view mercurial/changegroup.py @ 14093:ce99d887585f

httprepo: long arguments support (issue2126)

Send the command arguments in the HTTP headers. The command is still part
of the URL. If the server does not have the 'httpheader' capability, the
client will send the command arguments in the URL as it did previously.

Web servers typically allow more data to be placed within the headers than
in the URL, so this approach will:
- Avoid HTTP errors due to using a URL that is too large.
- Allow Mercurial to implement a more efficient wire protocol.

An alternate approach is to send the arguments as part of the request body.
This approach has been rejected because it requires the use of POST
requests, so it would break any existing configuration that relies on the
request type for authentication or caching.

Extensibility:
- The header size is provided by the server, which makes it possible to
  introduce an hgrc setting for it.
- The client ignores the capability value after the first comma, which
  allows more information to be included in the future.

# 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), # only when using unbundle on ssh and old http servers
                          # since the unification ssh accepts a header but there
                          # is no capability signaling it.
    "HG10UN": ("HG10UN", nocompress),
    "HG10BZ": ("HG10", lambda: bz2.BZ2Compressor()),
    "HG10GZ": ("HG10GZ", lambda: zlib.compressobj()),
}

# 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)

class bundle10(object):
    def __init__(self, lookup):
        self._lookup = lookup
    def close(self):
        return closechunk()
    def fileheader(self, fname):
        return chunkheader(len(fname)) + fname
    def revchunk(self, revlog, node='', p1='', p2='', prefix='', data=''):
        linknode = self._lookup(revlog, node)
        meta = node + p1 + p2 + linknode + prefix
        l = len(meta) + len(data)
        yield chunkheader(l)
        yield meta
        yield data