wireproto: move value encoding functions to wireprototypes (API)

These functions should live in the same place. I plan to separate
client from server code in upcoming commits. wireprototypes is
where we are putting shared code like this.

Differential Revision: https://phab.mercurial-scm.org/D3257

hgext/infinitepush/__init__.py

@@ -1,1186 +1,1187
 # Infinite push
 #
 # Copyright 2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """ store some pushes in a remote blob store on the server (EXPERIMENTAL)
 
     [infinitepush]
     # Server-side and client-side option. Pattern of the infinitepush bookmark
     branchpattern = PATTERN
 
     # Server or client
     server = False
 
     # Server-side option. Possible values: 'disk' or 'sql'. Fails if not set
     indextype = disk
 
     # Server-side option. Used only if indextype=sql.
     # Format: 'IP:PORT:DB_NAME:USER:PASSWORD'
     sqlhost = IP:PORT:DB_NAME:USER:PASSWORD
 
     # Server-side option. Used only if indextype=disk.
     # Filesystem path to the index store
     indexpath = PATH
 
     # Server-side option. Possible values: 'disk' or 'external'
     # Fails if not set
     storetype = disk
 
     # Server-side option.
     # Path to the binary that will save bundle to the bundlestore
     # Formatted cmd line will be passed to it (see `put_args`)
     put_binary = put
 
     # Serser-side option. Used only if storetype=external.
     # Format cmd-line string for put binary. Placeholder: {filename}
     put_args = {filename}
 
     # Server-side option.
     # Path to the binary that get bundle from the bundlestore.
     # Formatted cmd line will be passed to it (see `get_args`)
     get_binary = get
 
     # Serser-side option. Used only if storetype=external.
     # Format cmd-line string for get binary. Placeholders: {filename} {handle}
     get_args = {filename} {handle}
 
     # Server-side option
     logfile = FIlE
 
     # Server-side option
     loglevel = DEBUG
 
     # Server-side option. Used only if indextype=sql.
     # Sets mysql wait_timeout option.
     waittimeout = 300
 
     # Server-side option. Used only if indextype=sql.
     # Sets mysql innodb_lock_wait_timeout option.
     locktimeout = 120
 
     # Server-side option. Used only if indextype=sql.
     # Name of the repository
     reponame = ''
 
     # Client-side option. Used by --list-remote option. List of remote scratch
     # patterns to list if no patterns are specified.
     defaultremotepatterns = ['*']
 
     # Instructs infinitepush to forward all received bundle2 parts to the
     # bundle for storage. Defaults to False.
     storeallparts = True
 
     # routes each incoming push to the bundlestore. defaults to False
     pushtobundlestore = True
 
     [remotenames]
     # Client-side option
     # This option should be set only if remotenames extension is enabled.
     # Whether remote bookmarks are tracked by remotenames extension.
     bookmarks = True
 """
 
 from __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import functools
 import logging
 import os
 import random
 import re
 import socket
 import subprocess
 import tempfile
 import time
 
 from mercurial.node import (
     bin,
     hex,
 )
 
 from mercurial.i18n import _
 
 from mercurial.utils import (
     procutil,
     stringutil,
 )
 
 from mercurial import (
     bundle2,
     changegroup,
     commands,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     hg,
     localrepo,
     peer,
     phases,
     pushkey,
     pycompat,
     registrar,
     util,
     wireproto,
+    wireprototypes,
 )
 
 from . import (
     bundleparts,
     common,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('infinitepush', 'server',
     default=False,
 )
 configitem('infinitepush', 'storetype',
     default='',
 )
 configitem('infinitepush', 'indextype',
     default='',
 )
 configitem('infinitepush', 'indexpath',
     default='',
 )
 configitem('infinitepush', 'storeallparts',
     default=False,
 )
 configitem('infinitepush', 'reponame',
     default='',
 )
 configitem('scratchbranch', 'storepath',
     default='',
 )
 configitem('infinitepush', 'branchpattern',
     default='',
 )
 configitem('infinitepush', 'pushtobundlestore',
     default=False,
 )
 configitem('experimental', 'server-bundlestore-bookmark',
     default='',
 )
 configitem('experimental', 'infinitepush-scratchpush',
     default=False,
 )
 
 experimental = 'experimental'
 configbookmark = 'server-bundlestore-bookmark'
 configscratchpush = 'infinitepush-scratchpush'
 
 scratchbranchparttype = bundleparts.scratchbranchparttype
 revsetpredicate = registrar.revsetpredicate()
 templatekeyword = registrar.templatekeyword()
 _scratchbranchmatcher = lambda x: False
 _maybehash = re.compile(r'^[a-f0-9]+$').search
 
 def _buildexternalbundlestore(ui):
     put_args = ui.configlist('infinitepush', 'put_args', [])
     put_binary = ui.config('infinitepush', 'put_binary')
     if not put_binary:
         raise error.Abort('put binary is not specified')
     get_args = ui.configlist('infinitepush', 'get_args', [])
     get_binary = ui.config('infinitepush', 'get_binary')
     if not get_binary:
         raise error.Abort('get binary is not specified')
     from . import store
     return store.externalbundlestore(put_binary, put_args, get_binary, get_args)
 
 def _buildsqlindex(ui):
     sqlhost = ui.config('infinitepush', 'sqlhost')
     if not sqlhost:
         raise error.Abort(_('please set infinitepush.sqlhost'))
     host, port, db, user, password = sqlhost.split(':')
     reponame = ui.config('infinitepush', 'reponame')
     if not reponame:
         raise error.Abort(_('please set infinitepush.reponame'))
 
     logfile = ui.config('infinitepush', 'logfile', '')
     waittimeout = ui.configint('infinitepush', 'waittimeout', 300)
     locktimeout = ui.configint('infinitepush', 'locktimeout', 120)
     from . import sqlindexapi
     return sqlindexapi.sqlindexapi(
         reponame, host, port, db, user, password,
         logfile, _getloglevel(ui), waittimeout=waittimeout,
         locktimeout=locktimeout)
 
 def _getloglevel(ui):
     loglevel = ui.config('infinitepush', 'loglevel', 'DEBUG')
     numeric_loglevel = getattr(logging, loglevel.upper(), None)
     if not isinstance(numeric_loglevel, int):
         raise error.Abort(_('invalid log level %s') % loglevel)
     return numeric_loglevel
 
 def _tryhoist(ui, remotebookmark):
     '''returns a bookmarks with hoisted part removed
 
     Remotenames extension has a 'hoist' config that allows to use remote
     bookmarks without specifying remote path. For example, 'hg update master'
     works as well as 'hg update remote/master'. We want to allow the same in
     infinitepush.
     '''
 
     if common.isremotebooksenabled(ui):
         hoist = ui.config('remotenames', 'hoistedpeer') + '/'
         if remotebookmark.startswith(hoist):
             return remotebookmark[len(hoist):]
     return remotebookmark
 
 class bundlestore(object):
     def __init__(self, repo):
         self._repo = repo
         storetype = self._repo.ui.config('infinitepush', 'storetype')
         if storetype == 'disk':
             from . import store
             self.store = store.filebundlestore(self._repo.ui, self._repo)
         elif storetype == 'external':
             self.store = _buildexternalbundlestore(self._repo.ui)
         else:
             raise error.Abort(
                 _('unknown infinitepush store type specified %s') % storetype)
 
         indextype = self._repo.ui.config('infinitepush', 'indextype')
         if indextype == 'disk':
             from . import fileindexapi
             self.index = fileindexapi.fileindexapi(self._repo)
         elif indextype == 'sql':
             self.index = _buildsqlindex(self._repo.ui)
         else:
             raise error.Abort(
                 _('unknown infinitepush index type specified %s') % indextype)
 
 def _isserver(ui):
     return ui.configbool('infinitepush', 'server')
 
 def reposetup(ui, repo):
     if _isserver(ui) and repo.local():
         repo.bundlestore = bundlestore(repo)
 
 def extsetup(ui):
     commonsetup(ui)
     if _isserver(ui):
         serverextsetup(ui)
     else:
         clientextsetup(ui)
 
 def commonsetup(ui):
     wireproto.commands['listkeyspatterns'] = (
         wireprotolistkeyspatterns, 'namespace patterns')
     scratchbranchpat = ui.config('infinitepush', 'branchpattern')
     if scratchbranchpat:
         global _scratchbranchmatcher
         kind, pat, _scratchbranchmatcher = \
                 stringutil.stringmatcher(scratchbranchpat)
 
 def serverextsetup(ui):
     origpushkeyhandler = bundle2.parthandlermapping['pushkey']
 
     def newpushkeyhandler(*args, **kwargs):
         bundle2pushkey(origpushkeyhandler, *args, **kwargs)
     newpushkeyhandler.params = origpushkeyhandler.params
     bundle2.parthandlermapping['pushkey'] = newpushkeyhandler
 
     orighandlephasehandler = bundle2.parthandlermapping['phase-heads']
     newphaseheadshandler = lambda *args, **kwargs: \
         bundle2handlephases(orighandlephasehandler, *args, **kwargs)
     newphaseheadshandler.params = orighandlephasehandler.params
     bundle2.parthandlermapping['phase-heads'] = newphaseheadshandler
 
     extensions.wrapfunction(localrepo.localrepository, 'listkeys',
                             localrepolistkeys)
     wireproto.commands['lookup'] = (
         _lookupwrap(wireproto.commands['lookup'][0]), 'key')
     extensions.wrapfunction(exchange, 'getbundlechunks', getbundlechunks)
 
     extensions.wrapfunction(bundle2, 'processparts', processparts)
 
 def clientextsetup(ui):
     entry = extensions.wrapcommand(commands.table, 'push', _push)
 
     entry[1].append(
         ('', 'bundle-store', None,
          _('force push to go to bundle store (EXPERIMENTAL)')))
 
     extensions.wrapcommand(commands.table, 'pull', _pull)
 
     extensions.wrapfunction(discovery, 'checkheads', _checkheads)
 
     wireproto.wirepeer.listkeyspatterns = listkeyspatterns
 
     partorder = exchange.b2partsgenorder
     index = partorder.index('changeset')
     partorder.insert(
         index, partorder.pop(partorder.index(scratchbranchparttype)))
 
 def _checkheads(orig, pushop):
     if pushop.ui.configbool(experimental, configscratchpush, False):
         return
     return orig(pushop)
 
 def wireprotolistkeyspatterns(repo, proto, namespace, patterns):
-    patterns = wireproto.decodelist(patterns)
+    patterns = wireprototypes.decodelist(patterns)
     d = repo.listkeys(encoding.tolocal(namespace), patterns).iteritems()
     return pushkey.encodekeys(d)
 
 def localrepolistkeys(orig, self, namespace, patterns=None):
     if namespace == 'bookmarks' and patterns:
         index = self.bundlestore.index
         results = {}
         bookmarks = orig(self, namespace)
         for pattern in patterns:
             results.update(index.getbookmarks(pattern))
             if pattern.endswith('*'):
                 pattern = 're:^' + pattern[:-1] + '.*'
             kind, pat, matcher = stringutil.stringmatcher(pattern)
             for bookmark, node in bookmarks.iteritems():
                 if matcher(bookmark):
                     results[bookmark] = node
         return results
     else:
         return orig(self, namespace)
 
 @peer.batchable
 def listkeyspatterns(self, namespace, patterns):
     if not self.capable('pushkey'):
         yield {}, None
     f = peer.future()
     self.ui.debug('preparing listkeys for "%s" with pattern "%s"\n' %
                   (namespace, patterns))
     yield {
         'namespace': encoding.fromlocal(namespace),
-        'patterns': wireproto.encodelist(patterns)
+        'patterns': wireprototypes.encodelist(patterns)
     }, f
     d = f.value
     self.ui.debug('received listkey for "%s": %i bytes\n'
                   % (namespace, len(d)))
     yield pushkey.decodekeys(d)
 
 def _readbundlerevs(bundlerepo):
     return list(bundlerepo.revs('bundle()'))
 
 def _includefilelogstobundle(bundlecaps, bundlerepo, bundlerevs, ui):
     '''Tells remotefilelog to include all changed files to the changegroup
 
     By default remotefilelog doesn't include file content to the changegroup.
     But we need to include it if we are fetching from bundlestore.
     '''
     changedfiles = set()
     cl = bundlerepo.changelog
     for r in bundlerevs:
         # [3] means changed files
         changedfiles.update(cl.read(r)[3])
     if not changedfiles:
         return bundlecaps
 
     changedfiles = '\0'.join(changedfiles)
     newcaps = []
     appended = False
     for cap in (bundlecaps or []):
         if cap.startswith('excludepattern='):
             newcaps.append('\0'.join((cap, changedfiles)))
             appended = True
         else:
             newcaps.append(cap)
     if not appended:
         # Not found excludepattern cap. Just append it
         newcaps.append('excludepattern=' + changedfiles)
 
     return newcaps
 
 def _rebundle(bundlerepo, bundleroots, unknownhead):
     '''
     Bundle may include more revision then user requested. For example,
     if user asks for revision but bundle also consists its descendants.
     This function will filter out all revision that user is not requested.
     '''
     parts = []
 
     version = '02'
     outgoing = discovery.outgoing(bundlerepo, commonheads=bundleroots,
                                   missingheads=[unknownhead])
     cgstream = changegroup.makestream(bundlerepo, outgoing, version, 'pull')
     cgstream = util.chunkbuffer(cgstream).read()
     cgpart = bundle2.bundlepart('changegroup', data=cgstream)
     cgpart.addparam('version', version)
     parts.append(cgpart)
 
     return parts
 
 def _getbundleroots(oldrepo, bundlerepo, bundlerevs):
     cl = bundlerepo.changelog
     bundleroots = []
     for rev in bundlerevs:
         node = cl.node(rev)
         parents = cl.parents(node)
         for parent in parents:
             # include all revs that exist in the main repo
             # to make sure that bundle may apply client-side
             if parent in oldrepo:
                 bundleroots.append(parent)
     return bundleroots
 
 def _needsrebundling(head, bundlerepo):
     bundleheads = list(bundlerepo.revs('heads(bundle())'))
     return not (len(bundleheads) == 1 and
                 bundlerepo[bundleheads[0]].node() == head)
 
 def _generateoutputparts(head, bundlerepo, bundleroots, bundlefile):
     '''generates bundle that will be send to the user
 
     returns tuple with raw bundle string and bundle type
     '''
     parts = []
     if not _needsrebundling(head, bundlerepo):
         with util.posixfile(bundlefile, "rb") as f:
             unbundler = exchange.readbundle(bundlerepo.ui, f, bundlefile)
             if isinstance(unbundler, changegroup.cg1unpacker):
                 part = bundle2.bundlepart('changegroup',
                                           data=unbundler._stream.read())
                 part.addparam('version', '01')
                 parts.append(part)
             elif isinstance(unbundler, bundle2.unbundle20):
                 haschangegroup = False
                 for part in unbundler.iterparts():
                     if part.type == 'changegroup':
                         haschangegroup = True
                     newpart = bundle2.bundlepart(part.type, data=part.read())
                     for key, value in part.params.iteritems():
                         newpart.addparam(key, value)
                     parts.append(newpart)
 
                 if not haschangegroup:
                     raise error.Abort(
                         'unexpected bundle without changegroup part, ' +
                         'head: %s' % hex(head),
                         hint='report to administrator')
             else:
                 raise error.Abort('unknown bundle type')
     else:
         parts = _rebundle(bundlerepo, bundleroots, head)
 
     return parts
 
 def getbundlechunks(orig, repo, source, heads=None, bundlecaps=None, **kwargs):
     heads = heads or []
     # newheads are parents of roots of scratch bundles that were requested
     newphases = {}
     scratchbundles = []
     newheads = []
     scratchheads = []
     nodestobundle = {}
     allbundlestocleanup = []
     try:
         for head in heads:
             if head not in repo.changelog.nodemap:
                 if head not in nodestobundle:
                     newbundlefile = common.downloadbundle(repo, head)
                     bundlepath = "bundle:%s+%s" % (repo.root, newbundlefile)
                     bundlerepo = hg.repository(repo.ui, bundlepath)
 
                     allbundlestocleanup.append((bundlerepo, newbundlefile))
                     bundlerevs = set(_readbundlerevs(bundlerepo))
                     bundlecaps = _includefilelogstobundle(
                         bundlecaps, bundlerepo, bundlerevs, repo.ui)
                     cl = bundlerepo.changelog
                     bundleroots = _getbundleroots(repo, bundlerepo, bundlerevs)
                     for rev in bundlerevs:
                         node = cl.node(rev)
                         newphases[hex(node)] = str(phases.draft)
                         nodestobundle[node] = (bundlerepo, bundleroots,
                                                newbundlefile)
 
                 scratchbundles.append(
                     _generateoutputparts(head, *nodestobundle[head]))
                 newheads.extend(bundleroots)
                 scratchheads.append(head)
     finally:
         for bundlerepo, bundlefile in allbundlestocleanup:
             bundlerepo.close()
             try:
                 os.unlink(bundlefile)
             except (IOError, OSError):
                 # if we can't cleanup the file then just ignore the error,
                 # no need to fail
                 pass
 
     pullfrombundlestore = bool(scratchbundles)
     wrappedchangegrouppart = False
     wrappedlistkeys = False
     oldchangegrouppart = exchange.getbundle2partsmapping['changegroup']
     try:
         def _changegrouppart(bundler, *args, **kwargs):
             # Order is important here. First add non-scratch part
             # and only then add parts with scratch bundles because
             # non-scratch part contains parents of roots of scratch bundles.
             result = oldchangegrouppart(bundler, *args, **kwargs)
             for bundle in scratchbundles:
                 for part in bundle:
                     bundler.addpart(part)
             return result
 
         exchange.getbundle2partsmapping['changegroup'] = _changegrouppart
         wrappedchangegrouppart = True
 
         def _listkeys(orig, self, namespace):
             origvalues = orig(self, namespace)
             if namespace == 'phases' and pullfrombundlestore:
                 if origvalues.get('publishing') == 'True':
                     # Make repo non-publishing to preserve draft phase
                     del origvalues['publishing']
                 origvalues.update(newphases)
             return origvalues
 
         extensions.wrapfunction(localrepo.localrepository, 'listkeys',
                                 _listkeys)
         wrappedlistkeys = True
         heads = list((set(newheads) | set(heads)) - set(scratchheads))
         result = orig(repo, source, heads=heads,
                       bundlecaps=bundlecaps, **kwargs)
     finally:
         if wrappedchangegrouppart:
             exchange.getbundle2partsmapping['changegroup'] = oldchangegrouppart
         if wrappedlistkeys:
             extensions.unwrapfunction(localrepo.localrepository, 'listkeys',
                                       _listkeys)
     return result
 
 def _lookupwrap(orig):
     def _lookup(repo, proto, key):
         localkey = encoding.tolocal(key)
 
         if isinstance(localkey, str) and _scratchbranchmatcher(localkey):
             scratchnode = repo.bundlestore.index.getnode(localkey)
             if scratchnode:
                 return "%s %s\n" % (1, scratchnode)
             else:
                 return "%s %s\n" % (0, 'scratch branch %s not found' % localkey)
         else:
             try:
                 r = hex(repo.lookup(localkey))
                 return "%s %s\n" % (1, r)
             except Exception as inst:
                 if repo.bundlestore.index.getbundle(localkey):
                     return "%s %s\n" % (1, localkey)
                 else:
                     r = str(inst)
                     return "%s %s\n" % (0, r)
     return _lookup
 
 def _pull(orig, ui, repo, source="default", **opts):
     opts = pycompat.byteskwargs(opts)
     # Copy paste from `pull` command
     source, branches = hg.parseurl(ui.expandpath(source), opts.get('branch'))
 
     scratchbookmarks = {}
     unfi = repo.unfiltered()
     unknownnodes = []
     for rev in opts.get('rev', []):
         if rev not in unfi:
             unknownnodes.append(rev)
     if opts.get('bookmark'):
         bookmarks = []
         revs = opts.get('rev') or []
         for bookmark in opts.get('bookmark'):
             if _scratchbranchmatcher(bookmark):
                 # rev is not known yet
                 # it will be fetched with listkeyspatterns next
                 scratchbookmarks[bookmark] = 'REVTOFETCH'
             else:
                 bookmarks.append(bookmark)
 
         if scratchbookmarks:
             other = hg.peer(repo, opts, source)
             fetchedbookmarks = other.listkeyspatterns(
                 'bookmarks', patterns=scratchbookmarks)
             for bookmark in scratchbookmarks:
                 if bookmark not in fetchedbookmarks:
                     raise error.Abort('remote bookmark %s not found!' %
                                       bookmark)
                 scratchbookmarks[bookmark] = fetchedbookmarks[bookmark]
                 revs.append(fetchedbookmarks[bookmark])
         opts['bookmark'] = bookmarks
         opts['rev'] = revs
 
     if scratchbookmarks or unknownnodes:
         # Set anyincoming to True
         extensions.wrapfunction(discovery, 'findcommonincoming',
                                 _findcommonincoming)
     try:
         # Remote scratch bookmarks will be deleted because remotenames doesn't
         # know about them. Let's save it before pull and restore after
         remotescratchbookmarks = _readscratchremotebookmarks(ui, repo, source)
         result = orig(ui, repo, source, **pycompat.strkwargs(opts))
         # TODO(stash): race condition is possible
         # if scratch bookmarks was updated right after orig.
         # But that's unlikely and shouldn't be harmful.
         if common.isremotebooksenabled(ui):
             remotescratchbookmarks.update(scratchbookmarks)
             _saveremotebookmarks(repo, remotescratchbookmarks, source)
         else:
             _savelocalbookmarks(repo, scratchbookmarks)
         return result
     finally:
         if scratchbookmarks:
             extensions.unwrapfunction(discovery, 'findcommonincoming')
 
 def _readscratchremotebookmarks(ui, repo, other):
     if common.isremotebooksenabled(ui):
         remotenamesext = extensions.find('remotenames')
         remotepath = remotenamesext.activepath(repo.ui, other)
         result = {}
         # Let's refresh remotenames to make sure we have it up to date
         # Seems that `repo.names['remotebookmarks']` may return stale bookmarks
         # and it results in deleting scratch bookmarks. Our best guess how to
         # fix it is to use `clearnames()`
         repo._remotenames.clearnames()
         for remotebookmark in repo.names['remotebookmarks'].listnames(repo):
             path, bookname = remotenamesext.splitremotename(remotebookmark)
             if path == remotepath and _scratchbranchmatcher(bookname):
                 nodes = repo.names['remotebookmarks'].nodes(repo,
                                                             remotebookmark)
                 if nodes:
                     result[bookname] = hex(nodes[0])
         return result
     else:
         return {}
 
 def _saveremotebookmarks(repo, newbookmarks, remote):
     remotenamesext = extensions.find('remotenames')
     remotepath = remotenamesext.activepath(repo.ui, remote)
     branches = collections.defaultdict(list)
     bookmarks = {}
     remotenames = remotenamesext.readremotenames(repo)
     for hexnode, nametype, remote, rname in remotenames:
         if remote != remotepath:
             continue
         if nametype == 'bookmarks':
             if rname in newbookmarks:
                 # It's possible if we have a normal bookmark that matches
                 # scratch branch pattern. In this case just use the current
                 # bookmark node
                 del newbookmarks[rname]
             bookmarks[rname] = hexnode
         elif nametype == 'branches':
             # saveremotenames expects 20 byte binary nodes for branches
             branches[rname].append(bin(hexnode))
 
     for bookmark, hexnode in newbookmarks.iteritems():
         bookmarks[bookmark] = hexnode
     remotenamesext.saveremotenames(repo, remotepath, branches, bookmarks)
 
 def _savelocalbookmarks(repo, bookmarks):
     if not bookmarks:
         return
     with repo.wlock(), repo.lock(), repo.transaction('bookmark') as tr:
         changes = []
         for scratchbook, node in bookmarks.iteritems():
             changectx = repo[node]
             changes.append((scratchbook, changectx.node()))
         repo._bookmarks.applychanges(repo, tr, changes)
 
 def _findcommonincoming(orig, *args, **kwargs):
     common, inc, remoteheads = orig(*args, **kwargs)
     return common, True, remoteheads
 
 def _push(orig, ui, repo, dest=None, *args, **opts):
 
     bookmark = opts.get(r'bookmark')
     # we only support pushing one infinitepush bookmark at once
     if len(bookmark) == 1:
         bookmark = bookmark[0]
     else:
         bookmark = ''
 
     oldphasemove = None
     overrides = {(experimental, configbookmark): bookmark}
 
     with ui.configoverride(overrides, 'infinitepush'):
         scratchpush = opts.get('bundle_store')
         if _scratchbranchmatcher(bookmark):
             scratchpush = True
             # bundle2 can be sent back after push (for example, bundle2
             # containing `pushkey` part to update bookmarks)
             ui.setconfig(experimental, 'bundle2.pushback', True)
 
         if scratchpush:
             # this is an infinitepush, we don't want the bookmark to be applied
             # rather that should be stored in the bundlestore
             opts[r'bookmark'] = []
             ui.setconfig(experimental, configscratchpush, True)
             oldphasemove = extensions.wrapfunction(exchange,
                                                    '_localphasemove',
                                                    _phasemove)
         # Copy-paste from `push` command
         path = ui.paths.getpath(dest, default=('default-push', 'default'))
         if not path:
             raise error.Abort(_('default repository not configured!'),
                              hint=_("see 'hg help config.paths'"))
         destpath = path.pushloc or path.loc
         # Remote scratch bookmarks will be deleted because remotenames doesn't
         # know about them. Let's save it before push and restore after
         remotescratchbookmarks = _readscratchremotebookmarks(ui, repo, destpath)
         result = orig(ui, repo, dest, *args, **opts)
         if common.isremotebooksenabled(ui):
             if bookmark and scratchpush:
                 other = hg.peer(repo, opts, destpath)
                 fetchedbookmarks = other.listkeyspatterns('bookmarks',
                                                           patterns=[bookmark])
                 remotescratchbookmarks.update(fetchedbookmarks)
             _saveremotebookmarks(repo, remotescratchbookmarks, destpath)
     if oldphasemove:
         exchange._localphasemove = oldphasemove
     return result
 
 def _deleteinfinitepushbookmarks(ui, repo, path, names):
     """Prune remote names by removing the bookmarks we don't want anymore,
     then writing the result back to disk
     """
     remotenamesext = extensions.find('remotenames')
 
     # remotename format is:
     # (node, nametype ("branches" or "bookmarks"), remote, name)
     nametype_idx = 1
     remote_idx = 2
     name_idx = 3
     remotenames = [remotename for remotename in \
                    remotenamesext.readremotenames(repo) \
                    if remotename[remote_idx] == path]
     remote_bm_names = [remotename[name_idx] for remotename in \
                        remotenames if remotename[nametype_idx] == "bookmarks"]
 
     for name in names:
         if name not in remote_bm_names:
             raise error.Abort(_("infinitepush bookmark '{}' does not exist "
                                 "in path '{}'").format(name, path))
 
     bookmarks = {}
     branches = collections.defaultdict(list)
     for node, nametype, remote, name in remotenames:
         if nametype == "bookmarks" and name not in names:
             bookmarks[name] = node
         elif nametype == "branches":
             # saveremotenames wants binary nodes for branches
             branches[name].append(bin(node))
 
     remotenamesext.saveremotenames(repo, path, branches, bookmarks)
 
 def _phasemove(orig, pushop, nodes, phase=phases.public):
     """prevent commits from being marked public
 
     Since these are going to a scratch branch, they aren't really being
     published."""
 
     if phase != phases.public:
         orig(pushop, nodes, phase)
 
 @exchange.b2partsgenerator(scratchbranchparttype)
 def partgen(pushop, bundler):
     bookmark = pushop.ui.config(experimental, configbookmark)
     scratchpush = pushop.ui.configbool(experimental, configscratchpush)
     if 'changesets' in pushop.stepsdone or not scratchpush:
         return
 
     if scratchbranchparttype not in bundle2.bundle2caps(pushop.remote):
         return
 
     pushop.stepsdone.add('changesets')
     if not pushop.outgoing.missing:
         pushop.ui.status(_('no changes found\n'))
         pushop.cgresult = 0
         return
 
     # This parameter tells the server that the following bundle is an
     # infinitepush. This let's it switch the part processing to our infinitepush
     # code path.
     bundler.addparam("infinitepush", "True")
 
     scratchparts = bundleparts.getscratchbranchparts(pushop.repo,
                                                      pushop.remote,
                                                      pushop.outgoing,
                                                      pushop.ui,
                                                      bookmark)
 
     for scratchpart in scratchparts:
         bundler.addpart(scratchpart)
 
     def handlereply(op):
         # server either succeeds or aborts; no code to read
         pushop.cgresult = 1
 
     return handlereply
 
 bundle2.capabilities[bundleparts.scratchbranchparttype] = ()
 
 def _getrevs(bundle, oldnode, force, bookmark):
     'extracts and validates the revs to be imported'
     revs = [bundle[r] for r in bundle.revs('sort(bundle())')]
 
     # new bookmark
     if oldnode is None:
         return revs
 
     # Fast forward update
     if oldnode in bundle and list(bundle.set('bundle() & %s::', oldnode)):
         return revs
 
     return revs
 
 @contextlib.contextmanager
 def logservicecall(logger, service, **kwargs):
     start = time.time()
     logger(service, eventtype='start', **kwargs)
     try:
         yield
         logger(service, eventtype='success',
                elapsedms=(time.time() - start) * 1000, **kwargs)
     except Exception as e:
         logger(service, eventtype='failure',
                elapsedms=(time.time() - start) * 1000, errormsg=str(e),
                **kwargs)
         raise
 
 def _getorcreateinfinitepushlogger(op):
     logger = op.records['infinitepushlogger']
     if not logger:
         ui = op.repo.ui
         try:
             username = procutil.getuser()
         except Exception:
             username = 'unknown'
         # Generate random request id to be able to find all logged entries
         # for the same request. Since requestid is pseudo-generated it may
         # not be unique, but we assume that (hostname, username, requestid)
         # is unique.
         random.seed()
         requestid = random.randint(0, 2000000000)
         hostname = socket.gethostname()
         logger = functools.partial(ui.log, 'infinitepush', user=username,
                                    requestid=requestid, hostname=hostname,
                                    reponame=ui.config('infinitepush',
                                                       'reponame'))
         op.records.add('infinitepushlogger', logger)
     else:
         logger = logger[0]
     return logger
 
 def storetobundlestore(orig, repo, op, unbundler):
     """stores the incoming bundle coming from push command to the bundlestore
     instead of applying on the revlogs"""
 
     repo.ui.status(_("storing changesets on the bundlestore\n"))
     bundler = bundle2.bundle20(repo.ui)
 
     # processing each part and storing it in bundler
     with bundle2.partiterator(repo, op, unbundler) as parts:
         for part in parts:
             bundlepart = None
             if part.type == 'replycaps':
                 # This configures the current operation to allow reply parts.
                 bundle2._processpart(op, part)
             else:
                 bundlepart = bundle2.bundlepart(part.type, data=part.read())
                 for key, value in part.params.iteritems():
                     bundlepart.addparam(key, value)
 
                 # Certain parts require a response
                 if part.type in ('pushkey', 'changegroup'):
                     if op.reply is not None:
                         rpart = op.reply.newpart('reply:%s' % part.type)
                         rpart.addparam('in-reply-to', str(part.id),
                                        mandatory=False)
                         rpart.addparam('return', '1', mandatory=False)
 
             op.records.add(part.type, {
                 'return': 1,
             })
             if bundlepart:
                 bundler.addpart(bundlepart)
 
     # storing the bundle in the bundlestore
     buf = util.chunkbuffer(bundler.getchunks())
     fd, bundlefile = tempfile.mkstemp()
     try:
         try:
             fp = os.fdopen(fd, r'wb')
             fp.write(buf.read())
         finally:
             fp.close()
         storebundle(op, {}, bundlefile)
     finally:
         try:
             os.unlink(bundlefile)
         except Exception:
             # we would rather see the original exception
             pass
 
 def processparts(orig, repo, op, unbundler):
 
     # make sure we don't wrap processparts in case of `hg unbundle`
     if op.source == 'unbundle':
         return orig(repo, op, unbundler)
 
     # this server routes each push to bundle store
     if repo.ui.configbool('infinitepush', 'pushtobundlestore'):
         return storetobundlestore(orig, repo, op, unbundler)
 
     if unbundler.params.get('infinitepush') != 'True':
         return orig(repo, op, unbundler)
 
     handleallparts = repo.ui.configbool('infinitepush', 'storeallparts')
 
     bundler = bundle2.bundle20(repo.ui)
     cgparams = None
     with bundle2.partiterator(repo, op, unbundler) as parts:
         for part in parts:
             bundlepart = None
             if part.type == 'replycaps':
                 # This configures the current operation to allow reply parts.
                 bundle2._processpart(op, part)
             elif part.type == bundleparts.scratchbranchparttype:
                 # Scratch branch parts need to be converted to normal
                 # changegroup parts, and the extra parameters stored for later
                 # when we upload to the store. Eventually those parameters will
                 # be put on the actual bundle instead of this part, then we can
                 # send a vanilla changegroup instead of the scratchbranch part.
                 cgversion = part.params.get('cgversion', '01')
                 bundlepart = bundle2.bundlepart('changegroup', data=part.read())
                 bundlepart.addparam('version', cgversion)
                 cgparams = part.params
 
                 # If we're not dumping all parts into the new bundle, we need to
                 # alert the future pushkey and phase-heads handler to skip
                 # the part.
                 if not handleallparts:
                     op.records.add(scratchbranchparttype + '_skippushkey', True)
                     op.records.add(scratchbranchparttype + '_skipphaseheads',
                                    True)
             else:
                 if handleallparts:
                     # Ideally we would not process any parts, and instead just
                     # forward them to the bundle for storage, but since this
                     # differs from previous behavior, we need to put it behind a
                     # config flag for incremental rollout.
                     bundlepart = bundle2.bundlepart(part.type, data=part.read())
                     for key, value in part.params.iteritems():
                         bundlepart.addparam(key, value)
 
                     # Certain parts require a response
                     if part.type == 'pushkey':
                         if op.reply is not None:
                             rpart = op.reply.newpart('reply:pushkey')
                             rpart.addparam('in-reply-to', str(part.id),
                                            mandatory=False)
                             rpart.addparam('return', '1', mandatory=False)
                 else:
                     bundle2._processpart(op, part)
 
             if handleallparts:
                 op.records.add(part.type, {
                     'return': 1,
                 })
             if bundlepart:
                 bundler.addpart(bundlepart)
 
     # If commits were sent, store them
     if cgparams:
         buf = util.chunkbuffer(bundler.getchunks())
         fd, bundlefile = tempfile.mkstemp()
         try:
             try:
                 fp = os.fdopen(fd, r'wb')
                 fp.write(buf.read())
             finally:
                 fp.close()
             storebundle(op, cgparams, bundlefile)
         finally:
             try:
                 os.unlink(bundlefile)
             except Exception:
                 # we would rather see the original exception
                 pass
 
 def storebundle(op, params, bundlefile):
     log = _getorcreateinfinitepushlogger(op)
     parthandlerstart = time.time()
     log(scratchbranchparttype, eventtype='start')
     index = op.repo.bundlestore.index
     store = op.repo.bundlestore.store
     op.records.add(scratchbranchparttype + '_skippushkey', True)
 
     bundle = None
     try:  # guards bundle
         bundlepath = "bundle:%s+%s" % (op.repo.root, bundlefile)
         bundle = hg.repository(op.repo.ui, bundlepath)
 
         bookmark = params.get('bookmark')
         bookprevnode = params.get('bookprevnode', '')
         force = params.get('force')
 
         if bookmark:
             oldnode = index.getnode(bookmark)
         else:
             oldnode = None
         bundleheads = bundle.revs('heads(bundle())')
         if bookmark and len(bundleheads) > 1:
             raise error.Abort(
                 _('cannot push more than one head to a scratch branch'))
 
         revs = _getrevs(bundle, oldnode, force, bookmark)
 
         # Notify the user of what is being pushed
         plural = 's' if len(revs) > 1 else ''
         op.repo.ui.warn(_("pushing %d commit%s:\n") % (len(revs), plural))
         maxoutput = 10
         for i in range(0, min(len(revs), maxoutput)):
             firstline = bundle[revs[i]].description().split('\n')[0][:50]
             op.repo.ui.warn(("    %s  %s\n") % (revs[i], firstline))
 
         if len(revs) > maxoutput + 1:
             op.repo.ui.warn(("    ...\n"))
             firstline = bundle[revs[-1]].description().split('\n')[0][:50]
             op.repo.ui.warn(("    %s  %s\n") % (revs[-1], firstline))
 
         nodesctx = [bundle[rev] for rev in revs]
         inindex = lambda rev: bool(index.getbundle(bundle[rev].hex()))
         if bundleheads:
             newheadscount = sum(not inindex(rev) for rev in bundleheads)
         else:
             newheadscount = 0
         # If there's a bookmark specified, there should be only one head,
         # so we choose the last node, which will be that head.
         # If a bug or malicious client allows there to be a bookmark
         # with multiple heads, we will place the bookmark on the last head.
         bookmarknode = nodesctx[-1].hex() if nodesctx else None
         key = None
         if newheadscount:
             with open(bundlefile, 'r') as f:
                 bundledata = f.read()
                 with logservicecall(log, 'bundlestore',
                                     bundlesize=len(bundledata)):
                     bundlesizelimit = 100 * 1024 * 1024  # 100 MB
                     if len(bundledata) > bundlesizelimit:
                         error_msg = ('bundle is too big: %d bytes. ' +
                                      'max allowed size is 100 MB')
                         raise error.Abort(error_msg % (len(bundledata),))
                     key = store.write(bundledata)
 
         with logservicecall(log, 'index', newheadscount=newheadscount), index:
             if key:
                 index.addbundle(key, nodesctx)
             if bookmark:
                 index.addbookmark(bookmark, bookmarknode)
                 _maybeaddpushbackpart(op, bookmark, bookmarknode,
                                       bookprevnode, params)
         log(scratchbranchparttype, eventtype='success',
             elapsedms=(time.time() - parthandlerstart) * 1000)
 
     except Exception as e:
         log(scratchbranchparttype, eventtype='failure',
             elapsedms=(time.time() - parthandlerstart) * 1000,
             errormsg=str(e))
         raise
     finally:
         if bundle:
             bundle.close()
 
 @bundle2.parthandler(scratchbranchparttype,
                      ('bookmark', 'bookprevnode', 'force',
                       'pushbackbookmarks', 'cgversion'))
 def bundle2scratchbranch(op, part):
     '''unbundle a bundle2 part containing a changegroup to store'''
 
     bundler = bundle2.bundle20(op.repo.ui)
     cgversion = part.params.get('cgversion', '01')
     cgpart = bundle2.bundlepart('changegroup', data=part.read())
     cgpart.addparam('version', cgversion)
     bundler.addpart(cgpart)
     buf = util.chunkbuffer(bundler.getchunks())
 
     fd, bundlefile = tempfile.mkstemp()
     try:
         try:
             fp = os.fdopen(fd, r'wb')
             fp.write(buf.read())
         finally:
             fp.close()
         storebundle(op, part.params, bundlefile)
     finally:
         try:
             os.unlink(bundlefile)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
     return 1
 
 def _maybeaddpushbackpart(op, bookmark, newnode, oldnode, params):
     if params.get('pushbackbookmarks'):
         if op.reply and 'pushback' in op.reply.capabilities:
             params = {
                 'namespace': 'bookmarks',
                 'key': bookmark,
                 'new': newnode,
                 'old': oldnode,
             }
             op.reply.newpart('pushkey', mandatoryparams=params.iteritems())
 
 def bundle2pushkey(orig, op, part):
     '''Wrapper of bundle2.handlepushkey()
 
     The only goal is to skip calling the original function if flag is set.
     It's set if infinitepush push is happening.
     '''
     if op.records[scratchbranchparttype + '_skippushkey']:
         if op.reply is not None:
             rpart = op.reply.newpart('reply:pushkey')
             rpart.addparam('in-reply-to', str(part.id), mandatory=False)
             rpart.addparam('return', '1', mandatory=False)
         return 1
 
     return orig(op, part)
 
 def bundle2handlephases(orig, op, part):
     '''Wrapper of bundle2.handlephases()
 
     The only goal is to skip calling the original function if flag is set.
     It's set if infinitepush push is happening.
     '''
 
     if op.records[scratchbranchparttype + '_skipphaseheads']:
         return
 
     return orig(op, part)
 
 def _asyncsavemetadata(root, nodes):
     '''starts a separate process that fills metadata for the nodes
 
     This function creates a separate process and doesn't wait for it's
     completion. This was done to avoid slowing down pushes
     '''
 
     maxnodes = 50
     if len(nodes) > maxnodes:
         return
     nodesargs = []
     for node in nodes:
         nodesargs.append('--node')
         nodesargs.append(node)
     with open(os.devnull, 'w+b') as devnull:
         cmdline = [util.hgexecutable(), 'debugfillinfinitepushmetadata',
                    '-R', root] + nodesargs
         # Process will run in background. We don't care about the return code
         subprocess.Popen(cmdline, close_fds=True, shell=False,
                          stdin=devnull, stdout=devnull, stderr=devnull)

mercurial/wireproto.py

@@ -1,1307 +1,1287
 # 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 os
 import tempfile
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
 )
 
 from . import (
     bundle2,
     changegroup as changegroupmod,
     discovery,
     encoding,
     error,
     exchange,
     peer,
     pushkey as pushkeymod,
     pycompat,
     repository,
     streamclone,
     util,
     wireprototypes,
 )
 
 from .utils import (
     procutil,
     stringutil,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 bundle2requiredmain = _('incompatible Mercurial client; bundle2 required')
 bundle2requiredhint = _('see https://www.mercurial-scm.org/wiki/'
                         'IncompatibleClient')
 bundle2required = '%s\n(%s)\n' % (bundle2requiredmain, bundle2requiredhint)
 
 class remoteiterbatcher(peer.iterbatcher):
     def __init__(self, remote):
         super(remoteiterbatcher, self).__init__()
         self._remote = remote
 
     def __getattr__(self, name):
         # Validate this method is batchable, since submit() only supports
         # batchable methods.
         fn = getattr(self._remote, name)
         if not getattr(fn, 'batchable', None):
             raise error.ProgrammingError('Attempted to batch a 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.
         """
         # 2-tuple of (command, arguments) that represents what will be
         # sent over the wire.
         requests = []
 
         # 4-tuple of (command, final future, @batchable generator, remote
         # future).
         results = []
 
         for command, args, opts, finalfuture in self.calls:
             mtd = getattr(self._remote, command)
             batchable = mtd.batchable(mtd.__self__, *args, **opts)
 
             commandargs, fremote = next(batchable)
             assert fremote
             requests.append((command, commandargs))
             results.append((command, finalfuture, batchable, fremote))
 
         if requests:
             self._resultiter = self._remote._submitbatch(requests)
 
         self._results = results
 
     def results(self):
         for command, finalfuture, batchable, remotefuture in self._results:
             # Get the raw result, set it in the remote future, feed it
             # back into the @batchable generator so it can be decoded, and
             # set the result on the final future to this value.
             remoteresult = next(self._resultiter)
             remotefuture.set(remoteresult)
             finalfuture.set(next(batchable))
 
             # Verify our @batchable generators only emit 2 values.
             try:
                 next(batchable)
             except StopIteration:
                 pass
             else:
                 raise error.ProgrammingError('%s @batchable generator emitted '
                                              'unexpected value count' % command)
 
             yield finalfuture.value
 
 # 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 [bin(v) for v in  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."""
+    escapearg = wireprototypes.escapebatcharg
+
     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)
 
 def clientcompressionsupport(proto):
     """Returns a list of compression methods supported by the client.
 
     Returns a list of the compression methods supported by the client
     according to the protocol capabilities. If no such capability has
     been announced, fallback to the default of zlib and uncompressed.
     """
     for cap in proto.getprotocaps():
         if cap.startswith('comp='):
             return cap[5:].split(',')
     return ['zlib', 'none']
 
 # 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',
              'bookmarks': 'boolean',
              'common': 'nodes',
              'obsmarkers': 'boolean',
              'phases': 'boolean',
              'bundlecaps': 'scsv',
              'listkeys': 'csv',
              'cg': 'boolean',
              'cbattempted': 'boolean',
              'stream': 'boolean',
 }
 
 # client side
 
 class wirepeer(repository.legacypeer):
     """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.
     """
     # Begin of ipeercommands interface.
 
     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)
         else:
             self._abort(error.RepoError(data))
 
     @batchable
     def heads(self):
         f = future()
         yield {}, f
         d = f.value
         try:
-            yield decodelist(d[:-1])
+            yield wireprototypes.decodelist(d[:-1])
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     @batchable
     def known(self, nodes):
         f = future()
-        yield {'nodes': encodelist(nodes)}, f
+        yield {'nodes': wireprototypes.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)
+                branchheads = wireprototypes.decodelist(branchheads)
                 branchmap[branchname] = branchheads
             yield branchmap
         except TypeError:
             self._abort(error.ResponseError(_("unexpected response:"), 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)
 
     @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
 
     def stream_out(self):
         return self._callstream('stream_out')
 
     def getbundle(self, source, **kwargs):
         kwargs = pycompat.byteskwargs(kwargs)
         self.requirecap('getbundle', _('look up remote changes'))
         opts = {}
         bundlecaps = kwargs.get('bundlecaps') or set()
         for key, value in kwargs.iteritems():
             if value is None:
                 continue
             keytype = gboptsmap.get(key)
             if keytype is None:
                 raise error.ProgrammingError(
                     'Unexpectedly None keytype for key %s' % key)
             elif keytype == 'nodes':
-                value = encodelist(value)
+                value = wireprototypes.encodelist(value)
             elif keytype == 'csv':
                 value = ','.join(value)
             elif keytype == 'scsv':
                 value = ','.join(sorted(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", **pycompat.strkwargs(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 changegroup.apply()).
 
         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()])
+            heads = wireprototypes.encodelist(
+                ['hashed', hashlib.sha1(''.join(sorted(heads))).digest()])
         else:
-            heads = encodelist(heads)
+            heads = wireprototypes.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
 
     # End of ipeercommands interface.
 
     # Begin of ipeerlegacycommands interface.
 
     def branches(self, nodes):
-        n = encodelist(nodes)
+        n = wireprototypes.encodelist(nodes)
         d = self._call("branches", nodes=n)
         try:
-            br = [tuple(decodelist(b)) for b in d.splitlines()]
+            br = [tuple(wireprototypes.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]])
+            n = " ".join([wireprototypes.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())
+                r.extend(l and wireprototypes.decodelist(l) or []
+                         for l in d.splitlines())
             except ValueError:
                 self._abort(error.ResponseError(_("unexpected response:"), d))
         return r
 
     def changegroup(self, nodes, kind):
-        n = encodelist(nodes)
+        n = wireprototypes.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)
+        bases = wireprototypes.encodelist(bases)
+        heads = wireprototypes.encodelist(heads)
         f = self._callcompressable("changegroupsubset",
                                    bases=bases, heads=heads)
         return changegroupmod.cg1unpacker(f, 'UN')
 
     # End of ipeerlegacycommands interface.
 
     def _submitbatch(self, req):
         """run batch request <req> on the server
 
         Returns an iterator of the raw responses from the server.
         """
         ui = self.ui
         if ui.debugflag and ui.configbool('devel', 'debug.peer-request'):
             ui.debug('devel-peer-request: batched-content\n')
             for op, args in req:
                 msg = 'devel-peer-request:    - %s (%d arguments)\n'
                 ui.debug(msg % (op, len(args)))
 
+        unescapearg = wireprototypes.unescapebatcharg
+
         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, **pycompat.strkwargs(args))
 
     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[r'three'] = three
         if four is not None:
             opts[r'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.
 
 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)
 
     transportversion = wireprototypes.TRANSPORTS[proto.name]['version']
     commandtable = commandsv2 if transportversion == 2 else commands
     func, spec = commandtable[command]
 
     args = proto.getargs(spec)
 
     # Version 1 protocols define arguments as a list. Version 2 uses a dict.
     if isinstance(args, list):
         return func(repo, proto, *args)
     elif isinstance(args, dict):
         return func(repo, proto, **args)
     else:
         raise error.ProgrammingError('unexpected type returned from '
                                      'proto.getargs(): %s' % type(args))
 
 def options(cmd, keys, others):
     opts = {}
     for k in keys:
         if k in others:
             opts[k] = others[k]
             del others[k]
     if others:
         procutil.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)
         if v is not None:
             return v
 
     v = ui.configbool('server', 'bundle1.%s' % action)
     if v is not None:
         return v
 
     if gd:
         v = ui.configbool('server', 'bundle1gd')
         if v is not None:
             return v
 
     return ui.configbool('server', 'bundle1')
 
 def supportedcompengines(ui, role):
     """Obtain the list of supported compression engines for a request."""
     assert role in (util.CLIENTROLE, util.SERVERROLE)
 
     compengines = util.compengines.supportedwireengines(role)
 
     # Allow config to override default list and ordering.
     if role == util.SERVERROLE:
         configengines = ui.configlist('server', 'compressionengines')
         config = 'server.compressionengines'
     else:
         # This is currently implemented mainly to facilitate testing. In most
         # cases, the server should be in charge of choosing a compression engine
         # because a server has the most to lose from a sub-optimal choice. (e.g.
         # CPU DoS due to an expensive engine or a network DoS due to poor
         # compression ratio).
         configengines = ui.configlist('experimental',
                                       'clientcompressionengines')
         config = 'experimental.clientcompressionengines'
 
     # No explicit config. Filter out the ones that aren't supposed to be
     # advertised and return default ordering.
     if not configengines:
         attr = 'serverpriority' if role == util.SERVERROLE else 'clientpriority'
         return [e for e in compengines
                 if getattr(e.wireprotosupport(), attr) > 0]
 
     # If compression engines are listed in the config, assume there is a good
     # reason for it (like server operators wanting to achieve specific
     # performance characteristics). So fail fast if the config references
     # unusable compression engines.
     validnames = set(e.name() for e in compengines)
     invalidnames = set(e for e in configengines if e not in validnames)
     if invalidnames:
         raise error.Abort(_('invalid compression engine defined in %s: %s') %
                           (config, ', '.join(sorted(invalidnames))))
 
     compengines = [e for e in compengines if e.name() in configengines]
     compengines = sorted(compengines,
                          key=lambda e: configengines.index(e.name()))
 
     if not compengines:
         raise error.Abort(_('%s config option does not specify any known '
                             'compression engines') % config,
                           hint=_('usable compression engines: %s') %
                           ', '.sorted(validnames))
 
     return compengines
 
 class commandentry(object):
     """Represents a declared wire protocol command."""
     def __init__(self, func, args='', transports=None,
                  permission='push'):
         self.func = func
         self.args = args
         self.transports = transports or set()
         self.permission = permission
 
     def _merge(self, func, args):
         """Merge this instance with an incoming 2-tuple.
 
         This is called when a caller using the old 2-tuple API attempts
         to replace an instance. The incoming values are merged with
         data not captured by the 2-tuple and a new instance containing
         the union of the two objects is returned.
         """
         return commandentry(func, args=args, transports=set(self.transports),
                             permission=self.permission)
 
     # Old code treats instances as 2-tuples. So expose that interface.
     def __iter__(self):
         yield self.func
         yield self.args
 
     def __getitem__(self, i):
         if i == 0:
             return self.func
         elif i == 1:
             return self.args
         else:
             raise IndexError('can only access elements 0 and 1')
 
 class commanddict(dict):
     """Container for registered wire protocol commands.
 
     It behaves like a dict. But __setitem__ is overwritten to allow silent
     coercion of values from 2-tuples for API compatibility.
     """
     def __setitem__(self, k, v):
         if isinstance(v, commandentry):
             pass
         # Cast 2-tuples to commandentry instances.
         elif isinstance(v, tuple):
             if len(v) != 2:
                 raise ValueError('command tuples must have exactly 2 elements')
 
             # It is common for extensions to wrap wire protocol commands via
             # e.g. ``wireproto.commands[x] = (newfn, args)``. Because callers
             # doing this aren't aware of the new API that uses objects to store
             # command entries, we automatically merge old state with new.
             if k in self:
                 v = self[k]._merge(v[0], v[1])
             else:
                 # Use default values from @wireprotocommand.
                 v = commandentry(v[0], args=v[1],
                                  transports=set(wireprototypes.TRANSPORTS),
                                  permission='push')
         else:
             raise ValueError('command entries must be commandentry instances '
                              'or 2-tuples')
 
         return super(commanddict, self).__setitem__(k, v)
 
     def commandavailable(self, command, proto):
         """Determine if a command is available for the requested protocol."""
         assert proto.name in wireprototypes.TRANSPORTS
 
         entry = self.get(command)
 
         if not entry:
             return False
 
         if proto.name not in entry.transports:
             return False
 
         return True
 
 # Constants specifying which transports a wire protocol command should be
 # available on. For use with @wireprotocommand.
 POLICY_V1_ONLY = 'v1-only'
 POLICY_V2_ONLY = 'v2-only'
 
 # For version 1 transports.
 commands = commanddict()
 
 # For version 2 transports.
 commandsv2 = commanddict()
 
 def wireprotocommand(name, args=None, transportpolicy=POLICY_V1_ONLY,
                      permission='push'):
     """Decorator to declare a wire protocol command.
 
     ``name`` is the name of the wire protocol command being provided.
 
     ``args`` defines the named arguments accepted by the command. It is
     ideally a dict mapping argument names to their types. For backwards
     compatibility, it can be a space-delimited list of argument names. For
     version 1 transports, ``*`` denotes a special value that says to accept
     all named arguments.
 
     ``transportpolicy`` is a POLICY_* constant denoting which transports
     this wire protocol command should be exposed to. By default, commands
     are exposed to all wire protocol transports.
 
     ``permission`` defines the permission type needed to run this command.
     Can be ``push`` or ``pull``. These roughly map to read-write and read-only,
     respectively. Default is to assume command requires ``push`` permissions
     because otherwise commands not declaring their permissions could modify
     a repository that is supposed to be read-only.
     """
     if transportpolicy == POLICY_V1_ONLY:
         transports = {k for k, v in wireprototypes.TRANSPORTS.items()
                       if v['version'] == 1}
         transportversion = 1
     elif transportpolicy == POLICY_V2_ONLY:
         transports = {k for k, v in wireprototypes.TRANSPORTS.items()
                       if v['version'] == 2}
         transportversion = 2
     else:
         raise error.ProgrammingError('invalid transport policy value: %s' %
                                      transportpolicy)
 
     # Because SSHv2 is a mirror of SSHv1, we allow "batch" commands through to
     # SSHv2.
     # TODO undo this hack when SSH is using the unified frame protocol.
     if name == b'batch':
         transports.add(wireprototypes.SSHV2)
 
     if permission not in ('push', 'pull'):
         raise error.ProgrammingError('invalid wire protocol permission; '
                                      'got %s; expected "push" or "pull"' %
                                      permission)
 
     if transportversion == 1:
         if args is None:
             args = ''
 
         if not isinstance(args, bytes):
             raise error.ProgrammingError('arguments for version 1 commands '
                                          'must be declared as bytes')
     elif transportversion == 2:
         if args is None:
             args = {}
 
         if not isinstance(args, dict):
             raise error.ProgrammingError('arguments for version 2 commands '
                                          'must be declared as dicts')
 
     def register(func):
         if transportversion == 1:
             if name in commands:
                 raise error.ProgrammingError('%s command already registered '
                                              'for version 1' % name)
             commands[name] = commandentry(func, args=args,
                                           transports=transports,
                                           permission=permission)
         elif transportversion == 2:
             if name in commandsv2:
                 raise error.ProgrammingError('%s command already registered '
                                              'for version 2' % name)
 
             commandsv2[name] = commandentry(func, args=args,
                                             transports=transports,
                                             permission=permission)
         else:
             raise error.ProgrammingError('unhandled transport version: %d' %
                                          transportversion)
 
         return func
     return register
 
 # TODO define a more appropriate permissions type to use for this.
 @wireprotocommand('batch', 'cmds *', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def batch(repo, proto, cmds, others):
+    unescapearg = wireprototypes.unescapebatcharg
     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]
 
         # Validate that client has permissions to perform this command.
         perm = commands[op].permission
         assert perm in ('push', 'pull')
         proto.checkperm(perm)
 
         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, wireprototypes.ooberror):
             return result
 
         # For now, all batchable commands must return bytesresponse or
         # raw bytes (for backwards compatibility).
         assert isinstance(result, (wireprototypes.bytesresponse, bytes))
         if isinstance(result, wireprototypes.bytesresponse):
             result = result.data
-        res.append(escapearg(result))
+        res.append(wireprototypes.escapebatcharg(result))
 
     return wireprototypes.bytesresponse(';'.join(res))
 
 @wireprotocommand('between', 'pairs', transportpolicy=POLICY_V1_ONLY,
                   permission='pull')
 def between(repo, proto, pairs):
-    pairs = [decodelist(p, '-') for p in pairs.split(" ")]
+    pairs = [wireprototypes.decodelist(p, '-') for p in pairs.split(" ")]
     r = []
     for b in repo.between(pairs):
-        r.append(encodelist(b) + "\n")
+        r.append(wireprototypes.encodelist(b) + "\n")
 
     return wireprototypes.bytesresponse(''.join(r))
 
 @wireprotocommand('branchmap', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def branchmap(repo, proto):
     branchmap = repo.branchmap()
     heads = []
     for branch, nodes in branchmap.iteritems():
         branchname = urlreq.quote(encoding.fromlocal(branch))
-        branchnodes = encodelist(nodes)
+        branchnodes = wireprototypes.encodelist(nodes)
         heads.append('%s %s' % (branchname, branchnodes))
 
     return wireprototypes.bytesresponse('\n'.join(heads))
 
 @wireprotocommand('branches', 'nodes', transportpolicy=POLICY_V1_ONLY,
                   permission='pull')
 def branches(repo, proto, nodes):
-    nodes = decodelist(nodes)
+    nodes = wireprototypes.decodelist(nodes)
     r = []
     for b in repo.branches(nodes):
-        r.append(encodelist(b) + "\n")
+        r.append(wireprototypes.encodelist(b) + "\n")
 
     return wireprototypes.bytesresponse(''.join(r))
 
 @wireprotocommand('clonebundles', '', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 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 wireprototypes.bytesresponse(
         repo.vfs.tryread('clonebundles.manifest'))
 
 wireprotocaps = ['lookup', 'branchmap', 'pushkey',
                  'known', 'getbundle', 'unbundlehash']
 
 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)
 
     # Command of same name as capability isn't exposed to version 1 of
     # transports. So conditionally add it.
     if commands.commandavailable('changegroupsubset', proto):
         caps.append('changegroupsubset')
 
     if streamclone.allowservergeneration(repo):
         if repo.ui.configbool('server', 'preferuncompressed'):
             caps.append('stream-preferred')
         requiredformats = repo.requirements & repo.supportedformats
         # if our local revlogs are just revlogv1, add 'stream' cap
         if not requiredformats - {'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'):
         capsblob = bundle2.encodecaps(bundle2.getrepocaps(repo, role='server'))
         caps.append('bundle2=' + urlreq.quote(capsblob))
     caps.append('unbundle=%s' % ','.join(bundle2.bundlepriority))
 
     return proto.addcapabilities(repo, caps)
 
 # If you are writing an extension and consider wrapping this function. Wrap
 # `_capabilities` instead.
 @wireprotocommand('capabilities', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def capabilities(repo, proto):
     caps = _capabilities(repo, proto)
     return wireprototypes.bytesresponse(' '.join(sorted(caps)))
 
 @wireprotocommand('changegroup', 'roots', transportpolicy=POLICY_V1_ONLY,
                   permission='pull')
 def changegroup(repo, proto, roots):
-    nodes = decodelist(roots)
+    nodes = wireprototypes.decodelist(roots)
     outgoing = discovery.outgoing(repo, missingroots=nodes,
                                   missingheads=repo.heads())
     cg = changegroupmod.makechangegroup(repo, outgoing, '01', 'serve')
     gen = iter(lambda: cg.read(32768), '')
     return wireprototypes.streamres(gen=gen)
 
 @wireprotocommand('changegroupsubset', 'bases heads',
                   transportpolicy=POLICY_V1_ONLY,
                   permission='pull')
 def changegroupsubset(repo, proto, bases, heads):
-    bases = decodelist(bases)
-    heads = decodelist(heads)
+    bases = wireprototypes.decodelist(bases)
+    heads = wireprototypes.decodelist(heads)
     outgoing = discovery.outgoing(repo, missingroots=bases,
                                   missingheads=heads)
     cg = changegroupmod.makechangegroup(repo, outgoing, '01', 'serve')
     gen = iter(lambda: cg.read(32768), '')
     return wireprototypes.streamres(gen=gen)
 
 @wireprotocommand('debugwireargs', 'one two *',
                   permission='pull', transportpolicy=POLICY_V1_ONLY)
 def debugwireargs(repo, proto, one, two, others):
     # only accept optional args from the known set
     opts = options('debugwireargs', ['three', 'four'], others)
     return wireprototypes.bytesresponse(repo.debugwireargs(
         one, two, **pycompat.strkwargs(opts)))
 
 def find_pullbundle(repo, proto, opts, clheads, heads, common):
     """Return a file object for the first matching pullbundle.
 
     Pullbundles are specified in .hg/pullbundles.manifest similar to
     clonebundles.
     For each entry, the bundle specification is checked for compatibility:
     - Client features vs the BUNDLESPEC.
     - Revisions shared with the clients vs base revisions of the bundle.
       A bundle can be applied only if all its base revisions are known by
       the client.
     - At least one leaf of the bundle's DAG is missing on the client.
     - Every leaf of the bundle's DAG is part of node set the client wants.
       E.g. do not send a bundle of all changes if the client wants only
       one specific branch of many.
     """
     def decodehexstring(s):
         return set([h.decode('hex') for h in s.split(';')])
 
     manifest = repo.vfs.tryread('pullbundles.manifest')
     if not manifest:
         return None
     res = exchange.parseclonebundlesmanifest(repo, manifest)
     res = exchange.filterclonebundleentries(repo, res)
     if not res:
         return None
     cl = repo.changelog
     heads_anc = cl.ancestors([cl.rev(rev) for rev in heads], inclusive=True)
     common_anc = cl.ancestors([cl.rev(rev) for rev in common], inclusive=True)
     compformats = clientcompressionsupport(proto)
     for entry in res:
         if 'COMPRESSION' in entry and entry['COMPRESSION'] not in compformats:
             continue
         # No test yet for VERSION, since V2 is supported by any client
         # that advertises partial pulls
         if 'heads' in entry:
             try:
                 bundle_heads = decodehexstring(entry['heads'])
             except TypeError:
                 # Bad heads entry
                 continue
             if bundle_heads.issubset(common):
                 continue # Nothing new
             if all(cl.rev(rev) in common_anc for rev in bundle_heads):
                 continue # Still nothing new
             if any(cl.rev(rev) not in heads_anc and
                    cl.rev(rev) not in common_anc for rev in bundle_heads):
                 continue
         if 'bases' in entry:
             try:
                 bundle_bases = decodehexstring(entry['bases'])
             except TypeError:
                 # Bad bases entry
                 continue
             if not all(cl.rev(rev) in common_anc for rev in bundle_bases):
                 continue
         path = entry['URL']
         repo.ui.debug('sending pullbundle "%s"\n' % path)
         try:
             return repo.vfs.open(path)
         except IOError:
             repo.ui.debug('pullbundle "%s" not accessible\n' % path)
             continue
     return None
 
 @wireprotocommand('getbundle', '*', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 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)
+            opts[k] = wireprototypes.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')):
             if proto.name == 'http-v1':
                 return wireprototypes.ooberror(bundle2required)
             raise error.Abort(bundle2requiredmain,
                               hint=bundle2requiredhint)
 
     prefercompressed = True
 
     try:
         clheads = set(repo.changelog.heads())
         heads = set(opts.get('heads', set()))
         common = set(opts.get('common', set()))
         common.discard(nullid)
         if (repo.ui.configbool('server', 'pullbundle') and
             'partial-pull' in proto.getprotocaps()):
             # Check if a pre-built bundle covers this request.
             bundle = find_pullbundle(repo, proto, opts, clheads, heads, common)
             if bundle:
                 return wireprototypes.streamres(gen=util.filechunkiter(bundle),
                                                 prefer_uncompressed=True)
 
         if repo.ui.configbool('server', 'disablefullbundle'):
             # Check to see if this is a full clone.
             changegroup = opts.get('cg', True)
             if changegroup and not common and clheads == heads:
                 raise error.Abort(
                     _('server has pull-based clones disabled'),
                     hint=_('remove --pull if specified or upgrade Mercurial'))
 
         info, chunks = exchange.getbundlechunks(repo, 'serve',
                                                 **pycompat.strkwargs(opts))
         prefercompressed = info.get('prefercompressed', True)
     except error.Abort as exc:
         # cleanly forward Abort error to the client
         if not exchange.bundle2requested(opts.get('bundlecaps')):
             if proto.name == 'http-v1':
                 return wireprototypes.ooberror(pycompat.bytestr(exc) + '\n')
             raise # cannot do better for bundle1 + ssh
         # bundle2 request expect a bundle2 reply
         bundler = bundle2.bundle20(repo.ui)
         manargs = [('message', pycompat.bytestr(exc))]
         advargs = []
         if exc.hint is not None:
             advargs.append(('hint', exc.hint))
         bundler.addpart(bundle2.bundlepart('error:abort',
                                            manargs, advargs))
         chunks = bundler.getchunks()
         prefercompressed = False
 
     return wireprototypes.streamres(
         gen=chunks, prefer_uncompressed=not prefercompressed)
 
 @wireprotocommand('heads', permission='pull', transportpolicy=POLICY_V1_ONLY)
 def heads(repo, proto):
     h = repo.heads()
-    return wireprototypes.bytesresponse(encodelist(h) + '\n')
+    return wireprototypes.bytesresponse(wireprototypes.encodelist(h) + '\n')
 
 @wireprotocommand('hello', permission='pull', transportpolicy=POLICY_V1_ONLY)
 def hello(repo, proto):
     """Called as part of SSH handshake to obtain server info.
 
     Returns a list of lines describing interesting things about the
     server, in an RFC822-like format.
 
     Currently, the only one defined is ``capabilities``, which consists of a
     line of space separated tokens describing server abilities:
 
         capabilities: <token0> <token1> <token2>
     """
     caps = capabilities(repo, proto).data
     return wireprototypes.bytesresponse('capabilities: %s\n' % caps)
 
 @wireprotocommand('listkeys', 'namespace', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def listkeys(repo, proto, namespace):
     d = sorted(repo.listkeys(encoding.tolocal(namespace)).items())
     return wireprototypes.bytesresponse(pushkeymod.encodekeys(d))
 
 @wireprotocommand('lookup', 'key', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def lookup(repo, proto, key):
     try:
         k = encoding.tolocal(key)
         n = repo.lookup(k)
         r = hex(n)
         success = 1
     except Exception as inst:
         r = stringutil.forcebytestr(inst)
         success = 0
     return wireprototypes.bytesresponse('%d %s\n' % (success, r))
 
 @wireprotocommand('known', 'nodes *', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def known(repo, proto, nodes, others):
-    v = ''.join(b and '1' or '0' for b in repo.known(decodelist(nodes)))
+    v = ''.join(b and '1' or '0'
+                for b in repo.known(wireprototypes.decodelist(nodes)))
     return wireprototypes.bytesresponse(v)
 
 @wireprotocommand('protocaps', 'caps', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 def protocaps(repo, proto, caps):
     if proto.name == wireprototypes.SSHV1:
         proto._protocaps = set(caps.split(' '))
     return wireprototypes.bytesresponse('OK')
 
 @wireprotocommand('pushkey', 'namespace key old new', permission='push',
                   transportpolicy=POLICY_V1_ONLY)
 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 stringutil.escapestr(new) != 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
 
     with proto.mayberedirectstdio() as output:
         r = repo.pushkey(encoding.tolocal(namespace), encoding.tolocal(key),
                          encoding.tolocal(old), new) or False
 
     output = output.getvalue() if output else ''
     return wireprototypes.bytesresponse('%d\n%s' % (int(r), output))
 
 @wireprotocommand('stream_out', permission='pull',
                   transportpolicy=POLICY_V1_ONLY)
 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.
     '''
     return wireprototypes.streamreslegacy(
         streamclone.generatev1wireproto(repo))
 
 @wireprotocommand('unbundle', 'heads', permission='push',
                   transportpolicy=POLICY_V1_ONLY)
 def unbundle(repo, proto, heads):
-    their_heads = decodelist(heads)
+    their_heads = wireprototypes.decodelist(heads)
 
     with proto.mayberedirectstdio() as output:
         try:
             exchange.check_heads(repo, their_heads, 'preparing changes')
             cleanup = lambda: None
             try:
                 payload = proto.getpayload()
                 if repo.ui.configbool('server', 'streamunbundle'):
                     def cleanup():
                         # Ensure that the full payload is consumed, so
                         # that the connection doesn't contain trailing garbage.
                         for p in payload:
                             pass
                     fp = util.chunkbuffer(payload)
                 else:
                     # write bundle data to temporary file as it can be big
                     fp, tempname = None, None
                     def cleanup():
                         if fp:
                             fp.close()
                         if tempname:
                             os.unlink(tempname)
                     fd, tempname = tempfile.mkstemp(prefix='hg-unbundle-')
                     repo.ui.debug('redirecting incoming bundle to %s\n' %
                         tempname)
                     fp = os.fdopen(fd, pycompat.sysstr('wb+'))
                     r = 0
                     for p in payload:
                         fp.write(p)
                     fp.seek(0)
 
                 gen = exchange.readbundle(repo.ui, fp, None)
                 if (isinstance(gen, changegroupmod.cg1unpacker)
                     and not bundle1allowed(repo, 'push')):
                     if proto.name == 'http-v1':
                         # need to special case http because stderr do not get to
                         # the http client on failed push so we need to abuse
                         # some other error type to make sure the message get to
                         # the user.
                         return wireprototypes.ooberror(bundle2required)
                     raise error.Abort(bundle2requiredmain,
                                       hint=bundle2requiredhint)
 
                 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 wireprototypes.streamreslegacy(gen=r.getchunks())
                 return wireprototypes.pushres(
                     r, output.getvalue() if output else '')
 
             finally:
                 cleanup()
 
         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 procutil.stderr directly.
                     # We did not change it to minimise code change.
                     # This need to be moved to something proper.
                     # Feel free to do it.
                     procutil.stderr.write("abort: %s\n" % exc)
                     if exc.hint is not None:
                         procutil.stderr.write("(%s)\n" % exc.hint)
                     procutil.stderr.flush()
                     return wireprototypes.pushres(
                         0, output.getvalue() if output else '')
                 except error.PushRaced:
                     return wireprototypes.pusherr(
                         pycompat.bytestr(exc),
                         output.getvalue() if output else '')
 
             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', stringutil.forcebytestr(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', stringutil.forcebytestr(exc))])
             return wireprototypes.streamreslegacy(gen=bundler.getchunks())

mercurial/wireprototypes.py

@@ -1,171 +1,203
 # Copyright 2018 Gregory Szorc <[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
 
+from .node import (
+    bin,
+    hex,
+)
 from .thirdparty.zope import (
     interface as zi,
 )
 
 # Names of the SSH protocol implementations.
 SSHV1 = 'ssh-v1'
 # These are advertised over the wire. Increment the counters at the end
 # to reflect BC breakages.
 SSHV2 = 'exp-ssh-v2-0001'
 HTTPV2 = 'exp-http-v2-0001'
 
 # All available wire protocol transports.
 TRANSPORTS = {
     SSHV1: {
         'transport': 'ssh',
         'version': 1,
     },
     SSHV2: {
         'transport': 'ssh',
         # TODO mark as version 2 once all commands are implemented.
         'version': 1,
     },
     'http-v1': {
         'transport': 'http',
         'version': 1,
     },
     HTTPV2: {
         'transport': 'http',
         'version': 2,
     }
 }
 
 class bytesresponse(object):
     """A wire protocol response consisting of raw bytes."""
     def __init__(self, data):
         self.data = data
 
 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
 
 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, output):
         self.res = res
         self.output = output
 
 class pusherr(object):
     """wireproto reply: failure
 
     The call failed. The `self.res` attribute contains the error message.
     """
     def __init__(self, res, output):
         self.res = res
         self.output = output
 
 class streamres(object):
     """wireproto reply: binary stream
 
     The call was successful and the result is a stream.
 
     Accepts a generator containing chunks of data to be sent to the client.
 
     ``prefer_uncompressed`` indicates that the data is expected to be
     uncompressable and that the stream should therefore use the ``none``
     engine.
     """
     def __init__(self, gen=None, prefer_uncompressed=False):
         self.gen = gen
         self.prefer_uncompressed = prefer_uncompressed
 
 class streamreslegacy(object):
     """wireproto reply: uncompressed binary stream
 
     The call was successful and the result is a stream.
 
     Accepts a generator containing chunks of data to be sent to the client.
 
     Like ``streamres``, but sends an uncompressed data for "version 1" clients
     using the application/mercurial-0.1 media type.
     """
     def __init__(self, gen=None):
         self.gen = gen
 
 class cborresponse(object):
     """Encode the response value as CBOR."""
     def __init__(self, v):
         self.value = v
 
+# list of nodes encoding / decoding
+def decodelist(l, sep=' '):
+    if l:
+        return [bin(v) for v in  l.split(sep)]
+    return []
+
+def encodelist(l, sep=' '):
+    try:
+        return sep.join(map(hex, l))
+    except TypeError:
+        raise
+
+# batched call argument encoding
+
+def escapebatcharg(plain):
+    return (plain
+            .replace(':', ':c')
+            .replace(',', ':o')
+            .replace(';', ':s')
+            .replace('=', ':e'))
+
+def unescapebatcharg(escaped):
+    return (escaped
+            .replace(':e', '=')
+            .replace(':s', ';')
+            .replace(':o', ',')
+            .replace(':c', ':'))
+
 class baseprotocolhandler(zi.Interface):
     """Abstract base class for wire protocol handlers.
 
     A wire protocol handler serves as an interface between protocol command
     handlers and the wire protocol transport layer. Protocol handlers provide
     methods to read command arguments, redirect stdio for the duration of
     the request, handle response types, etc.
     """
 
     name = zi.Attribute(
         """The name of the protocol implementation.
 
         Used for uniquely identifying the transport type.
         """)
 
     def getargs(args):
         """return the value for arguments in <args>
 
         For version 1 transports, returns a list of values in the same
         order they appear in ``args``. For version 2 transports, returns
         a dict mapping argument name to value.
         """
 
     def getprotocaps():
         """Returns the list of protocol-level capabilities of client
 
         Returns a list of capabilities as declared by the client for
         the current request (or connection for stateful protocol handlers)."""
 
     def getpayload():
         """Provide a generator for the raw payload.
 
         The caller is responsible for ensuring that the full payload is
         processed.
         """
 
     def mayberedirectstdio():
         """Context manager to possibly redirect stdio.
 
         The context manager yields a file-object like object that receives
         stdout and stderr output when the context manager is active. Or it
         yields ``None`` if no I/O redirection occurs.
 
         The intent of this context manager is to capture stdio output
         so it may be sent in the response. Some transports support streaming
         stdio to the client in real time. For these transports, stdio output
         won't be captured.
         """
 
     def client():
         """Returns a string representation of this client (as bytes)."""
 
     def addcapabilities(repo, caps):
         """Adds advertised capabilities specific to this protocol.
 
         Receives the list of capabilities collected so far.
 
         Returns a list of capabilities. The passed in argument can be returned.
         """
 
     def checkperm(perm):
         """Validate that the client has permissions to perform a request.
 
         The argument is the permission required to proceed. If the client
         doesn't have that permission, the exception should raise or abort
         in a protocol specific manner.
         """