From: Fred Drake <fdrake@acm.org>
Date: Thu, 5 Jul 2001 18:21:57 +0000 (+0000)
Subject: Allow underscores in tag names and quote characters in unquoted attribute
X-Git-Tag: v2.2a3~1335
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=dc19163b18e193a729e75cb98926ff96c3154f99;p=thirdparty%2FPython%2Fcpython.git

Allow underscores in tag names and quote characters in unquoted attribute
values.  The change for attribute values matches the way Mozilla and
Navigator view the world, at least.

This closes SF bug #436621.
---

diff --git a/Lib/sgmllib.py b/Lib/sgmllib.py
index a471c0589b53..fe91c1b0398c 100644
--- a/Lib/sgmllib.py
+++ b/Lib/sgmllib.py
@@ -34,10 +34,10 @@ endbracket = re.compile('[<>]')
 special = re.compile('<![^<>]*>')
 commentopen = re.compile('<!--')
 commentclose = re.compile(r'--\s*>')
-tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9]*')
+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./:;+*%?!&$\(\)_#=~]*))?')
+    r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./:;+*%?!&$\(\)_#=~\'"]*))?')
 
 decldata = re.compile(r'[^>\'\"]+')
 declstringlit = re.compile(r'(\'[^\']*\'|"[^"]*")\s*')