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 5388c07b20d539450622e65fa286daac1bfe0d84..f612f2e900d9141a1fb9f4e51ffd550ba2ada82d 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./:;+*%?!&$\(\)_#=~\'"]*))?')
 
 declname = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*')
 declstringlit = re.compile(r'(\'[^\']*\'|"[^"]*")\s*')