from __future__ import absolute_import

import re

__all__ = [
    '_SGML_AVAILABLE',
    'sgmllib',
    'charref',
    'tagfind',
    'attrfind',
    'entityref',
    'incomplete',
    'interesting',
    'shorttag',
    'shorttagopen',
    'starttagopen',
    'endbracket',
]

# sgmllib is not available by default in Python 3; if the end user doesn't have
# it available then we'll lose illformed XML parsing and content sanitizing
try:
    import sgmllib
except ImportError:
    # This is probably Python 3, which doesn't include sgmllib anymore
    _SGML_AVAILABLE = 0

    # Mock sgmllib enough to allow subclassing later on
    class sgmllib(object):
        class SGMLParser(object):
            def goahead(self, i):
                pass
            def parse_starttag(self, i):
                pass
else:
    _SGML_AVAILABLE = 1

    # sgmllib defines a number of module-level regular expressions that are
    # insufficient for the XML parsing feedparser needs. Rather than modify
    # the variables directly in sgmllib, they're defined here using the same
    # names, and the compiled code objects of several sgmllib.SGMLParser
    # methods are copied into _BaseHTMLProcessor so that they execute in
    # feedparser's scope instead of sgmllib's scope.
    charref = re.compile('&#(\d+|[xX][0-9a-fA-F]+);')
    tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*')
    attrfind = re.compile(
        r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)[$]?(\s*=\s*'
        r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?'
    )

    # Unfortunately, these must be copied over to prevent NameError exceptions
    entityref = sgmllib.entityref
    incomplete = sgmllib.incomplete
    interesting = sgmllib.interesting
    shorttag = sgmllib.shorttag
    shorttagopen = sgmllib.shorttagopen
    starttagopen = sgmllib.starttagopen

    class _EndBracketRegEx:
        def __init__(self):
            # Overriding the built-in sgmllib.endbracket regex allows the
            # parser to find angle brackets embedded in element attributes.
            self.endbracket = re.compile('''([^'"<>]|"[^"]*"(?=>|/|\s|\w+=)|'[^']*'(?=>|/|\s|\w+=))*(?=[<>])|.*?(?=[<>])''')
        def search(self, target, index=0):
            match = self.endbracket.match(target, index)
            if match is not None:
                # Returning a new object in the calling thread's context
                # resolves a thread-safety.
                return EndBracketMatch(match)
            return None
    class EndBracketMatch:
        def __init__(self, match):
            self.match = match
        def start(self, n):
            return self.match.end(n)
    endbracket = _EndBracketRegEx()