contrib/casesmash.py
author Martin Geisler <mg@aragost.com>
Mon, 23 Jul 2012 15:55:26 -0600
branchstable
changeset 17236 9fb8312dbdbd
parent 14730 f5765353d430
child 19322 ff1586a3adc5
permissions -rw-r--r--
encoding: add fast-path for ASCII uppercase. This copies the performance hack from encoding.lower (c481761033bd). The case-folding logic that kicks in on case-insensitive filesystems hits encoding.upper hard: with a repository with 75k files, the timings went from hg perfstatus ! wall 3.156000 comb 3.156250 user 1.625000 sys 1.531250 (best of 3) to hg perfstatus ! wall 2.390000 comb 2.390625 user 1.078125 sys 1.312500 (best of 5) This is a 24% decrease. For comparison, Mercurial 2.0 gives: hg perfstatus ! wall 2.172000 comb 2.171875 user 0.984375 sys 1.187500 (best of 5) so we're only 10% slower than before we added the extra case-folding logic. The same decrease is seen when executing 'hg status' as normal, where we go from: hg status --time time: real 4.322 secs (user 2.219+0.000 sys 2.094+0.000) to hg status --time time: real 3.307 secs (user 1.750+0.000 sys 1.547+0.000)

import sys, os, __builtin__
from mercurial import util

def lowerwrap(scope, funcname):
    f = getattr(scope, funcname)
    def wrap(fname, *args, **kwargs):
        d, base = os.path.split(fname)
        try:
            files = os.listdir(d or '.')
        except OSError, inst:
            files = []
        if base in files:
            return f(fname, *args, **kwargs)
        for fn in files:
            if fn.lower() == base.lower():
                return f(os.path.join(d, fn), *args, **kwargs)
        return f(fname, *args, **kwargs)
    scope.__dict__[funcname] = wrap

def normcase(path):
    return path.lower()

os.path.normcase = normcase

for f in 'file open'.split():
    lowerwrap(__builtin__, f)

for f in "chmod chown open lstat stat remove unlink".split():
    lowerwrap(os, f)

for f in "exists lexists".split():
    lowerwrap(os.path, f)

lowerwrap(util, 'posixfile')