[Python-checkins] cpython (3.2): #7311: fix html.parser to accept non-ASCII attribute values.

ezio.melotti python-checkins at python.org
Thu Apr 7 21:27:23 CEST 2011


http://hg.python.org/cpython/rev/225400cb6e84
changeset:   69189:225400cb6e84
branch:      3.2
parent:      69186:3d7c9b38fbfd
user:        Ezio Melotti
date:        Thu Apr 07 22:03:31 2011 +0300
summary:
  #7311: fix html.parser to accept non-ASCII attribute values.

files:
  Lib/html/parser.py          |   2 +-
  Lib/test/test_htmlparser.py |  17 +++++++++++++++++
  Misc/NEWS                   |   2 ++
  3 files changed, 20 insertions(+), 1 deletions(-)


diff --git a/Lib/html/parser.py b/Lib/html/parser.py
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -28,7 +28,7 @@
 # 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
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -217,6 +217,23 @@
             ("starttag", "a", [("href", "mailto:xyz at 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", "&><\"'")]),
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -49,6 +49,8 @@
 Library
 -------
 
+- Issue #7311: fix html.parser to accept non-ASCII attribute values.
+
 - Issue #11605: email.parser.BytesFeedParser was incorrectly converting multipart
   subpararts with an 8bit CTE into unicode instead of preserving the bytes.
 

-- 
Repository URL: http://hg.python.org/cpython


More information about the Python-checkins mailing list