contrib/dumprevlog

copies: correctly skip directories that have already been considered

Previously, `if dsrc in invalid` would never be true, since we added
`dsrc +"/"` to invalid, not `dsrc` itself. Since it's much more common for
individual files (not whole directories) to be moved, it seemed cleaner to
delay appending the "/" until we know we have some directory moves to
actually consider.

I haven't benchmarked this, but I imagine this is a mild performance win.

Differential Revision: https://phab.mercurial-scm.org/D4284

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

from __future__ import absolute_import, print_function

import sys
from mercurial import (
    node,
    revlog,
)
from mercurial.utils import (
    procutil,
)

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

def binopen(path, mode='rb'):
    if 'b' not in mode:
        mode = mode + 'b'
    return open(path, mode)

for f in sys.argv[1:]:
    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-")