contrib/dumprevlog

narrow: when widening, don't include manifests the client already has

When widening, we already don't include the changelog (since
f1844a10ee19) and files that the client already has (since
c73c7653dfb9). However, we still include all manifests needed for the
new narrowspec. When using flat manifests, that means we resend all
the manifests even though the client necessarily has all of them. For
tree manifests, we unnecessarily resend the root manifests and any
subdirectory manifests that the client already has.

This patch makes it so we no longer resend manifests that the client
already has. It does so by passing an extra matcher to the changegroup
packer and it uses that for filtering out directories matching the old
matcher's visitdir(). For consistency between directories and files,
it also makes the filtering of files look at both old and new matcher
rather than passing in a diff matcher as we did before.

Differential Revision: https://phab.mercurial-scm.org/D4895

#!/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 (
    encoding,
    node,
    pycompat,
    revlog,
)
from mercurial.utils import (
    procutil,
)

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

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

def printb(data, end=b'\n'):
    sys.stdout.flush()
    pycompat.stdout.write(data + end)

for f in sys.argv[1:]:
    r = revlog.revlog(binopen, encoding.strtolocal(f))
    print("file:", f)
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        printb(b"node: %s" % node.hex(n))
        printb(b"linkrev: %d" % r.linkrev(i))
        printb(b"parents: %s %s" % (node.hex(p[0]), node.hex(p[1])))
        printb(b"length: %d" % len(d))
        printb(b"-start-")
        printb(d)
        printb(b"-end-")