view contrib/dumprevlog @ 28008:86c4cbdaffee

revset: use manifest.matches in _follow revset

The old _follow revset iterated over every file in the commit and checked if it
matched. For repos with large manifests, this could take 500ms. By switching to
use manifest.matches() we can take advantage of the fastpaths built in to
manifest.py that allows iterating over only the files in the matcher when it's a
simple matcher. This brings the time spent down from 500ms to 0ms during simple
operations like 'hg log -f file.txt'.

#!/usr/bin/env python
# Dump revlogs as raw data stream
# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump

import sys
from mercurial import revlog, node, util

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

for f in sys.argv[1:]:
    binopen = lambda fn: open(fn, 'rb')
    r = revlog.revlog(binopen, f)
    print "file:", f
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        print "node:", node.hex(n)
        print "linkrev:", r.linkrev(i)
        print "parents:", node.hex(p[0]), node.hex(p[1])
        print "length:", len(d)
        print "-start-"
        print d
        print "-end-"