view mercurial/py3kcompat.py @ 22449:da05fe01170b

revset: make descendants() lazier

Previously descendants() would force the provided subset to become a set.  In
the case of revsets like '(%ld::) - (%ld)' (as used by histedit) this would
force the '- (%ld)' set to be evaluated, which produced a set containing every
commit in the repo (except %ld). This takes 0.6s on large repos.

This changes descendants to trust the subset to implement __contains__
efficiently, which improves the above revset to 0.16s. Shaving 0.4 seconds off
of histedit.

revset #27: (20000::) - (20000)
0) obsolete feature not enabled but 54243 markers found!
! wall 0.023640 comb 0.020000 user 0.020000 sys 0.000000 (best of 100)
1) obsolete feature not enabled but 54243 markers found!
! wall 0.019589 comb 0.020000 user 0.020000 sys 0.000000 (best of 100)

This commit removes the final revset related perf hotspot from histedit.
Combined with the previous two patches, they shave a little over 3 seconds off
histedit on large repos.

# 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()