contrib/dumprevlog

commitctx: extract copy information encoding into extra into commit.py

The encoding of copy information into extra has multiple subcases and become
quite complicated (eg: empty list can be explicitly or implicitly stored for
example). In addition, it is niche experimental feature since as it affect the
hash, it is only suitable for user who don't mercurial for storage server side
(ie: Google).

Having this complexity part of the changelog will get in the way of further
cleanup. We could have to either move more of that logic into the changelog or
to move or extract more of the logic at the higher level. We take the second
approach and start gather logic in dedicated function in commit.py.

#!/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 (
    encoding,
    node,
    pycompat,
    revlog,
)
from mercurial.utils import procutil

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