[1.2.X] Fixed #12988 -- Extended regular expression of the URLValidator to fully support IDN-URLs, especially the long TLDs.

Backport from trunk (r15502).

git-svn-id: http://code.djangoproject.com/svn/django/branches/releases/1.2.X@15509 bcc190cf-cafb-0310-a4f2-bffc1f526a37

2 files changed, 28 insertions, 9 deletions

diff --git a/django/core/validators.py b/django/core/validators.py
index b1b82dbf0d..dad0a7924f 100644
--- a/django/core/validators.py
+++ b/django/core/validators.py
@@ -41,7 +41,7 @@ class RegexValidator(object):
 class URLValidator(RegexValidator):
     regex = re.compile(
         r'^https?://' # http:// or https://
-        r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+[A-Z]{2,6}\.?|' #domain...
+        r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|' #domain...
         r'localhost|' #localhost...
         r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})' # ...or ip
         r'(?::\d+)?' # optional port
diff --git a/tests/regressiontests/forms/tests/fields.py b/tests/regressiontests/forms/tests/fields.py
index e7516ad737..f198e6c796 100644
--- a/tests/regressiontests/forms/tests/fields.py
+++ b/tests/regressiontests/forms/tests/fields.py
@@ -567,13 +567,6 @@ class FieldsTests(TestCase):
             f.clean('http://google.com/we-love-microsoft.html') # good domain, bad page
         except ValidationError, e:
             self.assertEqual("[u'This URL appears to be a broken link.']", str(e))
-        # Valid and existent IDN
-        self.assertEqual(u'http://\u05e2\u05d1\u05e8\u05d9\u05ea.idn.icann.org/', f.clean(u'http://עברית.idn.icann.org/'))
-        # Valid but non-existent IDN
-        try:
-            f.clean(u'http://broken.עברית.idn.icann.org/')
-        except ValidationError, e:
-            self.assertEqual("[u'This URL appears to be a broken link.']", str(e))
 
     def test_urlfield_4(self):
         f = URLField(verify_exists=True, required=False)
@@ -597,10 +590,36 @@ class FieldsTests(TestCase):
         self.assertEqual(u'http://example.com/', f.clean('http://example.com'))
         self.assertEqual(u'http://example.com/test', f.clean('http://example.com/test'))
 
-    def test_urlfield_ticket11826(self):
+    def test_urlfield_8(self):
+        # ticket #11826
         f = URLField()
         self.assertEqual(u'http://example.com/?some_param=some_value', f.clean('http://example.com?some_param=some_value'))
 
+    def test_urlfield_9(self):
+        f = URLField(verify_exists=False)
+        urls = (
+            u'http://עברית.idn.icann.org/',
+            u'http://sãopaulo.com/',
+            u'http://sãopaulo.com.br/',
+            u'http://пример.испытание/',
+            u'http://مثال.إختبار/',
+            u'http://例子.测试/',
+            u'http://例子.測試/',
+            u'http://उदाहरण.परीक्षा/',
+            u'http://例え.テスト/',
+            u'http://مثال.آزمایشی/',
+            u'http://실례.테스트/',
+            u'http://العربية.idn.icann.org/',
+        )
+        for url in urls:
+            # Valid and existent IDN
+            self.assertEqual(url, f.clean(url))
+        # Valid but non-existent IDN
+        try:
+            f.clean(u'http://broken.עברית.idn.icann.org/')
+        except ValidationError, e:
+            self.assertEqual("[u'This URL appears to be a broken link.']", str(e))
+
     # BooleanField ################################################################
 
     def test_booleanfield_1(self):