view contrib/dumprevlog @ 51580:b70628a9aa7e

phases: use revision number in new_heads

All graph operations will be done using revision numbers, so passing nodes only
means they will eventually get converted to revision numbers internally.

As part of an effort to align the code on using revision number we make the
`phases.newheads` function operated on revision number, taking them as input
and using them in returns, instead of the node-id it used to consume and
produce.

This is part of multiple changesets effort to translate more part of the logic,
but is done step by step to facilitate the identification of issue that might
arise in mercurial core and extensions.

To make the change simpler to handle for third party extensions, we also rename
the function, using a more modern form. This will help detecting the different
between the node-id version and the rev-num version.

I also take this as an opportunity to add some comment about possible
performance improvement for the future. They don't matter too much now, but they
are worse exploring in a while.

#!/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-")