view contrib/undumprevlog @ 28490:959eadae589a

changelog: lazily parse manifest node

Like the description, we store the raw bytes and convert from
hex on access.

This patch also marks the beginning of our new parsing method,
which is based on newline offsets and doesn't rely on
str.split().

Many revsets showed a performance improvement:

author(mpm)
0.896565
0.869085
0.868598

desc(bug)
0.887169
0.928164
0.910400

extra(rebase_source)
0.865446
0.871500
0.841644

author(mpm) or author(greg)
1.801832
1.791589
1.731503

author(mpm) or desc(bug)
1.812438
1.851003
1.798764

date(2015) or branch(default)
0.968276
0.974027
0.945792

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

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

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()