contrib/dumprevlog
author Yuya Nishihara <yuya@tcha.org>
Sun, 15 Jul 2018 18:24:57 +0900
changeset 38707 6b5ca1d0aa1e
parent 37123 a8a902d7176e
child 39948 a063b84ce064
permissions -rwxr-xr-x
obsolete: store user name and note in UTF-8 (issue5754) (BC) Before, user names were stored in local encoding and transferred across repositories, which made it impossible to restore non-ASCII user names on different platforms. This patch fixes new markers to be encoded in UTF-8 and decoded back to local encoding when displaying. Existing markers are unfixable so they may result in mojibake. I don't like the API that requires metadata dict to be UTF-8 encoded, which is a source of bugs, but there's no abstraction layer to process the encoding thingy efficiently. So we apply the same rule as extras dict to obsstore metadata.

#!/usr/bin/env python
# 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 import (
    node,
    revlog,
)
from mercurial.utils import (
    procutil,
)

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

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

for f in sys.argv[1:]:
    r = revlog.revlog(binopen, f)
    print("file:", f)
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        print("node:", node.hex(n))
        print("linkrev:", r.linkrev(i))
        print("parents:", node.hex(p[0]), node.hex(p[1]))
        print("length:", len(d))
        print("-start-")
        print(d)
        print("-end-")