view contrib/dumprevlog @ 14087:f3d585c9b042

graphmod: restore generator nature of dagwalker

9966c95b8c4f introduced the ability to walk the DAG
given arbitrary revisions, but changed the behaviour of
it to return a list of all nodes (and create a changectx
for each one) rather than doing it lazily.

This has a pretty significant impact on performance for large
repositories (tested on CPython repo, with output disabled):

  $ time hg glog

  real	0m2.642s
  user	0m2.560s
  sys	0m0.080s

Before 9966c95b8c4f:

  $ time hg glog

  real	0m0.143s
  user	0m0.112s
  sys	0m0.032s

And after this fix:

  $ time hg glog

  real	0m0.213s
  user	0m0.184s
  sys	0m0.028s

#!/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.set_binary(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-"