contrib/bdiff-torture.py

rebase: add boolean config item rebase.store-source

This allows to use rebase without recording a rebase_source extra
field. This is useful for example to build a mirror converted from
another SCM (such as svn) by converting only new revisions, and
then incrementally add them to the destination by pulling from the
newly converted (unrelated) repo and rebasing the new revisions
onto the last old already stored changeset. Without this patch the
rebased changesets would always receive some rebase_source that
would depend on the particular history of the conversion process,
instead of only depending on the original source revisions.

This is used to implement a hg mirror repo of SvarDOS (a partially
nonfree but completely redistributable DOS distribution) in the
scripts at https://hg.pushbx.org/ecm/svardos.scr/

In particular, cre.sh creates an svn mirror, upd.sh recreates an
entire hg repo from the svn mirror (which takes too long to do in a
regular job), and akt.sh uses hg convert with the config item
convert.svn.startrev to incrementally convert only the two most
recent revisions already found in the mirror destination plus any
possible new revisions. If any are found, the temporary repo's
changesets are pulled into the destination (as changesets from an
unrelated repository). Then the changesets corresponding to the new
revisions are rebased onto the prior final changeset. (Finally, the
two remaining duplicates of the prior head and its parent are
stripped from the destination repository.)

Without this patch, the particular rebase_source extra field would
depend on the order and times at which akt.sh was used, instead of
only depending on the source repository. In other words, whatever
sequence of upd.sh and akt.sh is used at whatever times, it is
desired that the final output repositories always match each other
exactly.

# Randomized torture test generation for bdiff

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