from htmlentitydefs import name2codepoint as n2cp
from urllib import unquote
import re

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()

def unescape(string):
    entity_re = re.compile("&(#?)(\d{1,5}|\w{1,8});")
    return entity_re.subn(substitute_entity, unquote(string))[0]


"""
import re

def unescape(text):
   def fixup(m):
      text = m.group(0)
      if text[:2] == "&#":
         # character reference
         try:
            if text[:3] == "&#x":
               return unichr(int(text[3:-1], 16))
            else:
               return unichr(int(text[2:-1]))
         except ValueError:
            print "erreur de valeur"
            pass
      else:
         # named entity
         try:
            if text[1:-1] == "amp":
               text = "&"
            elif text[1:-1] == "gt":
               text = ">"
            elif text[1:-1] == "lt":
               text = "<"
            else:
               print text[1:-1]
               text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
         except KeyError:
            print "keyerror"
            pass
      return text # leave as is
   return re.sub("&#?\w+;", fixup, text)
"""