htmlentities.py

from htmlentitydefs import name2codepoint as n2cp
from htmlentitydefs import codepoint2name as cp2n
import re


def decode_htmlentities(string):
    """
    Decodes htmlentities or xmlentities
        >>> decode_htmlentities('"X>Y"')
        u'"X>Y"'
        
        >>> decode_htmlentities('m&m')
        u'm&m'
    """
    entity_re = re.compile("&(#?)(\d{1,5}|\w{1,8});")
    def substitute_entity(match):
        ent = match.group(2)
        if match.group(1) == "#":
            return unichr(int(ent))
        else:
            cp = n2cp.get(ent)

            if cp:
                return unichr(cp)
            else:
                return match.group()
    return entity_re.subn(substitute_entity, string)[0]


def html2xmlentities(string):
    """
    Converts htmlentities to xmlentities
        >>> html2xmlentities('m&m')
        'm&m'
    """
    xpr = re.compile('&(\w{1,8});')
    def substitute_entity(match):
        ent = match.group(1)
        if ent in n2cp.keys():
            return '&#%i;' % n2cp[ent]
        else:
            return match.group(0)
    return xpr.subn(substitute_entity, string)[0]


def xml2htmlentities(string):
    """
    Converts xmlentities to htmlentities
        >>> xml2htmlentities('m&m')
        'm&m'
    """
    xpr = re.compile('&#(\d{1,5});')
    def substitute_entity(match):
        ent = int(match.group(1))
        if ent in cp2n.keys():
            return '&%s;' % cp2n[ent]
        else:
            return match.group(0)
    return xpr.subn(substitute_entity, string)[0]