view contrib/undumprevlog @ 41881:e514799e4e07

discovery: use a lower level but faster way to retrieve parents

We already know that no revision in the undecided set are filtered, so we can
skip multiple checks and directly access lower level data.

In a private pathological case, this improves the timing from about 70 seconds
to about 50 seconds. There are other actions to be taken to improve that case,
however this gives an idea of the general overhead.

#!/usr/bin/env python
# Undump a dump from dumprevlog
# $ hg init
# $ undumprevlog < repo.dump

from __future__ import absolute_import, print_function

import sys
from mercurial import (
    encoding,
    node,
    pycompat,
    revlog,
    transaction,
    vfs as vfsmod,
)
from mercurial.utils import (
    procutil,
)

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

opener = vfsmod.vfs(b'.', False)
tr = transaction.transaction(sys.stderr.write, opener, {b'store': opener},
                             b"undump.journal")
while True:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = encoding.strtolocal(l[6:-1])
        r = revlog.revlog(opener, f)
        pycompat.stdout.write(b'%s\n' % f)
    elif l.startswith("node:"):
        n = node.bin(l[6:-1])
    elif l.startswith("linkrev:"):
        lr = int(l[9:-1])
    elif l.startswith("parents:"):
        p = l[9:-1].split()
        p1 = node.bin(p[0])
        p2 = node.bin(p[1])
    elif l.startswith("length:"):
        length = int(l[8:-1])
        sys.stdin.readline() # start marker
        d = encoding.strtolocal(sys.stdin.read(length))
        sys.stdin.readline() # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()