From: Fred Drake <fdrake@acm.org>
Date: Thu, 5 Jul 2001 18:22:48 +0000 (+0000)
Subject: Allow underscores in tag names and quote characters in unquoted attribute
X-Git-Tag: v2.1.1c1~27
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=f379622e2b7bdab3b498ff58f1e468092905fa7e;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 5388c07b20d5..f612f2e900d9 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./:;+*%?!&$\(\)_#=~\'"]*))?')
 
 declname = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*')
 declstringlit = re.compile(r'(\'[^\']*\'|"[^"]*")\s*')