view contrib/bdiff-torture.py @ 38713:27391d74aaa2

ssh: avoid reading beyond the end of stream when using compression Compressed streams can be used as part of getbundle. The normal read() operation of bufferedinputpipe will try to fulfill the request exactly and can deadlock if the server sends less as it is done. At the same time, the bundle2 logic will stop reading when it believes it has gotten all parts of the bundle, which can leave behind end of stream markers as used by bzip2 and zstd. To solve this, introduce a new optional unbufferedread interface and provided it in bufferedinputpipe and doublepipe. If there is buffered data left, it will be returned, otherwise it will issue a single read request and return whatever it obtains. Reorganize the decompression handlers to try harder to read until the end of stream, especially if the requested read can already be fulfilled. Check for end of stream is messy with Python 2, none of the standard compression modules properly exposes it. At least with zstd and bzip2, decompressing will remember EOS and fail for empty input after the EOS has been seen. For zlib, the only way to detect it with Python 2 is to duplicate the decompressobj and force some additional data into it. The common handler can be further optimized, but works as PoC. Differential Revision: https://phab.mercurial-scm.org/D3937
author Joerg Sonnenberger <joerg@bec.de>
date Thu, 12 Jul 2018 18:46:10 +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