"""A parser for HTML and XHTML."""

# This file is based on sgmllib.py, but the API is slightly different.

# XXX There should be a way to distinguish between PCDATA (parsed
# character data -- the normal case), RCDATA (replaceable character
# data -- only char and entity references and end tags are special)
# and CDATA (character data -- only end tags are special).


import re
import warnings
import _markupbase

from html import unescape


__all__ = ['HTMLParser']

# Regular expressions used for parsing

interesting_normal = re.compile('[&')
# Note:
#  1) the strict attrfind isn't really strict, but we can't make it
#     correctly strict without breaking backward compatibility;
#  2) if you change tagfind/attrfind remember to update locatestarttagend too;
#  3) if you change tagfind/attrfind and/or locatestarttagend the parser will
#     explode, so don't do it.
tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*')
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
attrfind = re.compile(
    r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
    r'(\'[^\']*\'|"[^"]*"|[^\s"\'=`]*))?')
attrfind_tolerant = re.compile(
    r'((?\s]*))?(?:\s|/(?!>))*')
locatestarttagend = re.compile(r"""
  ][^\s/=>]*  # attribute name
      (?:\s*=+\s*                    # value indicator
        (?:'[^']*'                   # LITA-enclosed value
          |"[^"]*"                   # LIT-enclosed value
          |(?!['"])[^>\s]*           # bare value
         )
         (?:\s*,)*                   # possibly followed by a comma
       )?(?:\s|/(?!>))*
     )*
   )?
  \s*                                # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
# = 0 and
                        not re.compile(r'[\s;]').search(rawdata, amppos)):
                        break  # wait till we get all the text
                    j = n
            else:
                match = self.interesting.search(rawdata, i)  # < or &
                if match:
                    j = match.start()
                else:
                    if self.cdata_elem:
                        break
                    j = n
            if i < j:
                if self.convert_charrefs and not self.cdata_elem:
                    self.handle_data(unescape(rawdata[i:j]))
                else:
                    self.handle_data(rawdata[i:j])
            i = self.updatepos(i, j)
            if i == n: break
            startswith = rawdata.startswith
            if startswith('