annotate contrib/casesmash.py @ 50400:95acba2c29f6

encoding: avoid quadratic time complexity when json-encoding non-UTF8 strings

Apparently the code uses "+=" with a bytes object, which is linear-time, so the
whole encoding is quadratic-time. This patch makes us use a bytearray object,
instead, which has a(n amortized-)constant-time append operation.

The encoding is still not particularly fast, but at least a 10MB file
takes tens of seconds, not many hours to encode.

import __builtin__
import os
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:
            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')