From 38787d0fb5102e41b153e4629d2ef374a02965e9 Mon Sep 17 00:00:00 2001
From: Samuel Merritt <sam@swiftstack.com>
Date: Tue, 26 May 2015 16:19:54 -0700
Subject: [PATCH] Remove simplejson from staticweb

Since we're dropping Python 2.6 support, we can rely on stdlib's json
and get rid of our dependency on simplejson.

This lets us get rid of some redundant Unicode encoding. Before, we
would take the container-listing response off the wire,
JSON-deserialize it (str -> unicode), then pass each of several fields
from each entry to get_valid_utf8_str(), which would encode it,
(unicode -> str), decode it (str -> unicode), and then encode it again
(unicode -> str) for good measure.

The net effect was that each object's name would, in the proxy server,
go str -> unicode -> str -> unicode -> str.

By replacing simplejson with stdlib json, we get a guarantee that each
container-listing entry's name, hash, content_type, and last_modified
are unicodes, so we can stop worrying about them being valid UTF-8 or
not. This takes an encode and decode out of the path, so we just have
str -> unicode -> str. While it'd be ideal to avoid this, the first
transform (str -> unicode) happens when we decode the
container-listing response body (json.loads()), so there's no way out.

Change-Id: I00aedf952d691a809c23025b89131ea0f02b6431
---
 swift/common/middleware/staticweb.py          | 18 +++++++------
 test/unit/common/middleware/test_staticweb.py | 26 +------------------
 2 files changed, 11 insertions(+), 33 deletions(-)

diff --git a/swift/common/middleware/staticweb.py b/swift/common/middleware/staticweb.py
index 34b102ea53..d16b5ae3e7 100644
--- a/swift/common/middleware/staticweb.py
+++ b/swift/common/middleware/staticweb.py
@@ -117,10 +117,11 @@ Example usage of this middleware via ``swift``:
 
 
 import cgi
+import json
 import time
 
 from swift.common.utils import human_readable, split_path, config_true_value, \
-    json, quote, get_valid_utf8_str, register_swift_info
+    quote, register_swift_info
 from swift.common.wsgi import make_pre_authed_env, WSGIContext
 from swift.common.http import is_success, is_redirection, HTTP_NOT_FOUND
 from swift.common.swob import Response, HTTPMovedPermanently, HTTPNotFound
@@ -289,7 +290,7 @@ class _StaticWebContext(WSGIContext):
                     '   </tr>\n'
         for item in listing:
             if 'subdir' in item:
-                subdir = get_valid_utf8_str(item['subdir'])
+                subdir = item['subdir'].encode("utf-8")
                 if prefix:
                     subdir = subdir[len(prefix):]
                 body += '   <tr class="item subdir">\n' \
@@ -300,13 +301,14 @@ class _StaticWebContext(WSGIContext):
                         (quote(subdir), cgi.escape(subdir))
         for item in listing:
             if 'name' in item:
-                name = get_valid_utf8_str(item['name'])
+                name = item['name'].encode("utf-8")
                 if prefix:
                     name = name[len(prefix):]
-                content_type = get_valid_utf8_str(item['content_type'])
-                bytes = get_valid_utf8_str(human_readable(item['bytes']))
-                last_modified = (cgi.escape(item['last_modified']).
-                                 split('.')[0].replace('T', ' '))
+                content_type = item['content_type'].encode("utf-8")
+                bytes = human_readable(item['bytes'])
+                last_modified = (
+                    cgi.escape(item['last_modified'].encode("utf-8")).
+                    split('.')[0].replace('T', ' '))
                 body += '   <tr class="item %s">\n' \
                         '    <td class="colname"><a href="%s">%s</a></td>\n' \
                         '    <td class="colsize">%s</td>\n' \
@@ -315,7 +317,7 @@ class _StaticWebContext(WSGIContext):
                         (' '.join('type-' + cgi.escape(t.lower(), quote=True)
                                   for t in content_type.split('/')),
                          quote(name), cgi.escape(name),
-                         bytes, get_valid_utf8_str(last_modified))
+                         bytes, last_modified)
         body += '  </table>\n' \
                 ' </body>\n' \
                 '</html>\n'
diff --git a/test/unit/common/middleware/test_staticweb.py b/test/unit/common/middleware/test_staticweb.py
index a5c61b1c31..fe361fde7a 100644
--- a/test/unit/common/middleware/test_staticweb.py
+++ b/test/unit/common/middleware/test_staticweb.py
@@ -13,15 +13,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-try:
-    import simplejson as json
-except ImportError:
-    import json
-import json as stdlib_json
+import json
 import unittest
 
-import mock
-
 from swift.common.swob import Request, Response
 from swift.common.middleware import staticweb
 
@@ -699,24 +693,6 @@ class TestStaticWeb(unittest.TestCase):
         self.assert_('listing.css' not in resp.body)
         self.assert_('<style' in resp.body)
 
-    def test_container_unicode_stdlib_json(self):
-        with mock.patch('swift.common.middleware.staticweb.json',
-                        new=stdlib_json):
-            resp = Request.blank(
-                '/v1/a/c10/').get_response(self.test_staticweb)
-            self.assertEquals(resp.status_int, 200)
-            self.assert_('Listing of /v1/a/c10/' in resp.body)
-            resp = Request.blank(
-                '/v1/a/c10/\xe2\x98\x83/').get_response(self.test_staticweb)
-            self.assertEquals(resp.status_int, 200)
-            self.assert_('Listing of /v1/a/c10/\xe2\x98\x83/' in resp.body)
-            resp = Request.blank(
-                '/v1/a/c10/\xe2\x98\x83/\xe2\x98\x83/'
-            ).get_response(self.test_staticweb)
-            self.assertEquals(resp.status_int, 200)
-            self.assert_(
-                'Listing of /v1/a/c10/\xe2\x98\x83/\xe2\x98\x83/' in resp.body)
-
     def test_subrequest_once_if_possible(self):
         resp = Request.blank(
             '/v1/a/c4/one.txt').get_response(self.test_staticweb)