phases: move binary encoding into a reusable function

We want to use binary phases for pushing and pulling. We extract the encoding
function out of the bundle2 module first.

mercurial/bundle2.py

@@ -1,1939 +1,1934 b''
 # bundle2.py - generic container format to transmit arbitrary data.
 #
 # Copyright 2013 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.
 """Handling of the new bundle2 format
 
 The goal of bundle2 is to act as an atomically packet to transmit a set of
 payloads in an application agnostic way. It consist in a sequence of "parts"
 that will be handed to and processed by the application layer.
 
 
 General format architecture
 ===========================
 
 The format is architectured as follow
 
  - magic string
  - stream level parameters
  - payload parts (any number)
  - end of stream marker.
 
 the Binary format
 ============================
 
 All numbers are unsigned and big-endian.
 
 stream level parameters
 ------------------------
 
 Binary format is as follow
 
 :params size: int32
 
   The total number of Bytes used by the parameters
 
 :params value: arbitrary number of Bytes
 
   A blob of `params size` containing the serialized version of all stream level
   parameters.
 
   The blob contains a space separated list of parameters. Parameters with value
   are stored in the form `<name>=<value>`. Both name and value are urlquoted.
 
   Empty name are obviously forbidden.
 
   Name MUST start with a letter. If this first letter is lower case, the
   parameter is advisory and can be safely ignored. However when the first
   letter is capital, the parameter is mandatory and the bundling process MUST
   stop if he is not able to proceed it.
 
   Stream parameters use a simple textual format for two main reasons:
 
   - Stream level parameters should remain simple and we want to discourage any
     crazy usage.
   - Textual data allow easy human inspection of a bundle2 header in case of
     troubles.
 
   Any Applicative level options MUST go into a bundle2 part instead.
 
 Payload part
 ------------------------
 
 Binary format is as follow
 
 :header size: int32
 
   The total number of Bytes used by the part header. When the header is empty
   (size = 0) this is interpreted as the end of stream marker.
 
 :header:
 
     The header defines how to interpret the part. It contains two piece of
     data: the part type, and the part parameters.
 
     The part type is used to route an application level handler, that can
     interpret payload.
 
     Part parameters are passed to the application level handler.  They are
     meant to convey information that will help the application level object to
     interpret the part payload.
 
     The binary format of the header is has follow
 
     :typesize: (one byte)
 
     :parttype: alphanumerical part name (restricted to [a-zA-Z0-9_:-]*)
 
     :partid: A 32bits integer (unique in the bundle) that can be used to refer
              to this part.
 
     :parameters:
 
         Part's parameter may have arbitrary content, the binary structure is::
 
             <mandatory-count><advisory-count><param-sizes><param-data>
 
         :mandatory-count: 1 byte, number of mandatory parameters
 
         :advisory-count:  1 byte, number of advisory parameters
 
         :param-sizes:
 
             N couple of bytes, where N is the total number of parameters. Each
             couple contains (<size-of-key>, <size-of-value) for one parameter.
 
         :param-data:
 
             A blob of bytes from which each parameter key and value can be
             retrieved using the list of size couples stored in the previous
             field.
 
             Mandatory parameters comes first, then the advisory ones.
 
             Each parameter's key MUST be unique within the part.
 
 :payload:
 
     payload is a series of `<chunksize><chunkdata>`.
 
     `chunksize` is an int32, `chunkdata` are plain bytes (as much as
     `chunksize` says)` The payload part is concluded by a zero size chunk.
 
     The current implementation always produces either zero or one chunk.
     This is an implementation limitation that will ultimately be lifted.
 
     `chunksize` can be negative to trigger special case processing. No such
     processing is in place yet.
 
 Bundle processing
 ============================
 
 Each part is processed in order using a "part handler". Handler are registered
 for a certain part type.
 
 The matching of a part to its handler is case insensitive. The case of the
 part type is used to know if a part is mandatory or advisory. If the Part type
 contains any uppercase char it is considered mandatory. When no handler is
 known for a Mandatory part, the process is aborted and an exception is raised.
 If the part is advisory and no handler is known, the part is ignored. When the
 process is aborted, the full bundle is still read from the stream to keep the
 channel usable. But none of the part read from an abort are processed. In the
 future, dropping the stream may become an option for channel we do not care to
 preserve.
 """
 
 from __future__ import absolute_import, division
 
 import errno
 import re
 import string
 import struct
 import sys
 
 from .i18n import _
 from . import (
     changegroup,
     error,
     obsolete,
     phases,
     pushkey,
     pycompat,
     tags,
     url,
     util,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 _fstreamparamsize = '>i'
 _fpartheadersize = '>i'
 _fparttypesize = '>B'
 _fpartid = '>I'
 _fpayloadsize = '>i'
 _fpartparamcount = '>BB'
 
-_fphasesentry = struct.Struct('>i20s')
-
 preferedchunksize = 4096
 
 _parttypeforbidden = re.compile('[^a-zA-Z0-9_:-]')
 
 def outdebug(ui, message):
     """debug regarding output stream (bundling)"""
     if ui.configbool('devel', 'bundle2.debug'):
         ui.debug('bundle2-output: %s\n' % message)
 
 def indebug(ui, message):
     """debug on input stream (unbundling)"""
     if ui.configbool('devel', 'bundle2.debug'):
         ui.debug('bundle2-input: %s\n' % message)
 
 def validateparttype(parttype):
     """raise ValueError if a parttype contains invalid character"""
     if _parttypeforbidden.search(parttype):
         raise ValueError(parttype)
 
 def _makefpartparamsizes(nbparams):
     """return a struct format to read part parameter sizes
 
     The number parameters is variable so we need to build that format
     dynamically.
     """
     return '>'+('BB'*nbparams)
 
 parthandlermapping = {}
 
 def parthandler(parttype, params=()):
     """decorator that register a function as a bundle2 part handler
 
     eg::
 
         @parthandler('myparttype', ('mandatory', 'param', 'handled'))
         def myparttypehandler(...):
             '''process a part of type "my part".'''
             ...
     """
     validateparttype(parttype)
     def _decorator(func):
         lparttype = parttype.lower() # enforce lower case matching.
         assert lparttype not in parthandlermapping
         parthandlermapping[lparttype] = func
         func.params = frozenset(params)
         return func
     return _decorator
 
 class unbundlerecords(object):
     """keep record of what happens during and unbundle
 
     New records are added using `records.add('cat', obj)`. Where 'cat' is a
     category of record and obj is an arbitrary object.
 
     `records['cat']` will return all entries of this category 'cat'.
 
     Iterating on the object itself will yield `('category', obj)` tuples
     for all entries.
 
     All iterations happens in chronological order.
     """
 
     def __init__(self):
         self._categories = {}
         self._sequences = []
         self._replies = {}
 
     def add(self, category, entry, inreplyto=None):
         """add a new record of a given category.
 
         The entry can then be retrieved in the list returned by
         self['category']."""
         self._categories.setdefault(category, []).append(entry)
         self._sequences.append((category, entry))
         if inreplyto is not None:
             self.getreplies(inreplyto).add(category, entry)
 
     def getreplies(self, partid):
         """get the records that are replies to a specific part"""
         return self._replies.setdefault(partid, unbundlerecords())
 
     def __getitem__(self, cat):
         return tuple(self._categories.get(cat, ()))
 
     def __iter__(self):
         return iter(self._sequences)
 
     def __len__(self):
         return len(self._sequences)
 
     def __nonzero__(self):
         return bool(self._sequences)
 
     __bool__ = __nonzero__
 
 class bundleoperation(object):
     """an object that represents a single bundling process
 
     Its purpose is to carry unbundle-related objects and states.
 
     A new object should be created at the beginning of each bundle processing.
     The object is to be returned by the processing function.
 
     The object has very little content now it will ultimately contain:
     * an access to the repo the bundle is applied to,
     * a ui object,
     * a way to retrieve a transaction to add changes to the repo,
     * a way to record the result of processing each part,
     * a way to construct a bundle response when applicable.
     """
 
     def __init__(self, repo, transactiongetter, captureoutput=True):
         self.repo = repo
         self.ui = repo.ui
         self.records = unbundlerecords()
         self.reply = None
         self.captureoutput = captureoutput
         self.hookargs = {}
         self._gettransaction = transactiongetter
 
     def gettransaction(self):
         transaction = self._gettransaction()
 
         if self.hookargs:
             # the ones added to the transaction supercede those added
             # to the operation.
             self.hookargs.update(transaction.hookargs)
             transaction.hookargs = self.hookargs
 
         # mark the hookargs as flushed.  further attempts to add to
         # hookargs will result in an abort.
         self.hookargs = None
 
         return transaction
 
     def addhookargs(self, hookargs):
         if self.hookargs is None:
             raise error.ProgrammingError('attempted to add hookargs to '
                                          'operation after transaction started')
         self.hookargs.update(hookargs)
 
 class TransactionUnavailable(RuntimeError):
     pass
 
 def _notransaction():
     """default method to get a transaction while processing a bundle
 
     Raise an exception to highlight the fact that no transaction was expected
     to be created"""
     raise TransactionUnavailable()
 
 def applybundle(repo, unbundler, tr, source=None, url=None, **kwargs):
     # transform me into unbundler.apply() as soon as the freeze is lifted
     if isinstance(unbundler, unbundle20):
         tr.hookargs['bundle2'] = '1'
         if source is not None and 'source' not in tr.hookargs:
             tr.hookargs['source'] = source
         if url is not None and 'url' not in tr.hookargs:
             tr.hookargs['url'] = url
         return processbundle(repo, unbundler, lambda: tr)
     else:
         # the transactiongetter won't be used, but we might as well set it
         op = bundleoperation(repo, lambda: tr)
         _processchangegroup(op, unbundler, tr, source, url, **kwargs)
         return op
 
 class partiterator(object):
     def __init__(self, repo, op, unbundler):
         self.repo = repo
         self.op = op
         self.unbundler = unbundler
         self.iterator = None
         self.count = 0
         self.current = None
 
     def __enter__(self):
         def func():
             itr = enumerate(self.unbundler.iterparts())
             for count, p in itr:
                 self.count = count
                 self.current = p
                 yield p
                 p.seek(0, 2)
                 self.current = None
         self.iterator = func()
         return self.iterator
 
     def __exit__(self, type, exc, tb):
         if not self.iterator:
             return
 
         if exc:
             # If exiting or interrupted, do not attempt to seek the stream in
             # the finally block below. This makes abort faster.
             if (self.current and
                 not isinstance(exc, (SystemExit, KeyboardInterrupt))):
                 # consume the part content to not corrupt the stream.
                 self.current.seek(0, 2)
 
             # Any exceptions seeking to the end of the bundle at this point are
             # almost certainly related to the underlying stream being bad.
             # And, chances are that the exception we're handling is related to
             # getting in that bad state. So, we swallow the seeking error and
             # re-raise the original error.
             seekerror = False
             try:
                 for part in self.iterator:
                     # consume the bundle content
                     part.seek(0, 2)
             except Exception:
                 seekerror = True
 
             # Small hack to let caller code distinguish exceptions from bundle2
             # processing from processing the old format. This is mostly needed
             # to handle different return codes to unbundle according to the type
             # of bundle. We should probably clean up or drop this return code
             # craziness in a future version.
             exc.duringunbundle2 = True
             salvaged = []
             replycaps = None
             if self.op.reply is not None:
                 salvaged = self.op.reply.salvageoutput()
                 replycaps = self.op.reply.capabilities
             exc._replycaps = replycaps
             exc._bundle2salvagedoutput = salvaged
 
             # Re-raising from a variable loses the original stack. So only use
             # that form if we need to.
             if seekerror:
                 raise exc
 
         self.repo.ui.debug('bundle2-input-bundle: %i parts total\n' %
                            self.count)
 
 def processbundle(repo, unbundler, transactiongetter=None, op=None):
     """This function process a bundle, apply effect to/from a repo
 
     It iterates over each part then searches for and uses the proper handling
     code to process the part. Parts are processed in order.
 
     Unknown Mandatory part will abort the process.
 
     It is temporarily possible to provide a prebuilt bundleoperation to the
     function. This is used to ensure output is properly propagated in case of
     an error during the unbundling. This output capturing part will likely be
     reworked and this ability will probably go away in the process.
     """
     if op is None:
         if transactiongetter is None:
             transactiongetter = _notransaction
         op = bundleoperation(repo, transactiongetter)
     # todo:
     # - replace this is a init function soon.
     # - exception catching
     unbundler.params
     if repo.ui.debugflag:
         msg = ['bundle2-input-bundle:']
         if unbundler.params:
             msg.append(' %i params' % len(unbundler.params))
         if op._gettransaction is None or op._gettransaction is _notransaction:
             msg.append(' no-transaction')
         else:
             msg.append(' with-transaction')
         msg.append('\n')
         repo.ui.debug(''.join(msg))
 
     processparts(repo, op, unbundler)
 
     return op
 
 def processparts(repo, op, unbundler):
     with partiterator(repo, op, unbundler) as parts:
         for part in parts:
             _processpart(op, part)
 
 def _processchangegroup(op, cg, tr, source, url, **kwargs):
     ret = cg.apply(op.repo, tr, source, url, **kwargs)
     op.records.add('changegroup', {
         'return': ret,
     })
     return ret
 
 def _gethandler(op, part):
     status = 'unknown' # used by debug output
     try:
         handler = parthandlermapping.get(part.type)
         if handler is None:
             status = 'unsupported-type'
             raise error.BundleUnknownFeatureError(parttype=part.type)
         indebug(op.ui, 'found a handler for part %s' % part.type)
         unknownparams = part.mandatorykeys - handler.params
         if unknownparams:
             unknownparams = list(unknownparams)
             unknownparams.sort()
             status = 'unsupported-params (%s)' % ', '.join(unknownparams)
             raise error.BundleUnknownFeatureError(parttype=part.type,
                                                   params=unknownparams)
         status = 'supported'
     except error.BundleUnknownFeatureError as exc:
         if part.mandatory: # mandatory parts
             raise
         indebug(op.ui, 'ignoring unsupported advisory part %s' % exc)
         return # skip to part processing
     finally:
         if op.ui.debugflag:
             msg = ['bundle2-input-part: "%s"' % part.type]
             if not part.mandatory:
                 msg.append(' (advisory)')
             nbmp = len(part.mandatorykeys)
             nbap = len(part.params) - nbmp
             if nbmp or nbap:
                 msg.append(' (params:')
                 if nbmp:
                     msg.append(' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(' %i advisory' % nbmp)
                 msg.append(')')
             msg.append(' %s\n' % status)
             op.ui.debug(''.join(msg))
 
     return handler
 
 def _processpart(op, part):
     """process a single part from a bundle
 
     The part is guaranteed to have been fully consumed when the function exits
     (even if an exception is raised)."""
     handler = _gethandler(op, part)
     if handler is None:
         return
 
     # handler is called outside the above try block so that we don't
     # risk catching KeyErrors from anything other than the
     # parthandlermapping lookup (any KeyError raised by handler()
     # itself represents a defect of a different variety).
     output = None
     if op.captureoutput and op.reply is not None:
         op.ui.pushbuffer(error=True, subproc=True)
         output = ''
     try:
         handler(op, part)
     finally:
         if output is not None:
             output = op.ui.popbuffer()
         if output:
             outpart = op.reply.newpart('output', data=output,
                                        mandatory=False)
             outpart.addparam(
                 'in-reply-to', pycompat.bytestr(part.id), mandatory=False)
 
 def decodecaps(blob):
     """decode a bundle2 caps bytes blob into a dictionary
 
     The blob is a list of capabilities (one per line)
     Capabilities may have values using a line of the form::
 
         capability=value1,value2,value3
 
     The values are always a list."""
     caps = {}
     for line in blob.splitlines():
         if not line:
             continue
         if '=' not in line:
             key, vals = line, ()
         else:
             key, vals = line.split('=', 1)
             vals = vals.split(',')
         key = urlreq.unquote(key)
         vals = [urlreq.unquote(v) for v in vals]
         caps[key] = vals
     return caps
 
 def encodecaps(caps):
     """encode a bundle2 caps dictionary into a bytes blob"""
     chunks = []
     for ca in sorted(caps):
         vals = caps[ca]
         ca = urlreq.quote(ca)
         vals = [urlreq.quote(v) for v in vals]
         if vals:
             ca = "%s=%s" % (ca, ','.join(vals))
         chunks.append(ca)
     return '\n'.join(chunks)
 
 bundletypes = {
     "": ("", 'UN'),       # only when using unbundle on ssh and old http servers
                           # since the unification ssh accepts a header but there
                           # is no capability signaling it.
     "HG20": (), # special-cased below
     "HG10UN": ("HG10UN", 'UN'),
     "HG10BZ": ("HG10", 'BZ'),
     "HG10GZ": ("HG10GZ", 'GZ'),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = ['HG10GZ', 'HG10BZ', 'HG10UN']
 
 class bundle20(object):
     """represent an outgoing bundle2 container
 
     Use the `addparam` method to add stream level parameter. and `newpart` to
     populate it. Then call `getchunks` to retrieve all the binary chunks of
     data that compose the bundle2 container."""
 
     _magicstring = 'HG20'
 
     def __init__(self, ui, capabilities=()):
         self.ui = ui
         self._params = []
         self._parts = []
         self.capabilities = dict(capabilities)
         self._compengine = util.compengines.forbundletype('UN')
         self._compopts = None
 
     def setcompression(self, alg, compopts=None):
         """setup core part compression to <alg>"""
         if alg in (None, 'UN'):
             return
         assert not any(n.lower() == 'compression' for n, v in self._params)
         self.addparam('Compression', alg)
         self._compengine = util.compengines.forbundletype(alg)
         self._compopts = compopts
 
     @property
     def nbparts(self):
         """total number of parts added to the bundler"""
         return len(self._parts)
 
     # methods used to defines the bundle2 content
     def addparam(self, name, value=None):
         """add a stream level parameter"""
         if not name:
             raise ValueError(r'empty parameter name')
         if name[0:1] not in pycompat.bytestr(string.ascii_letters):
             raise ValueError(r'non letter first character: %s' % name)
         self._params.append((name, value))
 
     def addpart(self, part):
         """add a new part to the bundle2 container
 
         Parts contains the actual applicative payload."""
         assert part.id is None
         part.id = len(self._parts) # very cheap counter
         self._parts.append(part)
 
     def newpart(self, typeid, *args, **kwargs):
         """create a new part and add it to the containers
 
         As the part is directly added to the containers. For now, this means
         that any failure to properly initialize the part after calling
         ``newpart`` should result in a failure of the whole bundling process.
 
         You can still fall back to manually create and add if you need better
         control."""
         part = bundlepart(typeid, *args, **kwargs)
         self.addpart(part)
         return part
 
     # methods used to generate the bundle2 stream
     def getchunks(self):
         if self.ui.debugflag:
             msg = ['bundle2-output-bundle: "%s",' % self._magicstring]
             if self._params:
                 msg.append(' (%i params)' % len(self._params))
             msg.append(' %i parts total\n' % len(self._parts))
             self.ui.debug(''.join(msg))
         outdebug(self.ui, 'start emission of %s stream' % self._magicstring)
         yield self._magicstring
         param = self._paramchunk()
         outdebug(self.ui, 'bundle parameter: %s' % param)
         yield _pack(_fstreamparamsize, len(param))
         if param:
             yield param
         for chunk in self._compengine.compressstream(self._getcorechunk(),
                                                      self._compopts):
             yield chunk
 
     def _paramchunk(self):
         """return a encoded version of all stream parameters"""
         blocks = []
         for par, value in self._params:
             par = urlreq.quote(par)
             if value is not None:
                 value = urlreq.quote(value)
                 par = '%s=%s' % (par, value)
             blocks.append(par)
         return ' '.join(blocks)
 
     def _getcorechunk(self):
         """yield chunk for the core part of the bundle
 
         (all but headers and parameters)"""
         outdebug(self.ui, 'start of parts')
         for part in self._parts:
             outdebug(self.ui, 'bundle part: "%s"' % part.type)
             for chunk in part.getchunks(ui=self.ui):
                 yield chunk
         outdebug(self.ui, 'end of bundle')
         yield _pack(_fpartheadersize, 0)
 
 
     def salvageoutput(self):
         """return a list with a copy of all output parts in the bundle
 
         This is meant to be used during error handling to make sure we preserve
         server output"""
         salvaged = []
         for part in self._parts:
             if part.type.startswith('output'):
                 salvaged.append(part.copy())
         return salvaged
 
 
 class unpackermixin(object):
     """A mixin to extract bytes and struct data from a stream"""
 
     def __init__(self, fp):
         self._fp = fp
 
     def _unpack(self, format):
         """unpack this struct format from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         data = self._readexact(struct.calcsize(format))
         return _unpack(format, data)
 
     def _readexact(self, size):
         """read exactly <size> bytes from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         return changegroup.readexactly(self._fp, size)
 
 def getunbundler(ui, fp, magicstring=None):
     """return a valid unbundler object for a given magicstring"""
     if magicstring is None:
         magicstring = changegroup.readexactly(fp, 4)
     magic, version = magicstring[0:2], magicstring[2:4]
     if magic != 'HG':
         ui.debug(
             "error: invalid magic: %r (version %r), should be 'HG'\n"
             % (magic, version))
         raise error.Abort(_('not a Mercurial bundle'))
     unbundlerclass = formatmap.get(version)
     if unbundlerclass is None:
         raise error.Abort(_('unknown bundle version %s') % version)
     unbundler = unbundlerclass(ui, fp)
     indebug(ui, 'start processing of %s stream' % magicstring)
     return unbundler
 
 class unbundle20(unpackermixin):
     """interpret a bundle2 stream
 
     This class is fed with a binary stream and yields parts through its
     `iterparts` methods."""
 
     _magicstring = 'HG20'
 
     def __init__(self, ui, fp):
         """If header is specified, we do not read it out of the stream."""
         self.ui = ui
         self._compengine = util.compengines.forbundletype('UN')
         self._compressed = None
         super(unbundle20, self).__init__(fp)
 
     @util.propertycache
     def params(self):
         """dictionary of stream level parameters"""
         indebug(self.ui, 'reading bundle2 stream parameters')
         params = {}
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError('negative bundle param size: %i'
                                          % paramssize)
         if paramssize:
             params = self._readexact(paramssize)
             params = self._processallparams(params)
         return params
 
     def _processallparams(self, paramsblock):
         """"""
         params = util.sortdict()
         for p in paramsblock.split(' '):
             p = p.split('=', 1)
             p = [urlreq.unquote(i) for i in p]
             if len(p) < 2:
                 p.append(None)
             self._processparam(*p)
             params[p[0]] = p[1]
         return params
 
 
     def _processparam(self, name, value):
         """process a parameter, applying its effect if needed
 
         Parameter starting with a lower case letter are advisory and will be
         ignored when unknown.  Those starting with an upper case letter are
         mandatory and will this function will raise a KeyError when unknown.
 
         Note: no option are currently supported. Any input will be either
               ignored or failing.
         """
         if not name:
             raise ValueError(r'empty parameter name')
         if name[0:1] not in pycompat.bytestr(string.ascii_letters):
             raise ValueError(r'non letter first character: %s' % name)
         try:
             handler = b2streamparamsmap[name.lower()]
         except KeyError:
             if name[0:1].islower():
                 indebug(self.ui, "ignoring unknown parameter %s" % name)
             else:
                 raise error.BundleUnknownFeatureError(params=(name,))
         else:
             handler(self, name, value)
 
     def _forwardchunks(self):
         """utility to transfer a bundle2 as binary
 
         This is made necessary by the fact the 'getbundle' command over 'ssh'
         have no way to know then the reply end, relying on the bundle to be
         interpreted to know its end. This is terrible and we are sorry, but we
         needed to move forward to get general delta enabled.
         """
         yield self._magicstring
         assert 'params' not in vars(self)
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError('negative bundle param size: %i'
                                          % paramssize)
         yield _pack(_fstreamparamsize, paramssize)
         if paramssize:
             params = self._readexact(paramssize)
             self._processallparams(params)
             yield params
             assert self._compengine.bundletype == 'UN'
         # From there, payload might need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         emptycount = 0
         while emptycount < 2:
             # so we can brainlessly loop
             assert _fpartheadersize == _fpayloadsize
             size = self._unpack(_fpartheadersize)[0]
             yield _pack(_fpartheadersize, size)
             if size:
                 emptycount = 0
             else:
                 emptycount += 1
                 continue
             if size == flaginterrupt:
                 continue
             elif size < 0:
                 raise error.BundleValueError('negative chunk size: %i')
             yield self._readexact(size)
 
 
     def iterparts(self):
         """yield all parts contained in the stream"""
         # make sure param have been loaded
         self.params
         # From there, payload need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         indebug(self.ui, 'start extraction of bundle2 parts')
         headerblock = self._readpartheader()
         while headerblock is not None:
             part = unbundlepart(self.ui, headerblock, self._fp)
             yield part
             # Seek to the end of the part to force it's consumption so the next
             # part can be read. But then seek back to the beginning so the
             # code consuming this generator has a part that starts at 0.
             part.seek(0, 2)
             part.seek(0)
             headerblock = self._readpartheader()
         indebug(self.ui, 'end of bundle2 stream')
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError('negative part header size: %i'
                                          % headersize)
         indebug(self.ui, 'part header size: %i' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def compressed(self):
         self.params # load params
         return self._compressed
 
     def close(self):
         """close underlying file"""
         if util.safehasattr(self._fp, 'close'):
             return self._fp.close()
 
 formatmap = {'20': unbundle20}
 
 b2streamparamsmap = {}
 
 def b2streamparamhandler(name):
     """register a handler for a stream level parameter"""
     def decorator(func):
         assert name not in formatmap
         b2streamparamsmap[name] = func
         return func
     return decorator
 
 @b2streamparamhandler('compression')
 def processcompression(unbundler, param, value):
     """read compression parameter and install payload decompression"""
     if value not in util.compengines.supportedbundletypes:
         raise error.BundleUnknownFeatureError(params=(param,),
                                               values=(value,))
     unbundler._compengine = util.compengines.forbundletype(value)
     if value is not None:
         unbundler._compressed = True
 
 class bundlepart(object):
     """A bundle2 part contains application level payload
 
     The part `type` is used to route the part to the application level
     handler.
 
     The part payload is contained in ``part.data``. It could be raw bytes or a
     generator of byte chunks.
 
     You can add parameters to the part using the ``addparam`` method.
     Parameters can be either mandatory (default) or advisory. Remote side
     should be able to safely ignore the advisory ones.
 
     Both data and parameters cannot be modified after the generation has begun.
     """
 
     def __init__(self, parttype, mandatoryparams=(), advisoryparams=(),
                  data='', mandatory=True):
         validateparttype(parttype)
         self.id = None
         self.type = parttype
         self._data = data
         self._mandatoryparams = list(mandatoryparams)
         self._advisoryparams = list(advisoryparams)
         # checking for duplicated entries
         self._seenparams = set()
         for pname, __ in self._mandatoryparams + self._advisoryparams:
             if pname in self._seenparams:
                 raise error.ProgrammingError('duplicated params: %s' % pname)
             self._seenparams.add(pname)
         # status of the part's generation:
         # - None: not started,
         # - False: currently generated,
         # - True: generation done.
         self._generated = None
         self.mandatory = mandatory
 
     def __repr__(self):
         cls = "%s.%s" % (self.__class__.__module__, self.__class__.__name__)
         return ('<%s object at %x; id: %s; type: %s; mandatory: %s>'
                 % (cls, id(self), self.id, self.type, self.mandatory))
 
     def copy(self):
         """return a copy of the part
 
         The new part have the very same content but no partid assigned yet.
         Parts with generated data cannot be copied."""
         assert not util.safehasattr(self.data, 'next')
         return self.__class__(self.type, self._mandatoryparams,
                               self._advisoryparams, self._data, self.mandatory)
 
     # methods used to defines the part content
     @property
     def data(self):
         return self._data
 
     @data.setter
     def data(self, data):
         if self._generated is not None:
             raise error.ReadOnlyPartError('part is being generated')
         self._data = data
 
     @property
     def mandatoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._mandatoryparams)
 
     @property
     def advisoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._advisoryparams)
 
     def addparam(self, name, value='', mandatory=True):
         """add a parameter to the part
 
         If 'mandatory' is set to True, the remote handler must claim support
         for this parameter or the unbundling will be aborted.
 
         The 'name' and 'value' cannot exceed 255 bytes each.
         """
         if self._generated is not None:
             raise error.ReadOnlyPartError('part is being generated')
         if name in self._seenparams:
             raise ValueError('duplicated params: %s' % name)
         self._seenparams.add(name)
         params = self._advisoryparams
         if mandatory:
             params = self._mandatoryparams
         params.append((name, value))
 
     # methods used to generates the bundle2 stream
     def getchunks(self, ui):
         if self._generated is not None:
             raise error.ProgrammingError('part can only be consumed once')
         self._generated = False
 
         if ui.debugflag:
             msg = ['bundle2-output-part: "%s"' % self.type]
             if not self.mandatory:
                 msg.append(' (advisory)')
             nbmp = len(self.mandatoryparams)
             nbap = len(self.advisoryparams)
             if nbmp or nbap:
                 msg.append(' (params:')
                 if nbmp:
                     msg.append(' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(' %i advisory' % nbmp)
                 msg.append(')')
             if not self.data:
                 msg.append(' empty payload')
             elif (util.safehasattr(self.data, 'next')
                   or util.safehasattr(self.data, '__next__')):
                 msg.append(' streamed payload')
             else:
                 msg.append(' %i bytes payload' % len(self.data))
             msg.append('\n')
             ui.debug(''.join(msg))
 
         #### header
         if self.mandatory:
             parttype = self.type.upper()
         else:
             parttype = self.type.lower()
         outdebug(ui, 'part %s: "%s"' % (pycompat.bytestr(self.id), parttype))
         ## parttype
         header = [_pack(_fparttypesize, len(parttype)),
                   parttype, _pack(_fpartid, self.id),
                  ]
         ## parameters
         # count
         manpar = self.mandatoryparams
         advpar = self.advisoryparams
         header.append(_pack(_fpartparamcount, len(manpar), len(advpar)))
         # size
         parsizes = []
         for key, value in manpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         for key, value in advpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         paramsizes = _pack(_makefpartparamsizes(len(parsizes) // 2), *parsizes)
         header.append(paramsizes)
         # key, value
         for key, value in manpar:
             header.append(key)
             header.append(value)
         for key, value in advpar:
             header.append(key)
             header.append(value)
         ## finalize header
         try:
             headerchunk = ''.join(header)
         except TypeError:
             raise TypeError(r'Found a non-bytes trying to '
                             r'build bundle part header: %r' % header)
         outdebug(ui, 'header chunk size: %i' % len(headerchunk))
         yield _pack(_fpartheadersize, len(headerchunk))
         yield headerchunk
         ## payload
         try:
             for chunk in self._payloadchunks():
                 outdebug(ui, 'payload chunk size: %i' % len(chunk))
                 yield _pack(_fpayloadsize, len(chunk))
                 yield chunk
         except GeneratorExit:
             # GeneratorExit means that nobody is listening for our
             # results anyway, so just bail quickly rather than trying
             # to produce an error part.
             ui.debug('bundle2-generatorexit\n')
             raise
         except BaseException as exc:
             bexc = util.forcebytestr(exc)
             # backup exception data for later
             ui.debug('bundle2-input-stream-interrupt: encoding exception %s'
                      % bexc)
             tb = sys.exc_info()[2]
             msg = 'unexpected error: %s' % bexc
             interpart = bundlepart('error:abort', [('message', msg)],
                                    mandatory=False)
             interpart.id = 0
             yield _pack(_fpayloadsize, -1)
             for chunk in interpart.getchunks(ui=ui):
                 yield chunk
             outdebug(ui, 'closing payload chunk')
             # abort current part payload
             yield _pack(_fpayloadsize, 0)
             pycompat.raisewithtb(exc, tb)
         # end of payload
         outdebug(ui, 'closing payload chunk')
         yield _pack(_fpayloadsize, 0)
         self._generated = True
 
     def _payloadchunks(self):
         """yield chunks of a the part payload
 
         Exists to handle the different methods to provide data to a part."""
         # we only support fixed size data now.
         # This will be improved in the future.
         if (util.safehasattr(self.data, 'next')
             or util.safehasattr(self.data, '__next__')):
             buff = util.chunkbuffer(self.data)
             chunk = buff.read(preferedchunksize)
             while chunk:
                 yield chunk
                 chunk = buff.read(preferedchunksize)
         elif len(self.data):
             yield self.data
 
 
 flaginterrupt = -1
 
 class interrupthandler(unpackermixin):
     """read one part and process it with restricted capability
 
     This allows to transmit exception raised on the producer size during part
     iteration while the consumer is reading a part.
 
     Part processed in this manner only have access to a ui object,"""
 
     def __init__(self, ui, fp):
         super(interrupthandler, self).__init__(fp)
         self.ui = ui
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError('negative part header size: %i'
                                          % headersize)
         indebug(self.ui, 'part header size: %i\n' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def __call__(self):
 
         self.ui.debug('bundle2-input-stream-interrupt:'
                       ' opening out of band context\n')
         indebug(self.ui, 'bundle2 stream interruption, looking for a part.')
         headerblock = self._readpartheader()
         if headerblock is None:
             indebug(self.ui, 'no part found during interruption.')
             return
         part = unbundlepart(self.ui, headerblock, self._fp)
         op = interruptoperation(self.ui)
         hardabort = False
         try:
             _processpart(op, part)
         except (SystemExit, KeyboardInterrupt):
             hardabort = True
             raise
         finally:
             if not hardabort:
                 part.seek(0, 2)
         self.ui.debug('bundle2-input-stream-interrupt:'
                       ' closing out of band context\n')
 
 class interruptoperation(object):
     """A limited operation to be use by part handler during interruption
 
     It only have access to an ui object.
     """
 
     def __init__(self, ui):
         self.ui = ui
         self.reply = None
         self.captureoutput = False
 
     @property
     def repo(self):
         raise error.ProgrammingError('no repo access from stream interruption')
 
     def gettransaction(self):
         raise TransactionUnavailable('no repo access from stream interruption')
 
 class unbundlepart(unpackermixin):
     """a bundle part read from a bundle"""
 
     def __init__(self, ui, header, fp):
         super(unbundlepart, self).__init__(fp)
         self._seekable = (util.safehasattr(fp, 'seek') and
                           util.safehasattr(fp, 'tell'))
         self.ui = ui
         # unbundle state attr
         self._headerdata = header
         self._headeroffset = 0
         self._initialized = False
         self.consumed = False
         # part data
         self.id = None
         self.type = None
         self.mandatoryparams = None
         self.advisoryparams = None
         self.params = None
         self.mandatorykeys = ()
         self._payloadstream = None
         self._readheader()
         self._mandatory = None
         self._chunkindex = [] #(payload, file) position tuples for chunk starts
         self._pos = 0
 
     def _fromheader(self, size):
         """return the next <size> byte from the header"""
         offset = self._headeroffset
         data = self._headerdata[offset:(offset + size)]
         self._headeroffset = offset + size
         return data
 
     def _unpackheader(self, format):
         """read given format from header
 
         This automatically compute the size of the format to read."""
         data = self._fromheader(struct.calcsize(format))
         return _unpack(format, data)
 
     def _initparams(self, mandatoryparams, advisoryparams):
         """internal function to setup all logic related parameters"""
         # make it read only to prevent people touching it by mistake.
         self.mandatoryparams = tuple(mandatoryparams)
         self.advisoryparams  = tuple(advisoryparams)
         # user friendly UI
         self.params = util.sortdict(self.mandatoryparams)
         self.params.update(self.advisoryparams)
         self.mandatorykeys = frozenset(p[0] for p in mandatoryparams)
 
     def _payloadchunks(self, chunknum=0):
         '''seek to specified chunk and start yielding data'''
         if len(self._chunkindex) == 0:
             assert chunknum == 0, 'Must start with chunk 0'
             self._chunkindex.append((0, self._tellfp()))
         else:
             assert chunknum < len(self._chunkindex), \
                    'Unknown chunk %d' % chunknum
             self._seekfp(self._chunkindex[chunknum][1])
 
         pos = self._chunkindex[chunknum][0]
         payloadsize = self._unpack(_fpayloadsize)[0]
         indebug(self.ui, 'payload chunk size: %i' % payloadsize)
         while payloadsize:
             if payloadsize == flaginterrupt:
                 # interruption detection, the handler will now read a
                 # single part and process it.
                 interrupthandler(self.ui, self._fp)()
             elif payloadsize < 0:
                 msg = 'negative payload chunk size: %i' %  payloadsize
                 raise error.BundleValueError(msg)
             else:
                 result = self._readexact(payloadsize)
                 chunknum += 1
                 pos += payloadsize
                 if chunknum == len(self._chunkindex):
                     self._chunkindex.append((pos, self._tellfp()))
                 yield result
             payloadsize = self._unpack(_fpayloadsize)[0]
             indebug(self.ui, 'payload chunk size: %i' % payloadsize)
 
     def _findchunk(self, pos):
         '''for a given payload position, return a chunk number and offset'''
         for chunk, (ppos, fpos) in enumerate(self._chunkindex):
             if ppos == pos:
                 return chunk, 0
             elif ppos > pos:
                 return chunk - 1, pos - self._chunkindex[chunk - 1][0]
         raise ValueError('Unknown chunk')
 
     def _readheader(self):
         """read the header and setup the object"""
         typesize = self._unpackheader(_fparttypesize)[0]
         self.type = self._fromheader(typesize)
         indebug(self.ui, 'part type: "%s"' % self.type)
         self.id = self._unpackheader(_fpartid)[0]
         indebug(self.ui, 'part id: "%s"' % pycompat.bytestr(self.id))
         # extract mandatory bit from type
         self.mandatory = (self.type != self.type.lower())
         self.type = self.type.lower()
         ## reading parameters
         # param count
         mancount, advcount = self._unpackheader(_fpartparamcount)
         indebug(self.ui, 'part parameters: %i' % (mancount + advcount))
         # param size
         fparamsizes = _makefpartparamsizes(mancount + advcount)
         paramsizes = self._unpackheader(fparamsizes)
         # make it a list of couple again
         paramsizes = list(zip(paramsizes[::2], paramsizes[1::2]))
         # split mandatory from advisory
         mansizes = paramsizes[:mancount]
         advsizes = paramsizes[mancount:]
         # retrieve param value
         manparams = []
         for key, value in mansizes:
             manparams.append((self._fromheader(key), self._fromheader(value)))
         advparams = []
         for key, value in advsizes:
             advparams.append((self._fromheader(key), self._fromheader(value)))
         self._initparams(manparams, advparams)
         ## part payload
         self._payloadstream = util.chunkbuffer(self._payloadchunks())
         # we read the data, tell it
         self._initialized = True
 
     def read(self, size=None):
         """read payload data"""
         if not self._initialized:
             self._readheader()
         if size is None:
             data = self._payloadstream.read()
         else:
             data = self._payloadstream.read(size)
         self._pos += len(data)
         if size is None or len(data) < size:
             if not self.consumed and self._pos:
                 self.ui.debug('bundle2-input-part: total payload size %i\n'
                               % self._pos)
             self.consumed = True
         return data
 
     def tell(self):
         return self._pos
 
     def seek(self, offset, whence=0):
         if whence == 0:
             newpos = offset
         elif whence == 1:
             newpos = self._pos + offset
         elif whence == 2:
             if not self.consumed:
                 self.read()
             newpos = self._chunkindex[-1][0] - offset
         else:
             raise ValueError('Unknown whence value: %r' % (whence,))
 
         if newpos > self._chunkindex[-1][0] and not self.consumed:
             self.read()
         if not 0 <= newpos <= self._chunkindex[-1][0]:
             raise ValueError('Offset out of range')
 
         if self._pos != newpos:
             chunk, internaloffset = self._findchunk(newpos)
             self._payloadstream = util.chunkbuffer(self._payloadchunks(chunk))
             adjust = self.read(internaloffset)
             if len(adjust) != internaloffset:
                 raise error.Abort(_('Seek failed\n'))
             self._pos = newpos
 
     def _seekfp(self, offset, whence=0):
         """move the underlying file pointer
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             return self._fp.seek(offset, whence)
         else:
             raise NotImplementedError(_('File pointer is not seekable'))
 
     def _tellfp(self):
         """return the file offset, or None if file is not seekable
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             try:
                 return self._fp.tell()
             except IOError as e:
                 if e.errno == errno.ESPIPE:
                     self._seekable = False
                 else:
                     raise
         return None
 
 # These are only the static capabilities.
 # Check the 'getrepocaps' function for the rest.
 capabilities = {'HG20': (),
                 'error': ('abort', 'unsupportedcontent', 'pushraced',
                           'pushkey'),
                 'listkeys': (),
                 'pushkey': (),
                 'digests': tuple(sorted(util.DIGESTS.keys())),
                 'remote-changegroup': ('http', 'https'),
                 'hgtagsfnodes': (),
                }
 
 def getrepocaps(repo, allowpushback=False):
     """return the bundle2 capabilities for a given repo
 
     Exists to allow extensions (like evolution) to mutate the capabilities.
     """
     caps = capabilities.copy()
     caps['changegroup'] = tuple(sorted(
         changegroup.supportedincomingversions(repo)))
     if obsolete.isenabled(repo, obsolete.exchangeopt):
         supportedformat = tuple('V%i' % v for v in obsolete.formats)
         caps['obsmarkers'] = supportedformat
     if allowpushback:
         caps['pushback'] = ()
     cpmode = repo.ui.config('server', 'concurrent-push-mode')
     if cpmode == 'check-related':
         caps['checkheads'] = ('related',)
     return caps
 
 def bundle2caps(remote):
     """return the bundle capabilities of a peer as dict"""
     raw = remote.capable('bundle2')
     if not raw and raw != '':
         return {}
     capsblob = urlreq.unquote(remote.capable('bundle2'))
     return decodecaps(capsblob)
 
 def obsmarkersversion(caps):
     """extract the list of supported obsmarkers versions from a bundle2caps dict
     """
     obscaps = caps.get('obsmarkers', ())
     return [int(c[1:]) for c in obscaps if c.startswith('V')]
 
 def writenewbundle(ui, repo, source, filename, bundletype, outgoing, opts,
                    vfs=None, compression=None, compopts=None):
     if bundletype.startswith('HG10'):
         cg = changegroup.makechangegroup(repo, outgoing, '01', source)
         return writebundle(ui, cg, filename, bundletype, vfs=vfs,
                            compression=compression, compopts=compopts)
     elif not bundletype.startswith('HG20'):
         raise error.ProgrammingError('unknown bundle type: %s' % bundletype)
 
     caps = {}
     if 'obsolescence' in opts:
         caps['obsmarkers'] = ('V1',)
     bundle = bundle20(ui, caps)
     bundle.setcompression(compression, compopts)
     _addpartsfromopts(ui, repo, bundle, source, outgoing, opts)
     chunkiter = bundle.getchunks()
 
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 def _addpartsfromopts(ui, repo, bundler, source, outgoing, opts):
     # We should eventually reconcile this logic with the one behind
     # 'exchange.getbundle2partsgenerator'.
     #
     # The type of input from 'getbundle' and 'writenewbundle' are a bit
     # different right now. So we keep them separated for now for the sake of
     # simplicity.
 
     # we always want a changegroup in such bundle
     cgversion = opts.get('cg.version')
     if cgversion is None:
         cgversion = changegroup.safeversion(repo)
     cg = changegroup.makechangegroup(repo, outgoing, cgversion, source)
     part = bundler.newpart('changegroup', data=cg.getchunks())
     part.addparam('version', cg.version)
     if 'clcount' in cg.extras:
         part.addparam('nbchanges', '%d' % cg.extras['clcount'],
                       mandatory=False)
     if opts.get('phases') and repo.revs('%ln and secret()',
                                         outgoing.missingheads):
         part.addparam('targetphase', '%d' % phases.secret, mandatory=False)
 
     addparttagsfnodescache(repo, bundler, outgoing)
 
     if opts.get('obsolescence', False):
         obsmarkers = repo.obsstore.relevantmarkers(outgoing.missing)
         buildobsmarkerspart(bundler, obsmarkers)
 
     if opts.get('phases', False):
         headsbyphase = phases.subsetphaseheads(repo, outgoing.missing)
-        phasedata = []
-        for phase in phases.allphases:
-            for head in headsbyphase[phase]:
-                phasedata.append(_fphasesentry.pack(phase, head))
-        bundler.newpart('phase-heads', data=''.join(phasedata))
+        phasedata = phases.binaryencode(headsbyphase)
+        bundler.newpart('phase-heads', data=phasedata)
 
 def addparttagsfnodescache(repo, bundler, outgoing):
     # we include the tags fnode cache for the bundle changeset
     # (as an optional parts)
     cache = tags.hgtagsfnodescache(repo.unfiltered())
     chunks = []
 
     # .hgtags fnodes are only relevant for head changesets. While we could
     # transfer values for all known nodes, there will likely be little to
     # no benefit.
     #
     # We don't bother using a generator to produce output data because
     # a) we only have 40 bytes per head and even esoteric numbers of heads
     # consume little memory (1M heads is 40MB) b) we don't want to send the
     # part if we don't have entries and knowing if we have entries requires
     # cache lookups.
     for node in outgoing.missingheads:
         # Don't compute missing, as this may slow down serving.
         fnode = cache.getfnode(node, computemissing=False)
         if fnode is not None:
             chunks.extend([node, fnode])
 
     if chunks:
         bundler.newpart('hgtagsfnodes', data=''.join(chunks))
 
 def buildobsmarkerspart(bundler, markers):
     """add an obsmarker part to the bundler with <markers>
 
     No part is created if markers is empty.
     Raises ValueError if the bundler doesn't support any known obsmarker format.
     """
     if not markers:
         return None
 
     remoteversions = obsmarkersversion(bundler.capabilities)
     version = obsolete.commonversion(remoteversions)
     if version is None:
         raise ValueError('bundler does not support common obsmarker format')
     stream = obsolete.encodemarkers(markers, True, version=version)
     return bundler.newpart('obsmarkers', data=stream)
 
 def writebundle(ui, cg, filename, bundletype, vfs=None, compression=None,
                 compopts=None):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     if bundletype == "HG20":
         bundle = bundle20(ui)
         bundle.setcompression(compression, compopts)
         part = bundle.newpart('changegroup', data=cg.getchunks())
         part.addparam('version', cg.version)
         if 'clcount' in cg.extras:
             part.addparam('nbchanges', '%d' % cg.extras['clcount'],
                           mandatory=False)
         chunkiter = bundle.getchunks()
     else:
         # compression argument is only for the bundle2 case
         assert compression is None
         if cg.version != '01':
             raise error.Abort(_('old bundle types only supports v1 '
                                 'changegroups'))
         header, comp = bundletypes[bundletype]
         if comp not in util.compengines.supportedbundletypes:
             raise error.Abort(_('unknown stream compression type: %s')
                               % comp)
         compengine = util.compengines.forbundletype(comp)
         def chunkiter():
             yield header
             for chunk in compengine.compressstream(cg.getchunks(), compopts):
                 yield chunk
         chunkiter = chunkiter()
 
     # parse the changegroup data, otherwise we will block
     # in case of sshrepo because we don't know the end of the stream
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 def combinechangegroupresults(op):
     """logic to combine 0 or more addchangegroup results into one"""
     results = [r.get('return', 0)
                for r in op.records['changegroup']]
     changedheads = 0
     result = 1
     for ret in results:
         # If any changegroup result is 0, return 0
         if ret == 0:
             result = 0
             break
         if ret < -1:
             changedheads += ret + 1
         elif ret > 1:
             changedheads += ret - 1
     if changedheads > 0:
         result = 1 + changedheads
     elif changedheads < 0:
         result = -1 + changedheads
     return result
 
 @parthandler('changegroup', ('version', 'nbchanges', 'treemanifest',
                              'targetphase'))
 def handlechangegroup(op, inpart):
     """apply a changegroup part on the repo
 
     This is a very early implementation that will massive rework before being
     inflicted to any end-user.
     """
     tr = op.gettransaction()
     unpackerversion = inpart.params.get('version', '01')
     # We should raise an appropriate exception here
     cg = changegroup.getunbundler(unpackerversion, inpart, None)
     # the source and url passed here are overwritten by the one contained in
     # the transaction.hookargs argument. So 'bundle2' is a placeholder
     nbchangesets = None
     if 'nbchanges' in inpart.params:
         nbchangesets = int(inpart.params.get('nbchanges'))
     if ('treemanifest' in inpart.params and
         'treemanifest' not in op.repo.requirements):
         if len(op.repo.changelog) != 0:
             raise error.Abort(_(
                 "bundle contains tree manifests, but local repo is "
                 "non-empty and does not use tree manifests"))
         op.repo.requirements.add('treemanifest')
         op.repo._applyopenerreqs()
         op.repo._writerequirements()
     extrakwargs = {}
     targetphase = inpart.params.get('targetphase')
     if targetphase is not None:
         extrakwargs['targetphase'] = int(targetphase)
     ret = _processchangegroup(op, cg, tr, 'bundle2', 'bundle2',
                               expectedtotal=nbchangesets, **extrakwargs)
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart('reply:changegroup', mandatory=False)
         part.addparam(
             'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False)
         part.addparam('return', '%i' % ret, mandatory=False)
     assert not inpart.read()
 
 _remotechangegroupparams = tuple(['url', 'size', 'digests'] +
     ['digest:%s' % k for k in util.DIGESTS.keys()])
 @parthandler('remote-changegroup', _remotechangegroupparams)
 def handleremotechangegroup(op, inpart):
     """apply a bundle10 on the repo, given an url and validation information
 
     All the information about the remote bundle to import are given as
     parameters. The parameters include:
       - url: the url to the bundle10.
       - size: the bundle10 file size. It is used to validate what was
         retrieved by the client matches the server knowledge about the bundle.
       - digests: a space separated list of the digest types provided as
         parameters.
       - digest:<digest-type>: the hexadecimal representation of the digest with
         that name. Like the size, it is used to validate what was retrieved by
         the client matches what the server knows about the bundle.
 
     When multiple digest types are given, all of them are checked.
     """
     try:
         raw_url = inpart.params['url']
     except KeyError:
         raise error.Abort(_('remote-changegroup: missing "%s" param') % 'url')
     parsed_url = util.url(raw_url)
     if parsed_url.scheme not in capabilities['remote-changegroup']:
         raise error.Abort(_('remote-changegroup does not support %s urls') %
             parsed_url.scheme)
 
     try:
         size = int(inpart.params['size'])
     except ValueError:
         raise error.Abort(_('remote-changegroup: invalid value for param "%s"')
             % 'size')
     except KeyError:
         raise error.Abort(_('remote-changegroup: missing "%s" param') % 'size')
 
     digests = {}
     for typ in inpart.params.get('digests', '').split():
         param = 'digest:%s' % typ
         try:
             value = inpart.params[param]
         except KeyError:
             raise error.Abort(_('remote-changegroup: missing "%s" param') %
                 param)
         digests[typ] = value
 
     real_part = util.digestchecker(url.open(op.ui, raw_url), size, digests)
 
     tr = op.gettransaction()
     from . import exchange
     cg = exchange.readbundle(op.repo.ui, real_part, raw_url)
     if not isinstance(cg, changegroup.cg1unpacker):
         raise error.Abort(_('%s: not a bundle version 1.0') %
             util.hidepassword(raw_url))
     ret = _processchangegroup(op, cg, tr, 'bundle2', 'bundle2')
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart('reply:changegroup')
         part.addparam(
             'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False)
         part.addparam('return', '%i' % ret, mandatory=False)
     try:
         real_part.validate()
     except error.Abort as e:
         raise error.Abort(_('bundle at %s is corrupted:\n%s') %
             (util.hidepassword(raw_url), str(e)))
     assert not inpart.read()
 
 @parthandler('reply:changegroup', ('return', 'in-reply-to'))
 def handlereplychangegroup(op, inpart):
     ret = int(inpart.params['return'])
     replyto = int(inpart.params['in-reply-to'])
     op.records.add('changegroup', {'return': ret}, replyto)
 
 @parthandler('check:heads')
 def handlecheckheads(op, inpart):
     """check that head of the repo did not change
 
     This is used to detect a push race when using unbundle.
     This replaces the "heads" argument of unbundle."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # Trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool('experimental', 'bundle2lazylocking'):
         op.gettransaction()
     if sorted(heads) != sorted(op.repo.heads()):
         raise error.PushRaced('repository changed while pushing - '
                               'please try again')
 
 @parthandler('check:updated-heads')
 def handlecheckupdatedheads(op, inpart):
     """check for race on the heads touched by a push
 
     This is similar to 'check:heads' but focus on the heads actually updated
     during the push. If other activities happen on unrelated heads, it is
     ignored.
 
     This allow server with high traffic to avoid push contention as long as
     unrelated parts of the graph are involved."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool('experimental', 'bundle2lazylocking'):
         op.gettransaction()
 
     currentheads = set()
     for ls in op.repo.branchmap().itervalues():
         currentheads.update(ls)
 
     for h in heads:
         if h not in currentheads:
             raise error.PushRaced('repository changed while pushing - '
                                   'please try again')
 
 @parthandler('output')
 def handleoutput(op, inpart):
     """forward output captured on the server to the client"""
     for line in inpart.read().splitlines():
         op.ui.status(_('remote: %s\n') % line)
 
 @parthandler('replycaps')
 def handlereplycaps(op, inpart):
     """Notify that a reply bundle should be created
 
     The payload contains the capabilities information for the reply"""
     caps = decodecaps(inpart.read())
     if op.reply is None:
         op.reply = bundle20(op.ui, caps)
 
 class AbortFromPart(error.Abort):
     """Sub-class of Abort that denotes an error from a bundle2 part."""
 
 @parthandler('error:abort', ('message', 'hint'))
 def handleerrorabort(op, inpart):
     """Used to transmit abort error over the wire"""
     raise AbortFromPart(inpart.params['message'],
                         hint=inpart.params.get('hint'))
 
 @parthandler('error:pushkey', ('namespace', 'key', 'new', 'old', 'ret',
                                'in-reply-to'))
 def handleerrorpushkey(op, inpart):
     """Used to transmit failure of a mandatory pushkey over the wire"""
     kwargs = {}
     for name in ('namespace', 'key', 'new', 'old', 'ret'):
         value = inpart.params.get(name)
         if value is not None:
             kwargs[name] = value
     raise error.PushkeyFailed(inpart.params['in-reply-to'], **kwargs)
 
 @parthandler('error:unsupportedcontent', ('parttype', 'params'))
 def handleerrorunsupportedcontent(op, inpart):
     """Used to transmit unknown content error over the wire"""
     kwargs = {}
     parttype = inpart.params.get('parttype')
     if parttype is not None:
         kwargs['parttype'] = parttype
     params = inpart.params.get('params')
     if params is not None:
         kwargs['params'] = params.split('\0')
 
     raise error.BundleUnknownFeatureError(**kwargs)
 
 @parthandler('error:pushraced', ('message',))
 def handleerrorpushraced(op, inpart):
     """Used to transmit push race error over the wire"""
     raise error.ResponseError(_('push failed:'), inpart.params['message'])
 
 @parthandler('listkeys', ('namespace',))
 def handlelistkeys(op, inpart):
     """retrieve pushkey namespace content stored in a bundle2"""
     namespace = inpart.params['namespace']
     r = pushkey.decodekeys(inpart.read())
     op.records.add('listkeys', (namespace, r))
 
 @parthandler('pushkey', ('namespace', 'key', 'old', 'new'))
 def handlepushkey(op, inpart):
     """process a pushkey request"""
     dec = pushkey.decode
     namespace = dec(inpart.params['namespace'])
     key = dec(inpart.params['key'])
     old = dec(inpart.params['old'])
     new = dec(inpart.params['new'])
     # Grab the transaction to ensure that we have the lock before performing the
     # pushkey.
     if op.ui.configbool('experimental', 'bundle2lazylocking'):
         op.gettransaction()
     ret = op.repo.pushkey(namespace, key, old, new)
     record = {'namespace': namespace,
               'key': key,
               'old': old,
               'new': new}
     op.records.add('pushkey', record)
     if op.reply is not None:
         rpart = op.reply.newpart('reply:pushkey')
         rpart.addparam(
             'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False)
         rpart.addparam('return', '%i' % ret, mandatory=False)
     if inpart.mandatory and not ret:
         kwargs = {}
         for key in ('namespace', 'key', 'new', 'old', 'ret'):
             if key in inpart.params:
                 kwargs[key] = inpart.params[key]
         raise error.PushkeyFailed(partid=str(inpart.id), **kwargs)
 
 def _readphaseheads(inpart):
     headsbyphase = [[] for i in phases.allphases]
-    entrysize = _fphasesentry.size
+    entrysize = phases._fphasesentry.size
     while True:
         entry = inpart.read(entrysize)
         if len(entry) < entrysize:
             if entry:
                 raise error.Abort(_('bad phase-heads bundle part'))
             break
-        phase, node = _fphasesentry.unpack(entry)
+        phase, node = phases._fphasesentry.unpack(entry)
         headsbyphase[phase].append(node)
     return headsbyphase
 
 @parthandler('phase-heads')
 def handlephases(op, inpart):
     """apply phases from bundle part to repo"""
     headsbyphase = _readphaseheads(inpart)
     phases.updatephases(op.repo.unfiltered(), op.gettransaction(), headsbyphase)
     op.records.add('phase-heads', {})
 
 @parthandler('reply:pushkey', ('return', 'in-reply-to'))
 def handlepushkeyreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params['return'])
     partid = int(inpart.params['in-reply-to'])
     op.records.add('pushkey', {'return': ret}, partid)
 
 @parthandler('obsmarkers')
 def handleobsmarker(op, inpart):
     """add a stream of obsmarkers to the repo"""
     tr = op.gettransaction()
     markerdata = inpart.read()
     if op.ui.config('experimental', 'obsmarkers-exchange-debug'):
         op.ui.write(('obsmarker-exchange: %i bytes received\n')
                     % len(markerdata))
     # The mergemarkers call will crash if marker creation is not enabled.
     # we want to avoid this if the part is advisory.
     if not inpart.mandatory and op.repo.obsstore.readonly:
         op.repo.ui.debug('ignoring obsolescence markers, feature not enabled')
         return
     new = op.repo.obsstore.mergemarkers(tr, markerdata)
     op.repo.invalidatevolatilesets()
     if new:
         op.repo.ui.status(_('%i new obsolescence markers\n') % new)
     op.records.add('obsmarkers', {'new': new})
     if op.reply is not None:
         rpart = op.reply.newpart('reply:obsmarkers')
         rpart.addparam(
             'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False)
         rpart.addparam('new', '%i' % new, mandatory=False)
 
 
 @parthandler('reply:obsmarkers', ('new', 'in-reply-to'))
 def handleobsmarkerreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params['new'])
     partid = int(inpart.params['in-reply-to'])
     op.records.add('obsmarkers', {'new': ret}, partid)
 
 @parthandler('hgtagsfnodes')
 def handlehgtagsfnodes(op, inpart):
     """Applies .hgtags fnodes cache entries to the local repo.
 
     Payload is pairs of 20 byte changeset nodes and filenodes.
     """
     # Grab the transaction so we ensure that we have the lock at this point.
     if op.ui.configbool('experimental', 'bundle2lazylocking'):
         op.gettransaction()
     cache = tags.hgtagsfnodescache(op.repo.unfiltered())
 
     count = 0
     while True:
         node = inpart.read(20)
         fnode = inpart.read(20)
         if len(node) < 20 or len(fnode) < 20:
             op.ui.debug('ignoring incomplete received .hgtags fnodes data\n')
             break
         cache.setfnode(node, fnode)
         count += 1
 
     cache.write()
     op.ui.debug('applied %i hgtags fnodes cache entries\n' % count)
 
 @parthandler('pushvars')
 def bundle2getvars(op, part):
     '''unbundle a bundle2 containing shellvars on the server'''
     # An option to disable unbundling on server-side for security reasons
     if op.ui.configbool('push', 'pushvars.server'):
         hookargs = {}
         for key, value in part.advisoryparams:
             key = key.upper()
             # We want pushed variables to have USERVAR_ prepended so we know
             # they came from the --pushvar flag.
             key = "USERVAR_" + key
             hookargs[key] = value
         op.addhookargs(hookargs)

mercurial/phases.py

@@ -1,596 +1,611 b''
 """ Mercurial phases support code
 
     ---
 
     Copyright 2011 Pierre-Yves David <[e-mail]>
                    Logilab SA        <[e-mail]>
                    Augie Fackler     <[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.
 
     ---
 
 This module implements most phase logic in mercurial.
 
 
 Basic Concept
 =============
 
 A 'changeset phase' is an indicator that tells us how a changeset is
 manipulated and communicated. The details of each phase is described
 below, here we describe the properties they have in common.
 
 Like bookmarks, phases are not stored in history and thus are not
 permanent and leave no audit trail.
 
 First, no changeset can be in two phases at once. Phases are ordered,
 so they can be considered from lowest to highest. The default, lowest
 phase is 'public' - this is the normal phase of existing changesets. A
 child changeset can not be in a lower phase than its parents.
 
 These phases share a hierarchy of traits:
 
             immutable shared
     public:     X        X
     draft:               X
     secret:
 
 Local commits are draft by default.
 
 Phase Movement and Exchange
 ===========================
 
 Phase data is exchanged by pushkey on pull and push. Some servers have
 a publish option set, we call such a server a "publishing server".
 Pushing a draft changeset to a publishing server changes the phase to
 public.
 
 A small list of fact/rules define the exchange of phase:
 
 * old client never changes server states
 * pull never changes server states
 * publish and old server changesets are seen as public by client
 * any secret changeset seen in another repository is lowered to at
   least draft
 
 Here is the final table summing up the 49 possible use cases of phase
 exchange:
 
                            server
                   old     publish      non-publish
                  N   X    N   D   P    N   D   P
     old client
     pull
      N           -   X/X  -   X/D X/P  -   X/D X/P
      X           -   X/X  -   X/D X/P  -   X/D X/P
     push
      X           X/X X/X  X/P X/P X/P  X/D X/D X/P
     new client
     pull
      N           -   P/X  -   P/D P/P  -   D/D P/P
      D           -   P/X  -   P/D P/P  -   D/D P/P
      P           -   P/X  -   P/D P/P  -   P/D P/P
     push
      D           P/X P/X  P/P P/P P/P  D/D D/D P/P
      P           P/X P/X  P/P P/P P/P  P/P P/P P/P
 
 Legend:
 
     A/B = final state on client / state on server
 
     * N = new/not present,
     * P = public,
     * D = draft,
     * X = not tracked (i.e., the old client or server has no internal
           way of recording the phase.)
 
     passive = only pushes
 
 
     A cell here can be read like this:
 
     "When a new client pushes a draft changeset (D) to a publishing
     server where it's not present (N), it's marked public on both
     sides (P/P)."
 
 Note: old client behave as a publishing server with draft only content
 - other people see it as public
 - content is pushed as draft
 
 """
 
 from __future__ import absolute_import
 
 import errno
+import struct
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 from . import (
     error,
     smartset,
     txnutil,
     util,
 )
 
+_fphasesentry = struct.Struct('>i20s')
+
 allphases = public, draft, secret = range(3)
 trackedphases = allphases[1:]
 phasenames = ['public', 'draft', 'secret']
 
 def _readroots(repo, phasedefaults=None):
     """Read phase roots from disk
 
     phasedefaults is a list of fn(repo, roots) callable, which are
     executed if the phase roots file does not exist. When phases are
     being initialized on an existing repository, this could be used to
     set selected changesets phase to something else than public.
 
     Return (roots, dirty) where dirty is true if roots differ from
     what is being stored.
     """
     repo = repo.unfiltered()
     dirty = False
     roots = [set() for i in allphases]
     try:
         f, pending = txnutil.trypending(repo.root, repo.svfs, 'phaseroots')
         try:
             for line in f:
                 phase, nh = line.split()
                 roots[int(phase)].add(bin(nh))
         finally:
             f.close()
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         if phasedefaults:
             for f in phasedefaults:
                 roots = f(repo, roots)
         dirty = True
     return roots, dirty
 
+def binaryencode(phasemapping):
+    """encode a 'phase -> nodes' mapping into a binary stream
+
+    Since phases are integer the mapping is actually a python list:
+    [[PUBLIC_HEADS], [DRAFTS_HEADS], [SECRET_HEADS]]
+    """
+    binarydata = []
+    for phase, nodes in enumerate(phasemapping):
+        for head in nodes:
+            binarydata.append(_fphasesentry.pack(phase, head))
+    return ''.join(binarydata)
+
 def _trackphasechange(data, rev, old, new):
     """add a phase move the <data> dictionnary
 
     If data is None, nothing happens.
     """
     if data is None:
         return
     existing = data.get(rev)
     if existing is not None:
         old = existing[0]
     data[rev] = (old, new)
 
 class phasecache(object):
     def __init__(self, repo, phasedefaults, _load=True):
         if _load:
             # Cheap trick to allow shallow-copy without copy module
             self.phaseroots, self.dirty = _readroots(repo, phasedefaults)
             self._phaserevs = None
             self._phasesets = None
             self.filterunknown(repo)
             self.opener = repo.svfs
 
     def getrevset(self, repo, phases):
         """return a smartset for the given phases"""
         self.loadphaserevs(repo) # ensure phase's sets are loaded
 
         if self._phasesets and all(self._phasesets[p] is not None
                                    for p in phases):
             # fast path - use _phasesets
             revs = self._phasesets[phases[0]]
             if len(phases) > 1:
                 revs = revs.copy() # only copy when needed
                 for p in phases[1:]:
                     revs.update(self._phasesets[p])
             if repo.changelog.filteredrevs:
                 revs = revs - repo.changelog.filteredrevs
             return smartset.baseset(revs)
         else:
             # slow path - enumerate all revisions
             phase = self.phase
             revs = (r for r in repo if phase(repo, r) in phases)
             return smartset.generatorset(revs, iterasc=True)
 
     def copy(self):
         # Shallow copy meant to ensure isolation in
         # advance/retractboundary(), nothing more.
         ph = self.__class__(None, None, _load=False)
         ph.phaseroots = self.phaseroots[:]
         ph.dirty = self.dirty
         ph.opener = self.opener
         ph._phaserevs = self._phaserevs
         ph._phasesets = self._phasesets
         return ph
 
     def replace(self, phcache):
         """replace all values in 'self' with content of phcache"""
         for a in ('phaseroots', 'dirty', 'opener', '_phaserevs', '_phasesets'):
             setattr(self, a, getattr(phcache, a))
 
     def _getphaserevsnative(self, repo):
         repo = repo.unfiltered()
         nativeroots = []
         for phase in trackedphases:
             nativeroots.append(map(repo.changelog.rev, self.phaseroots[phase]))
         return repo.changelog.computephases(nativeroots)
 
     def _computephaserevspure(self, repo):
         repo = repo.unfiltered()
         revs = [public] * len(repo.changelog)
         self._phaserevs = revs
         self._populatephaseroots(repo)
         for phase in trackedphases:
             roots = list(map(repo.changelog.rev, self.phaseroots[phase]))
             if roots:
                 for rev in roots:
                     revs[rev] = phase
                 for rev in repo.changelog.descendants(roots):
                     revs[rev] = phase
 
     def loadphaserevs(self, repo):
         """ensure phase information is loaded in the object"""
         if self._phaserevs is None:
             try:
                 res = self._getphaserevsnative(repo)
                 self._phaserevs, self._phasesets = res
             except AttributeError:
                 self._computephaserevspure(repo)
 
     def invalidate(self):
         self._phaserevs = None
         self._phasesets = None
 
     def _populatephaseroots(self, repo):
         """Fills the _phaserevs cache with phases for the roots.
         """
         cl = repo.changelog
         phaserevs = self._phaserevs
         for phase in trackedphases:
             roots = map(cl.rev, self.phaseroots[phase])
             for root in roots:
                 phaserevs[root] = phase
 
     def phase(self, repo, rev):
         # We need a repo argument here to be able to build _phaserevs
         # if necessary. The repository instance is not stored in
         # phasecache to avoid reference cycles. The changelog instance
         # is not stored because it is a filecache() property and can
         # be replaced without us being notified.
         if rev == nullrev:
             return public
         if rev < nullrev:
             raise ValueError(_('cannot lookup negative revision'))
         if self._phaserevs is None or rev >= len(self._phaserevs):
             self.invalidate()
             self.loadphaserevs(repo)
         return self._phaserevs[rev]
 
     def write(self):
         if not self.dirty:
             return
         f = self.opener('phaseroots', 'w', atomictemp=True, checkambig=True)
         try:
             self._write(f)
         finally:
             f.close()
 
     def _write(self, fp):
         for phase, roots in enumerate(self.phaseroots):
             for h in roots:
                 fp.write('%i %s\n' % (phase, hex(h)))
         self.dirty = False
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
         tr.addfilegenerator('phase', ('phaseroots',), self._write)
         tr.hookargs['phases_moved'] = '1'
 
     def registernew(self, repo, tr, targetphase, nodes):
         repo = repo.unfiltered()
         self._retractboundary(repo, tr, targetphase, nodes)
         if tr is not None and 'phases' in tr.changes:
             phasetracking = tr.changes['phases']
             torev = repo.changelog.rev
             phase = self.phase
             for n in nodes:
                 rev = torev(n)
                 revphase = phase(repo, rev)
                 _trackphasechange(phasetracking, rev, None, revphase)
         repo.invalidatevolatilesets()
 
     def advanceboundary(self, repo, tr, targetphase, nodes):
         """Set all 'nodes' to phase 'targetphase'
 
         Nodes with a phase lower than 'targetphase' are not affected.
         """
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
         if tr is None:
             phasetracking = None
         else:
             phasetracking = tr.changes.get('phases')
 
         repo = repo.unfiltered()
 
         delroots = [] # set of root deleted by this path
         for phase in xrange(targetphase + 1, len(allphases)):
             # filter nodes that are not in a compatible phase already
             nodes = [n for n in nodes
                      if self.phase(repo, repo[n].rev()) >= phase]
             if not nodes:
                 break # no roots to move anymore
 
             olds = self.phaseroots[phase]
 
             affected = repo.revs('%ln::%ln', olds, nodes)
             for r in affected:
                 _trackphasechange(phasetracking, r, self.phase(repo, r),
                                   targetphase)
 
             roots = set(ctx.node() for ctx in repo.set(
                     'roots((%ln::) - %ld)', olds, affected))
             if olds != roots:
                 self._updateroots(phase, roots, tr)
                 # some roots may need to be declared for lower phases
                 delroots.extend(olds - roots)
         # declare deleted root in the target phase
         if targetphase != 0:
             self._retractboundary(repo, tr, targetphase, delroots)
         repo.invalidatevolatilesets()
 
     def retractboundary(self, repo, tr, targetphase, nodes):
         oldroots = self.phaseroots[:targetphase + 1]
         if tr is None:
             phasetracking = None
         else:
             phasetracking = tr.changes.get('phases')
         repo = repo.unfiltered()
         if (self._retractboundary(repo, tr, targetphase, nodes)
             and phasetracking is not None):
 
             # find the affected revisions
             new = self.phaseroots[targetphase]
             old = oldroots[targetphase]
             affected = set(repo.revs('(%ln::) - (%ln::)', new, old))
 
             # find the phase of the affected revision
             for phase in xrange(targetphase, -1, -1):
                 if phase:
                     roots = oldroots[phase]
                     revs = set(repo.revs('%ln::%ld', roots, affected))
                     affected -= revs
                 else: # public phase
                     revs = affected
                 for r in revs:
                     _trackphasechange(phasetracking, r, phase, targetphase)
         repo.invalidatevolatilesets()
 
     def _retractboundary(self, repo, tr, targetphase, nodes):
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
 
         repo = repo.unfiltered()
         currentroots = self.phaseroots[targetphase]
         finalroots = oldroots = set(currentroots)
         newroots = [n for n in nodes
                     if self.phase(repo, repo[n].rev()) < targetphase]
         if newroots:
 
             if nullid in newroots:
                 raise error.Abort(_('cannot change null revision phase'))
             currentroots = currentroots.copy()
             currentroots.update(newroots)
 
             # Only compute new roots for revs above the roots that are being
             # retracted.
             minnewroot = min(repo[n].rev() for n in newroots)
             aboveroots = [n for n in currentroots
                           if repo[n].rev() >= minnewroot]
             updatedroots = repo.set('roots(%ln::)', aboveroots)
 
             finalroots = set(n for n in currentroots if repo[n].rev() <
                              minnewroot)
             finalroots.update(ctx.node() for ctx in updatedroots)
         if finalroots != oldroots:
             self._updateroots(targetphase, finalroots, tr)
             return True
         return False
 
     def filterunknown(self, repo):
         """remove unknown nodes from the phase boundary
 
         Nothing is lost as unknown nodes only hold data for their descendants.
         """
         filtered = False
         nodemap = repo.changelog.nodemap # to filter unknown nodes
         for phase, nodes in enumerate(self.phaseroots):
             missing = sorted(node for node in nodes if node not in nodemap)
             if missing:
                 for mnode in missing:
                     repo.ui.debug(
                         'removing unknown node %s from %i-phase boundary\n'
                         % (short(mnode), phase))
                 nodes.symmetric_difference_update(missing)
                 filtered = True
         if filtered:
             self.dirty = True
         # filterunknown is called by repo.destroyed, we may have no changes in
         # root but phaserevs contents is certainly invalid (or at least we
         # have not proper way to check that). related to issue 3858.
         #
         # The other caller is __init__ that have no _phaserevs initialized
         # anyway. If this change we should consider adding a dedicated
         # "destroyed" function to phasecache or a proper cache key mechanism
         # (see branchmap one)
         self.invalidate()
 
 def advanceboundary(repo, tr, targetphase, nodes):
     """Add nodes to a phase changing other nodes phases if necessary.
 
     This function move boundary *forward* this means that all nodes
     are set in the target phase or kept in a *lower* phase.
 
     Simplify boundary to contains phase roots only."""
     phcache = repo._phasecache.copy()
     phcache.advanceboundary(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def retractboundary(repo, tr, targetphase, nodes):
     """Set nodes back to a phase changing other nodes phases if
     necessary.
 
     This function move boundary *backward* this means that all nodes
     are set in the target phase or kept in a *higher* phase.
 
     Simplify boundary to contains phase roots only."""
     phcache = repo._phasecache.copy()
     phcache.retractboundary(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def registernew(repo, tr, targetphase, nodes):
     """register a new revision and its phase
 
     Code adding revisions to the repository should use this function to
     set new changeset in their target phase (or higher).
     """
     phcache = repo._phasecache.copy()
     phcache.registernew(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def listphases(repo):
     """List phases root for serialization over pushkey"""
     # Use ordered dictionary so behavior is deterministic.
     keys = util.sortdict()
     value = '%i' % draft
     for root in repo._phasecache.phaseroots[draft]:
         keys[hex(root)] = value
 
     if repo.publishing():
         # Add an extra data to let remote know we are a publishing
         # repo. Publishing repo can't just pretend they are old repo.
         # When pushing to a publishing repo, the client still need to
         # push phase boundary
         #
         # Push do not only push changeset. It also push phase data.
         # New phase data may apply to common changeset which won't be
         # push (as they are common). Here is a very simple example:
         #
         # 1) repo A push changeset X as draft to repo B
         # 2) repo B make changeset X public
         # 3) repo B push to repo A. X is not pushed but the data that
         #    X as now public should
         #
         # The server can't handle it on it's own as it has no idea of
         # client phase data.
         keys['publishing'] = 'True'
     return keys
 
 def pushphase(repo, nhex, oldphasestr, newphasestr):
     """List phases root for serialization over pushkey"""
     repo = repo.unfiltered()
     with repo.lock():
         currentphase = repo[nhex].phase()
         newphase = abs(int(newphasestr)) # let's avoid negative index surprise
         oldphase = abs(int(oldphasestr)) # let's avoid negative index surprise
         if currentphase == oldphase and newphase < oldphase:
             with repo.transaction('pushkey-phase') as tr:
                 advanceboundary(repo, tr, newphase, [bin(nhex)])
             return True
         elif currentphase == newphase:
             # raced, but got correct result
             return True
         else:
             return False
 
 def subsetphaseheads(repo, subset):
     """Finds the phase heads for a subset of a history
 
     Returns a list indexed by phase number where each item is a list of phase
     head nodes.
     """
     cl = repo.changelog
 
     headsbyphase = [[] for i in allphases]
     # No need to keep track of secret phase; any heads in the subset that
     # are not mentioned are implicitly secret.
     for phase in allphases[:-1]:
         revset = "heads(%%ln & %s())" % phasenames[phase]
         headsbyphase[phase] = [cl.node(r) for r in repo.revs(revset, subset)]
     return headsbyphase
 
 def updatephases(repo, tr, headsbyphase):
     """Updates the repo with the given phase heads"""
     # Now advance phase boundaries of all but secret phase
     for phase in allphases[:-1]:
         advanceboundary(repo, tr, phase, headsbyphase[phase])
 
 def analyzeremotephases(repo, subset, roots):
     """Compute phases heads and root in a subset of node from root dict
 
     * subset is heads of the subset
     * roots is {<nodeid> => phase} mapping. key and value are string.
 
     Accept unknown element input
     """
     repo = repo.unfiltered()
     # build list from dictionary
     draftroots = []
     nodemap = repo.changelog.nodemap # to filter unknown nodes
     for nhex, phase in roots.iteritems():
         if nhex == 'publishing': # ignore data related to publish option
             continue
         node = bin(nhex)
         phase = int(phase)
         if phase == public:
             if node != nullid:
                 repo.ui.warn(_('ignoring inconsistent public root'
                                ' from remote: %s\n') % nhex)
         elif phase == draft:
             if node in nodemap:
                 draftroots.append(node)
         else:
             repo.ui.warn(_('ignoring unexpected root from remote: %i %s\n')
                          % (phase, nhex))
     # compute heads
     publicheads = newheads(repo, subset, draftroots)
     return publicheads, draftroots
 
 def newheads(repo, heads, roots):
     """compute new head of a subset minus another
 
     * `heads`: define the first subset
     * `roots`: define the second we subtract from the first"""
     repo = repo.unfiltered()
     revset = repo.set('heads((%ln + parents(%ln)) - (%ln::%ln))',
                       heads, roots, roots, heads)
     return [c.node() for c in revset]
 
 
 def newcommitphase(ui):
     """helper to get the target phase of new commit
 
     Handle all possible values for the phases.new-commit options.
 
     """
     v = ui.config('phases', 'new-commit', draft)
     try:
         return phasenames.index(v)
     except ValueError:
         try:
             return int(v)
         except ValueError:
             msg = _("phases.new-commit: not a valid phase name ('%s')")
             raise error.ConfigError(msg % v)
 
 def hassecret(repo):
     """utility function that check if a repo have any secret changeset."""
     return bool(repo._phasecache.phaseroots[2])