view contrib/bdiff-torture.py @ 33927:853574db5b12

encoding: add fast path of from/tolocal() for ASCII strings

This is micro optimization, but seems not bad since to/fromlocal() is called
lots of times and isasciistr() is cheap and simple.

We boldly assume that any non-ASCII characters have at least one 8-bit byte.
This isn't true for some email character sets (e.g. ISO-2022-JP and UTF-7),
but I believe no such encodings are used as a platform default. Shift_JIS,
a major crap, is okay as it should have a leading byte in 0x80-0xff range.

  (with mercurial repo)
  $ export HGRCPATH=/dev/null HGPLAIN=
  $ hg log --time --config experimental.stabilization=all > /dev/null

  (original)
  time: real 7.460 secs (user 7.420+0.000 sys 0.030+0.000)
  time: real 7.670 secs (user 7.590+0.000 sys 0.080+0.000)
  time: real 7.560 secs (user 7.510+0.000 sys 0.040+0.000)

  (this patch)
  time: real 7.340 secs (user 7.260+0.000 sys 0.060+0.000)
  time: real 7.260 secs (user 7.210+0.000 sys 0.030+0.000)
  time: real 7.310 secs (user 7.260+0.000 sys 0.060+0.000)

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
import random
import sys

from mercurial import (
    mdiff,
)

def reducetest(a, b):
    tries = 0
    reductions = 0
    print("reducing...")
    while tries < 1000:
        a2 = "\n".join(l for l in a.splitlines()
                       if random.randint(0, 100) > 0) + "\n"
        b2 = "\n".join(l for l in b.splitlines()
                       if random.randint(0, 100) > 0) + "\n"
        if a2 == a and b2 == b:
            continue
        if a2 == b2:
            continue
        tries += 1

        try:
            test1(a, b)
        except Exception as inst:
            reductions += 1
            tries = 0
            a = a2
            b = b2

    print("reduced:", reductions, len(a) + len(b),
          repr(a), repr(b))
    try:
        test1(a, b)
    except Exception as inst:
        print("failed:", inst)

    sys.exit(0)

def test1(a, b):
    d = mdiff.textdiff(a, b)
    if not d:
        raise ValueError("empty")
    c = mdiff.patches(a, [d])
    if c != b:
        raise ValueError("bad")

def testwrap(a, b):
    try:
        test1(a, b)
        return
    except Exception as inst:
        pass
    print("exception:", inst)
    reducetest(a, b)

def test(a, b):
    testwrap(a, b)
    testwrap(b, a)

def rndtest(size, noise):
    a = []
    src = "                aaaaaaaabbbbccd"
    for x in xrange(size):
        a.append(src[random.randint(0, len(src) - 1)])

    while True:
        b = [c for c in a if random.randint(0, 99) > noise]
        b2 = []
        for c in b:
            b2.append(c)
            while random.randint(0, 99) < noise:
                b2.append(src[random.randint(0, len(src) - 1)])
        if b2 != a:
            break

    a = "\n".join(a) + "\n"
    b = "\n".join(b2) + "\n"

    test(a, b)

maxvol = 10000
startsize = 2
while True:
    size = startsize
    count = 0
    while size < maxvol:
        print(size)
        volume = 0
        while volume < maxvol:
            rndtest(size, 2)
            volume += size
            count += 2
        size *= 2
    maxvol *= 4
    startsize *= 4