Merged revisions 87542 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r87542 | senthil.kumaran | 2010-12-28 23:55:16 +0800 (Tue, 28 Dec 2010) | 3 lines Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax ........

Merged revisions 87542 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r87542 | senthil.kumaran | 2010-12-28 23:55:16 +0800 (Tue, 28 Dec 2010) | 3 lines Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax ........
6c858384 · Senthil Kumaran · 18f6b198 · 6c858384 · 6c858384
Kaydet (Commit) 6c858384 authored Ara 28, 2010 tarafından Senthil Kumaran
Hide whitespace changes
Inline Side-by-side

Showing with 14 additions and 7 deletions

parser.py Lib/html/parser.py +10 -7

test_htmlparser.py Lib/test/test_htmlparser.py +4 -0

No files found.
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -367,13 +367,16 @@ class HTMLParser(_markupbase.ParserBase):
            return s
        def replaceEntities(s):
            s = s.groups()[0]
-            if s[0] == "#":
-                s = s[1:]
-                if s[0] in ['x','X']:
-                    c = int(s[1:], 16)
-                else:
-                    c = int(s)
-                return chr(c)
+            try:
+                if s[0] == "#":
+                    s = s[1:]
+                    if s[0] in ['x','X']:
+                        c = int(s[1:], 16)
+                    else:
+                        c = int(s)
+                    return chr(c)
+            except ValueError:
+                return '&#'+ s +';'
            else:
                # Cannot use name2codepoint directly, because HTMLParser
                # supports apos, which is not part of HTML 4

--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -319,6 +319,10 @@ DOCTYPE html [
        self._run_check("<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>", [
                ("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])
                ])
+    def test_unescape_function(self):
+        p = html.parser.HTMLParser()
+        self.assertEqual(p.unescape('&#bad;'),'&#bad;')
+        self.assertEqual(p.unescape('&#0038;'),'&')


 def test_main():