test0908
/
django
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Simplified smart_urlquote and added some basic tests.

This commit is contained in:
Florian Apolloner 2013-07-28 10:05:39 +02:00
parent 0d0ccf81a0
commit b70c371fc1
3 changed files with 21 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
django/utils/html.py
View File

@ -4,13 +4,13 @@ from __future__ import unicode_literals
import re
try:
from urllib.parse import quote, urlsplit, urlunsplit
from urllib.parse import quote, unquote, urlsplit, urlunsplit
except ImportError: # Python 2
from urllib import quote
from urllib import quote, unquote
from urlparse import urlsplit, urlunsplit
from django.utils.safestring import SafeData, mark_safe
from django.utils.encoding import force_bytes, force_text
from django.utils.encoding import force_text, force_str
from django.utils.functional import allow_lazy
from django.utils import six
from django.utils.text import normalize_newlines
@ -26,7 +26,6 @@ WRAPPING_PUNCTUATION = [('(', ')'), ('<', '>'), ('[', ']'), ('&lt;', '&gt;')]
DOTS = ['&middot;', '*', '\u2022', '&#149;', '&bull;', '&#8226;']
unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
unquoted_percents_re = re.compile(r'%(?![0-9A-Fa-f]{2})')
word_split_re = re.compile(r'(\s+)')
simple_url_re = re.compile(r'^https?://\[?\w', re.IGNORECASE)
simple_url_2_re = re.compile(r'^www\.|^(?!http)\w[^@]+\.(com|edu|gov|int|mil|net|org)$', re.IGNORECASE)
@ -185,11 +184,9 @@ def smart_urlquote(url):
# invalid IPv6 URL (normally square brackets in hostname part).
pass
# An URL is considered unquoted if it contains no % characters or
# contains a % not followed by two hexadecimal digits. See #9655.
if '%' not in url or unquoted_percents_re.search(url):
url = unquote(force_str(url))
# See http://bugs.python.org/issue2637
url = quote(force_bytes(url), safe=b'!*\'();:@&=+$,/?#[]~')
url = quote(url, safe=b'!*\'();:@&=+$,/?#[]~')
return force_text(url)

7
tests/defaultfilters/tests.py
View File

@ -249,9 +249,10 @@ class DefaultFiltersTests(TestCase):
'<a href="https://google.com" rel="nofollow">https://google.com</a>')
# Check urlize doesn't overquote already quoted urls - see #9655
self.assertEqual(urlize('http://hi.baidu.com/%D6%D8%D0%C2%BF'),
'<a href="http://hi.baidu.com/%D6%D8%D0%C2%BF" rel="nofollow">'
'http://hi.baidu.com/%D6%D8%D0%C2%BF</a>')
# The teststring is the urlquoted version of 'http://hi.baidu.com/重新开始'
self.assertEqual(urlize('http://hi.baidu.com/%E9%87%8D%E6%96%B0%E5%BC%80%E5%A7%8B'),
'<a href="http://hi.baidu.com/%E9%87%8D%E6%96%B0%E5%BC%80%E5%A7%8B" rel="nofollow">'
'http://hi.baidu.com/%E9%87%8D%E6%96%B0%E5%BC%80%E5%A7%8B</a>')
self.assertEqual(urlize('www.mystore.com/30%OffCoupons!'),
'<a href="http://www.mystore.com/30%25OffCoupons!" rel="nofollow">'
'www.mystore.com/30%OffCoupons!</a>')

11
tests/utils_tests/test_html.py
View File

@ -1,3 +1,4 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from datetime import datetime
@ -181,3 +182,13 @@ class TestUtilsHtml(TestCase):
)
for value, tags, output in items:
self.assertEqual(f(value, tags), output)
def test_smart_urlquote(self):
quote = html.smart_urlquote
# Ensure that IDNs are properly quoted
self.assertEqual(quote('http://öäü.com/'), 'http://xn--4ca9at.com/')
self.assertEqual(quote('http://öäü.com/öäü/'), 'http://xn--4ca9at.com/%C3%B6%C3%A4%C3%BC/')
# Ensure that everything unsafe is quoted, !*'();:@&=+$,/?#[]~ is considered safe as per RFC
self.assertEqual(quote('http://example.com/path/öäü/'), 'http://example.com/path/%C3%B6%C3%A4%C3%BC/')
self.assertEqual(quote('http://example.com/%C3%B6/ä/'), 'http://example.com/%C3%B6/%C3%A4/')
self.assertEqual(quote('http://example.com/?x=1&y=2'), 'http://example.com/?x=1&y=2')