Accept commas in unquoted attribute values.
This closes SF patch #669683.
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
index 908b30e..c082fde 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -26,7 +26,7 @@
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./,:;+*%?!&$\(\)_#=~]*))?')
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
diff --git a/Lib/sgmllib.py b/Lib/sgmllib.py
index 021c8b5..a4f0a8b 100644
--- a/Lib/sgmllib.py
+++ b/Lib/sgmllib.py
@@ -34,7 +34,7 @@
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./,:;+*%?!&$\(\)_#=~\'"]*))?')
class SGMLParseError(RuntimeError):
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 8422751..a10c40b 100755
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -197,6 +197,10 @@
self._run_check("""<a b='' c="">""", [
("starttag", "a", [("b", ""), ("c", "")]),
])
+ # Regression test for SF patch #669683.
+ self._run_check("<e a=rgb(1,2,3)>", [
+ ("starttag", "e", [("a", "rgb(1,2,3)")]),
+ ])
def test_attr_entity_replacement(self):
self._run_check("""<a b='&><"''>""", [
diff --git a/Lib/test/test_sgmllib.py b/Lib/test/test_sgmllib.py
index 90ed87e..6f4454f 100644
--- a/Lib/test/test_sgmllib.py
+++ b/Lib/test/test_sgmllib.py
@@ -200,6 +200,10 @@
self.check_events("""<a b='' c="">""", [
("starttag", "a", [("b", ""), ("c", "")]),
])
+ # Regression test for SF patch #669683.
+ self.check_events("<e a=rgb(1,2,3)>", [
+ ("starttag", "e", [("a", "rgb(1,2,3)")]),
+ ])
def test_attr_funky_names(self):
self.check_events("""<a a.b='v' c:d=v e-f=v>""", [