contrib/dumprevlog
author Pierre-Yves David <pierre-yves.david@octobus.net>
Fri, 05 Apr 2024 14:11:02 +0200
changeset 51583 22cc679a7312
parent 48875 6000f5b25c9b
permissions -rwxr-xr-x
phases: move RemotePhasesSummary to revision number This continue our quest to align more logic on revision number instead of node-ids. The motivation is similar to the change to `new_heads` and `analyze_remote_phases` a few changeset earlier. Again, we take this as an opportunity to rename the class, and the attribute to the new naming scheme. This will highlight the need for code update for any code using it an expecting node-ids. Many of the rev-num → node-id conversion we had to introduce in the previous changesets can now be removed. More will be removed in the future as we continue to align code toward rev-num usage. time saved in the 100 milliseconds order of magnitude for the mozilla-try benchmark I have been using.

#!/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-")