view mercurial/changegroup.py @ 5192:33015dac5df5

convert: fix mercurial_sink.putcommit Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a revision that touches no files, but this can break regular conversions from some repositories: - conceptually, since we're converting a repo, we should try to make the new hg repo as similar as possible to the original repo - we should create a new changeset, even if the original revision didn't touch any files (maybe the commit message had some important bit); - even if a "regular" revision that doesn't touch any file may seem weird (and maybe even broken), it's completely legitimate for a merge revision to not touch any file, and, if we just skip it, the converted repo will end up with wrong history and possibly an extra head. As an example, say the crew and main hg repos are sync'ed. Somebody sends an important patch to the mailing list. Matt quickly applies and pushes it. But at the same time somebody also applies it to crew and pushes it. Suppose the commit message ended up being a bit different (say, there was a typo and somebody didn't fix it) or that the date ended up being different (because of different patch-applying scripts): the changeset hashes will be different, but the manifests will be the same. Since both changesets were pushed to public repos, it's hard to recall them. If both are merged, the manifest from the resulting merge revision will have the exact same contents as its parents - i.e. the merge revision really doesn't touch any file at all. To keep the file filtering stuff "working", the generic code was changed to skip empty revisions if we're filtering the repo, fixing a bug in the process (we want parents[0] instead of tip).
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
date Fri, 17 Aug 2007 20:18:05 -0300
parents e0793314360e
children 61462e7d62ed
line wrap: on
line source

"""
changegroup.py - Mercurial changegroup manipulation functions

 Copyright 2006 Matt Mackall <mpm@selenic.com>

This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
"""

from i18n import _
import struct, os, bz2, zlib, util, tempfile

def getchunk(source):
    """get a chunk from a changegroup"""
    d = source.read(4)
    if not d:
        return ""
    l = struct.unpack(">l", d)[0]
    if l <= 4:
        return ""
    d = source.read(l - 4)
    if len(d) < l - 4:
        raise util.Abort(_("premature EOF reading chunk"
                           " (got %d bytes, expected %d)")
                          % (len(d), l - 4))
    return d

def chunkiter(source):
    """iterate through the chunks in source"""
    while 1:
        c = getchunk(source)
        if not c:
            break
        yield c

def genchunk(data):
    """build a changegroup chunk"""
    header = struct.pack(">l", len(data)+ 4)
    return "%s%s" % (header, data)

def closechunk():
    return struct.pack(">l", 0)

class nocompress(object):
    def compress(self, x):
        return x
    def flush(self):
        return ""

bundletypes = {
    "": ("", nocompress),
    "HG10UN": ("HG10UN", nocompress),
    "HG10BZ": ("HG10", lambda: bz2.BZ2Compressor()),
    "HG10GZ": ("HG10GZ", lambda: zlib.compressobj()),
}

def writebundle(cg, filename, bundletype):
    """Write a bundle file and return its filename.

    Existing files will not be overwritten.
    If no filename is specified, a temporary file is created.
    bz2 compression can be turned off.
    The bundle file will be deleted in case of errors.
    """

    fh = None
    cleanup = None
    try:
        if filename:
            fh = open(filename, "wb")
        else:
            fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
            fh = os.fdopen(fd, "wb")
        cleanup = filename

        header, compressor = bundletypes[bundletype]
        fh.write(header)
        z = compressor()

        # parse the changegroup data, otherwise we will block
        # in case of sshrepo because we don't know the end of the stream

        # an empty chunkiter is the end of the changegroup
        empty = False
        while not empty:
            empty = True
            for chunk in chunkiter(cg):
                empty = False
                fh.write(z.compress(genchunk(chunk)))
            fh.write(z.compress(closechunk()))
        fh.write(z.flush())
        cleanup = None
        return filename
    finally:
        if fh is not None:
            fh.close()
        if cleanup is not None:
            os.unlink(cleanup)

def readbundle(fh, fname):
    header = fh.read(6)
    if not header.startswith("HG"):
        raise util.Abort(_("%s: not a Mercurial bundle file") % fname)
    elif not header.startswith("HG10"):
        raise util.Abort(_("%s: unknown bundle version") % fname)

    if header == "HG10BZ":
        def generator(f):
            zd = bz2.BZ2Decompressor()
            zd.decompress("BZ")
            for chunk in util.filechunkiter(f, 4096):
                yield zd.decompress(chunk)
        return util.chunkbuffer(generator(fh))
    elif header == "HG10UN":
        return fh

    raise util.Abort(_("%s: unknown bundle compression type")
                     % fname)