view contrib/bdiff-torture.py @ 45871:a985c4fb23ca

transaction: change list of journal entries into a dictionary

The transaction object used to keep a mapping table of path names to
journal entries and a list of journal entries consisting of path and
file offset to truncate on rollback. The offsets are used in three
cases. repair.strip and rollback process all of them in one go, but they
care about the order. For them, it is perfectly reasonable to read the
journal back from disk as both operations already involve at least one
system call per journal entry. The other consumer is the revlog logic
for moving from inline to external data storage. It doesn't care about
the order of the journal and just needs to original offset stored.
Further optimisations are possible here to move the in-memory journal to
a set(), but without memoisation of the original revlog size this could
turn it into O(n^2) behavior in worst case when many revlogs need to
migrated.

Differential Revision: https://phab.mercurial-scm.org/D9277

# 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