view mercurial/py3kcompat.py @ 22864:96b6b3d78697

revset: cache most conditions used in `filter`

Except when stated otherwise, the condition used in `smartset.filter` will be
cached. A new argument has been introduced to disable that behavior. We use it
for filters created from `and` and `sub` operations.

This gives massive performance boosts for revsets with expensive conditions.

revset: branch(stable) or branch(default)
before) wall 4.329070 comb 4.320000 user 4.310000 sys 0.010000 (best of 3)
after)  wall 2.356451 comb 2.360000 user 2.330000 sys 0.030000 (best of 4)

revset: author(mpm) or author(lmoscovicz)
before) wall 4.434719 comb 4.440000 user 4.440000 sys 0.000000 (best of 3)
after)  wall 2.321720 comb 2.320000 user 2.320000 sys 0.000000 (best of 4)

# 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 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

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()