##// 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:

r43812:2fe6121c default
r45139:00e0c5c0 default
Show More
charencode.py
90 lines | 2.3 KiB | text/x-python | PythonLexer
# charencode.py - miscellaneous character encoding
#
# Copyright 2005-2009 Matt Mackall <mpm@selenic.com> and others
#
# 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 array
from .. import pycompat
def isasciistr(s):
try:
s.decode('ascii')
return True
except UnicodeDecodeError:
return False
def asciilower(s):
'''convert a string to lowercase if ASCII
Raises UnicodeDecodeError if non-ASCII characters are found.'''
s.decode('ascii')
return s.lower()
def asciiupper(s):
'''convert a string to uppercase if ASCII
Raises UnicodeDecodeError if non-ASCII characters are found.'''
s.decode('ascii')
return s.upper()
_jsonmap = []
_jsonmap.extend(b"\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append(b'\\u007f')
_jsonmap[0x09] = b'\\t'
_jsonmap[0x0A] = b'\\n'
_jsonmap[0x22] = b'\\"'
_jsonmap[0x5C] = b'\\\\'
_jsonmap[0x08] = b'\\b'
_jsonmap[0x0C] = b'\\f'
_jsonmap[0x0D] = b'\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3C] = b'\\u003c' # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3E] = b'\\u003e' # '>'
_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))
def jsonescapeu8fast(u8chars, paranoid):
"""Convert a UTF-8 byte string to JSON-escaped form (fast path)
Raises ValueError if non-ASCII characters have to be escaped.
"""
if paranoid:
jm = _paranoidjsonmap
else:
jm = _jsonmap
try:
return b''.join(jm[x] for x in bytearray(u8chars))
except IndexError:
raise ValueError
if pycompat.ispy3:
_utf8strict = r'surrogatepass'
else:
_utf8strict = r'strict'
def jsonescapeu8fallback(u8chars, paranoid):
"""Convert a UTF-8 byte string to JSON-escaped form (slow path)
Escapes all non-ASCII characters no matter if paranoid is False.
"""
if paranoid:
jm = _paranoidjsonmap
else:
jm = _jsonmap
# non-BMP char is represented as UTF-16 surrogate pair
u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
u16codes = array.array('H', u16b)
u16codes.pop(0) # drop BOM
return b''.join(jm[x] if x < 128 else b'\\u%04x' % x for x in u16codes)