mercurial/py3kcompat.py

encoding: default ambiguous character to narrow

The current implementation of colwidth was treating 'A'mbiguous
characters as wide, which was incorrect in a non-East Asian context.
As per http://unicode.org/reports/tr11/#Recommendations, we should
instead default to 'narrow' if we don't know better. As character
width is dependent on the particular font used and we have no idea
what fonts are in use, this recommendation applies.

This introduces HGENCODINGAMBIGUOUS to get the old behavior back.

# 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()