From: Chris Withers <chris@simplistix.co.uk>
Date: Fri, 4 Sep 2009 16:51:16 +0000 (+0000)
Subject: Fixes issue #6838: use a list to accumulate the value instead of repeatedly concatena... 
X-Git-Tag: v2.6.3rc1~91
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=49148cf5287e34a399ecfc1958d62d2d83339f64;p=python

Fixes issue #6838: use a list to accumulate the value instead of repeatedly concatenating strings.
---

diff --git a/Lib/httplib.py b/Lib/httplib.py
index 1f584ef077..3566c0eb05 100644
--- a/Lib/httplib.py
+++ b/Lib/httplib.py
@@ -544,10 +544,7 @@ class HTTPResponse:
     def _read_chunked(self, amt):
         assert self.chunked != _UNKNOWN
         chunk_left = self.chunk_left
-        value = ''
-
-        # XXX This accumulates chunks by repeated string concatenation,
-        # which is not efficient as the number or size of chunks gets big.
+        value = []
         while True:
             if chunk_left is None:
                 line = self.fp.readline()
@@ -560,22 +557,22 @@ class HTTPResponse:
                     # close the connection as protocol synchronisation is
                     # probably lost
                     self.close()
-                    raise IncompleteRead(value)
+                    raise IncompleteRead(''.join(value))
                 if chunk_left == 0:
                     break
             if amt is None:
-                value += self._safe_read(chunk_left)
+                value.append(self._safe_read(chunk_left))
             elif amt < chunk_left:
-                value += self._safe_read(amt)
+                value.append(self._safe_read(amt))
                 self.chunk_left = chunk_left - amt
-                return value
+                return ''.join(value)
             elif amt == chunk_left:
-                value += self._safe_read(amt)
+                value.append(self._safe_read(amt))
                 self._safe_read(2)  # toss the CRLF at the end of the chunk
                 self.chunk_left = None
-                return value
+                return ''.join(value)
             else:
-                value += self._safe_read(chunk_left)
+                value.append(self._safe_read(chunk_left))
                 amt -= chunk_left
 
             # we read the whole chunk, get another
@@ -596,7 +593,7 @@ class HTTPResponse:
         # we read everything; close the "file"
         self.close()
 
-        return value
+        return ''.join(value)
 
     def _safe_read(self, amt):
         """Read the number of bytes requested, compensating for partial reads.
diff --git a/Misc/NEWS b/Misc/NEWS
index c2eea0f580..aed5bf845b 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -72,6 +72,11 @@ Core and Builtins
 Library
 -------
 
+- Issue #6838: Use a list to accumulate the value instead of
+  repeatedly concatenating strings in httplib's
+  HTTPResponse._read_chunked providing a significant speed increase
+  when downloading large files servend with a Transfer-Encoding of 'chunked'.
+
 - Issue #6794: Fix Decimal.compare_total and Decimal.compare_total_mag: NaN
   payloads are now ordered by integer value rather than lexicographically.