annotate convert-repo @ 190:3dd5ce2fddb6

merge: short-circuit search for merge into empty repo

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

merge: short-circuit search for merge into empty repo

We should have 3 cases for merge:

- - we have no changesets
- - we have less than half the changesets
- - we have more than half the changesets

For no changesets, we can immediately tell that we need everything.
This happens when we initially branch from a remote repo, so we simply shortcircuit the search and grab everything from the root

When we're actually tracking a project, we should generally have most
of the changesets, so the current search algorithm should minimize
searching.

It should rarely occur that upstreams gets far ahead of us, in which
case, we suffer a longer search.

manifest hash: eabd55841b03225176ea72b985aad36431a438a9
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (GNU/Linux)

iD8DBQFCmfajywK+sNU5EO8RAuyKAKCf7Nw6XSK5HEzbrZae7Q06e3dk4wCgjbK6
YUTEfkpPP1h3mNHIHRKz+aI=
=eGMq
-----END PGP SIGNATURE-----

#!/usr/bin/env python
import sys, os, sha, base64, re
from mercurial import hg

ui = hg.ui()
repo = hg.repository(ui=ui)
known = {}

def encodepath(path):
    s = sha.sha(path).digest()
    s = base64.encodestring(s)[:-3]
    s = re.sub("\+", "%", s)
    s = re.sub("/", "_", s)
    return s

for i in range(repo.changelog.count()):
    n = repo.changelog.node(i)
    changes = repo.changelog.read(n)
    for f in changes[3]:
        known[f] = 1

try:
    os.mkdir(".hg/data-new")
except:
    pass

files = known.keys()
files.sort()
for f in files:
    pb = ".hg/data/" + encodepath(f)
    pn = ".hg/data-new/" + f
    print f
    try:
        file(pn+".i", "w").write(file(pb+"i").read())
    except:
        os.makedirs(os.path.dirname(pn))
        # we actually copy the files to get nice disk layout
        file(pn+".i", "w").write(file(pb+"i").read())

    file(pn+".d", "w").write(file(pb).read())

os.rename(".hg/data", ".hg/data-old")
os.rename(".hg/data-new", ".hg/data")