##// END OF EJS Templates
pycompat: change argv conversion semantics...
pycompat: change argv conversion semantics Use of os.fsencode() to convert Python's sys.argv back to bytes was not correct because it isn't the logically inverse operation from what CPython was doing under the hood. This commit changes the logic for doing the str -> bytes conversion. This required a separate implementation for POSIX and Windows. The Windows behavior is arguably not ideal. The previous behavior on Windows was leading to failing tests, such as test-http-branchmap.t, which defines a utf-8 branch name via a command argument. Previously, Mercurial's argument parser looked to be receiving wchar_t bytes in some cases. After this commit, behavior on Windows is compatible with Python 2, where CPython did not implement `int wmain()` and Windows was performing a Unicode to ANSI conversion on the wchar_t native command line. Arguably better behavior on Windows would be for Mercurial to preserve the original Unicode sequence coming from Python and to wrap this in a bytes-like type so we can round trip safely. But, this would be new, backwards incompatible behavior. My goal for this commit was to converge Mercurial behavior on Python 3 on Windows to fix busted tests. And I believe I was successful, as this commit fixes 9 tests on my Windows machine and 14 tests in the AWS CI environment! Differential Revision: https://phab.mercurial-scm.org/D8337

File last commit:

r44082:4cd91104 stable
r45139:00e0c5c0 default
Show More
base85.py
88 lines | 2.0 KiB | text/x-python | PythonLexer
# base85.py: pure python base85 codec
#
# Copyright (C) 2009 Brendan Cully <brendan@kublai.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import struct
from .. import pycompat
_b85chars = pycompat.bytestr(
b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdef"
b"ghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~"
)
_b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
_b85dec = {}
def _mkb85dec():
for i, c in enumerate(_b85chars):
_b85dec[c] = i
def b85encode(text, pad=False):
"""encode text in base85 format"""
l = len(text)
r = l % 4
if r:
text += b'\0' * (4 - r)
longs = len(text) >> 2
words = struct.unpack(b'>%dL' % longs, text)
out = b''.join(
_b85chars[(word // 52200625) % 85]
+ _b85chars2[(word // 7225) % 7225]
+ _b85chars2[word % 7225]
for word in words
)
if pad:
return out
# Trim padding
olen = l % 4
if olen:
olen += 1
olen += l // 4 * 5
return out[:olen]
def b85decode(text):
"""decode base85-encoded text"""
if not _b85dec:
_mkb85dec()
l = len(text)
out = []
for i in range(0, len(text), 5):
chunk = text[i : i + 5]
chunk = pycompat.bytestr(chunk)
acc = 0
for j, c in enumerate(chunk):
try:
acc = acc * 85 + _b85dec[c]
except KeyError:
raise ValueError(
'bad base85 character at position %d' % (i + j)
)
if acc > 4294967295:
raise ValueError('Base85 overflow in hunk starting at byte %d' % i)
out.append(acc)
# Pad final chunk if necessary
cl = l % 5
if cl:
acc *= 85 ** (5 - cl)
if cl > 1:
acc += 0xFFFFFF >> (cl - 2) * 8
out[-1] = acc
out = struct.pack(b'>%dL' % (len(out)), *out)
if cl:
out = out[: -(5 - cl)]
return out