"""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 markupbase
import re

# Regular expressions used for parsing

interesting_normal = re.compile('[&')

# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
# note: if you change tagfind/attrfind remember to update locatestarttagend too
tagfind = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
# this regex is currently unused, but left for backward compatibility
tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')

attrfind = re.compile(
    r'((?\s]*))?(?:\s|/(?!>))*')

locatestarttagend = re.compile(r"""
  \x00]*       # tag name
  (?:[\s/]*                          # optional whitespace before attribute name
    (?:(?\s]*           # bare value
         )
       )?(?:\s|/(?!>))*
     )*
   )?
  \s*                                # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
#