view contrib/undumprevlog @ 29615:a2a380e2750f stable

rbc: fix superfluous rebuilding from scratch - don't abuse self._rbcnamescount

The code used self._rbcnamescount as if it was the length of self._names ...
but actually it is just the number of good entries on disk. This caused the
cache to be populated inefficiently. In some cases very inefficiently.

Instead of checking the length before lookup, just try a lookup in self._names
- that is also in most cases faster.

Comments and debug messages are tweaked to help understanding the issue
and the fix.

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

from __future__ import absolute_import

import sys
from mercurial import (
    node,
    revlog,
    scmutil,
    transaction,
    util,
)

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

opener = scmutil.opener('.', False)
tr = transaction.transaction(sys.stderr.write, opener, {'store': opener},
                             "undump.journal")
while True:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = l[6:-1]
        r = revlog.revlog(opener, f)
        print 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 = sys.stdin.read(length)
        sys.stdin.readline() # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()