#7311: fix HTMLParser to accept non-ASCII attribute values.

2 files changed, 18 insertions, 1 deletions

diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
index 4fdc09a..e018901 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -26,7 +26,7 @@ commentclose = re.compile(r'--\s*>')
 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'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
 
 locatestarttagend = re.compile(r"""
   <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 717585c..0620d0b 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -208,6 +208,23 @@ DOCTYPE html [
             ("starttag", "a", [("href", "mailto:xyz@example.com")]),
             ])
 
+    def test_attr_nonascii(self):
+        # see issue 7311
+        self._run_check(u"<img src=/foo/bar.png alt=\u4e2d\u6587>", [
+            ("starttag", "img", [("src", "/foo/bar.png"),
+                                 ("alt", u"\u4e2d\u6587")]),
+            ])
+        self._run_check(u"<a title='\u30c6\u30b9\u30c8' "
+                        u"href='\u30c6\u30b9\u30c8.html'>", [
+            ("starttag", "a", [("title", u"\u30c6\u30b9\u30c8"),
+                               ("href", u"\u30c6\u30b9\u30c8.html")]),
+            ])
+        self._run_check(u'<a title="\u30c6\u30b9\u30c8" '
+                        u'href="\u30c6\u30b9\u30c8.html">', [
+            ("starttag", "a", [("title", u"\u30c6\u30b9\u30c8"),
+                               ("href", u"\u30c6\u30b9\u30c8.html")]),
+            ])
+
     def test_attr_entity_replacement(self):
         self._run_check("""<a b='&amp;&gt;&lt;&quot;&apos;'>""", [
             ("starttag", "a", [("b", "&><\"'")]),