From 0e8710d5900a75b9a4a1caebb82c939896e99cff Mon Sep 17 00:00:00 2001 From: Brian Rosner Date: Tue, 1 Jul 2008 15:49:08 +0000 Subject: newforms-admin: Merged from trunk up to [7814]. git-svn-id: http://code.djangoproject.com/svn/django/branches/newforms-admin@7815 bcc190cf-cafb-0310-a4f2-bffc1f526a37 --- django/utils/text.py | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'django/utils/text.py') diff --git a/django/utils/text.py b/django/utils/text.py index aa190c8c4f..3686a454a8 100644 --- a/django/utils/text.py +++ b/django/utils/text.py @@ -3,6 +3,7 @@ from django.conf import settings from django.utils.encoding import force_unicode from django.utils.functional import allow_lazy from django.utils.translation import ugettext_lazy +from htmlentitydefs import name2codepoint # Capitalizes the first letter of a string. capfirst = lambda x: x and force_unicode(x)[0].upper() + force_unicode(x)[1:] @@ -222,3 +223,26 @@ def smart_split(text): yield bit smart_split = allow_lazy(smart_split, unicode) +def _replace_entity(match): + text = match.group(1) + if text[0] == u'#': + text = text[1:] + try: + if text[0] in u'xX': + c = int(text[1:], 16) + else: + c = int(text) + return unichr(c) + except ValueError: + return match.group(0) + else: + try: + return unichr(name2codepoint[text]) + except (ValueError, KeyError): + return match.group(0) + +_entity_re = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));") + +def unescape_entities(text): + return _entity_re.sub(_replace_entity, text) +unescape_entities = allow_lazy(unescape_entities, unicode) -- cgit v1.3