Fixed #21574 -- Handle bytes consistently in utils.text.normalize_newlines.

All input is now coerced to text before being normalized.
This changes nothing under Python 2 but it allows bytes
to be passed to the function without a TypeError under Python3
(bytes are assumed to be utf-8 encoded text).

Thanks to trac user vajrasky for the report.
This commit is contained in:
Baptiste Mispelon 2013-12-12 15:58:14 +01:00
parent b9c7234e2a
commit 2c837233f5
2 changed files with 10 additions and 2 deletions

View File

@ -250,7 +250,9 @@ get_text_list = allow_lazy(get_text_list, six.text_type)
def normalize_newlines(text): def normalize_newlines(text):
return force_text(re_newlines.sub('\n', text)) """Normalizes CRLF and CR newlines to just LF."""
text = force_text(text)
return re_newlines.sub('\n', text)
normalize_newlines = allow_lazy(normalize_newlines, six.text_type) normalize_newlines = allow_lazy(normalize_newlines, six.text_type)

View File

@ -2,7 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from django.test import SimpleTestCase from django.test import SimpleTestCase
from django.utils import text from django.utils import six, text
class TestUtilsText(SimpleTestCase): class TestUtilsText(SimpleTestCase):
@ -114,6 +114,12 @@ class TestUtilsText(SimpleTestCase):
self.assertEqual(text.normalize_newlines("abcdefghi"), "abcdefghi") self.assertEqual(text.normalize_newlines("abcdefghi"), "abcdefghi")
self.assertEqual(text.normalize_newlines(""), "") self.assertEqual(text.normalize_newlines(""), "")
def test_normalize_newlines_bytes(self):
"""normalize_newlines should be able to handle bytes too"""
normalized = text.normalize_newlines(b"abc\ndef\rghi\r\n")
self.assertEqual(normalized, "abc\ndef\nghi\n")
self.assertIsInstance(normalized, six.text_type)
def test_slugify(self): def test_slugify(self):
items = ( items = (
('Hello, World!', 'hello-world'), ('Hello, World!', 'hello-world'),