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

2 files changed, 18 insertions, 1 deletions

diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index 21ebbc3..a3586eb 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -28,7 +28,7 @@ tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
 # make it correctly strict without breaking backward compatibility.
 attrfind = re.compile(
     r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
-    r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?')
+    r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
 attrfind_tolerant = re.compile(
     r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
     r'(\'[^\']*\'|"[^"]*"|[^>\s]*))?')
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 5ecd016..637ab01 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -217,6 +217,23 @@ DOCTYPE html [
             ("starttag", "a", [("href", "mailto:xyz@example.com")]),
             ])
 
+    def test_attr_nonascii(self):
+        # see issue 7311
+        self._run_check("<img src=/foo/bar.png alt=\u4e2d\u6587>", [
+            ("starttag", "img", [("src", "/foo/bar.png"),
+                                 ("alt", "\u4e2d\u6587")]),
+            ])
+        self._run_check("<a title='\u30c6\u30b9\u30c8' "
+                        "href='\u30c6\u30b9\u30c8.html'>", [
+            ("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
+                               ("href", "\u30c6\u30b9\u30c8.html")]),
+            ])
+        self._run_check('<a title="\u30c6\u30b9\u30c8" '
+                        'href="\u30c6\u30b9\u30c8.html">', [
+            ("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
+                               ("href", "\u30c6\u30b9\u30c8.html")]),
+            ])
+
     def test_attr_entity_replacement(self):
         self._run_check("""<a b='&amp;&gt;&lt;&quot;&apos;'>""", [
             ("starttag", "a", [("b", "&><\"'")]),