bundle: unify/refactor unbundle/readbundle

mercurial/changegroup.py

@@ -1,161 +1,161 b''
 # 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 getchunk(source):
     """return the next chunk from changegroup 'source' as a string"""
     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, progress=None):
     """iterate through the chunks in source, yielding a sequence of chunks
     (strings)"""
     while 1:
         c = getchunk(source)
         if not c:
             break
         elif progress is not None:
             progress()
         yield c
 
 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 chunkiter is the end of the changegroup
         # a changegroup has at least 2 chunkiters (changelog and manifest).
         # after that, an empty chunkiter is the end of the changegroup
         empty = False
         count = 0
         while not empty or count <= 2:
             empty = True
             count += 1
             for chunk in chunkiter(cg):
                 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 generator(fh)
 
-def unbundle(header, fh):
-    if not header.startswith('HG'):
-        def fixup(f, h):
-            yield h
-            for x in f:
-                yield x
-        fh = fixup(f, h)
-        header = "HG10UN"
-
-    alg = header[4:6]
-    return util.chunkbuffer(decompressor(fh, alg))
-
 def readbundle(fh, fname):
     header = fh.read(6)
-    if not header.startswith('HG'):
-        raise util.Abort(_('%s: not a Mercurial bundle file') % fname)
-    if not header.startswith('HG10'):
-        raise util.Abort(_('%s: unknown bundle version') % fname)
-    elif header not in bundletypes:
-        raise util.Abort(_('%s: unknown bundle compression type') % fname)
-    return unbundle(header, fh)
+
+    if not fname:
+        fname = "stream"
+        if not header.startswith('HG') and header.startswith('\0'):
+            # headerless bundle, clean things up
+            def fixup(f, h):
+                yield h
+                for x in f:
+                    yield x
+            fh = fixup(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 util.chunkbuffer(decompressor(fh, alg))

mercurial/wireproto.py

@@ -1,332 +1,326 b''
 # wireproto.py - generic wire protocol support functions
 #
 # Copyright 2005-2010 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.
 
 import urllib, tempfile, os, sys
 from i18n import _
 from node import bin, hex
 import changegroup as changegroupmod
 import repo, error, encoding, util, store
 import pushkey as pushkey_
 
 # list of nodes encoding / decoding
 
 def decodelist(l, sep=' '):
     return map(bin, l.split(sep))
 
 def encodelist(l, sep=' '):
     return sep.join(map(hex, l))
 
 # client side
 
 class wirerepository(repo.repository):
     def lookup(self, key):
         self.requirecap('lookup', _('look up remote revision'))
         d = self._call("lookup", key=key)
         success, data = d[:-1].split(" ", 1)
         if int(success):
             return bin(data)
         self._abort(error.RepoError(data))
 
     def heads(self):
         d = self._call("heads")
         try:
             return decodelist(d[:-1])
         except:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     def branchmap(self):
         d = self._call("branchmap")
         try:
             branchmap = {}
             for branchpart in d.splitlines():
                 branchname, branchheads = branchpart.split(' ', 1)
                 branchname = urllib.unquote(branchname)
                 # Earlier servers (1.3.x) send branch names in (their) local
                 # charset. The best we can do is assume it's identical to our
                 # own local charset, in case it's not utf-8.
                 try:
                     branchname.decode('utf-8')
                 except UnicodeDecodeError:
                     branchname = encoding.fromlocal(branchname)
                 branchheads = decodelist(branchheads)
                 branchmap[branchname] = branchheads
             return branchmap
         except TypeError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     def branches(self, nodes):
         n = encodelist(nodes)
         d = self._call("branches", nodes=n)
         try:
             br = [tuple(decodelist(b)) for b in d.splitlines()]
             return br
         except:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     def between(self, pairs):
         batch = 8 # avoid giant requests
         r = []
         for i in xrange(0, len(pairs), batch):
             n = " ".join([encodelist(p, '-') for p in pairs[i:i + batch]])
             d = self._call("between", pairs=n)
             try:
                 r.extend(l and decodelist(l) or [] for l in d.splitlines())
             except:
                 self._abort(error.ResponseError(_("unexpected response:"), d))
         return r
 
     def pushkey(self, namespace, key, old, new):
         if not self.capable('pushkey'):
             return False
         d = self._call("pushkey",
                       namespace=namespace, key=key, old=old, new=new)
         return bool(int(d))
 
     def listkeys(self, namespace):
         if not self.capable('pushkey'):
             return {}
         d = self._call("listkeys", namespace=namespace)
         r = {}
         for l in d.splitlines():
             k, v = l.split('\t')
             r[k.decode('string-escape')] = v.decode('string-escape')
         return r
 
     def stream_out(self):
         return self._callstream('stream_out')
 
     def changegroup(self, nodes, kind):
         n = encodelist(nodes)
         f = self._callstream("changegroup", roots=n)
         return self._decompress(f)
 
     def changegroupsubset(self, bases, heads, kind):
         self.requirecap('changegroupsubset', _('look up remote changes'))
         bases = encodelist(bases)
         heads = encodelist(heads)
         return self._decompress(self._callstream("changegroupsubset",
                                                  bases=bases, heads=heads))
 
     def unbundle(self, cg, heads, source):
         '''Send cg (a readable file-like object representing the
         changegroup to push, typically a chunkbuffer object) to the
         remote server as a bundle. Return an integer indicating the
         result of the push (see localrepository.addchangegroup()).'''
 
         ret, output = self._callpush("unbundle", cg, heads=encodelist(heads))
         if ret == "":
             raise error.ResponseError(
                 _('push failed:'), output)
         try:
             ret = int(ret)
         except ValueError, err:
             raise error.ResponseError(
                 _('push failed (unexpected response):'), ret)
 
         for l in output.splitlines(True):
             self.ui.status(_('remote: '), l)
         return ret
 
 # server side
 
 class streamres(object):
     def __init__(self, gen):
         self.gen = gen
 
 class pushres(object):
     def __init__(self, res):
         self.res = res
 
 def dispatch(repo, proto, command):
     func, spec = commands[command]
     args = proto.getargs(spec)
     return func(repo, proto, *args)
 
 def between(repo, proto, pairs):
     pairs = [decodelist(p, '-') for p in pairs.split(" ")]
     r = []
     for b in repo.between(pairs):
         r.append(encodelist(b) + "\n")
     return "".join(r)
 
 def branchmap(repo, proto):
     branchmap = repo.branchmap()
     heads = []
     for branch, nodes in branchmap.iteritems():
         branchname = urllib.quote(branch)
         branchnodes = encodelist(nodes)
         heads.append('%s %s' % (branchname, branchnodes))
     return '\n'.join(heads)
 
 def branches(repo, proto, nodes):
     nodes = decodelist(nodes)
     r = []
     for b in repo.branches(nodes):
         r.append(encodelist(b) + "\n")
     return "".join(r)
 
 def capabilities(repo, proto):
     caps = 'lookup changegroupsubset branchmap pushkey'.split()
     if _allowstream(repo.ui):
         caps.append('stream=%d' % repo.changelog.version)
     caps.append('unbundle=%s' % ','.join(changegroupmod.bundlepriority))
     return ' '.join(caps)
 
 def changegroup(repo, proto, roots):
     nodes = decodelist(roots)
     cg = repo.changegroup(nodes, 'serve')
     return streamres(proto.groupchunks(cg))
 
 def changegroupsubset(repo, proto, bases, heads):
     bases = decodelist(bases)
     heads = decodelist(heads)
     cg = repo.changegroupsubset(bases, heads, 'serve')
     return streamres(proto.groupchunks(cg))
 
 def heads(repo, proto):
     h = repo.heads()
     return encodelist(h) + "\n"
 
 def hello(repo, proto):
     '''the hello command returns a set of lines describing various
     interesting things about the server, in an RFC822-like format.
     Currently the only one defined is "capabilities", which
     consists of a line in the form:
 
     capabilities: space separated list of tokens
     '''
     return "capabilities: %s\n" % (capabilities(repo, proto))
 
 def listkeys(repo, proto, namespace):
     d = pushkey_.list(repo, namespace).items()
     t = '\n'.join(['%s\t%s' % (k.encode('string-escape'),
                                v.encode('string-escape')) for k, v in d])
     return t
 
 def lookup(repo, proto, key):
     try:
         r = hex(repo.lookup(key))
         success = 1
     except Exception, inst:
         r = str(inst)
         success = 0
     return "%s %s\n" % (success, r)
 
 def pushkey(repo, proto, namespace, key, old, new):
     r = pushkey_.push(repo, namespace, key, old, new)
     return '%s\n' % int(r)
 
 def _allowstream(ui):
     return ui.configbool('server', 'uncompressed', True, untrusted=True)
 
 def stream(repo, proto):
     '''If the server supports streaming clone, it advertises the "stream"
     capability with a value representing the version and flags of the repo
     it is serving. Client checks to see if it understands the format.
 
     The format is simple: the server writes out a line with the amount
     of files, then the total amount of bytes to be transfered (separated
     by a space). Then, for each file, the server first writes the filename
     and filesize (separated by the null character), then the file contents.
     '''
 
     if not _allowstream(repo.ui):
         return '1\n'
 
     entries = []
     total_bytes = 0
     try:
         # get consistent snapshot of repo, lock during scan
         lock = repo.lock()
         try:
             repo.ui.debug('scanning\n')
             for name, ename, size in repo.store.walk():
                 entries.append((name, size))
                 total_bytes += size
         finally:
             lock.release()
     except error.LockError:
         return '2\n' # error: 2
 
     def streamer(repo, entries, total):
         '''stream out all metadata files in repository.'''
         yield '0\n' # success
         repo.ui.debug('%d files, %d bytes to transfer\n' %
                       (len(entries), total_bytes))
         yield '%d %d\n' % (len(entries), total_bytes)
         for name, size in entries:
             repo.ui.debug('sending %s (%d bytes)\n' % (name, size))
             # partially encode name over the wire for backwards compat
             yield '%s\0%d\n' % (store.encodedir(name), size)
             for chunk in util.filechunkiter(repo.sopener(name), limit=size):
                 yield chunk
 
     return streamres(streamer(repo, entries, total_bytes))
 
 def unbundle(repo, proto, heads):
     their_heads = decodelist(heads)
 
     def check_heads():
         heads = repo.heads()
         return their_heads == ['force'] or their_heads == heads
 
     # fail early if possible
     if not check_heads():
         return 'unsynced changes'
 
     # write bundle data to temporary file because it can be big
     fd, tempname = tempfile.mkstemp(prefix='hg-unbundle-')
     fp = os.fdopen(fd, 'wb+')
     r = 0
     proto.redirect()
     try:
         proto.getfile(fp)
         lock = repo.lock()
         try:
             if not check_heads():
                 # someone else committed/pushed/unbundled while we
                 # were transferring data
                 return 'unsynced changes'
 
             # push can proceed
             fp.seek(0)
-            header = fp.read(6)
-            if header.startswith('HG'):
-                if not header.startswith('HG10'):
-                    raise ValueError('unknown bundle version')
-                elif header not in changegroupmod.bundletypes:
-                    raise ValueError('unknown bundle compression type')
-            gen = changegroupmod.unbundle(header, fp)
+            gen = changegroupmod.readbundle(fp, None)
 
             try:
                 r = repo.addchangegroup(gen, 'serve', proto._client(),
                                         lock=lock)
             except util.Abort, inst:
                 sys.stderr.write("abort: %s\n" % inst)
         finally:
             lock.release()
             return pushres(r)
 
     finally:
         fp.close()
         os.unlink(tempname)
 
 commands = {
     'between': (between, 'pairs'),
     'branchmap': (branchmap, ''),
     'branches': (branches, 'nodes'),
     'capabilities': (capabilities, ''),
     'changegroup': (changegroup, 'roots'),
     'changegroupsubset': (changegroupsubset, 'bases heads'),
     'heads': (heads, ''),
     'hello': (hello, ''),
     'listkeys': (listkeys, 'namespace'),
     'lookup': (lookup, 'key'),
     'pushkey': (pushkey, 'namespace key old new'),
     'stream_out': (stream, ''),
     'unbundle': (unbundle, 'heads'),
 }