view mercurial/py3kcompat.py @ 21568:8dd17b19e722 stable

subrepo: normalize path in the specific way for problematic encodings

Before this patch, "reporelpath()" uses "rstrip(os.sep)" to trim
"os.sep" at the end of "parent.root" path.

But it doesn't work correctly with some problematic encodings on
Windows, because some multi-byte characters in such encodings contain
'\\' (0x5c) as the tail byte of them.

In such cases, "reporelpath()" leaves unexpected '\\' at the beginning
of the path returned to callers.

"lcalrepository.root" seems not to have tail "os.sep", because it is
always normalized by "os.path.realpath()" in "vfs.__init__()", but in
fact it has tail "os.sep", if it is a root (of the drive): path
normalization trims tail "os.sep" off "/foo/bar/", but doesn't trim
one off "/".

So, just avoiding "rstrip(os.sep)" in "reporelpath()" causes
regression around issue3033 fixed by fccd350acf79.

This patch introduces "pathutil.normasprefix" to normalize specified
path in the specific way for problematic encodings without regression
around issue3033.

# py3kcompat.py - compatibility definitions for running hg in py3k
#
# Copyright 2010 Renato Cunha <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import os, builtins

from numbers import Number

def bytesformatter(format, args):
    '''Custom implementation of a formatter for bytestrings.

    This function currently relies on the string formatter to do the
    formatting and always returns bytes objects.

    >>> bytesformatter(20, 10)
    0
    >>> bytesformatter('unicode %s, %s!', ('string', 'foo'))
    b'unicode string, foo!'
    >>> bytesformatter(b'test %s', 'me')
    b'test me'
    >>> bytesformatter('test %s', 'me')
    b'test me'
    >>> bytesformatter(b'test %s', b'me')
    b'test me'
    >>> bytesformatter('test %s', b'me')
    b'test me'
    >>> bytesformatter('test %d: %s', (1, b'result'))
    b'test 1: result'
    '''
    # The current implementation just converts from bytes to unicode, do
    # what's needed and then convert the results back to bytes.
    # Another alternative is to use the Python C API implementation.
    if isinstance(format, Number):
        # If the fixer erroneously passes a number remainder operation to
        # bytesformatter, we just return the correct operation
        return format % args
    if isinstance(format, bytes):
        format = format.decode('utf-8', 'surrogateescape')
    if isinstance(args, bytes):
        args = args.decode('utf-8', 'surrogateescape')
    if isinstance(args, tuple):
        newargs = []
        for arg in args:
            if isinstance(arg, bytes):
                arg = arg.decode('utf-8', 'surrogateescape')
            newargs.append(arg)
        args = tuple(newargs)
    ret = format % args
    return ret.encode('utf-8', 'surrogateescape')
builtins.bytesformatter = bytesformatter

# Create bytes equivalents for os.environ values
for key in list(os.environ.keys()):
    # UTF-8 is fine for us
    bkey = key.encode('utf-8', 'surrogateescape')
    bvalue = os.environ[key].encode('utf-8', 'surrogateescape')
    os.environ[bkey] = bvalue

origord = builtins.ord
def fakeord(char):
    if isinstance(char, int):
        return char
    return origord(char)
builtins.ord = fakeord

if __name__ == '__main__':
    import doctest
    doctest.testmod()