view mercurial/py3kcompat.py @ 27784:432242f41d9f

obsolete: make _computeobsoleteset much faster

This patch makes _computeobsoleteset much faster by looping
over the draft and secrets as opposed to looping over the
successors.
This works because "number of draft and secret" is typically
way smaller(<100) than the number of successor in the repo (~90k in
my checkout of core mercurial as of today). And also because
it is very fast to compute "not public()".

I timed the code with the following setup:
"""
from mercurial import hg, ui, obsolete
ui = ui.ui()
repo = hg.repository(ui, "~/hg")
l = repo.obsstore.successors # This caches the result
"""

With about 90k successors.

k=obsolete._computeobsoleteset(repo) before this patch:
10 loops, best of 3: 33.9 ms per loop

k=obsolete._computeobsoleteset(repo) after this patch:
10000 loops, best of 3: 83.3 µs per loop

# 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.

from __future__ import absolute_import

import builtins
import numbers

Number = numbers.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()