view convert-repo @ 301:5add718d92db

revlog: allow duplicates

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

revlog: allow duplicates

If two branches make the same change to the same parent, the result
will be an identical hash. Git apparently does this all the time. Deal
with it gracefully.

manifest hash: c6217eab4b310e1ae529dd75ab90e717dbe5d55d
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (GNU/Linux)

iD8DBQFCqU61ywK+sNU5EO8RAkFqAJ9KhWUQgjZbzzB/+mTkolH0GkT1awCfa+Mj
ulbI4xCRZcvfQE492mcNwQA=
=N6In
-----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")