view contrib/bdiff-torture.py @ 38737:913ca175c4ae

aggressivemergedelta: document rename and move to `revlog` section The config does not follow our naming guideline and "Aggressive" is probably a word to keep away from users. The option does not truly fit in the `format` section. It can be turned on and off for existing repository without much consequence regarding compatibility. A new `revlog` option is created to control behavior related to revlog writing and reading. We can see multiple other config options that could be migrated there. * format.maxchainlen * experimental.mmapindexthreshold * experimental.sparse-read.density-threshold (in an updated form) * experimental.sparse-read.min-gap-size (in an updated form) In addition, we can foresee at least a couple of sparse-revlog related option coming too (to reduce delta chain length and increase snapshot reuse) These two extra options might fit there too. Unless we want to create a section dedicated to caches and performance. * format.chunkcachesize * format.manifestcachesize For now, we only migrate `optimize-delta-parent-choice` since it is getting out of experimental. It is too close to the release to move the other one. In addition, we still lack proper the prioritization of alias that would help renaming them without bad consequence for users. (Not fully happy about the `revlog` name but could not find better).
author Boris Feld <boris.feld@octobus.net>
date Thu, 19 Jul 2018 10:35:29 +0200
parents 0c73634d0570
children 876494fd967d
line wrap: on
line source

# 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