contrib/bdiff-torture.py
author Simon Sapin <simon.sapin@octobus.net>
Fri, 28 May 2021 20:07:27 +0200
changeset 47347 73ddcedeaadf
parent 43076 2372284d9457
child 48875 6000f5b25c9b
permissions -rw-r--r--
dirstate-tree: Change status() results to not borrow DirstateMap The `status` function takes a `&'tree mut DirstateMap<'on_disk>` parameter. `'on_disk` borrows a read-only byte buffer with the contents of the `.hg/dirstate` file. `DirstateMap` internally uses represents file paths as `std::borrow::Cow<'on_disk, HgPath>`, which borrows the byte buffer when possible and allocates an owned string if not, such as for files added to the dirstate after it was loaded from disk. Previously the return type of of `status` has a `'tree` lifetime, meaning it could borrow all paths from the `DirstateMap`. With this changeset, that lifetime is changed to `'on_disk` meaning that only paths from the byte buffer can be borrowed, and paths allocated by `DirstateMap` must be copied. Usually most paths are in the byte buffer, and most paths are not part of the return value of `status`, so the number of extra copies should be small. This change will enable `status` to mutate the `DirstateMap` after it has finished constructing its return value. Previously such mutation would be prevented by possible on-going borrows. Differential Revision: https://phab.mercurial-scm.org/D10824

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
import random
import sys

from mercurial import (
    mdiff,
    pycompat,
)


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:
            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:
        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 pycompat.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