Ticket #15181: filepath_to_uri.patch

tests/regressiontests/file_storage/tests.py

@@ -204 +204 @@
         self.assertEqual(self.storage.url('test.file'),
             '%s%s' % (self.storage.base_url, 'test.file'))
 
+        # should encode special chars except ~!*()' 
+        # like encodeURIComponent() JavaScript function do
+        self.assertEqual(self.storage.url(r"""~!*()'@#$%^&*abc`+=.file"""),
+            """/test_media_url/~!*()'%40%23%24%25%5E%26*abc%60%2B%3D.file""")
+
+        # should stanslate os path separator(s) to the url path separator
+        self.assertEqual(self.storage.url("""a/b\\c.file"""),
+            """/test_media_url/a/b/c.file""")
+
         self.storage.base_url = None
         self.assertRaises(ValueError, self.storage.url, 'test.file')
 

django/core/files/storage.py

@@ -8 +8 @@
 from django.core.exceptions import ImproperlyConfigured, SuspiciousOperation
 from django.core.files import locks, File
 from django.core.files.move import file_move_safe
-from django.utils.encoding import force_unicode
+from django.utils.encoding import force_unicode, filepath_to_uri
 from django.utils.functional import LazyObject
 from django.utils.importlib import import_module
 from django.utils.text import get_valid_filename
@@ -240 +240 @@
     def url(self, name):
         if self.base_url is None:
             raise ValueError("This file is not accessible via a URL.")
-        return urlparse.urljoin(self.base_url, name).replace('\\', '/')
+        return urlparse.urljoin(self.base_url, filepath_to_uri(name))
 
     def accessed_time(self, name):
         return datetime.fromtimestamp(os.path.getatime(self.path(name)))

django/utils/encoding.py

@@ -156 +156 @@
         return iri
     return urllib.quote(smart_str(iri), safe="/#%[]=:;$&()+,!?*@'~")
 
+def filepath_to_uri(path):
+    """Convert an file system path to a URI portion that is suitable for
+    inclusion in a URL.
 
+    We are assuming input is either UTF-8 or unicode already.
+    
+    This method will encode certain chars that would normally be recognized as
+    special chars for URIs.  Note that this method does not encode the '
+    character, as it is a valid character within URIs.  See
+    encodeURIComponent() JavaScript function for more details.
+
+    Returns an ASCII string containing the encoded result.
+    """
+    if path is None:
+        return path
+    # I know about `os.sep` and `os.altsep` but I want to leave
+    # some flexibility for hardcoding separators.
+    return urllib.quote(smart_str(path).replace("\\", "/"), safe="/~!*()'")
+
 # The encoding of the default system locale but falls back to the
 # given fallback encoding if the encoding is unsupported by python or could
 # not be determined.  See tickets #10335 and #5846