From 8c85ddf306e6d707e4bd521e7708509a3fb29bf1 Mon Sep 17 00:00:00 2001
From: Malcolm Tredinnick <malcolm.tredinnick@gmail.com>
Date: Sat, 7 Jul 2007 18:24:27 +0000
Subject: [PATCH] Fixed #4772 -- Fixed reverse URL creation to work with
 non-ASCII arguments. Also included a test for non-ASCII strings in URL
 patterns, although that already worked correctly.

git-svn-id: http://code.djangoproject.com/svn/django/trunk@5630 bcc190cf-cafb-0310-a4f2-bffc1f526a37
---
 django/core/urlresolvers.py              | 12 ++++++------
 django/template/__init__.py              |  4 ++--
 tests/regressiontests/templates/tests.py |  3 ++-
 tests/regressiontests/templates/urls.py  |  4 +++-
 4 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/django/core/urlresolvers.py b/django/core/urlresolvers.py
index 000a56a726..1a56f11dda 100644
--- a/django/core/urlresolvers.py
+++ b/django/core/urlresolvers.py
@@ -9,7 +9,7 @@ a string) and returns a tuple in this format:
 
 from django.http import Http404
 from django.core.exceptions import ImproperlyConfigured, ViewDoesNotExist
-from django.utils.encoding import iri_to_uri
+from django.utils.encoding import iri_to_uri, force_unicode
 from django.utils.functional import memoize
 import re
 
@@ -101,7 +101,7 @@ class MatchChecker(object):
         # First we need to figure out whether it's a named or unnamed group.
         #
         grouped = match_obj.group(1)
-        m = re.search(r'^\?P<(\w+)>(.*?)$', grouped)
+        m = re.search(r'^\?P<(\w+)>(.*?)$', grouped, re.UNICODE)
         if m: # If this was a named group...
             # m.group(1) is the name of the group
             # m.group(2) is the regex.
@@ -127,9 +127,9 @@ class MatchChecker(object):
             test_regex = grouped
         # Note we're using re.match here on purpose because the start of
         # to string needs to match.
-        if not re.match(test_regex + '$', str(value)): # TODO: Unicode?
+        if not re.match(test_regex + '$', force_unicode(value), re.UNICODE):
             raise NoReverseMatch("Value %r didn't match regular expression %r" % (value, test_regex))
-        return str(value) # TODO: Unicode?
+        return force_unicode(value)
 
 class RegexURLPattern(object):
     def __init__(self, regex, callback, default_args=None, name=None):
@@ -137,7 +137,7 @@ class RegexURLPattern(object):
         # callback is either a string like 'foo.views.news.stories.story_detail'
         # which represents the path to a module and a view function name, or a
         # callable object (view).
-        self.regex = re.compile(regex)
+        self.regex = re.compile(regex, re.UNICODE)
         if callable(callback):
             self._callback = callback
         else:
@@ -201,7 +201,7 @@ class RegexURLResolver(object):
     def __init__(self, regex, urlconf_name, default_kwargs=None):
         # regex is a string representing a regular expression.
         # urlconf_name is a string representing the module containing urlconfs.
-        self.regex = re.compile(regex)
+        self.regex = re.compile(regex, re.UNICODE)
         self.urlconf_name = urlconf_name
         self.callback = None
         self.default_kwargs = default_kwargs or {}
diff --git a/django/template/__init__.py b/django/template/__init__.py
index b58e9f049c..6880fd5997 100644
--- a/django/template/__init__.py
+++ b/django/template/__init__.py
@@ -512,7 +512,7 @@ filter_raw_string = r"""
          )?
  )""" % {
     'str': r"""[^"\\]*(?:\\.[^"\\]*)*""",
-    'var_chars': "A-Za-z0-9\_\." ,
+    'var_chars': "\w\." ,
     'filter_sep': re.escape(FILTER_SEPARATOR),
     'arg_sep': re.escape(FILTER_ARGUMENT_SEPARATOR),
     'i18n_open' : re.escape("_("),
@@ -520,7 +520,7 @@ filter_raw_string = r"""
   }
 
 filter_raw_string = filter_raw_string.replace("\n", "").replace(" ", "")
-filter_re = re.compile(filter_raw_string)
+filter_re = re.compile(filter_raw_string, re.UNICODE)
 
 class FilterExpression(object):
     """
diff --git a/tests/regressiontests/templates/tests.py b/tests/regressiontests/templates/tests.py
index 5b4ff10bdb..143d1ddaa4 100644
--- a/tests/regressiontests/templates/tests.py
+++ b/tests/regressiontests/templates/tests.py
@@ -735,7 +735,8 @@ class Templates(unittest.TestCase):
             'url02' : ('{% url regressiontests.templates.views.client_action client.id, action="update" %}', {'client': {'id': 1}}, '/url_tag/client/1/update/'),
             'url03' : ('{% url regressiontests.templates.views.index %}', {}, '/url_tag/'),
             'url04' : ('{% url named.client client.id %}', {'client': {'id': 1}}, '/url_tag/named-client/1/'),
-            'url05' : (u'{% url метка_оператора 1 %}', {}, '/url_tag/unicode/1/'),
+            'url05' : (u'{% url метка_оператора v %}', {'v': u'Ω'},
+                    '/url_tag/%D0%AE%D0%BD%D0%B8%D0%BA%D0%BE%D0%B4/%CE%A9/'),
 
             # Failures
             'url-fail01' : ('{% url %}', {}, template.TemplateSyntaxError),
diff --git a/tests/regressiontests/templates/urls.py b/tests/regressiontests/templates/urls.py
index 4ac9eb29f7..d79f38e0a7 100644
--- a/tests/regressiontests/templates/urls.py
+++ b/tests/regressiontests/templates/urls.py
@@ -9,5 +9,7 @@ urlpatterns = patterns('',
     (r'^client/(\d+)/$', views.client),
     (r'^client/(\d+)/(?P<action>[^/]+)/$', views.client_action),
     url(r'^named-client/(\d+)/$', views.client, name="named.client"),
-    url(r'^unicode/(\d+)/$', views.client, name=u"метка_оператора"),
+
+    # Unicode strings are permitted everywhere.
+    url(ur'^Юникод/(\w+)/$', views.client, name=u"метка_оператора"),
 )