized_key(s)
        return s   # already rational
    except UnsupportedVersionError:
        pass

    rs = s.lower()

    # part of this could use maketrans
    for orig, repl in (('-alpha', 'a'), ('-beta', 'b'), ('alpha', 'a'),
                       ('beta', 'b'), ('rc', 'c'), ('-final', ''),
                       ('-pre', 'c'),
                       ('-release', ''), ('.release', ''), ('-stable', ''),
                       ('+', '.'), ('_', '.'), (' ', ''), ('.final', ''),
                       ('final', '')):
        rs = rs.replace(orig, repl)

    # if something ends with dev or pre, we add a 0
    rs = re.sub(r"pre$", r"pre0", rs)
    rs = re.sub(r"dev$", r"dev0", rs)

    # if we have something like "b-2" or "a.2" at the end of the
    # version, that is probably beta, alpha, etc
    # let's remove the dash or dot
    rs = re.sub(r"([abc]|rc)[\-\.](\d+)$", r"\1\2", rs)

    # 1.0-dev-r371 -> 1.0.dev371
    # 0.1-dev-r79 -> 0.1.dev79
    rs = re.sub(r"[\-\.](dev)[\-\.]?r?(\d+)$", r".\1\2", rs)

    # Clean: 2.0.a.3, 2.0.b1, 0.9.0~c1
    rs = re.sub(r"[.~]?([abc])\.?", r"\1", rs)

    # Clean: v0.3, v1.0
    if rs.startswith('v'):
        rs = rs[1:]

    # Clean leading '0's on numbers.
    # TODO: unintended side-effect on, e.g., "2003.05.09"
    # PyPI stats: 77 (~2%) better
    rs = re.sub(r"\b0+(\d+)(?!\d)", r"\1", rs)

    # Clean a/b/c with no version. E.g. "1.0a" -> "1.0a0". Setuptools infers
    # zero.
    # PyPI stats: 245 (7.56%) better
    rs = re.sub(r"(\d+[abc])$", r"\g<1>0", rs)

    # the 'dev-rNNN' tag is a dev tag
    rs = re.sub(r"\.?(dev-r|dev\.r)\.?(\d+)$", r".dev\2", rs)

    # clean the - when used as a pre delimiter
    rs = re.sub(r"-(a|b|c)(\d+)$", r"\1\2", rs)

    # a terminal "dev" or "devel" can be changed into ".dev0"
    rs = re.sub(r"[\.\-](dev|devel)$", r".dev0", rs)

    # a terminal "dev" can be changed into ".dev0"
    rs = re.sub(r"(?![\.\-])dev$", r".dev0", rs)

    # a terminal "final" or "stable" can be removed
    rs = re.sub(r"(final|stable)$", "", rs)

    # The 'r' and the '-' tags are post release tags
    #   0.4a1.r10       ->  0.4a1.post10
    #   0.9.33-17222    ->  0.9.33.post17222
    #   0.9.33-r17222   ->  0.9.33.post17222
    rs = re.sub(r"\.?(r|-|-r)\.?(\d+)$", r".post\2", rs)

    # Clean 'r' instead of 'dev' usage:
    #   0.9.33+r17222   ->  0.9.33.dev17222
    #   1.0dev123       ->  1.0.dev123
    #   1.0.git123      ->  1.0.dev123
    #   1.0.bzr123      ->  1.0.dev123
    #   0.1a0dev.123    ->  0.1a0.dev123
    # PyPI stats:  ~150 (~4%) better
    rs = re.sub(r"\.?(dev|git|bzr)\.?(\d+)$", r".dev\2", rs)

    # Clean '.pre' (normalized from '-pre' above) instead of 'c' usage:
    #   0.2.pre1        ->  0.2c1
    #   0.2-c1         ->  0.2c1
    #   1.0preview123   ->  1.0c123
    # PyPI stats: ~21 (0.62%) better
    rs = re.sub(r"\.?(pre|preview|-c)(\d+)$", r"c\g<2>", rs)

    # Tcl/Tk uses "px" for their post release markers
    rs = re.sub(r"p(\d+)$", r".post\1", rs)

    try:
        _normalized_key(rs)
    except UnsupportedVersionError:
        rs = None
    return rs

#
#   Legacy version processing (distribute-compatible)
#


_VERSION_PART = re.compile(r'([a-z]+|\d+|[\.-])', re.I)
_VERSION_REPLACE = {
    'pre': 'c',
    'preview': 'c',
    '-': 'final-',
    'rc': 'c',
    'dev': '@',
    '': None,
    '.': None,
}


def _legacy_key(s):
    def get_parts(s):
        result = []
        for p in _VERSION_PART.split(s.lower()):
            p = _VERSION_REPLACE.get(p, p)
            if p:
                if '0' <= p[:1] <= '9':
                    p = p.zfill(8)
                else:
                    p = '*' + p
                result.append(p)
        result.append('*final')
        return result

    result = []
    for p in get_parts(s):
        if p.startswith('*'):
            if p < '*final':
                while result and result[-1] == '*final-':
                    result.pop()
            while result and result[-1] == '00000000':
                result.pop()
        result.append(p)
    return tuple(result)


class LegacyVersion(Version):
    def parse(self, s):
        return _legacy_key(s)

    @property
    def is_prerelease(self):
        result = False
        for x in self._parts:
            if (isinstance(x, string_types) and x.startswith('*') and x < '*final'):
                result = True
                break
        return result


class LegacyMatcher(Matcher):
    version_class = LegacyVersion

    _operators = dict(Matcher._operators)
    _operators['~='] = '_match_compatible'

    numeric_re = re.compile(r'^(\d+(\.\d+)*)')

    def _match_compatible(self, version, constraint, prefix):
        if version < constraint:
            return False
        m = self.numeric_re.match(str(constraint))
        if not m:
            logger.warning('Cannot compute compatible match for version %s '
                           ' and constraint %s', version, constraint)
            return True
        s = m.groups()[0]
        if '.' in s:
            s = s.rsplit('.', 1)[0]
        return _match_prefix(version, s)

#
#   Semantic versioning
#


_SEMVER_RE = re.compile(r'^(\d+)\.(\d+)\.(\d+)'
                        r'(-[a-z0-9]+(\.[a-z0-9-]+)*)?'
                        r'(\+[a-z0-9]+(\.[a-z0-9-]+)*)?$', re.I)


def is_semver(s):
    return _SEMVER_RE.match(s)


def _semantic_key(s):
    def make_tuple(s, absent):
        if s is None:
            result = (absent,)
        else:
            parts = s[1:].split('.')
            # We can't compare ints and strings on Python 3, so fudge it
            # by zero-filling numeric values so simulate a numeric comparison
            result = tuple([p.zfill(8) if p.isdigit() else p for p in parts])
        return result

    m = is_semver(s)
    if not m:
        raise UnsupportedVersionError(s)
    groups = m.groups()
    major, minor, patch = [int(i) for i in groups[:3]]
    # choose the '|' and '*' so that versions sort correctly
    pre, build = make_tuple(groups[3], '|'), make_tuple(groups[5], '*')
    return (major, minor, patch), pre, build


class SemanticVersion(Version):
    def parse(self, s):
        return _semantic_key(s)

    @property
    def is_prerelease(self):
        return self._parts[1][0] != '|'


class SemanticMatcher(Matcher):
    version_class = SemanticVersion


class VersionScheme(object):
    def __init__(self, key, matcher, suggester=None):
        self.key = key
        self.matcher = matcher
        self.suggester = suggester

    def is_valid_version(self, s):
        try:
            self.matcher.version_class(s)
            result = True
        except UnsupportedVersionError:
            result = False
        return result

    def is_valid_matcher(self, s):
        try:
            self.matcher(s)
            result = True
        except UnsupportedVersionError:
            result = False
        return result

    def is_valid_constraint_list(self, s):
        """
        Used for processing some metadata fields
        """
        # See issue #140. Be tolerant of a single trailing comma.
        if s.endswith(','):
            s = s[:-1]
        return self.is_valid_matcher('dummy_name (%s)' % s)

    def suggest(self, s):
        if self.suggester is None:
            result = None
        else:
            result = self.suggester(s)
        return result


_SCHEMES = {
    'normalized': VersionScheme(_normalized_key, NormalizedMatcher,
                                _suggest_normalized_version),
    'legacy': VersionScheme(_legacy_key, LegacyMatcher, lambda self, s: s),
    'semantic': VersionScheme(_semantic_key, SemanticMatcher,
                              _suggest_semantic_version),
}

_SCHEMES['default'] = _SCHEMES['normalized']


def get_scheme(name):
    if name not in _SCHEMES:
        raise ValueError('unknown scheme name: %r' % name)
    return _SCHEMES[name]

# This file is dual licensed under the terms of the Apache License, Version
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.
"""
.. testsetup::

    from pip._vendor.packaging.version import parse, Version
"""

from __future__ import annotations

import itertools
import re
from typing import Any, Callable, NamedTuple, SupportsInt, Tuple, Union

from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType

__all__ = ["VERSION_PATTERN", "parse", "Version", "InvalidVersion"]

LocalType = Tuple[Union[int, str], ...]

CmpPrePostDevType = Union[InfinityType, NegativeInfinityType, Tuple[str, int]]
CmpLocalType = Union[
    NegativeInfinityType,
    Tuple[Union[Tuple[int, str], Tuple[NegativeInfinityType, Union[int, str]]], ...],
]
CmpKey = Tuple[
    int,
    Tuple[int, ...],
    CmpPrePostDevType,
    CmpPrePostDevType,
    CmpPrePostDevType,
    CmpLocalType,
]
VersionComparisonMethod = Callable[[CmpKey, CmpKey], bool]


class _Version(NamedTuple):
    epoch: int
    release: tuple[int, ...]
    dev: tuple[str, int] | None
    pre: tuple[str, int] | None
    post: tuple[str, int] | None
    local: LocalType | None


def parse(version: str) -> Version:
    """Parse the given version string.

    >>> parse('1.0.dev1')
    <Version('1.0.dev1')>

    :param version: The version string to parse.
    :raises InvalidVersion: When the version string is not a valid version.
    """
    return Version(version)


class InvalidVersion(ValueError):
    """Raised when a version string is not a valid version.

    >>> Version("invalid")
    Traceback (most recent call last):
        ...
    packaging.version.InvalidVersion: Invalid version: 'invalid'
    """


class _BaseVersion:
    _key: tuple[Any, ...]

    def __hash__(self) -> int:
        return hash(self._key)

    # Please keep the duplicated `isinstance` check
    # in the six comparisons hereunder
    # unless you find a way to avoid adding overhead function calls.
    def __lt__(self, other: _BaseVersion) -> bool:
        if not isinstance(other, _BaseVersion):
            return NotImplemented

        return self._key < other._key

    def __le__(self, other: _BaseVersion) -> bool:
        if not isinstance(other, _BaseVersion):
            return NotImplemented

        return self._key <= other._key

    def __eq__(self, other: object) -> bool:
        if not isinstance(other, _BaseVersion):
            return NotImplemented

        return self._key == other._key

    def __ge__(self, other: _BaseVersion) -> bool:
        if not isinstance(other, _BaseVersion):
            return NotImplemented

        return self._key >= other._key

    def __gt__(self, other: _BaseVersion) -> bool:
        if not isinstance(other, _BaseVersion):
            return NotImplemented

        return self._key > other._key

    def __ne__(self, other: object) -> bool:
        if not isinstance(other, _BaseVersion):
            return NotImplemented

        return self._key != other._key


# Deliberately not anchored to the start and end of the string, to make it
# easier for 3rd party code to reuse
_VERSION_PATTERN = r"""
    v?
    (?:
        (?:(?P<epoch>[0-9]+)!)?                           # epoch
        (?P<release>[0-9]+(?:\.[0-9]+)*)                  # release segment
        (?P<pre>                                          # pre-release
            [-_\.]?
            (?P<pre_l>alpha|a|beta|b|preview|pre|c|rc)
            [-_\.]?
            (?P<pre_n>[0-9]+)?
        )?
        (?P<post>                                         # post release
            (?:-(?P<post_n1>[0-9]+))
            |
            (?:
                [-_\.]?
                (?P<post_l>post|rev|r)
                [-_\.]?
                (?P<post_n2>[0-9]+)?
            )
        )?
        (?P<dev>                                          # dev release
            [-_\.]?
            (?P<dev_l>dev)
            [-_\.]?
            (?P<dev_n>[0-9]+)?
        )?
    )
    (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
"""

VERSION_PATTERN = _VERSION_PATTERN
"""
A string containing the regular expression used to match a valid version.

The pattern is not anchored at either end, and is intended for embedding in larger
expressions (for example, matching a version number as part of a file name). The
regular expression should be compiled with the ``re.VERBOSE`` and ``re.IGNORECASE``
flags set.

:meta hide-value:
"""


class Version(_BaseVersion):
    """This class abstracts handling of a project's versions.

    A :class:`Version` instance is comparison aware and can be compared and
    sorted using the standard Python interfaces.

    >>> v1 = Version("1.0a5")
    >>> v2 = Version("1.0")
    >>> v1
    <Version('1.0a5')>
    >>> v2
    <Version('1.0')>
    >>> v1 < v2
    True
    >>> v1 == v2
    False
    >>> v1 > v2
    False
    >>> v1 >= v2
    False
    >>> v1 <= v2
    True
    """

    _regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
    _key: CmpKey

    def __init__(self, version: str) -> None:
        """Initialize a Version object.

        :param version:
            The string representation of a version which will be parsed and normalized
            before use.
        :raises InvalidVersion:
            If the ``version`` does not conform to PEP 440 in any way then this
            exception will be raised.
        """

        # Validate the version and parse it into pieces
        match = self._regex.search(version)
        if not match:
            raise InvalidVersion(f"Invalid version: '{version}'")

        # Store the parsed out pieces of the version
        self._version = _Version(
            epoch=int(match.group("epoch")) if match.group("epoch") else 0,
            release=tuple(int(i) for i in match.group("release").split(".")),
            pre=_parse_letter_version(match.group("pre_l"), match.group("pre_n")),
            post=_parse_letter_version(
                match.group("post_l"), match.group("post_n1") or match.group("post_n2")
            ),
            dev=_parse_letter_version(match.group("dev_l"), match.group("dev_n")),
            local=_parse_local_version(match.group("local")),
        )

        # Generate a key which will be used for sorting
        self._key = _cmpkey(
            self._version.epoch,
            self._version.release,
            self._version.pre,
            self._version.post,
            self._version.dev,
            self._version.local,
        )

    def __repr__(self) -> str:
        """A representation of the Version that shows all internal state.

        >>> Version('1.0.0')
        <Version('1.0.0')>
        """
        return f"<Version('{self}')>"

    def __str__(self) -> str:
        """A string representation of the version that can be rounded-tripped.

        >>> str(Version("1.0a5"))
        '1.0a5'
        """
        parts = []

        # Epoch
        if self.epoch != 0:
            parts.append(f"{self.epoch}!")

        # Release segment
        parts.append(".".join(str(x) for x in self.release))

        # Pre-release
        if self.pre is not None:
            parts.append("".join(str(x) for x in self.pre))

        # Post-release
        if self.post is not None:
            parts.append(f".post{self.post}")

        # Development release
        if self.dev is not None:
            parts.append(f".dev{self.dev}")

        # Local version segment
        if self.local is not None:
            parts.append(f"+{self.local}")

        return "".join(parts)

    @property
    def epoch(self) -> int:
        """The epoch of the version.

        >>> Version("2.0.0").epoch
        0
        >>> Version("1!2.0.0").epoch
        1
        """
        return self._version.epoch

    @property
    def release(self) -> tuple[int, ...]:
        """The components of the "release" segment of the version.

        >>> Version("1.2.3").release
        (1, 2, 3)
        >>> Version("2.0.0").release
        (2, 0, 0)
        >>> Version("1!2.0.0.post0").release
        (2, 0, 0)

        Includes trailing zeroes but not the epoch or any pre-release / development /
        post-release suffixes.
        """
        return self._version.release

    @property
    def pre(self) -> tuple[str, int] | None:
        """The pre-release segment of the version.

        >>> print(Version("1.2.3").pre)
        None
        >>> Version("1.2.3a1").pre
        ('a', 1)
        >>> Version("1.2.3b1").pre
        ('b', 1)
        >>> Version("1.2.3rc1").pre
        ('rc', 1)
        """
        return self._version.pre

    @property
    def post(self) -> int | None:
        """The post-release number of the version.

        >>> print(Version("1.2.3").post)
        None
        >>> Version("1.2.3.post1").post
        1
        """
        return self._version.post[1] if self._version.post else None

    @property
    def dev(self) -> int | None:
        """The development number of the version.

        >>> print(Version("1.2.3").dev)
        None
        >>> Version("1.2.3.dev1").dev
        1
        """
        return self._version.dev[1] if self._version.dev else None

    @property
    def local(self) -> str | None:
        """The local version segment of the version.

        >>> print(Version("1.2.3").local)
        None
        >>> Version("1.2.3+abc").local
        'abc'
        """
        if self._version.local:
            return ".".join(str(x) for x in self._version.local)
        else:
            return None

    @property
    def public(self) -> str:
        """The public portion of the version.

        >>> Version("1.2.3").public
        '1.2.3'
        >>> Version("1.2.3+abc").public
        '1.2.3'
        >>> Version("1.2.3+abc.dev1").public
        '1.2.3'
        """
        return str(self).split("+", 1)[0]

    @property
    def base_version(self) -> str:
        """The "base version" of the version.

        >>> Version("1.2.3").base_version
        '1.2.3'
        >>> Version("1.2.3+abc").base_version
        '1.2.3'
        >>> Version("1!1.2.3+abc.dev1").base_version
        '1!1.2.3'

        The "base version" is the public version of the project without any pre or post
        release markers.
        """
        parts = []

        # Epoch
        if self.epoch != 0:
            parts.append(f"{self.epoch}!")

        # Release segment
        parts.append(".".join(str(x) for x in self.release))

        return "".join(parts)

    @property
    def is_prerelease(self) -> bool:
        """Whether this version is a pre-release.

        >>> Version("1.2.3").is_prerelease
        False
        >>> Version("1.2.3a1").is_prerelease
        True
        >>> Version("1.2.3b1").is_prerelease
        True
        >>> Version("1.2.3rc1").is_prerelease
        True
        >>> Version("1.2.3dev1").is_prerelease
        True
        """
        return self.dev is not None or self.pre is not None

    @property
    def is_postrelease(self) -> bool:
        """Whether this version is a post-release.

        >>> Version("1.2.3").is_postrelease
        False
        >>> Version("1.2.3.post1").is_postrelease
        True
        """
        return self.post is not None

    @property
    def is_devrelease(self) -> bool:
        """Whether this version is a development release.

        >>> Version("1.2.3").is_devrelease
        False
        >>> Version("1.2.3.dev1").is_devrelease
        True
        """
        return self.dev is not None

    @property
    def major(self) -> int:
        """The first item of :attr:`release` or ``0`` if unavailable.

        >>> Version("1.2.3").major
        1
        """
        return self.release[0] if len(self.release) >= 1 else 0

    @property
    def minor(self) -> int:
        """The second item of :attr:`release` or ``0`` if unavailable.

        >>> Version("1.2.3").minor
        2
        >>> Version("1").minor
        0
        """
        return self.release[1] if len(self.release) >= 2 else 0

    @property
    def micro(self) -> int:
        """The third item of :attr:`release` or ``0`` if unavailable.

        >>> Version("1.2.3").micro
        3
        >>> Version("1").micro
        0
        """
        return self.release[2] if len(self.release) >= 3 else 0


def _parse_letter_version(
    letter: str | None, number: str | bytes | SupportsInt | None
) -> tuple[str, int] | None:
    if letter:
        # We consider there to be an implicit 0 in a pre-release if there is
        # not a numeral associated with it.
        if number is None:
            number = 0

        # We normalize any letters to their lower case form
        letter = letter.lower()

        # We consider some words to be alternate spellings of other words and
        # in those cases we want to normalize the spellings to our preferred
        # spelling.
        if letter == "alpha":
            letter = "a"
        elif letter == "beta":
            letter = "b"
        elif letter in ["c", "pre", "preview"]:
            letter = "rc"
        elif letter in ["rev", "r"]:
            letter = "post"

        return letter, int(number)
    if not letter and number:
        # We assume if we are given a number, but we are not given a letter
        # then this is using the implicit post release syntax (e.g. 1.0-1)
        letter = "post"

        return letter, int(number)

    return None


_local_version_separators = re.compile(r"[\._-]")


def _parse_local_version(local: str | None) -> LocalType | None:
    """
    Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
    """
    if local is not None:
        return tuple(
            part.lower() if not part.isdigit() else int(part)
            for part in _local_version_separators.split(local)
        )
    return None


def _cmpkey(
    epoch: int,
    release: tuple[int, ...],
    pre: tuple[str, int] | None,
    post: tuple[str, int] | None,
    dev: tuple[str, int] | None,
    local: LocalType | None,
) -> CmpKey:
    # When we compare a release version, we want to compare it with all of the
    # trailing zeros removed. So we'll use a reverse the list, drop all the now
    # leading zeros until we come to something non zero, then take the rest
    # re-reverse it back into the correct order and make it a tuple and use
    # that for our sorting key.
    _release = tuple(
        reversed(list(itertools.dropwhile(lambda x: x == 0, reversed(release))))
    )

    # We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0.
    # We'll do this by abusing the pre segment, but we _only_ want to do this
    # if there is not a pre or a post segment. If we have one of those then
    # the normal sorting rules will handle this case correctly.
    if pre is None and post is None and dev is not None:
        _pre: CmpPrePostDevType = NegativeInfinity
    # Versions without a pre-release (except as noted above) should sort after
    # those with one.
    elif pre is None:
        _pre = Infinity
    else:
        _pre = pre

    # Versions without a post segment should sort before those with one.
    if post is None:
        _post: CmpPrePostDevType = NegativeInfinity

    else:
        _post = post

    # Versions without a development segment should sort after those with one.
    if dev is None:
        _dev: CmpPrePostDevType = Infinity

    else:
        _dev = dev

    if local is None:
        # Versions without a local segment should sort before those with one.
        _local: CmpLocalType = NegativeInfinity
    else:
        # Versions with a local segment need that segment parsed to implement
        # the sorting rules in PEP440.
        # - Alpha numeric segments sort before numeric segments
        # - Alpha numeric segments sort lexicographically
        # - Numeric segments sort numerically
        # - Shorter versions sort before longer versions when the prefixes
        #   match exactly
        _local = tuple(
            (i, "") if isinstance(i, int) else (NegativeInfinity, i) for i in local
        )

    return epoch, _release, _pre, _post, _dev, _local