Merge branch 'develop'

Author: dstufft

AUTHORS.txt

@@ -99,6 +99,7 @@ Hugo Lopes Tavares <[email protected]>
 Hynek Schlawack <[email protected]>
 Ian Bicking <[email protected]>
 Ian Cordasco <[email protected]>
+Ian Lee <[email protected]>
 Ian Wienand <[email protected]>
 Igor Sobreira <[email protected]>
 Ilya Baryshev <[email protected]>
@@ -261,6 +262,7 @@ Thomas Smith <[email protected]>
 Tim Harder <[email protected]>
 tim smith <[email protected]>
 Tomer Chachamu <[email protected]>
+Tony Zhaocheng Tan <[email protected]>
 Toshio Kuratomi <[email protected]>
 Travis Swicegood <[email protected]>
 Valentin Haenel <[email protected]>

CHANGES.txt

@@ -1,3 +1,9 @@
+**8.1.1 (2016-03-17)**
+
+* Fix regression with non-ascii requirement files on Python 2 and add support
+  for encoding headers in requirement files (:issue:`3548`, :pull:`3547`).
+
+
 **8.1.0 (2016-03-05)**
 
 * Implement PEP 513, which adds support for the manylinux1 platform tag,

pip/__init__.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 from __future__ import absolute_import
 
+import locale
 import logging
 import os
 import optparse
@@ -30,7 +31,7 @@
 cmdoptions = pip.cmdoptions
 
 # The version as used in the setup.py and the docs conf.py
-__version__ = "8.1.0"
+__version__ = "8.1.1"
 
 
 logger = logging.getLogger(__name__)
@@ -209,6 +210,9 @@ def main(args=None):
         sys.stderr.write(os.linesep)
         sys.exit(1)
 
+    # Needed for locale.getpreferredencoding(False) to work
+    # in pip.utils.encoding.auto_decode
+    locale.setlocale(locale.LC_ALL, '')
     command = commands_dict[cmd_name](isolated=check_isolated(cmd_args))
     return command.main(cmd_args)
 

pip/cmdoptions.py

@@ -247,7 +247,7 @@ def find_links():
         default=[],
         metavar='url',
         help="If a url or path to an html file, then parse for links to "
-             "archives. If a local path or file:// url that's a directory,"
+             "archives. If a local path or file:// url that's a directory, "
              "then look for archives in the directory listing.")
 
 

pip/utils/encoding.py

@@ -1,5 +1,6 @@
 import codecs
 import locale
+import re
 
 
 BOMS = [
@@ -12,6 +13,8 @@
     (codecs.BOM_UTF32_LE, 'utf32-le'),
 ]
 
+ENCODING_RE = re.compile(b'coding[:=]\s*([-\w.]+)')
+
 
 def auto_decode(data):
     """Check a bytes string for a BOM to correctly detect the encoding
@@ -20,4 +23,9 @@ def auto_decode(data):
     for bom, encoding in BOMS:
         if data.startswith(bom):
             return data[len(bom):].decode(encoding)
+    # Lets check the first two lines as in PEP263
+    for line in data.split(b'\n')[:2]:
+        if line[0:1] == b'#' and ENCODING_RE.search(line):
+            encoding = ENCODING_RE.search(line).groups()[0].decode('ascii')
+            return data.decode(encoding)
     return data.decode(locale.getpreferredencoding(False))

tests/unit/test_utils.py

@@ -464,3 +464,7 @@ def test_auto_decode_utf16_le(self):
 
     def test_auto_decode_no_bom(self):
         assert auto_decode(b'foobar') == u'foobar'
+
+    def test_auto_decode_pep263_headers(self):
+        latin1_req = u'# coding=latin1\n# Pas trop de café'
+        assert auto_decode(latin1_req.encode('latin1')) == latin1_req