50
  #   ˆl–Ãa¾”d*j"TÚzã@¸Ø”Å£ÂƒÏ;ÁÅÄ G    """Convert a NT pathname to a file URL and vice versa.

This module only exists to provide OS-specific code
for urllib.requests, thus do not use directly.
"""
# Testing is done through test_urllib.

def url2pathname(url):
    """OS-specific conversion from a relative URL of the 'file' scheme
    to a file system path; not recommended for general use."""
    # e.g.
    #   ///C|/foo/bar/spam.foo
    # and
    #   ///C:/foo/bar/spam.foo
    # become
    #   C:\foo\bar\spam.foo
    import string, urllib.parse
    # Windows itself uses ":" even in URLs.
    url = url.replace(':', '|')
    if not '|' in url:
        # No drive specifier, just convert slashes
        if url[:4] == '////':
            # path is something like ////host/path/on/remote/host
            # convert this to \\host\path\on\remote\host
            # (notice halving of slashes at the start of the path)
            url = url[2:]
        components = url.split('/')
        # make sure not to convert quoted slashes :-)
        return urllib.parse.unquote('\\'.join(components))
    comp = url.split('|')
    if len(comp) != 2 or comp[0][-1] not in string.ascii_letters:
        error = 'Bad URL: ' + url
        raise OSError(error)
    drive = comp[0][-1].upper()
    components = comp[1].split('/')
    path = drive + ':'
    for comp in components:
        if comp:
            path = path + '\\' + urllib.parse.unquote(comp)
    # Issue #11474 - handing url such as |c/|
    if path.endswith(':') and url.endswith('/'):
        path += '\\'
    return path

def pathname2url(p):
    """OS-specific conversion from a file system path to a relative URL
    of the 'file' scheme; not recommended for general use."""
    # e.g.
    #   C:\foo\bar\spam.foo
    # becomes
    #   ///C:/foo/bar/spam.foo
    import urllib.parse
    # First, clean up some special forms. We are going to sacrifice
    # the additional information anyway
    if p[:4] == '\\\\?\\':
        p = p[4:]
        if p[:4].upper() == 'UNC\\':
            p = '\\' + p[4:]
        elif p[1:2] != ':':
            raise OSError('Bad path: ' + p)
    if not ':' in p:
        # No drive specifier, just convert slashes and quote the name
        if p[:2] == '\\\\':
        # path is something like \\host\path\on\remote\host
        # convert this to ////host/path/on/remote/host
        # (notice doubling of slashes at the start of the path)
            p = '\\\\' + p
        components = p.split('\\')
        return urllib.parse.quote('/'.join(components))
    comp = p.split(':', maxsplit=2)
    if len(comp) != 2 or len(comp[0]) > 1:
        error = 'Bad path: ' + p
        raise OSError(error)

    drive = urllib.parse.quote(comp[0].upper())
    components = comp[1].split('\\')
    path = '///' + drive + ':'
    for comp in components:
        if comp:
            path = path + '/' + urllib.parse.quote(comp)
    return path
     ˆ¾Â„N	ŸÁÅÄ 9    """Shared support for scanning document type declarations in HTML and XHTML.

This module is used as a foundation for the html.parser module.  It has no
documented public API and should not be used directly.

"""

import re

_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
_commentclose = re.compile(r'--\s*>')
_markedsectionclose = re.compile(r']\s*]\s*>')

# An analysis of the MS-Word extensions is available at
# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf

_msmarkedsectionclose = re.compile(r']\s*>')

del re


class ParserBase:
    """Parser base class which provides some common support methods used
    by the SGML/HTML and XHTML parsers."""

    def __init__(self):
        if self.__class__ is ParserBase:
            raise RuntimeError(
                "_markupbase.ParserBase must be subclassed")

    def error(self, message):
        raise NotImplementedError(
            "subclasses of ParserBase must override error()")

    def reset(self):
        self.lineno = 1
        self.offset = 0

    de