view mercurial/py3kcompat.py @ 13750:7eb82f88e157

# User Dan Villiom Podlaski Christiansen <[e-mail]>
# Date 1289564504 -3600
# Node ID b75264c15cc888cf38c3c7b8f619801e3c2589c7
# Parent  89b2e5d940f669e590096c6be70eee61c9172fff
revsets: overload the branch() revset to also take a branch name.

This should only change semantics in the specific case of a tag/branch
conflict where the tag wasn't done on the branch with the same
name. Previously, branch(whatever) would resolve to the branch of the
tag in that case, whereas now it will resolve to the branch of the
name. The previous behaviour, while documented, seemed very
counter-intuitive to me.

An alternate approach would be to introduce a new revset such as
branchname() or namedbranch(). While this would retain backwards
compatibility, the distinction between it and branch() would not be
readily apparent to users. The most intuitive behaviour would be to
have branch(x) require 'x' to be a branch name, and something like
branchof(x) or samebranch(x) do what branch(x) currently
does. Unfortunately, our backwards compatibility guarantees prevent us
from doing that.

Please note that while 'hg tag' guards against shadowing a branch, 'hg
branch' does not. Besides, even if it did, that wouldn't solve the
issue of conversions with such tags and branches...

# 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 relias 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()