From dc19163b18e193a729e75cb98926ff96c3154f99 Mon Sep 17 00:00:00 2001
From: Fred Drake <fdrake@acm.org>
Date: Thu, 5 Jul 2001 18:21:57 +0000
Subject: 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.
---
 Lib/sgmllib.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Lib/sgmllib.py b/Lib/sgmllib.py
index a471c05..fe91c1b 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*')
-- 
cgit v0.12