ref: ec60da4961b4acff96631e7b99c90a0f4500dbed
dir: /sys/src/cmd/hg/hgext/win32mbcs.py/
# win32mbcs.py -- MBCS filename support for Mercurial
#
# Copyright (c) 2008 Shun-ichi Goto <[email protected]>
#
# Version: 0.2
# Author: Shun-ichi Goto <[email protected]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2, incorporated herein by reference.
#
'''allow the use of MBCS paths with problematic encodings
Some MBCS encodings are not good for some path operations (i.e.
splitting path, case conversion, etc.) with its encoded bytes. We call
such a encoding (i.e. shift_jis and big5) as "problematic encoding".
This extension can be used to fix the issue with those encodings by
wrapping some functions to convert to Unicode string before path
operation.
This extension is useful for:
- Japanese Windows users using shift_jis encoding.
- Chinese Windows users using big5 encoding.
- All users who use a repository with one of problematic encodings on
case-insensitive file system.
This extension is not needed for:
- Any user who use only ASCII chars in path.
- Any user who do not use any of problematic encodings.
Note that there are some limitations on using this extension:
- You should use single encoding in one repository.
- You should set same encoding for the repository by locale or
HGENCODING.
Path encoding conversion are done between Unicode and
encoding.encoding which is decided by Mercurial from current locale
setting or HGENCODING.
'''
import os, sys
from mercurial.i18n import _
from mercurial import util, encoding
def decode(arg):
if isinstance(arg, str):
uarg = arg.decode(encoding.encoding)
if arg == uarg.encode(encoding.encoding):
return uarg
raise UnicodeError("Not local encoding")
elif isinstance(arg, tuple):
return tuple(map(decode, arg))
elif isinstance(arg, list):
return map(decode, arg)
elif isinstance(arg, dict):
for k, v in arg.items():
arg[k] = decode(v)
return arg
def encode(arg):
if isinstance(arg, unicode):
return arg.encode(encoding.encoding)
elif isinstance(arg, tuple):
return tuple(map(encode, arg))
elif isinstance(arg, list):
return map(encode, arg)
elif isinstance(arg, dict):
for k, v in arg.items():
arg[k] = encode(v)
return arg
def appendsep(s):
# ensure the path ends with os.sep, appending it if necessary.
try:
us = decode(s)
except UnicodeError:
us = s
if us and us[-1] not in ':/\\':
s += os.sep
return s
def wrapper(func, args, kwds):
# check argument is unicode, then call original
for arg in args:
if isinstance(arg, unicode):
return func(*args, **kwds)
try:
# convert arguments to unicode, call func, then convert back
return encode(func(*decode(args), **decode(kwds)))
except UnicodeError:
raise util.Abort(_("[win32mbcs] filename conversion failed with"
" %s encoding\n") % (encoding.encoding))
def wrapperforlistdir(func, args, kwds):
# Ensure 'path' argument ends with os.sep to avoids
# misinterpreting last 0x5c of MBCS 2nd byte as path separator.
if args:
args = list(args)
args[0] = appendsep(args[0])
if kwds.has_key('path'):
kwds['path'] = appendsep(kwds['path'])
return func(*args, **kwds)
def wrapname(name, wrapper):
module, name = name.rsplit('.', 1)
module = sys.modules[module]
func = getattr(module, name)
def f(*args, **kwds):
return wrapper(func, args, kwds)
try:
f.__name__ = func.__name__ # fail with python23
except Exception:
pass
setattr(module, name, f)
# List of functions to be wrapped.
# NOTE: os.path.dirname() and os.path.basename() are safe because
# they use result of os.path.split()
funcs = '''os.path.join os.path.split os.path.splitext
os.path.splitunc os.path.normpath os.path.normcase os.makedirs
mercurial.util.endswithsep mercurial.util.splitpath mercurial.util.checkcase
mercurial.util.fspath mercurial.windows.pconvert'''
# codec and alias names of sjis and big5 to be faked.
problematic_encodings = '''big5 big5-tw csbig5 big5hkscs big5-hkscs
hkscs cp932 932 ms932 mskanji ms-kanji shift_jis csshiftjis shiftjis
sjis s_jis shift_jis_2004 shiftjis2004 sjis_2004 sjis2004
shift_jisx0213 shiftjisx0213 sjisx0213 s_jisx0213 950 cp950 ms950 '''
def reposetup(ui, repo):
# TODO: decide use of config section for this extension
if not os.path.supports_unicode_filenames:
ui.warn(_("[win32mbcs] cannot activate on this platform.\n"))
return
# fake is only for relevant environment.
if encoding.encoding.lower() in problematic_encodings.split():
for f in funcs.split():
wrapname(f, wrapper)
wrapname("mercurial.osutil.listdir", wrapperforlistdir)
ui.debug(_("[win32mbcs] activated with encoding: %s\n")
% encoding.encoding)