contrib/dumprevlog

rev-branch-cache: properly ignores unaligned trailing data

Previously, trailing data could lead to crash and would be written back to disk,
disaligning all new data…

This is no longer the cases.

This was detected while playing with branchmap-v3 that access the
rev-branch-cache much more aggressively.

#!/usr/bin/env python3
# Dump revlogs as raw data stream
# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump


import sys
from mercurial.node import hex
from mercurial import (
    encoding,
    pycompat,
    revlog,
)
from mercurial.utils import procutil

from mercurial.revlogutils import (
    constants as revlog_constants,
)

for fp in (sys.stdin, sys.stdout, sys.stderr):
    procutil.setbinary(fp)


def binopen(path, mode=b'rb'):
    if b'b' not in mode:
        mode = mode + b'b'
    return open(path, pycompat.sysstr(mode))


binopen.options = {}


def printb(data, end=b'\n'):
    sys.stdout.flush()
    procutil.stdout.write(data + end)


for f in sys.argv[1:]:
    localf = encoding.strtolocal(f)
    if not localf.endswith(b'.i'):
        print("file:", f, file=sys.stderr)
        print("  invalid filename", file=sys.stderr)

    r = revlog.revlog(
        binopen,
        target=(revlog_constants.KIND_OTHER, b'dump-revlog'),
        radix=localf[:-2],
    )
    print("file:", f)
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        printb(b"node: %s" % hex(n))
        printb(b"linkrev: %d" % r.linkrev(i))
        printb(b"parents: %s %s" % (hex(p[0]), hex(p[1])))
        printb(b"length: %d" % len(d))
        printb(b"-start-")
        printb(d)
        printb(b"-end-")