contrib/bdiff-torture.py
author Matt Harbison <matt_harbison@yahoo.com>
Fri, 17 Nov 2017 00:06:45 -0500
changeset 35476 417e8e040102
parent 32203 0c73634d0570
child 41365 876494fd967d
permissions -rw-r--r--
lfs: verify lfs object content when transferring to and from the remote store This avoids inserting corrupt files into the usercache, and local and remote stores. One down side is that the bad file won't be available locally for forensic purposes after a remote download. I'm thinking about adding an 'incoming' directory to the local lfs store to handle the download, and then move it to the 'objects' directory after it passes verification. That would have the additional benefit of not concatenating each transfer chunk in memory until the full file is transferred. Verification isn't needed when the data is passed back through the revlog interface or when the oid was just calculated, but otherwise it is on by default. The additional overhead should be well worth avoiding problems with file based remote stores, or buggy lfs servers. Having two different verify functions is a little sad, but the full data of the blob is mostly passed around in memory, because that's what the revlog interface wants. The upload function, however, chunks up the data. It would be ideal if that was how the content is always handled, but that's probably a huge project. I don't really like printing the long hash, but `hg debugdata` isn't a public interface, and is the only way to get it. The filelog and revision info is nowhere near this area, so recommending `hg verify` is the easiest thing to do.

# 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