wireproto: perform chunking and compression at protocol layer (API)

Currently, the "streamres" response type is populated with a generator
of chunks with compression possibly already applied. This puts the onus
on commands to perform chunking and compression. Architecturally, I
think this is the wrong place to perform this work. I think commands
should say "here is the data" and the protocol layer should take care
of encoding the final bytes to put on the wire.

Additionally, upcoming commits will improve wire protocol support for
compression. Having a central place for performing compression in the
protocol transport layer will be easier than having to deal with
compression at the commands layer.

This commit refactors the "streamres" response type to accept either
a generator or an object with "read." Additionally, the type now
accepts a flag indicating whether the response is a "version 1
compressible" response. This basically identifies all commands
currently performing compression. I could have used a special type
for this, but a flag works just as well. The argument name
foreshadows the introduction of wire protocol changes, hence the "v1."

The code for chunking and compressing has been moved to the output
generation function for each protocol transport. Some code has been
inlined, resulting in the deletion of now unused methods.

hgext/largefiles/proto.py

@@ -1,189 +1,189
 # Copyright 2011 Fog Creek Software
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import os
 import re
 
 from mercurial.i18n import _
 
 from mercurial import (
     error,
     httppeer,
     util,
     wireproto,
 )
 
 from . import (
     lfutil,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 LARGEFILES_REQUIRED_MSG = ('\nThis repository uses the largefiles extension.'
                            '\n\nPlease enable it in your Mercurial config '
                            'file.\n')
 
 # these will all be replaced by largefiles.uisetup
 capabilitiesorig = None
 ssholdcallstream = None
 httpoldcallstream = None
 
 def putlfile(repo, proto, sha):
     '''Server command for putting a largefile into a repository's local store
     and into the user cache.'''
     proto.redirect()
 
     path = lfutil.storepath(repo, sha)
     util.makedirs(os.path.dirname(path))
     tmpfp = util.atomictempfile(path, createmode=repo.store.createmode)
 
     try:
         proto.getfile(tmpfp)
         tmpfp._fp.seek(0)
         if sha != lfutil.hexsha1(tmpfp._fp):
             raise IOError(0, _('largefile contents do not match hash'))
         tmpfp.close()
         lfutil.linktousercache(repo, sha)
     except IOError as e:
         repo.ui.warn(_('largefiles: failed to put %s into store: %s\n') %
                      (sha, e.strerror))
         return wireproto.pushres(1)
     finally:
         tmpfp.discard()
 
     return wireproto.pushres(0)
 
 def getlfile(repo, proto, sha):
     '''Server command for retrieving a largefile from the repository-local
     cache or user cache.'''
     filename = lfutil.findfile(repo, sha)
     if not filename:
         raise error.Abort(_('requested largefile %s not present in cache')
                           % sha)
     f = open(filename, 'rb')
     length = os.fstat(f.fileno())[6]
 
     # Since we can't set an HTTP content-length header here, and
     # Mercurial core provides no way to give the length of a streamres
     # (and reading the entire file into RAM would be ill-advised), we
     # just send the length on the first line of the response, like the
     # ssh proto does for string responses.
     def generator():
         yield '%d\n' % length
         for chunk in util.filechunkiter(f):
             yield chunk
-    return wireproto.streamres(generator())
+    return wireproto.streamres(gen=generator())
 
 def statlfile(repo, proto, sha):
     '''Server command for checking if a largefile is present - returns '2\n' if
     the largefile is missing, '0\n' if it seems to be in good condition.
 
     The value 1 is reserved for mismatched checksum, but that is too expensive
     to be verified on every stat and must be caught be running 'hg verify'
     server side.'''
     filename = lfutil.findfile(repo, sha)
     if not filename:
         return '2\n'
     return '0\n'
 
 def wirereposetup(ui, repo):
     class lfileswirerepository(repo.__class__):
         def putlfile(self, sha, fd):
             # unfortunately, httprepository._callpush tries to convert its
             # input file-like into a bundle before sending it, so we can't use
             # it ...
             if issubclass(self.__class__, httppeer.httppeer):
                 res = self._call('putlfile', data=fd, sha=sha,
                     headers={'content-type':'application/mercurial-0.1'})
                 try:
                     d, output = res.split('\n', 1)
                     for l in output.splitlines(True):
                         self.ui.warn(_('remote: '), l) # assume l ends with \n
                     return int(d)
                 except ValueError:
                     self.ui.warn(_('unexpected putlfile response: %r\n') % res)
                     return 1
             # ... but we can't use sshrepository._call because the data=
             # argument won't get sent, and _callpush does exactly what we want
             # in this case: send the data straight through
             else:
                 try:
                     ret, output = self._callpush("putlfile", fd, sha=sha)
                     if ret == "":
                         raise error.ResponseError(_('putlfile failed:'),
                                 output)
                     return int(ret)
                 except IOError:
                     return 1
                 except ValueError:
                     raise error.ResponseError(
                         _('putlfile failed (unexpected response):'), ret)
 
         def getlfile(self, sha):
             """returns an iterable with the chunks of the file with sha sha"""
             stream = self._callstream("getlfile", sha=sha)
             length = stream.readline()
             try:
                 length = int(length)
             except ValueError:
                 self._abort(error.ResponseError(_("unexpected response:"),
                                                 length))
 
             # SSH streams will block if reading more than length
             for chunk in util.filechunkiter(stream, limit=length):
                 yield chunk
             # HTTP streams must hit the end to process the last empty
             # chunk of Chunked-Encoding so the connection can be reused.
             if issubclass(self.__class__, httppeer.httppeer):
                 chunk = stream.read(1)
                 if chunk:
                     self._abort(error.ResponseError(_("unexpected response:"),
                                                     chunk))
 
         @wireproto.batchable
         def statlfile(self, sha):
             f = wireproto.future()
             result = {'sha': sha}
             yield result, f
             try:
                 yield int(f.value)
             except (ValueError, urlerr.httperror):
                 # If the server returns anything but an integer followed by a
                 # newline, newline, it's not speaking our language; if we get
                 # an HTTP error, we can't be sure the largefile is present;
                 # either way, consider it missing.
                 yield 2
 
     repo.__class__ = lfileswirerepository
 
 # advertise the largefiles=serve capability
 def capabilities(repo, proto):
     '''Wrap server command to announce largefile server capability'''
     return capabilitiesorig(repo, proto) + ' largefiles=serve'
 
 def heads(repo, proto):
     '''Wrap server command - largefile capable clients will know to call
     lheads instead'''
     if lfutil.islfilesrepo(repo):
         return wireproto.ooberror(LARGEFILES_REQUIRED_MSG)
     return wireproto.heads(repo, proto)
 
 def sshrepocallstream(self, cmd, **args):
     if cmd == 'heads' and self.capable('largefiles'):
         cmd = 'lheads'
     if cmd == 'batch' and self.capable('largefiles'):
         args['cmds'] = args['cmds'].replace('heads ', 'lheads ')
     return ssholdcallstream(self, cmd, **args)
 
 headsre = re.compile(r'(^|;)heads\b')
 
 def httprepocallstream(self, cmd, **args):
     if cmd == 'heads' and self.capable('largefiles'):
         cmd = 'lheads'
     if cmd == 'batch' and self.capable('largefiles'):
         args['cmds'] = headsre.sub('lheads', args['cmds'])
     return httpoldcallstream(self, cmd, **args)

mercurial/hgweb/protocol.py

@@ -1,126 +1,124
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 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 __future__ import absolute_import
 
 import cgi
 
 from .common import (
     HTTP_OK,
 )
 
 from .. import (
     util,
     wireproto,
 )
 stringio = util.stringio
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 HGTYPE = 'application/mercurial-0.1'
 HGERRTYPE = 'application/hg-error'
 
 class webproto(wireproto.abstractserverproto):
     def __init__(self, req, ui):
         self.req = req
         self.response = ''
         self.ui = ui
     def getargs(self, args):
         knownargs = self._args()
         data = {}
         keys = args.split()
         for k in keys:
             if k == '*':
                 star = {}
                 for key in knownargs.keys():
                     if key != 'cmd' and key not in keys:
                         star[key] = knownargs[key][0]
                 data['*'] = star
             else:
                 data[k] = knownargs[k][0]
         return [data[k] for k in keys]
     def _args(self):
         args = self.req.form.copy()
         postlen = int(self.req.env.get('HTTP_X_HGARGS_POST', 0))
         if postlen:
             args.update(cgi.parse_qs(
                 self.req.read(postlen), keep_blank_values=True))
             return args
         chunks = []
         i = 1
         while True:
             h = self.req.env.get('HTTP_X_HGARG_' + str(i))
             if h is None:
                 break
             chunks += [h]
             i += 1
         args.update(cgi.parse_qs(''.join(chunks), keep_blank_values=True))
         return args
     def getfile(self, fp):
         length = int(self.req.env['CONTENT_LENGTH'])
         for s in util.filechunkiter(self.req, limit=length):
             fp.write(s)
     def redirect(self):
         self.oldio = self.ui.fout, self.ui.ferr
         self.ui.ferr = self.ui.fout = stringio()
     def restore(self):
         val = self.ui.fout.getvalue()
         self.ui.ferr, self.ui.fout = self.oldio
         return val
 
-    def groupchunks(self, fh):
-        def getchunks():
-            while True:
-                chunk = fh.read(32768)
-                if not chunk:
-                    break
-                yield chunk
-
-        return self.compresschunks(getchunks())
-
     def compresschunks(self, chunks):
         # Don't allow untrusted settings because disabling compression or
         # setting a very high compression level could lead to flooding
         # the server's network or CPU.
         opts = {'level': self.ui.configint('server', 'zliblevel', -1)}
         return util.compengines['zlib'].compressstream(chunks, opts)
 
     def _client(self):
         return 'remote:%s:%s:%s' % (
             self.req.env.get('wsgi.url_scheme') or 'http',
             urlreq.quote(self.req.env.get('REMOTE_HOST', '')),
             urlreq.quote(self.req.env.get('REMOTE_USER', '')))
 
 def iscmd(cmd):
     return cmd in wireproto.commands
 
 def call(repo, req, cmd):
     p = webproto(req, repo.ui)
     rsp = wireproto.dispatch(repo, p, cmd)
     if isinstance(rsp, str):
         req.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireproto.streamres):
+        if rsp.reader:
+            gen = iter(lambda: rsp.reader.read(32768), '')
+        else:
+            gen = rsp.gen
+
+        if rsp.v1compressible:
+            gen = p.compresschunks(gen)
+
         req.respond(HTTP_OK, HGTYPE)
-        return rsp.gen
+        return gen
     elif isinstance(rsp, wireproto.pushres):
         val = p.restore()
         rsp = '%d\n%s' % (rsp.res, val)
         req.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireproto.pusherr):
         # drain the incoming bundle
         req.drain()
         p.restore()
         rsp = '0\n%s\n' % rsp.res
         req.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireproto.ooberror):
         rsp = rsp.message
         req.respond(HTTP_OK, HGERRTYPE, body=rsp)
         return []

mercurial/sshserver.py

@@ -1,135 +1,134
 # sshserver.py - ssh protocol server support for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[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 __future__ import absolute_import
 
 import os
 import sys
 
 from .i18n import _
 from . import (
     error,
     hook,
     util,
     wireproto,
 )
 
 class sshserver(wireproto.abstractserverproto):
     def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
         self.lock = None
         self.fin = ui.fin
         self.fout = ui.fout
 
         hook.redirect(True)
         ui.fout = repo.ui.fout = ui.ferr
 
         # Prevent insertion/deletion of CRs
         util.setbinary(self.fin)
         util.setbinary(self.fout)
 
     def getargs(self, args):
         data = {}
         keys = args.split()
         for n in xrange(len(keys)):
             argline = self.fin.readline()[:-1]
             arg, l = argline.split()
             if arg not in keys:
                 raise error.Abort(_("unexpected parameter %r") % arg)
             if arg == '*':
                 star = {}
                 for k in xrange(int(l)):
                     argline = self.fin.readline()[:-1]
                     arg, l = argline.split()
                     val = self.fin.read(int(l))
                     star[arg] = val
                 data['*'] = star
             else:
                 val = self.fin.read(int(l))
                 data[arg] = val
         return [data[k] for k in keys]
 
     def getarg(self, name):
         return self.getargs(name)[0]
 
     def getfile(self, fpout):
         self.sendresponse('')
         count = int(self.fin.readline())
         while count:
             fpout.write(self.fin.read(count))
             count = int(self.fin.readline())
 
     def redirect(self):
         pass
 
-    def groupchunks(self, fh):
-        return iter(lambda: fh.read(4096), '')
-
-    def compresschunks(self, chunks):
-        for chunk in chunks:
-            yield chunk
-
     def sendresponse(self, v):
         self.fout.write("%d\n" % len(v))
         self.fout.write(v)
         self.fout.flush()
 
     def sendstream(self, source):
         write = self.fout.write
-        for chunk in source.gen:
+
+        if source.reader:
+            gen = iter(lambda: source.reader.read(4096), '')
+        else:
+            gen = source.gen
+
+        for chunk in gen:
             write(chunk)
         self.fout.flush()
 
     def sendpushresponse(self, rsp):
         self.sendresponse('')
         self.sendresponse(str(rsp.res))
 
     def sendpusherror(self, rsp):
         self.sendresponse(rsp.res)
 
     def sendooberror(self, rsp):
         self.ui.ferr.write('%s\n-\n' % rsp.message)
         self.ui.ferr.flush()
         self.fout.write('\n')
         self.fout.flush()
 
     def serve_forever(self):
         try:
             while self.serve_one():
                 pass
         finally:
             if self.lock is not None:
                 self.lock.release()
         sys.exit(0)
 
     handlers = {
         str: sendresponse,
         wireproto.streamres: sendstream,
         wireproto.pushres: sendpushresponse,
         wireproto.pusherr: sendpusherror,
         wireproto.ooberror: sendooberror,
     }
 
     def serve_one(self):
         cmd = self.fin.readline()[:-1]
         if cmd and cmd in wireproto.commands:
             rsp = wireproto.dispatch(self.repo, self, cmd)
             self.handlers[rsp.__class__](self, rsp)
         elif cmd:
             impl = getattr(self, 'do_' + cmd, None)
             if impl:
                 r = impl()
                 if r is not None:
                     self.sendresponse(r)
             else: self.sendresponse("")
         return cmd != ''
 
     def _client(self):
         client = os.environ.get('SSH_CLIENT', '').split(' ', 1)[0]
         return 'remote:ssh:' + client

mercurial/wireproto.py

@@ -1,965 +1,959
 # 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.
 
 from __future__ import absolute_import
 
 import hashlib
 import itertools
 import os
 import sys
 import tempfile
 
 from .i18n import _
 from .node import (
     bin,
     hex,
 )
 
 from . import (
     bundle2,
     changegroup as changegroupmod,
     encoding,
     error,
     exchange,
     peer,
     pushkey as pushkeymod,
     streamclone,
     util,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 bundle2required = _(
     'incompatible Mercurial client; bundle2 required\n'
     '(see https://www.mercurial-scm.org/wiki/IncompatibleClient)\n')
 
 class abstractserverproto(object):
     """abstract class that summarizes the protocol API
 
     Used as reference and documentation.
     """
 
     def getargs(self, args):
         """return the value for arguments in <args>
 
         returns a list of values (same order as <args>)"""
         raise NotImplementedError()
 
     def getfile(self, fp):
         """write the whole content of a file into a file like object
 
         The file is in the form::
 
             (<chunk-size>\n<chunk>)+0\n
 
         chunk size is the ascii version of the int.
         """
         raise NotImplementedError()
 
     def redirect(self):
         """may setup interception for stdout and stderr
 
         See also the `restore` method."""
         raise NotImplementedError()
 
     # If the `redirect` function does install interception, the `restore`
     # function MUST be defined. If interception is not used, this function
     # MUST NOT be defined.
     #
     # left commented here on purpose
     #
     #def restore(self):
     #    """reinstall previous stdout and stderr and return intercepted stdout
     #    """
     #    raise NotImplementedError()
 
-    def groupchunks(self, fh):
-        """Generator of chunks to send to the client.
-
-        Some protocols may have compressed the contents.
-        """
-        raise NotImplementedError()
-
-    def compresschunks(self, chunks):
-        """Generator of possible compressed chunks to send to the client.
-
-        This is like ``groupchunks()`` except it accepts a generator as
-        its argument.
-        """
-        raise NotImplementedError()
-
 class remotebatch(peer.batcher):
     '''batches the queued calls; uses as few roundtrips as possible'''
     def __init__(self, remote):
         '''remote must support _submitbatch(encbatch) and
         _submitone(op, encargs)'''
         peer.batcher.__init__(self)
         self.remote = remote
     def submit(self):
         req, rsp = [], []
         for name, args, opts, resref in self.calls:
             mtd = getattr(self.remote, name)
             batchablefn = getattr(mtd, 'batchable', None)
             if batchablefn is not None:
                 batchable = batchablefn(mtd.im_self, *args, **opts)
                 encargsorres, encresref = next(batchable)
                 if encresref:
                     req.append((name, encargsorres,))
                     rsp.append((batchable, encresref, resref,))
                 else:
                     resref.set(encargsorres)
             else:
                 if req:
                     self._submitreq(req, rsp)
                     req, rsp = [], []
                 resref.set(mtd(*args, **opts))
         if req:
             self._submitreq(req, rsp)
     def _submitreq(self, req, rsp):
         encresults = self.remote._submitbatch(req)
         for encres, r in zip(encresults, rsp):
             batchable, encresref, resref = r
             encresref.set(encres)
             resref.set(next(batchable))
 
 class remoteiterbatcher(peer.iterbatcher):
     def __init__(self, remote):
         super(remoteiterbatcher, self).__init__()
         self._remote = remote
 
     def __getattr__(self, name):
         if not getattr(self._remote, name, False):
             raise AttributeError(
                 'Attempted to iterbatch non-batchable call to %r' % name)
         return super(remoteiterbatcher, self).__getattr__(name)
 
     def submit(self):
         """Break the batch request into many patch calls and pipeline them.
 
         This is mostly valuable over http where request sizes can be
         limited, but can be used in other places as well.
         """
         req, rsp = [], []
         for name, args, opts, resref in self.calls:
             mtd = getattr(self._remote, name)
             batchable = mtd.batchable(mtd.im_self, *args, **opts)
             encargsorres, encresref = next(batchable)
             assert encresref
             req.append((name, encargsorres))
             rsp.append((batchable, encresref))
         if req:
             self._resultiter = self._remote._submitbatch(req)
         self._rsp = rsp
 
     def results(self):
         for (batchable, encresref), encres in itertools.izip(
                 self._rsp, self._resultiter):
             encresref.set(encres)
             yield next(batchable)
 
 # Forward a couple of names from peer to make wireproto interactions
 # slightly more sensible.
 batchable = peer.batchable
 future = peer.future
 
 # list of nodes encoding / decoding
 
 def decodelist(l, sep=' '):
     if l:
         return map(bin, l.split(sep))
     return []
 
 def encodelist(l, sep=' '):
     try:
         return sep.join(map(hex, l))
     except TypeError:
         raise
 
 # batched call argument encoding
 
 def escapearg(plain):
     return (plain
             .replace(':', ':c')
             .replace(',', ':o')
             .replace(';', ':s')
             .replace('=', ':e'))
 
 def unescapearg(escaped):
     return (escaped
             .replace(':e', '=')
             .replace(':s', ';')
             .replace(':o', ',')
             .replace(':c', ':'))
 
 def encodebatchcmds(req):
     """Return a ``cmds`` argument value for the ``batch`` command."""
     cmds = []
     for op, argsdict in req:
         # Old servers didn't properly unescape argument names. So prevent
         # the sending of argument names that may not be decoded properly by
         # servers.
         assert all(escapearg(k) == k for k in argsdict)
 
         args = ','.join('%s=%s' % (escapearg(k), escapearg(v))
                         for k, v in argsdict.iteritems())
         cmds.append('%s %s' % (op, args))
 
     return ';'.join(cmds)
 
 # mapping of options accepted by getbundle and their types
 #
 # Meant to be extended by extensions. It is extensions responsibility to ensure
 # such options are properly processed in exchange.getbundle.
 #
 # supported types are:
 #
 # :nodes: list of binary nodes
 # :csv:   list of comma-separated values
 # :scsv:  list of comma-separated values return as set
 # :plain: string with no transformation needed.
 gboptsmap = {'heads':  'nodes',
              'common': 'nodes',
              'obsmarkers': 'boolean',
              'bundlecaps': 'scsv',
              'listkeys': 'csv',
              'cg': 'boolean',
              'cbattempted': 'boolean'}
 
 # client side
 
 class wirepeer(peer.peerrepository):
     """Client-side interface for communicating with a peer repository.
 
     Methods commonly call wire protocol commands of the same name.
 
     See also httppeer.py and sshpeer.py for protocol-specific
     implementations of this interface.
     """
     def batch(self):
         if self.capable('batch'):
             return remotebatch(self)
         else:
             return peer.localbatch(self)
     def _submitbatch(self, req):
         """run batch request <req> on the server
 
         Returns an iterator of the raw responses from the server.
         """
         rsp = self._callstream("batch", cmds=encodebatchcmds(req))
         chunk = rsp.read(1024)
         work = [chunk]
         while chunk:
             while ';' not in chunk and chunk:
                 chunk = rsp.read(1024)
                 work.append(chunk)
             merged = ''.join(work)
             while ';' in merged:
                 one, merged = merged.split(';', 1)
                 yield unescapearg(one)
             chunk = rsp.read(1024)
             work = [merged, chunk]
         yield unescapearg(''.join(work))
 
     def _submitone(self, op, args):
         return self._call(op, **args)
 
     def iterbatch(self):
         return remoteiterbatcher(self)
 
     @batchable
     def lookup(self, key):
         self.requirecap('lookup', _('look up remote revision'))
         f = future()
         yield {'key': encoding.fromlocal(key)}, f
         d = f.value
         success, data = d[:-1].split(" ", 1)
         if int(success):
             yield bin(data)
         self._abort(error.RepoError(data))
 
     @batchable
     def heads(self):
         f = future()
         yield {}, f
         d = f.value
         try:
             yield decodelist(d[:-1])
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     @batchable
     def known(self, nodes):
         f = future()
         yield {'nodes': encodelist(nodes)}, f
         d = f.value
         try:
             yield [bool(int(b)) for b in d]
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     @batchable
     def branchmap(self):
         f = future()
         yield {}, f
         d = f.value
         try:
             branchmap = {}
             for branchpart in d.splitlines():
                 branchname, branchheads = branchpart.split(' ', 1)
                 branchname = encoding.tolocal(urlreq.unquote(branchname))
                 branchheads = decodelist(branchheads)
                 branchmap[branchname] = branchheads
             yield 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 ValueError:
             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 ValueError:
                 self._abort(error.ResponseError(_("unexpected response:"), d))
         return r
 
     @batchable
     def pushkey(self, namespace, key, old, new):
         if not self.capable('pushkey'):
             yield False, None
         f = future()
         self.ui.debug('preparing pushkey for "%s:%s"\n' % (namespace, key))
         yield {'namespace': encoding.fromlocal(namespace),
                'key': encoding.fromlocal(key),
                'old': encoding.fromlocal(old),
                'new': encoding.fromlocal(new)}, f
         d = f.value
         d, output = d.split('\n', 1)
         try:
             d = bool(int(d))
         except ValueError:
             raise error.ResponseError(
                 _('push failed (unexpected response):'), d)
         for l in output.splitlines(True):
             self.ui.status(_('remote: '), l)
         yield d
 
     @batchable
     def listkeys(self, namespace):
         if not self.capable('pushkey'):
             yield {}, None
         f = future()
         self.ui.debug('preparing listkeys for "%s"\n' % namespace)
         yield {'namespace': encoding.fromlocal(namespace)}, f
         d = f.value
         self.ui.debug('received listkey for "%s": %i bytes\n'
                       % (namespace, len(d)))
         yield pushkeymod.decodekeys(d)
 
     def stream_out(self):
         return self._callstream('stream_out')
 
     def changegroup(self, nodes, kind):
         n = encodelist(nodes)
         f = self._callcompressable("changegroup", roots=n)
         return changegroupmod.cg1unpacker(f, 'UN')
 
     def changegroupsubset(self, bases, heads, kind):
         self.requirecap('changegroupsubset', _('look up remote changes'))
         bases = encodelist(bases)
         heads = encodelist(heads)
         f = self._callcompressable("changegroupsubset",
                                    bases=bases, heads=heads)
         return changegroupmod.cg1unpacker(f, 'UN')
 
     def getbundle(self, source, **kwargs):
         self.requirecap('getbundle', _('look up remote changes'))
         opts = {}
         bundlecaps = kwargs.get('bundlecaps')
         if bundlecaps is not None:
             kwargs['bundlecaps'] = sorted(bundlecaps)
         else:
             bundlecaps = () # kwargs could have it to None
         for key, value in kwargs.iteritems():
             if value is None:
                 continue
             keytype = gboptsmap.get(key)
             if keytype is None:
                 assert False, 'unexpected'
             elif keytype == 'nodes':
                 value = encodelist(value)
             elif keytype in ('csv', 'scsv'):
                 value = ','.join(value)
             elif keytype == 'boolean':
                 value = '%i' % bool(value)
             elif keytype != 'plain':
                 raise KeyError('unknown getbundle option type %s'
                                % keytype)
             opts[key] = value
         f = self._callcompressable("getbundle", **opts)
         if any((cap.startswith('HG2') for cap in bundlecaps)):
             return bundle2.getunbundler(self.ui, f)
         else:
             return changegroupmod.cg1unpacker(f, 'UN')
 
     def unbundle(self, cg, heads, url):
         '''Send cg (a readable file-like object representing the
         changegroup to push, typically a chunkbuffer object) to the
         remote server as a bundle.
 
         When pushing a bundle10 stream, return an integer indicating the
         result of the push (see localrepository.addchangegroup()).
 
         When pushing a bundle20 stream, return a bundle20 stream.
 
         `url` is the url the client thinks it's pushing to, which is
         visible to hooks.
         '''
 
         if heads != ['force'] and self.capable('unbundlehash'):
             heads = encodelist(['hashed',
                                 hashlib.sha1(''.join(sorted(heads))).digest()])
         else:
             heads = encodelist(heads)
 
         if util.safehasattr(cg, 'deltaheader'):
             # this a bundle10, do the old style call sequence
             ret, output = self._callpush("unbundle", cg, heads=heads)
             if ret == "":
                 raise error.ResponseError(
                     _('push failed:'), output)
             try:
                 ret = int(ret)
             except ValueError:
                 raise error.ResponseError(
                     _('push failed (unexpected response):'), ret)
 
             for l in output.splitlines(True):
                 self.ui.status(_('remote: '), l)
         else:
             # bundle2 push. Send a stream, fetch a stream.
             stream = self._calltwowaystream('unbundle', cg, heads=heads)
             ret = bundle2.getunbundler(self.ui, stream)
         return ret
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         # don't pass optional arguments left at their default value
         opts = {}
         if three is not None:
             opts['three'] = three
         if four is not None:
             opts['four'] = four
         return self._call('debugwireargs', one=one, two=two, **opts)
 
     def _call(self, cmd, **args):
         """execute <cmd> on the server
 
         The command is expected to return a simple string.
 
         returns the server reply as a string."""
         raise NotImplementedError()
 
     def _callstream(self, cmd, **args):
         """execute <cmd> on the server
 
         The command is expected to return a stream. Note that if the
         command doesn't return a stream, _callstream behaves
         differently for ssh and http peers.
 
         returns the server reply as a file like object.
         """
         raise NotImplementedError()
 
     def _callcompressable(self, cmd, **args):
         """execute <cmd> on the server
 
         The command is expected to return a stream.
 
         The stream may have been compressed in some implementations. This
         function takes care of the decompression. This is the only difference
         with _callstream.
 
         returns the server reply as a file like object.
         """
         raise NotImplementedError()
 
     def _callpush(self, cmd, fp, **args):
         """execute a <cmd> on server
 
         The command is expected to be related to a push. Push has a special
         return method.
 
         returns the server reply as a (ret, output) tuple. ret is either
         empty (error) or a stringified int.
         """
         raise NotImplementedError()
 
     def _calltwowaystream(self, cmd, fp, **args):
         """execute <cmd> on server
 
         The command will send a stream to the server and get a stream in reply.
         """
         raise NotImplementedError()
 
     def _abort(self, exception):
         """clearly abort the wire protocol connection and raise the exception
         """
         raise NotImplementedError()
 
 # server side
 
 # wire protocol command can either return a string or one of these classes.
 class streamres(object):
     """wireproto reply: binary stream
 
     The call was successful and the result is a stream.
-    Iterate on the `self.gen` attribute to retrieve chunks.
+
+    Accepts either a generator or an object with a ``read(size)`` method.
+
+    ``v1compressible`` indicates whether this data can be compressed to
+    "version 1" clients (technically: HTTP peers using
+    application/mercurial-0.1 media type). This flag should NOT be used on
+    new commands because new clients should support a more modern compression
+    mechanism.
     """
-    def __init__(self, gen):
+    def __init__(self, gen=None, reader=None, v1compressible=False):
         self.gen = gen
+        self.reader = reader
+        self.v1compressible = v1compressible
 
 class pushres(object):
     """wireproto reply: success with simple integer return
 
     The call was successful and returned an integer contained in `self.res`.
     """
     def __init__(self, res):
         self.res = res
 
 class pusherr(object):
     """wireproto reply: failure
 
     The call failed. The `self.res` attribute contains the error message.
     """
     def __init__(self, res):
         self.res = res
 
 class ooberror(object):
     """wireproto reply: failure of a batch of operation
 
     Something failed during a batch call. The error message is stored in
     `self.message`.
     """
     def __init__(self, message):
         self.message = message
 
 def getdispatchrepo(repo, proto, command):
     """Obtain the repo used for processing wire protocol commands.
 
     The intent of this function is to serve as a monkeypatch point for
     extensions that need commands to operate on different repo views under
     specialized circumstances.
     """
     return repo.filtered('served')
 
 def dispatch(repo, proto, command):
     repo = getdispatchrepo(repo, proto, command)
     func, spec = commands[command]
     args = proto.getargs(spec)
     return func(repo, proto, *args)
 
 def options(cmd, keys, others):
     opts = {}
     for k in keys:
         if k in others:
             opts[k] = others[k]
             del others[k]
     if others:
         sys.stderr.write("warning: %s ignored unexpected arguments %s\n"
                          % (cmd, ",".join(others)))
     return opts
 
 def bundle1allowed(repo, action):
     """Whether a bundle1 operation is allowed from the server.
 
     Priority is:
 
     1. server.bundle1gd.<action> (if generaldelta active)
     2. server.bundle1.<action>
     3. server.bundle1gd (if generaldelta active)
     4. server.bundle1
     """
     ui = repo.ui
     gd = 'generaldelta' in repo.requirements
 
     if gd:
         v = ui.configbool('server', 'bundle1gd.%s' % action, None)
         if v is not None:
             return v
 
     v = ui.configbool('server', 'bundle1.%s' % action, None)
     if v is not None:
         return v
 
     if gd:
         v = ui.configbool('server', 'bundle1gd', None)
         if v is not None:
             return v
 
     return ui.configbool('server', 'bundle1', True)
 
 # list of commands
 commands = {}
 
 def wireprotocommand(name, args=''):
     """decorator for wire protocol command"""
     def register(func):
         commands[name] = (func, args)
         return func
     return register
 
 @wireprotocommand('batch', 'cmds *')
 def batch(repo, proto, cmds, others):
     repo = repo.filtered("served")
     res = []
     for pair in cmds.split(';'):
         op, args = pair.split(' ', 1)
         vals = {}
         for a in args.split(','):
             if a:
                 n, v = a.split('=')
                 vals[unescapearg(n)] = unescapearg(v)
         func, spec = commands[op]
         if spec:
             keys = spec.split()
             data = {}
             for k in keys:
                 if k == '*':
                     star = {}
                     for key in vals.keys():
                         if key not in keys:
                             star[key] = vals[key]
                     data['*'] = star
                 else:
                     data[k] = vals[k]
             result = func(repo, proto, *[data[k] for k in keys])
         else:
             result = func(repo, proto)
         if isinstance(result, ooberror):
             return result
         res.append(escapearg(result))
     return ';'.join(res)
 
 @wireprotocommand('between', 'pairs')
 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)
 
 @wireprotocommand('branchmap')
 def branchmap(repo, proto):
     branchmap = repo.branchmap()
     heads = []
     for branch, nodes in branchmap.iteritems():
         branchname = urlreq.quote(encoding.fromlocal(branch))
         branchnodes = encodelist(nodes)
         heads.append('%s %s' % (branchname, branchnodes))
     return '\n'.join(heads)
 
 @wireprotocommand('branches', 'nodes')
 def branches(repo, proto, nodes):
     nodes = decodelist(nodes)
     r = []
     for b in repo.branches(nodes):
         r.append(encodelist(b) + "\n")
     return "".join(r)
 
 @wireprotocommand('clonebundles', '')
 def clonebundles(repo, proto):
     """Server command for returning info for available bundles to seed clones.
 
     Clients will parse this response and determine what bundle to fetch.
 
     Extensions may wrap this command to filter or dynamically emit data
     depending on the request. e.g. you could advertise URLs for the closest
     data center given the client's IP address.
     """
     return repo.opener.tryread('clonebundles.manifest')
 
 wireprotocaps = ['lookup', 'changegroupsubset', 'branchmap', 'pushkey',
                  'known', 'getbundle', 'unbundlehash', 'batch']
 
 def _capabilities(repo, proto):
     """return a list of capabilities for a repo
 
     This function exists to allow extensions to easily wrap capabilities
     computation
 
     - returns a lists: easy to alter
     - change done here will be propagated to both `capabilities` and `hello`
       command without any other action needed.
     """
     # copy to prevent modification of the global list
     caps = list(wireprotocaps)
     if streamclone.allowservergeneration(repo.ui):
         if repo.ui.configbool('server', 'preferuncompressed', False):
             caps.append('stream-preferred')
         requiredformats = repo.requirements & repo.supportedformats
         # if our local revlogs are just revlogv1, add 'stream' cap
         if not requiredformats - set(('revlogv1',)):
             caps.append('stream')
         # otherwise, add 'streamreqs' detailing our local revlog format
         else:
             caps.append('streamreqs=%s' % ','.join(sorted(requiredformats)))
     if repo.ui.configbool('experimental', 'bundle2-advertise', True):
         capsblob = bundle2.encodecaps(bundle2.getrepocaps(repo))
         caps.append('bundle2=' + urlreq.quote(capsblob))
     caps.append('unbundle=%s' % ','.join(bundle2.bundlepriority))
     caps.append(
         'httpheader=%d' % repo.ui.configint('server', 'maxhttpheaderlen', 1024))
     if repo.ui.configbool('experimental', 'httppostargs', False):
         caps.append('httppostargs')
     return caps
 
 # If you are writing an extension and consider wrapping this function. Wrap
 # `_capabilities` instead.
 @wireprotocommand('capabilities')
 def capabilities(repo, proto):
     return ' '.join(_capabilities(repo, proto))
 
 @wireprotocommand('changegroup', 'roots')
 def changegroup(repo, proto, roots):
     nodes = decodelist(roots)
     cg = changegroupmod.changegroup(repo, nodes, 'serve')
-    return streamres(proto.groupchunks(cg))
+    return streamres(reader=cg, v1compressible=True)
 
 @wireprotocommand('changegroupsubset', 'bases heads')
 def changegroupsubset(repo, proto, bases, heads):
     bases = decodelist(bases)
     heads = decodelist(heads)
     cg = changegroupmod.changegroupsubset(repo, bases, heads, 'serve')
-    return streamres(proto.groupchunks(cg))
+    return streamres(reader=cg, v1compressible=True)
 
 @wireprotocommand('debugwireargs', 'one two *')
 def debugwireargs(repo, proto, one, two, others):
     # only accept optional args from the known set
     opts = options('debugwireargs', ['three', 'four'], others)
     return repo.debugwireargs(one, two, **opts)
 
 @wireprotocommand('getbundle', '*')
 def getbundle(repo, proto, others):
     opts = options('getbundle', gboptsmap.keys(), others)
     for k, v in opts.iteritems():
         keytype = gboptsmap[k]
         if keytype == 'nodes':
             opts[k] = decodelist(v)
         elif keytype == 'csv':
             opts[k] = list(v.split(','))
         elif keytype == 'scsv':
             opts[k] = set(v.split(','))
         elif keytype == 'boolean':
             # Client should serialize False as '0', which is a non-empty string
             # so it evaluates as a True bool.
             if v == '0':
                 opts[k] = False
             else:
                 opts[k] = bool(v)
         elif keytype != 'plain':
             raise KeyError('unknown getbundle option type %s'
                            % keytype)
 
     if not bundle1allowed(repo, 'pull'):
         if not exchange.bundle2requested(opts.get('bundlecaps')):
             return ooberror(bundle2required)
 
     chunks = exchange.getbundlechunks(repo, 'serve', **opts)
-    return streamres(proto.compresschunks(chunks))
+    return streamres(gen=chunks, v1compressible=True)
 
 @wireprotocommand('heads')
 def heads(repo, proto):
     h = repo.heads()
     return encodelist(h) + "\n"
 
 @wireprotocommand('hello')
 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))
 
 @wireprotocommand('listkeys', 'namespace')
 def listkeys(repo, proto, namespace):
     d = repo.listkeys(encoding.tolocal(namespace)).items()
     return pushkeymod.encodekeys(d)
 
 @wireprotocommand('lookup', 'key')
 def lookup(repo, proto, key):
     try:
         k = encoding.tolocal(key)
         c = repo[k]
         r = c.hex()
         success = 1
     except Exception as inst:
         r = str(inst)
         success = 0
     return "%s %s\n" % (success, r)
 
 @wireprotocommand('known', 'nodes *')
 def known(repo, proto, nodes, others):
     return ''.join(b and "1" or "0" for b in repo.known(decodelist(nodes)))
 
 @wireprotocommand('pushkey', 'namespace key old new')
 def pushkey(repo, proto, namespace, key, old, new):
     # compatibility with pre-1.8 clients which were accidentally
     # sending raw binary nodes rather than utf-8-encoded hex
     if len(new) == 20 and new.encode('string-escape') != new:
         # looks like it could be a binary node
         try:
             new.decode('utf-8')
             new = encoding.tolocal(new) # but cleanly decodes as UTF-8
         except UnicodeDecodeError:
             pass # binary, leave unmodified
     else:
         new = encoding.tolocal(new) # normal path
 
     if util.safehasattr(proto, 'restore'):
 
         proto.redirect()
 
         try:
             r = repo.pushkey(encoding.tolocal(namespace), encoding.tolocal(key),
                              encoding.tolocal(old), new) or False
         except error.Abort:
             r = False
 
         output = proto.restore()
 
         return '%s\n%s' % (int(r), output)
 
     r = repo.pushkey(encoding.tolocal(namespace), encoding.tolocal(key),
                      encoding.tolocal(old), new)
     return '%s\n' % int(r)
 
 @wireprotocommand('stream_out')
 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.
     '''
     if not streamclone.allowservergeneration(repo.ui):
         return '1\n'
 
     def getstream(it):
         yield '0\n'
         for chunk in it:
             yield chunk
 
     try:
         # LockError may be raised before the first result is yielded. Don't
         # emit output until we're sure we got the lock successfully.
         it = streamclone.generatev1wireproto(repo)
-        return streamres(getstream(it))
+        return streamres(gen=getstream(it))
     except error.LockError:
         return '2\n'
 
 @wireprotocommand('unbundle', 'heads')
 def unbundle(repo, proto, heads):
     their_heads = decodelist(heads)
 
     try:
         proto.redirect()
 
         exchange.check_heads(repo, their_heads, 'preparing 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
         try:
             proto.getfile(fp)
             fp.seek(0)
             gen = exchange.readbundle(repo.ui, fp, None)
             if (isinstance(gen, changegroupmod.cg1unpacker)
                 and not bundle1allowed(repo, 'push')):
                 return ooberror(bundle2required)
 
             r = exchange.unbundle(repo, gen, their_heads, 'serve',
                                   proto._client())
             if util.safehasattr(r, 'addpart'):
                 # The return looks streamable, we are in the bundle2 case and
                 # should return a stream.
-                return streamres(r.getchunks())
+                return streamres(gen=r.getchunks())
             return pushres(r)
 
         finally:
             fp.close()
             os.unlink(tempname)
 
     except (error.BundleValueError, error.Abort, error.PushRaced) as exc:
         # handle non-bundle2 case first
         if not getattr(exc, 'duringunbundle2', False):
             try:
                 raise
             except error.Abort:
                 # The old code we moved used sys.stderr directly.
                 # We did not change it to minimise code change.
                 # This need to be moved to something proper.
                 # Feel free to do it.
                 sys.stderr.write("abort: %s\n" % exc)
                 return pushres(0)
             except error.PushRaced:
                 return pusherr(str(exc))
 
         bundler = bundle2.bundle20(repo.ui)
         for out in getattr(exc, '_bundle2salvagedoutput', ()):
             bundler.addpart(out)
         try:
             try:
                 raise
             except error.PushkeyFailed as exc:
                 # check client caps
                 remotecaps = getattr(exc, '_replycaps', None)
                 if (remotecaps is not None
                         and 'pushkey' not in remotecaps.get('error', ())):
                     # no support remote side, fallback to Abort handler.
                     raise
                 part = bundler.newpart('error:pushkey')
                 part.addparam('in-reply-to', exc.partid)
                 if exc.namespace is not None:
                     part.addparam('namespace', exc.namespace, mandatory=False)
                 if exc.key is not None:
                     part.addparam('key', exc.key, mandatory=False)
                 if exc.new is not None:
                     part.addparam('new', exc.new, mandatory=False)
                 if exc.old is not None:
                     part.addparam('old', exc.old, mandatory=False)
                 if exc.ret is not None:
                     part.addparam('ret', exc.ret, mandatory=False)
         except error.BundleValueError as exc:
             errpart = bundler.newpart('error:unsupportedcontent')
             if exc.parttype is not None:
                 errpart.addparam('parttype', exc.parttype)
             if exc.params:
                 errpart.addparam('params', '\0'.join(exc.params))
         except error.Abort as exc:
             manargs = [('message', str(exc))]
             advargs = []
             if exc.hint is not None:
                 advargs.append(('hint', exc.hint))
             bundler.addpart(bundle2.bundlepart('error:abort',
                                                manargs, advargs))
         except error.PushRaced as exc:
             bundler.newpart('error:pushraced', [('message', str(exc))])
-        return streamres(bundler.getchunks())
+        return streamres(gen=bundler.getchunks())