gistfile1.diff

From: Chris Kuehl <[email protected]>
Date: Fri, 23 Jan 2015 14:54:24 -0800
Subject: [PATCH] Don't raise IncompleteRead if response reads fails

This is a backport of the following commits onto the python-pip package.

https://github.com/pypa/pip/commit/53eab2357e4425436b51e109bfaedcb9f3772072
https://github.com/pypa/pip/commit/e77c0c573c059bb4a86b2c5c06835f57e4af6c47

This fixes Debian bug#744145 by allowing pip to continue to work with
upgraded versions of the requests library.
---
 pip/download.py | 35 +++++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/pip/download.py b/pip/download.py
index adff2ec..768e7ba 100644
--- a/pip/download.py
+++ b/pip/download.py
@@ -22,8 +22,7 @@ from pip.log import logger
 import requests, six
 from requests.adapters import BaseAdapter
 from requests.auth import AuthBase, HTTPBasicAuth
-from requests.compat import IncompleteRead
-from requests.exceptions import InvalidURL, ChunkedEncodingError
+from requests.exceptions import InvalidURL
 from requests.models import Response
 from requests.structures import CaseInsensitiveDict
 
@@ -416,12 +415,32 @@ def _download_url(resp, link, temp_location):
         def resp_read(chunk_size):
             try:
                 # Special case for urllib3.
-                try:
-                    for chunk in resp.raw.stream(
-                            chunk_size, decode_content=False):
-                        yield chunk
-                except IncompleteRead as e:
-                    raise ChunkedEncodingError(e)
+                for chunk in resp.raw.stream(
+                        chunk_size,
+                        # We use decode_content=False here because we do
+                        # want urllib3 to mess with the raw bytes we get
+                        # from the server. If we decompress inside of
+                        # urllib3 then we cannot verify the checksum
+                        # because the checksum will be of the compressed
+                        # file. This breakage will only occur if the
+                        # server adds a Content-Encoding header, which
+                        # depends on how the server was configured:
+                        # - Some servers will notice that the file isn't a
+                        #   compressible file and will leave the file alone
+                        #   and with an empty Content-Encoding
+                        # - Some servers will notice that the file is
+                        #   already compressed and will leave the file
+                        #   alone and will add a Content-Encoding: gzip
+                        #   header
+                        # - Some servers won't notice anything at all and
+                        #   will take a file that's already been compressed
+                        #   and compress it again and set the
+                        #   Content-Encoding: gzip header
+                        #
+                        # By setting this not to decode automatically we
+                        # hope to eliminate problems with the second case.
+                        decode_content=False):
+                    yield chunk
             except AttributeError:
                 # Standard file-like object.
                 while True:
-- 
2.1.4