contrib/dumprevlog
author pacien <pacien.trangirard@pacien.net>
Mon, 14 Feb 2022 12:34:02 +0100
changeset 48768 7dd5a2c0116a
parent 47177 5d5abfdc32d8
child 48875 6000f5b25c9b
permissions -rwxr-xr-x
revlog: implement changelogv2 packing and unpacking in C This introduces a C implementation of changelogv2 records packing and unpacking operations matching the pure Python counterpart, similarly to what we already have for revlogv1 and revlogv2. This is also necessary to access changelogv2 record fields from future Rust code without going through the Python part, which would annihilate any performance benefit. Differential Revision: https://phab.mercurial-scm.org/D12178

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

from __future__ import absolute_import, print_function

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-")