From caa3562d5bec1196502352a715a539bdb0f73c2d Mon Sep 17 00:00:00 2001
From: Matthew Somerville <matthew-github@dracos.co.uk>
Date: Thu, 29 Jan 2015 07:59:41 +0000
Subject: [PATCH] Fixed #24242 -- Improved efficiency of
 utils.text.compress_sequence()

The function no longer flushes zfile after each write as doing so can
lead to the gzipped streamed content being larger than the original
content; each flush adds a 5/6 byte type 0 block. Removing this means
buf.read() may return nothing, so only yield if that has some data.
Testing shows without the flush() the buffer is being flushed every 17k
or so and compresses the same as if it had been done as a whole string.
---
 django/utils/text.py           |  7 +++++--
 tests/utils_tests/test_text.py | 11 +++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/django/utils/text.py b/django/utils/text.py
index 88c38f4b2ff..ad549c349de 100644
--- a/django/utils/text.py
+++ b/django/utils/text.py
@@ -302,6 +302,8 @@ class StreamingBuffer(object):
         self.vals.append(val)
 
     def read(self):
+        if not self.vals:
+            return b''
         ret = b''.join(self.vals)
         self.vals = []
         return ret
@@ -321,8 +323,9 @@ def compress_sequence(sequence):
     yield buf.read()
     for item in sequence:
         zfile.write(item)
-        zfile.flush()
-        yield buf.read()
+        data = buf.read()
+        if data:
+            yield data
     zfile.close()
     yield buf.read()
 
diff --git a/tests/utils_tests/test_text.py b/tests/utils_tests/test_text.py
index aa185346881..d8675fa8c5e 100644
--- a/tests/utils_tests/test_text.py
+++ b/tests/utils_tests/test_text.py
@@ -1,6 +1,8 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
+import json
+
 from django.test import SimpleTestCase
 from django.utils import six, text
 from django.utils.encoding import force_text
@@ -192,3 +194,12 @@ class TestUtilsText(SimpleTestCase):
     def test_get_valid_filename(self):
         filename = "^&'@{}[],$=!-#()%+~_123.txt"
         self.assertEqual(text.get_valid_filename(filename), "-_123.txt")
+
+    def test_compress_sequence(self):
+        data = [{'key': i} for i in range(10)]
+        seq = list(json.JSONEncoder().iterencode(data))
+        seq = [s.encode('utf-8') for s in seq]
+        actual_length = len(b''.join(seq))
+        out = text.compress_sequence(seq)
+        compressed_length = len(b''.join(out))
+        self.assertTrue(compressed_length < actual_length)