[1.0.X] Fixed #10254: Changed the regex in get_valid_filename to allow unicode alphanumerics (thanks gulliver). Also updated the file_uploads test for this case to check the name after saving the uploaded file. As it was the test ensured that files with unicode characters in their names could be uploaded, but it wasn't actually ensuring that the unicode characters were preserved through save.

Backport of [10388]


git-svn-id: http://code.djangoproject.com/svn/django/branches/releases/1.0.X@10389 bcc190cf-cafb-0310-a4f2-bffc1f526a37

1 files changed, 3 insertions, 3 deletions

diff --git a/django/utils/text.py b/django/utils/text.py
index 1548cfa77e..cd631983d7 100644
--- a/django/utils/text.py
+++ b/django/utils/text.py
@@ -116,13 +116,13 @@ def get_valid_filename(s):
     """
     Returns the given string converted to a string that can be used for a clean
     filename. Specifically, leading and trailing spaces are removed; other
-    spaces are converted to underscores; and all non-filename-safe characters
-    are removed.
+    spaces are converted to underscores; and anything that is not a unicode
+    alphanumeric, dash, underscore, or dot, is removed.
     >>> get_valid_filename("john's portrait in 2004.jpg")
     u'johns_portrait_in_2004.jpg'
     """
     s = force_unicode(s).strip().replace(' ', '_')
-    return re.sub(r'[^-A-Za-z0-9_.]', '', s)
+    return re.sub(r'(?u)[^-\w.]', '', s)
 get_valid_filename = allow_lazy(get_valid_filename, unicode)
 
 def get_text_list(list_, last_word=ugettext_lazy(u'or')):