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 a471c05..fe91c1b 100644
--- a/Lib/sgmllib.py
+++ b/Lib/sgmllib.py
@@ -34,10 +34,10 @@
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*')