view mercurial/py3kcompat.py @ 25343:7fbef7932af9

revset: optimize 'or' operation of trivial revisions to a list As seen in issue4565 and issue4624, GUI wrappers and automated scripts are likely to generate a long query that just has numeric revisions joined by 'or'. One reason why is that they allows users to choose arbitrary revisions from a list. Because this use case isn't handled well by smartset, let's optimize it to a plain old list. Benchmarks: 1) reduce nesting of chained 'or' operations 2) optimize to a list (this patch) revset #0: 0 + 1 + 2 + ... + 1000 1) wall 0.483341 comb 0.480000 user 0.480000 sys 0.000000 (best of 20) 2) wall 0.025393 comb 0.020000 user 0.020000 sys 0.000000 (best of 107) revset #1: sort(0 + 1 + 2 + ... + 1000) 1) wall 0.035240 comb 0.040000 user 0.040000 sys 0.000000 (best of 100) 2) wall 0.026432 comb 0.030000 user 0.030000 sys 0.000000 (best of 102) revset #2: first(0 + 1 + 2 + ... + 1000) 1) wall 0.028949 comb 0.030000 user 0.030000 sys 0.000000 (best of 100) 2) wall 0.025503 comb 0.030000 user 0.030000 sys 0.000000 (best of 106)
author Yuya Nishihara <yuya@tcha.org>
date Sun, 17 May 2015 15:11:38 +0900
parents a7a9d84f5e4a
children 5bfd01a3c2a9
line wrap: on
line source

# py3kcompat.py - compatibility definitions for running hg in py3k
#
# Copyright 2010 Renato Cunha <renatoc@gmail.com>
#
# 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()