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 a471c0589b5376f8716812f6e0053412a5b58b0f..fe91c1b0398c440871ce10e4bff74793037308dc 100644 (file)
--- 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*')