view mercurial/changegroup.py @ 13750:7eb82f88e157

# User Dan Villiom Podlaski Christiansen <[e-mail]>
# Date 1289564504 -3600
# Node ID b75264c15cc888cf38c3c7b8f619801e3c2589c7
# Parent  89b2e5d940f669e590096c6be70eee61c9172fff
revsets: overload the branch() revset to also take a branch name.

This should only change semantics in the specific case of a tag/branch
conflict where the tag wasn't done on the branch with the same
name. Previously, branch(whatever) would resolve to the branch of the
tag in that case, whereas now it will resolve to the branch of the
name. The previous behaviour, while documented, seemed very
counter-intuitive to me.

An alternate approach would be to introduce a new revset such as
branchname() or namedbranch(). While this would retain backwards
compatibility, the distinction between it and branch() would not be
readily apparent to users. The most intuitive behaviour would be to
have branch(x) require 'x' to be a branch name, and something like
branchof(x) or samebranch(x) do what branch(x) currently
does. Unfortunately, our backwards compatibility guarantees prevent us
from doing that.

Please note that while 'hg tag' guards against shadowing a branch, 'hg
branch' does not. Besides, even if it did, that wouldn't solve the
issue of conversions with such tags and branches...

# changegroup.py - Mercurial changegroup manipulation functions
#
#  Copyright 2006 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

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

def readexactly(stream, n):
    '''read n bytes from stream.read and abort if less was available'''
    s = stream.read(n)
    if len(s) < n:
        raise util.Abort(_("stream ended unexpectedly"
                           " (got %d bytes, expected %d)")
                          % (len(s), n))
    return s

def getchunk(stream):
    """return the next chunk from stream as a string"""
    d = readexactly(stream, 4)
    l = struct.unpack(">l", d)[0]
    if l <= 4:
        if l:
            raise util.Abort(_("invalid chunk length %d") % l)
        return ""
    return readexactly(stream, l - 4)

def chunkheader(length):
    """return a changegroup chunk header (string)"""
    return struct.pack(">l", length + 4)

def closechunk():
    """return a changegroup chunk header (string) for a zero-length chunk"""
    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 collector(cl, mmfs, files):
    # Gather information about changeset nodes going out in a bundle.
    # We want to gather manifests needed and filelogs affected.
    def collect(node):
        c = cl.read(node)
        files.update(c[3])
        mmfs.setdefault(c[0], node)
    return collect

# hgweb uses this list to communicate its preferred type
bundlepriority = ['HG10GZ', 'HG10BZ', 'HG10UN']

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 chunkgroup is the end of the changegroup
        # a changegroup has at least 2 chunkgroups (changelog and manifest).
        # after that, an empty chunkgroup is the end of the changegroup
        empty = False
        count = 0
        while not empty or count <= 2:
            empty = True
            count += 1
            while 1:
                chunk = getchunk(cg)
                if not chunk:
                    break
                empty = False
                fh.write(z.compress(chunkheader(len(chunk))))
                pos = 0
                while pos < len(chunk):
                    next = pos + 2**20
                    fh.write(z.compress(chunk[pos:next]))
                    pos = next
            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 decompressor(fh, alg):
    if alg == 'UN':
        return fh
    elif alg == 'GZ':
        def generator(f):
            zd = zlib.decompressobj()
            for chunk in f:
                yield zd.decompress(chunk)
    elif alg == 'BZ':
        def generator(f):
            zd = bz2.BZ2Decompressor()
            zd.decompress("BZ")
            for chunk in util.filechunkiter(f, 4096):
                yield zd.decompress(chunk)
    else:
        raise util.Abort("unknown bundle compression '%s'" % alg)
    return util.chunkbuffer(generator(fh))

class unbundle10(object):
    def __init__(self, fh, alg):
        self._stream = decompressor(fh, alg)
        self._type = alg
        self.callback = None
    def compressed(self):
        return self._type != 'UN'
    def read(self, l):
        return self._stream.read(l)
    def seek(self, pos):
        return self._stream.seek(pos)
    def tell(self):
        return self._stream.tell()
    def close(self):
        return self._stream.close()

    def chunklength(self):
        d = readexactly(self._stream, 4)
        l = struct.unpack(">l", d)[0]
        if l <= 4:
            if l:
                raise util.Abort(_("invalid chunk length %d") % l)
            return 0
        if self.callback:
            self.callback()
        return l - 4

    def chunk(self):
        """return the next chunk from changegroup 'source' as a string"""
        l = self.chunklength()
        return readexactly(self._stream, l)

    def parsechunk(self):
        l = self.chunklength()
        if not l:
            return {}
        h = readexactly(self._stream, 80)
        node, p1, p2, cs = struct.unpack("20s20s20s20s", h)
        data = readexactly(self._stream, l - 80)
        return dict(node=node, p1=p1, p2=p2, cs=cs, data=data)

class headerlessfixup(object):
    def __init__(self, fh, h):
        self._h = h
        self._fh = fh
    def read(self, n):
        if self._h:
            d, self._h = self._h[:n], self._h[n:]
            if len(d) < n:
                d += readexactly(self._fh, n - len(d))
            return d
        return readexactly(self._fh, n)

def readbundle(fh, fname):
    header = readexactly(fh, 6)

    if not fname:
        fname = "stream"
        if not header.startswith('HG') and header.startswith('\0'):
            fh = headerlessfixup(fh, header)
            header = "HG10UN"

    magic, version, alg = header[0:2], header[2:4], header[4:6]

    if magic != 'HG':
        raise util.Abort(_('%s: not a Mercurial bundle') % fname)
    if version != '10':
        raise util.Abort(_('%s: unknown bundle version %s') % (fname, version))
    return unbundle10(fh, alg)