merge: stable into default

mercurial/bundle2.py

@@ -1,2588 +1,2589 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.
 """
 
 
 import collections
 import errno
 import os
 import re
 import string
 import struct
 import sys
 
 from .i18n import _
 from .node import (
     hex,
     short,
 )
 from . import (
     bookmarks,
     changegroup,
     encoding,
     error,
     obsolete,
     phases,
     pushkey,
     pycompat,
     requirements,
     scmutil,
     streamclone,
     tags,
     url,
     util,
 )
 from .utils import (
     stringutil,
     urlutil,
 )
 from .interfaces import repository
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 _fstreamparamsize = b'>i'
 _fpartheadersize = b'>i'
 _fparttypesize = b'>B'
 _fpartid = b'>I'
 _fpayloadsize = b'>i'
 _fpartparamcount = b'>BB'
 
 preferedchunksize = 32768
 
 _parttypeforbidden = re.compile(b'[^a-zA-Z0-9_:-]')
 
 
 def outdebug(ui, message):
     """debug regarding output stream (bundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-output: %s\n' % message)
 
 
 def indebug(ui, message):
     """debug on input stream (unbundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'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 b'>' + (b'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:
     """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:
     """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, source=b''):
         self.repo = repo
         self.ui = repo.ui
         self.records = unbundlerecords()
         self.reply = None
         self.captureoutput = captureoutput
         self.hookargs = {}
         self._gettransaction = transactiongetter
         # carries value that can modify part behavior
         self.modes = {}
         self.source = source
 
     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(
                 b'attempted to add hookargs to '
                 b'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, url=None, **kwargs):
     # transform me into unbundler.apply() as soon as the freeze is lifted
     if isinstance(unbundler, unbundle20):
         tr.hookargs[b'bundle2'] = b'1'
         if source is not None and b'source' not in tr.hookargs:
             tr.hookargs[b'source'] = source
         if url is not None and b'url' not in tr.hookargs:
             tr.hookargs[b'url'] = url
         return processbundle(repo, unbundler, lambda: tr, source=source)
     else:
         # the transactiongetter won't be used, but we might as well set it
         op = bundleoperation(repo, lambda: tr, source=source)
         _processchangegroup(op, unbundler, tr, source, url, **kwargs)
         return op
 
 
 class partiterator:
     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(), 1)
             for count, p in itr:
                 self.count = count
                 self.current = p
                 yield p
                 p.consume()
                 self.current = None
 
         self.iterator = func()
         return self.iterator
 
     def __exit__(self, type, exc, tb):
         if not self.iterator:
             return
 
         # Only gracefully abort in a normal exception situation. User aborts
         # like Ctrl+C throw a KeyboardInterrupt which is not a base Exception,
         # and should not gracefully cleanup.
         if isinstance(exc, Exception):
             # 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:
                 if self.current:
                     # consume the part content to not corrupt the stream.
                     self.current.consume()
 
                 for part in self.iterator:
                     # consume the bundle content
                     part.consume()
             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(
             b'bundle2-input-bundle: %i parts total\n' % self.count
         )
 
 
 def processbundle(repo, unbundler, transactiongetter=None, op=None, source=b''):
     """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, source=source)
     # todo:
     # - replace this is a init function soon.
     # - exception catching
     unbundler.params
     if repo.ui.debugflag:
         msg = [b'bundle2-input-bundle:']
         if unbundler.params:
             msg.append(b' %i params' % len(unbundler.params))
         if op._gettransaction is None or op._gettransaction is _notransaction:
             msg.append(b' no-transaction')
         else:
             msg.append(b' with-transaction')
         msg.append(b'\n')
         repo.ui.debug(b''.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(
         b'changegroup',
         {
             b'return': ret,
         },
     )
     return ret
 
 
 def _gethandler(op, part):
     status = b'unknown'  # used by debug output
     try:
         handler = parthandlermapping.get(part.type)
         if handler is None:
             status = b'unsupported-type'
             raise error.BundleUnknownFeatureError(parttype=part.type)
         indebug(op.ui, b'found a handler for part %s' % part.type)
         unknownparams = part.mandatorykeys - handler.params
         if unknownparams:
             unknownparams = list(unknownparams)
             unknownparams.sort()
             status = b'unsupported-params (%s)' % b', '.join(unknownparams)
             raise error.BundleUnknownFeatureError(
                 parttype=part.type, params=unknownparams
             )
         status = b'supported'
     except error.BundleUnknownFeatureError as exc:
         if part.mandatory:  # mandatory parts
             raise
         indebug(op.ui, b'ignoring unsupported advisory part %s' % exc)
         return  # skip to part processing
     finally:
         if op.ui.debugflag:
             msg = [b'bundle2-input-part: "%s"' % part.type]
             if not part.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(part.mandatorykeys)
             nbap = len(part.params) - nbmp
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             msg.append(b' %s\n' % status)
             op.ui.debug(b''.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 = b''
     try:
         handler(op, part)
     finally:
         if output is not None:
             output = op.ui.popbuffer()
         if output:
             outpart = op.reply.newpart(b'output', data=output, mandatory=False)
             outpart.addparam(
                 b'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 b'=' not in line:
             key, vals = line, ()
         else:
             key, vals = line.split(b'=', 1)
             vals = vals.split(b',')
         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 = b"%s=%s" % (ca, b','.join(vals))
         chunks.append(ca)
     return b'\n'.join(chunks)
 
 
 bundletypes = {
     b"": (b"", b'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.
     b"HG20": (),  # special-cased below
     b"HG10UN": (b"HG10UN", b'UN'),
     b"HG10BZ": (b"HG10", b'BZ'),
     b"HG10GZ": (b"HG10GZ", b'GZ'),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = [b'HG10GZ', b'HG10BZ', b'HG10UN']
 
 
 class bundle20:
     """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 = b'HG20'
 
     def __init__(self, ui, capabilities=()):
         self.ui = ui
         self._params = []
         self._parts = []
         self.capabilities = dict(capabilities)
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compopts = None
         # If compression is being handled by a consumer of the raw
         # data (e.g. the wire protocol), unsetting this flag tells
         # consumers that the bundle is best left uncompressed.
         self.prefercompressed = True
 
     def setcompression(self, alg, compopts=None):
         """setup core part compression to <alg>"""
         if alg in (None, b'UN'):
             return
         assert not any(n.lower() == b'compression' for n, v in self._params)
         self.addparam(b'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 error.ProgrammingError(b'empty parameter name')
         if name[0:1] not in pycompat.bytestr(
             string.ascii_letters  # pytype: disable=wrong-arg-types
         ):
             raise error.ProgrammingError(
                 b'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 = [b'bundle2-output-bundle: "%s",' % self._magicstring]
             if self._params:
                 msg.append(b' (%i params)' % len(self._params))
             msg.append(b' %i parts total\n' % len(self._parts))
             self.ui.debug(b''.join(msg))
         outdebug(self.ui, b'start emission of %s stream' % self._magicstring)
         yield self._magicstring
         param = self._paramchunk()
         outdebug(self.ui, b'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 = b'%s=%s' % (par, value)
             blocks.append(par)
         return b' '.join(blocks)
 
     def _getcorechunk(self):
         """yield chunk for the core part of the bundle
 
         (all but headers and parameters)"""
         outdebug(self.ui, b'start of parts')
         for part in self._parts:
             outdebug(self.ui, b'bundle part: "%s"' % part.type)
             for chunk in part.getchunks(ui=self.ui):
                 yield chunk
         outdebug(self.ui, b'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(b'output'):
                 salvaged.append(part.copy())
         return salvaged
 
 
 class unpackermixin:
     """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 != b'HG':
         ui.debug(
             b"error: invalid magic: %r (version %r), should be 'HG'\n"
             % (magic, version)
         )
         raise error.Abort(_(b'not a Mercurial bundle'))
     unbundlerclass = formatmap.get(version)
     if unbundlerclass is None:
         raise error.Abort(_(b'unknown bundle version %s') % version)
     unbundler = unbundlerclass(ui, fp)
     indebug(ui, b'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 = b'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(b'UN')
         self._compressed = None
         super(unbundle20, self).__init__(fp)
 
     @util.propertycache
     def params(self):
         """dictionary of stream level parameters"""
         indebug(self.ui, b'reading bundle2 stream parameters')
         params = {}
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'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(b' '):
             p = p.split(b'=', 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('empty parameter name')
         if name[0:1] not in pycompat.bytestr(
             string.ascii_letters  # pytype: disable=wrong-arg-types
         ):
             raise ValueError('non letter first character: %s' % name)
         try:
             handler = b2streamparamsmap[name.lower()]
         except KeyError:
             if name[0:1].islower():
                 indebug(self.ui, b"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(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             self._processallparams(params)
             # The payload itself is decompressed below, so drop
             # the compression parameter passed down to compensate.
             outparams = []
             for p in params.split(b' '):
                 k, v = p.split(b'=', 1)
                 if k.lower() != b'compression':
                     outparams.append(p)
             outparams = b' '.join(outparams)
             yield _pack(_fstreamparamsize, len(outparams))
             yield outparams
         else:
             yield _pack(_fstreamparamsize, paramssize)
         # 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(b'negative chunk size: %i')
             yield self._readexact(size)
 
     def iterparts(self, seekable=False):
         """yield all parts contained in the stream"""
         cls = seekableunbundlepart if seekable else unbundlepart
         # 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, b'start extraction of bundle2 parts')
         headerblock = self._readpartheader()
         while headerblock is not None:
             part = cls(self.ui, headerblock, self._fp)
             yield part
             # Ensure part is fully consumed so we can start reading the next
             # part.
             part.consume()
 
             headerblock = self._readpartheader()
         indebug(self.ui, b'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(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'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 = {b'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(b'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:
     """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=b'',
         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(b'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(b'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=b'', 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(b'part is being generated')
         if name in self._seenparams:
             raise ValueError(b'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(b'part can only be consumed once')
         self._generated = False
 
         if ui.debugflag:
             msg = [b'bundle2-output-part: "%s"' % self.type]
             if not self.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(self.mandatoryparams)
             nbap = len(self.advisoryparams)
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             if not self.data:
                 msg.append(b' empty payload')
             elif util.safehasattr(self.data, 'next') or util.safehasattr(
                 self.data, b'__next__'
             ):
                 msg.append(b' streamed payload')
             else:
                 msg.append(b' %i bytes payload' % len(self.data))
             msg.append(b'\n')
             ui.debug(b''.join(msg))
 
         #### header
         if self.mandatory:
             parttype = self.type.upper()
         else:
             parttype = self.type.lower()
         outdebug(ui, b'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 = b''.join(header)
         except TypeError:
             raise TypeError(
                 'Found a non-bytes trying to '
                 'build bundle part header: %r' % header
             )
         outdebug(ui, b'header chunk size: %i' % len(headerchunk))
         yield _pack(_fpartheadersize, len(headerchunk))
         yield headerchunk
         ## payload
         try:
             for chunk in self._payloadchunks():
                 outdebug(ui, b'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(b'bundle2-generatorexit\n')
             raise
         except BaseException as exc:
             bexc = stringutil.forcebytestr(exc)
             # backup exception data for later
             ui.debug(
                 b'bundle2-input-stream-interrupt: encoding exception %s' % bexc
             )
             tb = sys.exc_info()[2]
             msg = b'unexpected error: %s' % bexc
             interpart = bundlepart(
                 b'error:abort', [(b'message', msg)], mandatory=False
             )
             interpart.id = 0
             yield _pack(_fpayloadsize, -1)
             for chunk in interpart.getchunks(ui=ui):
                 yield chunk
             outdebug(ui, b'closing payload chunk')
             # abort current part payload
             yield _pack(_fpayloadsize, 0)
             pycompat.raisewithtb(exc, tb)
         # end of payload
         outdebug(ui, b'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, b'__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(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i\n' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def __call__(self):
 
         self.ui.debug(
             b'bundle2-input-stream-interrupt: opening out of band context\n'
         )
         indebug(self.ui, b'bundle2 stream interruption, looking for a part.')
         headerblock = self._readpartheader()
         if headerblock is None:
             indebug(self.ui, b'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.consume()
         self.ui.debug(
             b'bundle2-input-stream-interrupt: closing out of band context\n'
         )
 
 
 class interruptoperation:
     """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(b'no repo access from stream interruption')
 
     def gettransaction(self):
         raise TransactionUnavailable(b'no repo access from stream interruption')
 
 
 def decodepayloadchunks(ui, fh):
     """Reads bundle2 part payload data into chunks.
 
     Part payload data consists of framed chunks. This function takes
     a file handle and emits those chunks.
     """
     dolog = ui.configbool(b'devel', b'bundle2.debug')
     debug = ui.debug
 
     headerstruct = struct.Struct(_fpayloadsize)
     headersize = headerstruct.size
     unpack = headerstruct.unpack
 
     readexactly = changegroup.readexactly
     read = fh.read
 
     chunksize = unpack(readexactly(fh, headersize))[0]
     indebug(ui, b'payload chunk size: %i' % chunksize)
 
     # changegroup.readexactly() is inlined below for performance.
     while chunksize:
         if chunksize >= 0:
             s = read(chunksize)
             if len(s) < chunksize:
                 raise error.Abort(
                     _(
                         b'stream ended unexpectedly '
                         b' (got %d bytes, expected %d)'
                     )
                     % (len(s), chunksize)
                 )
 
             yield s
         elif chunksize == flaginterrupt:
             # Interrupt "signal" detected. The regular stream is interrupted
             # and a bundle2 part follows. Consume it.
             interrupthandler(ui, fh)()
         else:
             raise error.BundleValueError(
                 b'negative payload chunk size: %s' % chunksize
             )
 
         s = read(headersize)
         if len(s) < headersize:
             raise error.Abort(
                 _(b'stream ended unexpectedly  (got %d bytes, expected %d)')
                 % (len(s), chunksize)
             )
 
         chunksize = unpack(s)[0]
 
         # indebug() inlined for performance.
         if dolog:
             debug(b'bundle2-input: payload chunk size: %i\n' % chunksize)
 
 
 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, b'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._readheader()
         self._mandatory = None
         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 _readheader(self):
         """read the header and setup the object"""
         typesize = self._unpackheader(_fparttypesize)[0]
         self.type = self._fromheader(typesize)
         indebug(self.ui, b'part type: "%s"' % self.type)
         self.id = self._unpackheader(_fpartid)[0]
         indebug(self.ui, b'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, b'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 _payloadchunks(self):
         """Generator of decoded chunks in the payload."""
         return decodepayloadchunks(self.ui, self._fp)
 
     def consume(self):
         """Read the part payload until completion.
 
         By consuming the part data, the underlying stream read offset will
         be advanced to the next part (or end of stream).
         """
         if self.consumed:
             return
 
         chunk = self.read(32768)
         while chunk:
             self._pos += len(chunk)
             chunk = self.read(32768)
 
     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(
                     b'bundle2-input-part: total payload size %i\n' % self._pos
                 )
             self.consumed = True
         return data
 
 
 class seekableunbundlepart(unbundlepart):
     """A bundle2 part in a bundle that is seekable.
 
     Regular ``unbundlepart`` instances can only be read once. This class
     extends ``unbundlepart`` to enable bi-directional seeking within the
     part.
 
     Bundle2 part data consists of framed chunks. Offsets when seeking
     refer to the decoded data, not the offsets in the underlying bundle2
     stream.
 
     To facilitate quickly seeking within the decoded data, instances of this
     class maintain a mapping between offsets in the underlying stream and
     the decoded payload. This mapping will consume memory in proportion
     to the number of chunks within the payload (which almost certainly
     increases in proportion with the size of the part).
     """
 
     def __init__(self, ui, header, fp):
         # (payload, file) offsets for chunk starts.
         self._chunkindex = []
 
         super(seekableunbundlepart, self).__init__(ui, header, fp)
 
     def _payloadchunks(self, chunknum=0):
         '''seek to specified chunk and start yielding data'''
         if len(self._chunkindex) == 0:
             assert chunknum == 0, b'Must start with chunk 0'
             self._chunkindex.append((0, self._tellfp()))
         else:
             assert chunknum < len(self._chunkindex), (
                 b'Unknown chunk %d' % chunknum
             )
             self._seekfp(self._chunkindex[chunknum][1])
 
         pos = self._chunkindex[chunknum][0]
 
         for chunk in decodepayloadchunks(self.ui, self._fp):
             chunknum += 1
             pos += len(chunk)
             if chunknum == len(self._chunkindex):
                 self._chunkindex.append((pos, self._tellfp()))
 
             yield chunk
 
     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(b'Unknown chunk')
 
     def tell(self):
         return self._pos
 
     def seek(self, offset, whence=os.SEEK_SET):
         if whence == os.SEEK_SET:
             newpos = offset
         elif whence == os.SEEK_CUR:
             newpos = self._pos + offset
         elif whence == os.SEEK_END:
             if not self.consumed:
                 # Can't use self.consume() here because it advances self._pos.
                 chunk = self.read(32768)
                 while chunk:
                     chunk = self.read(32768)
             newpos = self._chunkindex[-1][0] - offset
         else:
             raise ValueError(b'Unknown whence value: %r' % (whence,))
 
         if newpos > self._chunkindex[-1][0] and not self.consumed:
             # Can't use self.consume() here because it advances self._pos.
             chunk = self.read(32768)
             while chunk:
                 chunk = self.read(32668)
 
         if not 0 <= newpos <= self._chunkindex[-1][0]:
             raise ValueError(b'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(_(b'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(_(b'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 = {
     b'HG20': (),
     b'bookmarks': (),
     b'error': (b'abort', b'unsupportedcontent', b'pushraced', b'pushkey'),
     b'listkeys': (),
     b'pushkey': (),
     b'digests': tuple(sorted(util.DIGESTS.keys())),
     b'remote-changegroup': (b'http', b'https'),
     b'hgtagsfnodes': (),
     b'phases': (b'heads',),
     b'stream': (b'v2',),
 }
 
 
 def getrepocaps(repo, allowpushback=False, role=None):
     """return the bundle2 capabilities for a given repo
 
     Exists to allow extensions (like evolution) to mutate the capabilities.
 
     The returned value is used for servers advertising their capabilities as
     well as clients advertising their capabilities to servers as part of
     bundle2 requests. The ``role`` argument specifies which is which.
     """
     if role not in (b'client', b'server'):
         raise error.ProgrammingError(b'role argument must be client or server')
 
     caps = capabilities.copy()
     caps[b'changegroup'] = tuple(
         sorted(changegroup.supportedincomingversions(repo))
     )
     if obsolete.isenabled(repo, obsolete.exchangeopt):
         supportedformat = tuple(b'V%i' % v for v in obsolete.formats)
         caps[b'obsmarkers'] = supportedformat
     if allowpushback:
         caps[b'pushback'] = ()
     cpmode = repo.ui.config(b'server', b'concurrent-push-mode')
     if cpmode == b'check-related':
         caps[b'checkheads'] = (b'related',)
     if b'phases' in repo.ui.configlist(b'devel', b'legacy.exchange'):
         caps.pop(b'phases')
 
     # Don't advertise stream clone support in server mode if not configured.
     if role == b'server':
         streamsupported = repo.ui.configbool(
             b'server', b'uncompressed', untrusted=True
         )
         featuresupported = repo.ui.configbool(b'server', b'bundle2.stream')
 
         if not streamsupported or not featuresupported:
             caps.pop(b'stream')
     # Else always advertise support on client, because payload support
     # should always be advertised.
 
     # b'rev-branch-cache is no longer advertised, but still supported
     # for legacy clients.
 
     return caps
 
 
 def bundle2caps(remote):
     """return the bundle capabilities of a peer as dict"""
     raw = remote.capable(b'bundle2')
     if not raw and raw != b'':
         return {}
     capsblob = urlreq.unquote(remote.capable(b'bundle2'))
     return decodecaps(capsblob)
 
 
 def obsmarkersversion(caps):
     """extract the list of supported obsmarkers versions from a bundle2caps dict"""
     obscaps = caps.get(b'obsmarkers', ())
     return [int(c[1:]) for c in obscaps if c.startswith(b'V')]
 
 
 def writenewbundle(
     ui,
     repo,
     source,
     filename,
     bundletype,
     outgoing,
     opts,
     vfs=None,
     compression=None,
     compopts=None,
 ):
     if bundletype.startswith(b'HG10'):
         cg = changegroup.makechangegroup(repo, outgoing, b'01', source)
         return writebundle(
             ui,
             cg,
             filename,
             bundletype,
             vfs=vfs,
             compression=compression,
             compopts=compopts,
         )
     elif not bundletype.startswith(b'HG20'):
         raise error.ProgrammingError(b'unknown bundle type: %s' % bundletype)
 
     caps = {}
     if b'obsolescence' in opts:
         caps[b'obsmarkers'] = (b'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 might not always want a changegroup in such bundle, for example in
     # stream bundles
     if opts.get(b'changegroup', True):
         cgversion = opts.get(b'cg.version')
         if cgversion is None:
             cgversion = changegroup.safeversion(repo)
         cg = changegroup.makechangegroup(repo, outgoing, cgversion, source)
         part = bundler.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         if opts.get(b'phases') and repo.revs(
             b'%ln and secret()', outgoing.ancestorsof
         ):
             part.addparam(
                 b'targetphase', b'%d' % phases.secret, mandatory=False
             )
     if repository.REPO_FEATURE_SIDE_DATA in repo.features:
         part.addparam(b'exp-sidedata', b'1')
 
     if opts.get(b'streamv2', False):
         addpartbundlestream2(bundler, repo, stream=True)
 
     if opts.get(b'tagsfnodescache', True):
         addparttagsfnodescache(repo, bundler, outgoing)
 
     if opts.get(b'revbranchcache', True):
         addpartrevbranchcache(repo, bundler, outgoing)
 
     if opts.get(b'obsolescence', False):
         obsmarkers = repo.obsstore.relevantmarkers(outgoing.missing)
         buildobsmarkerspart(
             bundler,
             obsmarkers,
             mandatory=opts.get(b'obsolescence-mandatory', True),
         )
 
     if opts.get(b'phases', False):
         headsbyphase = phases.subsetphaseheads(repo, outgoing.missing)
         phasedata = phases.binaryencode(headsbyphase)
         bundler.newpart(b'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.ancestorsof:
         # Don't compute missing, as this may slow down serving.
         fnode = cache.getfnode(node, computemissing=False)
         if fnode:
             chunks.extend([node, fnode])
 
     if chunks:
         bundler.newpart(b'hgtagsfnodes', data=b''.join(chunks))
 
 
 def addpartrevbranchcache(repo, bundler, outgoing):
     # we include the rev branch cache for the bundle changeset
     # (as an optional parts)
     cache = repo.revbranchcache()
     cl = repo.unfiltered().changelog
     branchesdata = collections.defaultdict(lambda: (set(), set()))
     for node in outgoing.missing:
         branch, close = cache.branchinfo(cl.rev(node))
         branchesdata[branch][close].add(node)
 
     def generate():
         for branch, (nodes, closed) in sorted(branchesdata.items()):
             utf8branch = encoding.fromlocal(branch)
             yield rbcstruct.pack(len(utf8branch), len(nodes), len(closed))
             yield utf8branch
             for n in sorted(nodes):
                 yield n
             for n in sorted(closed):
                 yield n
 
     bundler.newpart(b'cache:rev-branch-cache', data=generate(), mandatory=False)
 
 
 def _formatrequirementsspec(requirements):
     requirements = [req for req in requirements if req != b"shared"]
     return urlreq.quote(b','.join(sorted(requirements)))
 
 
 def _formatrequirementsparams(requirements):
     requirements = _formatrequirementsspec(requirements)
     params = b"%s%s" % (urlreq.quote(b"requirements="), requirements)
     return params
 
 
 def format_remote_wanted_sidedata(repo):
     """Formats a repo's wanted sidedata categories into a bytestring for
     capabilities exchange."""
     wanted = b""
     if repo._wanted_sidedata:
         wanted = b','.join(
             pycompat.bytestr(c) for c in sorted(repo._wanted_sidedata)
         )
     return wanted
 
 
 def read_remote_wanted_sidedata(remote):
     sidedata_categories = remote.capable(b'exp-wanted-sidedata')
     return read_wanted_sidedata(sidedata_categories)
 
 
 def read_wanted_sidedata(formatted):
     if formatted:
         return set(formatted.split(b','))
     return set()
 
 
 def addpartbundlestream2(bundler, repo, **kwargs):
     if not kwargs.get('stream', False):
         return
 
     if not streamclone.allowservergeneration(repo):
         raise error.Abort(
             _(
                 b'stream data requested but server does not allow '
                 b'this feature'
             ),
             hint=_(
                 b'well-behaved clients should not be '
                 b'requesting stream data from servers not '
                 b'advertising it; the client may be buggy'
             ),
         )
 
     # Stream clones don't compress well. And compression undermines a
     # goal of stream clones, which is to be fast. Communicate the desire
     # to avoid compression to consumers of the bundle.
     bundler.prefercompressed = False
 
     # get the includes and excludes
     includepats = kwargs.get('includepats')
     excludepats = kwargs.get('excludepats')
 
     narrowstream = repo.ui.configbool(
         b'experimental', b'server.stream-narrow-clones'
     )
 
     if (includepats or excludepats) and not narrowstream:
         raise error.Abort(_(b'server does not support narrow stream clones'))
 
     includeobsmarkers = False
     if repo.obsstore:
         remoteversions = obsmarkersversion(bundler.capabilities)
         if not remoteversions:
             raise error.Abort(
                 _(
                     b'server has obsolescence markers, but client '
                     b'cannot receive them via stream clone'
                 )
             )
         elif repo.obsstore._version in remoteversions:
             includeobsmarkers = True
 
     filecount, bytecount, it = streamclone.generatev2(
         repo, includepats, excludepats, includeobsmarkers
     )
     requirements = streamclone.streamed_requirements(repo)
     requirements = _formatrequirementsspec(requirements)
     part = bundler.newpart(b'stream2', data=it)
     part.addparam(b'bytecount', b'%d' % bytecount, mandatory=True)
     part.addparam(b'filecount', b'%d' % filecount, mandatory=True)
     part.addparam(b'requirements', requirements, mandatory=True)
 
 
 def buildobsmarkerspart(bundler, markers, mandatory=True):
     """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(b'bundler does not support common obsmarker format')
     stream = obsolete.encodemarkers(markers, True, version=version)
     return bundler.newpart(b'obsmarkers', data=stream, mandatory=mandatory)
 
 
 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 == b"HG20":
         bundle = bundle20(ui)
         bundle.setcompression(compression, compopts)
         part = bundle.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         chunkiter = bundle.getchunks()
     else:
         # compression argument is only for the bundle2 case
         assert compression is None
         if cg.version != b'01':
             raise error.Abort(
                 _(b'old bundle types only supports v1 changegroups')
             )
         header, comp = bundletypes[bundletype]
         if comp not in util.compengines.supportedbundletypes:
             raise error.Abort(_(b'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(b'return', 0) for r in op.records[b'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(
     b'changegroup',
     (
         b'version',
         b'nbchanges',
         b'exp-sidedata',
         b'exp-wanted-sidedata',
         b'treemanifest',
         b'targetphase',
     ),
 )
 def handlechangegroup(op, inpart):
     """apply a changegroup part on the repo"""
     from . import localrepo
 
     tr = op.gettransaction()
     unpackerversion = inpart.params.get(b'version', b'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 b'nbchanges' in inpart.params:
         nbchangesets = int(inpart.params.get(b'nbchanges'))
     if b'treemanifest' in inpart.params and not scmutil.istreemanifest(op.repo):
         if len(op.repo.changelog) != 0:
             raise error.Abort(
                 _(
                     b"bundle contains tree manifests, but local repo is "
                     b"non-empty and does not use tree manifests"
                 )
             )
         op.repo.requirements.add(requirements.TREEMANIFEST_REQUIREMENT)
         op.repo.svfs.options = localrepo.resolvestorevfsoptions(
             op.repo.ui, op.repo.requirements, op.repo.features
         )
         scmutil.writereporequirements(op.repo)
 
     extrakwargs = {}
     targetphase = inpart.params.get(b'targetphase')
     if targetphase is not None:
         extrakwargs['targetphase'] = int(targetphase)
 
     remote_sidedata = inpart.params.get(b'exp-wanted-sidedata')
     extrakwargs['sidedata_categories'] = read_wanted_sidedata(remote_sidedata)
 
     ret = _processchangegroup(
         op,
         cg,
         tr,
         op.source,
         b'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(b'reply:changegroup', mandatory=False)
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     assert not inpart.read()
 
 
 _remotechangegroupparams = tuple(
     [b'url', b'size', b'digests']
     + [b'digest:%s' % k for k in util.DIGESTS.keys()]
 )
 
 
 @parthandler(b'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[b'url']
     except KeyError:
         raise error.Abort(_(b'remote-changegroup: missing "%s" param') % b'url')
     parsed_url = urlutil.url(raw_url)
     if parsed_url.scheme not in capabilities[b'remote-changegroup']:
         raise error.Abort(
             _(b'remote-changegroup does not support %s urls')
             % parsed_url.scheme
         )
 
     try:
         size = int(inpart.params[b'size'])
     except ValueError:
         raise error.Abort(
             _(b'remote-changegroup: invalid value for param "%s"') % b'size'
         )
     except KeyError:
         raise error.Abort(
             _(b'remote-changegroup: missing "%s" param') % b'size'
         )
 
     digests = {}
     for typ in inpart.params.get(b'digests', b'').split():
         param = b'digest:%s' % typ
         try:
             value = inpart.params[param]
         except KeyError:
             raise error.Abort(
                 _(b'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(
             _(b'%s: not a bundle version 1.0') % urlutil.hidepassword(raw_url)
         )
     ret = _processchangegroup(op, cg, tr, op.source, b'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(b'reply:changegroup')
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     try:
         real_part.validate()
     except error.Abort as e:
         raise error.Abort(
             _(b'bundle at %s is corrupted:\n%s')
             % (urlutil.hidepassword(raw_url), e.message)
         )
     assert not inpart.read()
 
 
 @parthandler(b'reply:changegroup', (b'return', b'in-reply-to'))
 def handlereplychangegroup(op, inpart):
     ret = int(inpart.params[b'return'])
     replyto = int(inpart.params[b'in-reply-to'])
     op.records.add(b'changegroup', {b'return': ret}, replyto)
 
 
 @parthandler(b'check:bookmarks')
 def handlecheckbookmarks(op, inpart):
     """check location of bookmarks
 
     This part is to be used to detect push race regarding bookmark, it
     contains binary encoded (bookmark, node) tuple. If the local state does
     not marks the one in the part, a PushRaced exception is raised
     """
     bookdata = bookmarks.binarydecode(op.repo, inpart)
 
     msgstandard = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" move from %s to %s)'
     )
     msgmissing = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" is missing, expected %s)'
     )
     msgexist = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" set on %s, expected missing)'
     )
     for book, node in bookdata:
         currentnode = op.repo._bookmarks.get(book)
         if currentnode != node:
             if node is None:
                 finalmsg = msgexist % (book, short(currentnode))
             elif currentnode is None:
                 finalmsg = msgmissing % (book, short(node))
             else:
                 finalmsg = msgstandard % (
                     book,
                     short(node),
                     short(currentnode),
                 )
             raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'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(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     if sorted(heads) != sorted(op.repo.heads()):
         raise error.PushRaced(
             b'remote repository changed while pushing - please try again'
         )
 
 
 @parthandler(b'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(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
 
     currentheads = set()
     for ls in op.repo.branchmap().iterheads():
         currentheads.update(ls)
 
     for h in heads:
         if h not in currentheads:
             raise error.PushRaced(
                 b'remote repository changed while pushing - '
                 b'please try again'
             )
 
 
 @parthandler(b'check:phases')
 def handlecheckphases(op, inpart):
     """check that phase boundaries of the repository did not change
 
     This is used to detect a push race.
     """
     phasetonodes = phases.binarydecode(inpart)
     unfi = op.repo.unfiltered()
     cl = unfi.changelog
     phasecache = unfi._phasecache
     msg = (
         b'remote repository changed while pushing - please try again '
         b'(%s is %s expected %s)'
     )
     for expectedphase, nodes in phasetonodes.items():
         for n in nodes:
             actualphase = phasecache.phase(unfi, cl.rev(n))
             if actualphase != expectedphase:
                 finalmsg = msg % (
                     short(n),
                     phases.phasenames[actualphase],
                     phases.phasenames[expectedphase],
                 )
                 raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'output')
 def handleoutput(op, inpart):
     """forward output captured on the server to the client"""
     for line in inpart.read().splitlines():
         op.ui.status(_(b'remote: %s\n') % line)
 
 
 @parthandler(b'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(b'error:abort', (b'message', b'hint'))
 def handleerrorabort(op, inpart):
     """Used to transmit abort error over the wire"""
     raise AbortFromPart(
         inpart.params[b'message'], hint=inpart.params.get(b'hint')
     )
 
 
 @parthandler(
     b'error:pushkey',
     (b'namespace', b'key', b'new', b'old', b'ret', b'in-reply-to'),
 )
 def handleerrorpushkey(op, inpart):
     """Used to transmit failure of a mandatory pushkey over the wire"""
     kwargs = {}
     for name in (b'namespace', b'key', b'new', b'old', b'ret'):
         value = inpart.params.get(name)
         if value is not None:
             kwargs[name] = value
     raise error.PushkeyFailed(
         inpart.params[b'in-reply-to'], **pycompat.strkwargs(kwargs)
     )
 
 
 @parthandler(b'error:unsupportedcontent', (b'parttype', b'params'))
 def handleerrorunsupportedcontent(op, inpart):
     """Used to transmit unknown content error over the wire"""
     kwargs = {}
     parttype = inpart.params.get(b'parttype')
     if parttype is not None:
         kwargs[b'parttype'] = parttype
     params = inpart.params.get(b'params')
     if params is not None:
         kwargs[b'params'] = params.split(b'\0')
 
     raise error.BundleUnknownFeatureError(**pycompat.strkwargs(kwargs))
 
 
 @parthandler(b'error:pushraced', (b'message',))
 def handleerrorpushraced(op, inpart):
     """Used to transmit push race error over the wire"""
     raise error.ResponseError(_(b'push failed:'), inpart.params[b'message'])
 
 
 @parthandler(b'listkeys', (b'namespace',))
 def handlelistkeys(op, inpart):
     """retrieve pushkey namespace content stored in a bundle2"""
     namespace = inpart.params[b'namespace']
     r = pushkey.decodekeys(inpart.read())
     op.records.add(b'listkeys', (namespace, r))
 
 
 @parthandler(b'pushkey', (b'namespace', b'key', b'old', b'new'))
 def handlepushkey(op, inpart):
     """process a pushkey request"""
     dec = pushkey.decode
     namespace = dec(inpart.params[b'namespace'])
     key = dec(inpart.params[b'key'])
     old = dec(inpart.params[b'old'])
     new = dec(inpart.params[b'new'])
     # Grab the transaction to ensure that we have the lock before performing the
     # pushkey.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     ret = op.repo.pushkey(namespace, key, old, new)
     record = {b'namespace': namespace, b'key': key, b'old': old, b'new': new}
     op.records.add(b'pushkey', record)
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:pushkey')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'return', b'%i' % ret, mandatory=False)
     if inpart.mandatory and not ret:
         kwargs = {}
         for key in (b'namespace', b'key', b'new', b'old', b'ret'):
             if key in inpart.params:
                 kwargs[key] = inpart.params[key]
         raise error.PushkeyFailed(
             partid=b'%d' % inpart.id, **pycompat.strkwargs(kwargs)
         )
 
 
 @parthandler(b'bookmarks')
 def handlebookmark(op, inpart):
     """transmit bookmark information
 
     The part contains binary encoded bookmark information.
 
     The exact behavior of this part can be controlled by the 'bookmarks' mode
     on the bundle operation.
 
     When mode is 'apply' (the default) the bookmark information is applied as
     is to the unbundling repository. Make sure a 'check:bookmarks' part is
     issued earlier to check for push races in such update. This behavior is
     suitable for pushing.
 
     When mode is 'records', the information is recorded into the 'bookmarks'
     records of the bundle operation. This behavior is suitable for pulling.
     """
     changes = bookmarks.binarydecode(op.repo, inpart)
 
     pushkeycompat = op.repo.ui.configbool(
         b'server', b'bookmarks-pushkey-compat'
     )
     bookmarksmode = op.modes.get(b'bookmarks', b'apply')
 
     if bookmarksmode == b'apply':
         tr = op.gettransaction()
         bookstore = op.repo._bookmarks
         if pushkeycompat:
             allhooks = []
             for book, node in changes:
                 hookargs = tr.hookargs.copy()
                 hookargs[b'pushkeycompat'] = b'1'
                 hookargs[b'namespace'] = b'bookmarks'
                 hookargs[b'key'] = book
                 hookargs[b'old'] = hex(bookstore.get(book, b''))
                 hookargs[b'new'] = hex(node if node is not None else b'')
                 allhooks.append(hookargs)
 
             for hookargs in allhooks:
                 op.repo.hook(
                     b'prepushkey', throw=True, **pycompat.strkwargs(hookargs)
                 )
 
         for book, node in changes:
             if bookmarks.isdivergent(book):
                 msg = _(b'cannot accept divergent bookmark %s!') % book
                 raise error.Abort(msg)
 
         bookstore.applychanges(op.repo, op.gettransaction(), changes)
 
         if pushkeycompat:
 
             def runhook(unused_success):
                 for hookargs in allhooks:
                     op.repo.hook(b'pushkey', **pycompat.strkwargs(hookargs))
 
             op.repo._afterlock(runhook)
 
     elif bookmarksmode == b'records':
         for book, node in changes:
             record = {b'bookmark': book, b'node': node}
             op.records.add(b'bookmarks', record)
     else:
         raise error.ProgrammingError(
             b'unknown bookmark mode: %s' % bookmarksmode
         )
 
 
 @parthandler(b'phase-heads')
 def handlephases(op, inpart):
     """apply phases from bundle part to repo"""
     headsbyphase = phases.binarydecode(inpart)
     phases.updatephases(op.repo.unfiltered(), op.gettransaction, headsbyphase)
 
 
 @parthandler(b'reply:pushkey', (b'return', b'in-reply-to'))
 def handlepushkeyreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'return'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'pushkey', {b'return': ret}, partid)
 
 
 @parthandler(b'obsmarkers')
 def handleobsmarker(op, inpart):
     """add a stream of obsmarkers to the repo"""
     tr = op.gettransaction()
     markerdata = inpart.read()
     if op.ui.config(b'experimental', b'obsmarkers-exchange-debug'):
         op.ui.writenoi18n(
             b'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(
             b'ignoring obsolescence markers, feature not enabled\n'
         )
         return
     new = op.repo.obsstore.mergemarkers(tr, markerdata)
     op.repo.invalidatevolatilesets()
     op.records.add(b'obsmarkers', {b'new': new})
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:obsmarkers')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'new', b'%i' % new, mandatory=False)
 
 
 @parthandler(b'reply:obsmarkers', (b'new', b'in-reply-to'))
 def handleobsmarkerreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'new'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'obsmarkers', {b'new': ret}, partid)
 
 
 @parthandler(b'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(b'experimental', b'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(b'ignoring incomplete received .hgtags fnodes data\n')
             break
         cache.setfnode(node, fnode)
         count += 1
 
     cache.write()
     op.ui.debug(b'applied %i hgtags fnodes cache entries\n' % count)
 
 
 rbcstruct = struct.Struct(b'>III')
 
 
 @parthandler(b'cache:rev-branch-cache')
 def handlerbc(op, inpart):
     """Legacy part, ignored for compatibility with bundles from or
     for Mercurial before 5.7. Newer Mercurial computes the cache
     efficiently enough during unbundling that the additional transfer
     is unnecessary."""
 
 
 @parthandler(b'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(b'push', b'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 = b"USERVAR_" + key
             hookargs[key] = value
         op.addhookargs(hookargs)
 
 
 @parthandler(b'stream2', (b'requirements', b'filecount', b'bytecount'))
 def handlestreamv2bundle(op, part):
 
-    requirements = urlreq.unquote(part.params[b'requirements']).split(b',')
+    requirements = urlreq.unquote(part.params[b'requirements'])
+    requirements = requirements.split(b',') if requirements else []
     filecount = int(part.params[b'filecount'])
     bytecount = int(part.params[b'bytecount'])
 
     repo = op.repo
     if len(repo):
         msg = _(b'cannot apply stream clone to non empty repository')
         raise error.Abort(msg)
 
     repo.ui.debug(b'applying stream bundle\n')
     streamclone.applybundlev2(repo, part, filecount, bytecount, requirements)
 
 
 def widen_bundle(
     bundler, repo, oldmatcher, newmatcher, common, known, cgversion, ellipses
 ):
     """generates bundle2 for widening a narrow clone
 
     bundler is the bundle to which data should be added
     repo is the localrepository instance
     oldmatcher matches what the client already has
     newmatcher matches what the client needs (including what it already has)
     common is set of common heads between server and client
     known is a set of revs known on the client side (used in ellipses)
     cgversion is the changegroup version to send
     ellipses is boolean value telling whether to send ellipses data or not
 
     returns bundle2 of the data required for extending
     """
     commonnodes = set()
     cl = repo.changelog
     for r in repo.revs(b"::%ln", common):
         commonnodes.add(cl.node(r))
     if commonnodes:
         packer = changegroup.getbundler(
             cgversion,
             repo,
             oldmatcher=oldmatcher,
             matcher=newmatcher,
             fullnodes=commonnodes,
         )
         cgdata = packer.generate(
             {repo.nullid},
             list(commonnodes),
             False,
             b'narrow_widen',
             changelog=False,
         )
 
         part = bundler.newpart(b'changegroup', data=cgdata)
         part.addparam(b'version', cgversion)
         if scmutil.istreemanifest(repo):
             part.addparam(b'treemanifest', b'1')
     if repository.REPO_FEATURE_SIDE_DATA in repo.features:
         part.addparam(b'exp-sidedata', b'1')
         wanted = format_remote_wanted_sidedata(repo)
         part.addparam(b'exp-wanted-sidedata', wanted)
 
     return bundler

mercurial/cext/parsers.c

@@ -1,1304 +1,1306 b''
 /*
  parsers.c - efficient content parsing
 
  Copyright 2008 Olivia Mackall <[e-mail]> and others
 
  This software may be used and distributed according to the terms of
  the GNU General Public License, incorporated herein by reference.
 */
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
 #include <ctype.h>
 #include <stddef.h>
 #include <string.h>
 
 #include "bitmanipulation.h"
 #include "charencode.h"
 #include "util.h"
 
 static const char *const versionerrortext = "Python minor version mismatch";
 
 static const int dirstate_v1_from_p2 = -2;
 static const int dirstate_v1_nonnormal = -1;
 static const int ambiguous_time = -1;
 
 static PyObject *dict_new_presized(PyObject *self, PyObject *args)
 {
 	Py_ssize_t expected_size;
 
 	if (!PyArg_ParseTuple(args, "n:make_presized_dict", &expected_size)) {
 		return NULL;
 	}
 
 	return _dict_new_presized(expected_size);
 }
 
 static PyObject *dirstate_item_new(PyTypeObject *subtype, PyObject *args,
                                    PyObject *kwds)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	dirstateItemObject *t;
 	int wc_tracked;
 	int p1_tracked;
 	int p2_info;
 	int has_meaningful_data;
 	int has_meaningful_mtime;
 	int mtime_second_ambiguous;
 	int mode;
 	int size;
 	int mtime_s;
 	int mtime_ns;
 	PyObject *parentfiledata;
 	PyObject *mtime;
 	PyObject *fallback_exec;
 	PyObject *fallback_symlink;
 	static char *keywords_name[] = {
 	    "wc_tracked",          "p1_tracked",           "p2_info",
 	    "has_meaningful_data", "has_meaningful_mtime", "parentfiledata",
 	    "fallback_exec",       "fallback_symlink",     NULL,
 	};
 	wc_tracked = 0;
 	p1_tracked = 0;
 	p2_info = 0;
 	has_meaningful_mtime = 1;
 	has_meaningful_data = 1;
 	mtime_second_ambiguous = 0;
 	parentfiledata = Py_None;
 	fallback_exec = Py_None;
 	fallback_symlink = Py_None;
 	if (!PyArg_ParseTupleAndKeywords(args, kwds, "|iiiiiOOO", keywords_name,
 	                                 &wc_tracked, &p1_tracked, &p2_info,
 	                                 &has_meaningful_data,
 	                                 &has_meaningful_mtime, &parentfiledata,
 	                                 &fallback_exec, &fallback_symlink)) {
 		return NULL;
 	}
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
 
 	t->flags = 0;
 	if (wc_tracked) {
 		t->flags |= dirstate_flag_wc_tracked;
 	}
 	if (p1_tracked) {
 		t->flags |= dirstate_flag_p1_tracked;
 	}
 	if (p2_info) {
 		t->flags |= dirstate_flag_p2_info;
 	}
 
 	if (fallback_exec != Py_None) {
 		t->flags |= dirstate_flag_has_fallback_exec;
 		if (PyObject_IsTrue(fallback_exec)) {
 			t->flags |= dirstate_flag_fallback_exec;
 		}
 	}
 	if (fallback_symlink != Py_None) {
 		t->flags |= dirstate_flag_has_fallback_symlink;
 		if (PyObject_IsTrue(fallback_symlink)) {
 			t->flags |= dirstate_flag_fallback_symlink;
 		}
 	}
 
 	if (parentfiledata != Py_None) {
 		if (!PyArg_ParseTuple(parentfiledata, "iiO", &mode, &size,
 		                      &mtime)) {
 			return NULL;
 		}
 		if (mtime != Py_None) {
 			if (!PyArg_ParseTuple(mtime, "iii", &mtime_s, &mtime_ns,
 			                      &mtime_second_ambiguous)) {
 				return NULL;
 			}
 		} else {
 			has_meaningful_mtime = 0;
 		}
 	} else {
 		has_meaningful_data = 0;
 		has_meaningful_mtime = 0;
 	}
 	if (has_meaningful_data) {
 		t->flags |= dirstate_flag_has_meaningful_data;
 		t->mode = mode;
 		t->size = size;
 		if (mtime_second_ambiguous) {
 			t->flags |= dirstate_flag_mtime_second_ambiguous;
 		}
 	} else {
 		t->mode = 0;
 		t->size = 0;
 	}
 	if (has_meaningful_mtime) {
 		t->flags |= dirstate_flag_has_mtime;
 		t->mtime_s = mtime_s;
 		t->mtime_ns = mtime_ns;
 	} else {
 		t->mtime_s = 0;
 		t->mtime_ns = 0;
 	}
 	return (PyObject *)t;
 }
 
 static void dirstate_item_dealloc(PyObject *o)
 {
 	PyObject_Del(o);
 }
 
 static inline bool dirstate_item_c_tracked(dirstateItemObject *self)
 {
 	return (self->flags & dirstate_flag_wc_tracked);
 }
 
 static inline bool dirstate_item_c_any_tracked(dirstateItemObject *self)
 {
 	const int mask = dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
 	                 dirstate_flag_p2_info;
 	return (self->flags & mask);
 }
 
 static inline bool dirstate_item_c_added(dirstateItemObject *self)
 {
 	const int mask = (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
 	                  dirstate_flag_p2_info);
 	const int target = dirstate_flag_wc_tracked;
 	return (self->flags & mask) == target;
 }
 
 static inline bool dirstate_item_c_removed(dirstateItemObject *self)
 {
 	if (self->flags & dirstate_flag_wc_tracked) {
 		return false;
 	}
 	return (self->flags &
 	        (dirstate_flag_p1_tracked | dirstate_flag_p2_info));
 }
 
 static inline bool dirstate_item_c_merged(dirstateItemObject *self)
 {
 	return ((self->flags & dirstate_flag_wc_tracked) &&
 	        (self->flags & dirstate_flag_p1_tracked) &&
 	        (self->flags & dirstate_flag_p2_info));
 }
 
 static inline bool dirstate_item_c_from_p2(dirstateItemObject *self)
 {
 	return ((self->flags & dirstate_flag_wc_tracked) &&
 	        !(self->flags & dirstate_flag_p1_tracked) &&
 	        (self->flags & dirstate_flag_p2_info));
 }
 
 static inline char dirstate_item_c_v1_state(dirstateItemObject *self)
 {
 	if (dirstate_item_c_removed(self)) {
 		return 'r';
 	} else if (dirstate_item_c_merged(self)) {
 		return 'm';
 	} else if (dirstate_item_c_added(self)) {
 		return 'a';
 	} else {
 		return 'n';
 	}
 }
 
 static inline bool dirstate_item_c_has_fallback_exec(dirstateItemObject *self)
 {
 	return (bool)self->flags & dirstate_flag_has_fallback_exec;
 }
 
 static inline bool
 dirstate_item_c_has_fallback_symlink(dirstateItemObject *self)
 {
 	return (bool)self->flags & dirstate_flag_has_fallback_symlink;
 }
 
 static inline int dirstate_item_c_v1_mode(dirstateItemObject *self)
 {
 	if (self->flags & dirstate_flag_has_meaningful_data) {
 		return self->mode;
 	} else {
 		return 0;
 	}
 }
 
 static inline int dirstate_item_c_v1_size(dirstateItemObject *self)
 {
 	if (!(self->flags & dirstate_flag_wc_tracked) &&
 	    (self->flags & dirstate_flag_p2_info)) {
 		if (self->flags & dirstate_flag_p1_tracked) {
 			return dirstate_v1_nonnormal;
 		} else {
 			return dirstate_v1_from_p2;
 		}
 	} else if (dirstate_item_c_removed(self)) {
 		return 0;
 	} else if (self->flags & dirstate_flag_p2_info) {
 		return dirstate_v1_from_p2;
 	} else if (dirstate_item_c_added(self)) {
 		return dirstate_v1_nonnormal;
 	} else if (self->flags & dirstate_flag_has_meaningful_data) {
 		return self->size;
 	} else {
 		return dirstate_v1_nonnormal;
 	}
 }
 
 static inline int dirstate_item_c_v1_mtime(dirstateItemObject *self)
 {
 	if (dirstate_item_c_removed(self)) {
 		return 0;
 	} else if (!(self->flags & dirstate_flag_has_mtime) ||
 	           !(self->flags & dirstate_flag_p1_tracked) ||
 	           !(self->flags & dirstate_flag_wc_tracked) ||
 	           (self->flags & dirstate_flag_p2_info) ||
 	           (self->flags & dirstate_flag_mtime_second_ambiguous)) {
 		return ambiguous_time;
 	} else {
 		return self->mtime_s;
 	}
 }
 
 static PyObject *dirstate_item_v2_data(dirstateItemObject *self)
 {
 	int flags = self->flags;
 	int mode = dirstate_item_c_v1_mode(self);
 #ifdef S_IXUSR
 	/* This is for platforms with an exec bit */
 	if ((mode & S_IXUSR) != 0) {
 		flags |= dirstate_flag_mode_exec_perm;
 	} else {
 		flags &= ~dirstate_flag_mode_exec_perm;
 	}
 #else
 	flags &= ~dirstate_flag_mode_exec_perm;
 #endif
 #ifdef S_ISLNK
 	/* This is for platforms with support for symlinks */
 	if (S_ISLNK(mode)) {
 		flags |= dirstate_flag_mode_is_symlink;
 	} else {
 		flags &= ~dirstate_flag_mode_is_symlink;
 	}
 #else
 	flags &= ~dirstate_flag_mode_is_symlink;
 #endif
 	return Py_BuildValue("iiii", flags, self->size, self->mtime_s,
 	                     self->mtime_ns);
 };
 
 static PyObject *dirstate_item_v1_state(dirstateItemObject *self)
 {
 	char state = dirstate_item_c_v1_state(self);
 	return PyBytes_FromStringAndSize(&state, 1);
 };
 
 static PyObject *dirstate_item_v1_mode(dirstateItemObject *self)
 {
 	return PyLong_FromLong(dirstate_item_c_v1_mode(self));
 };
 
 static PyObject *dirstate_item_v1_size(dirstateItemObject *self)
 {
 	return PyLong_FromLong(dirstate_item_c_v1_size(self));
 };
 
 static PyObject *dirstate_item_v1_mtime(dirstateItemObject *self)
 {
 	return PyLong_FromLong(dirstate_item_c_v1_mtime(self));
 };
 
 static PyObject *dirstate_item_mtime_likely_equal_to(dirstateItemObject *self,
                                                      PyObject *other)
 {
 	int other_s;
 	int other_ns;
 	int other_second_ambiguous;
 	if (!PyArg_ParseTuple(other, "iii", &other_s, &other_ns,
 	                      &other_second_ambiguous)) {
 		return NULL;
 	}
 	if (!(self->flags & dirstate_flag_has_mtime)) {
 		Py_RETURN_FALSE;
 	}
 	if (self->mtime_s != other_s) {
 		Py_RETURN_FALSE;
 	}
 	if (self->mtime_ns == 0 || other_ns == 0) {
 		if (self->flags & dirstate_flag_mtime_second_ambiguous) {
 			Py_RETURN_FALSE;
 		} else {
 			Py_RETURN_TRUE;
 		}
 	}
 	if (self->mtime_ns == other_ns) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 /* This will never change since it's bound to V1
  */
 static inline dirstateItemObject *
 dirstate_item_from_v1_data(char state, int mode, int size, int mtime)
 {
 	dirstateItemObject *t =
 	    PyObject_New(dirstateItemObject, &dirstateItemType);
 	if (!t) {
 		return NULL;
 	}
 	t->flags = 0;
 	t->mode = 0;
 	t->size = 0;
 	t->mtime_s = 0;
 	t->mtime_ns = 0;
 
 	if (state == 'm') {
 		t->flags = (dirstate_flag_wc_tracked |
 		            dirstate_flag_p1_tracked | dirstate_flag_p2_info);
 	} else if (state == 'a') {
 		t->flags = dirstate_flag_wc_tracked;
 	} else if (state == 'r') {
 		if (size == dirstate_v1_nonnormal) {
 			t->flags =
 			    dirstate_flag_p1_tracked | dirstate_flag_p2_info;
 		} else if (size == dirstate_v1_from_p2) {
 			t->flags = dirstate_flag_p2_info;
 		} else {
 			t->flags = dirstate_flag_p1_tracked;
 		}
 	} else if (state == 'n') {
 		if (size == dirstate_v1_from_p2) {
 			t->flags =
 			    dirstate_flag_wc_tracked | dirstate_flag_p2_info;
 		} else if (size == dirstate_v1_nonnormal) {
 			t->flags =
 			    dirstate_flag_wc_tracked | dirstate_flag_p1_tracked;
 		} else if (mtime == ambiguous_time) {
 			t->flags = (dirstate_flag_wc_tracked |
 			            dirstate_flag_p1_tracked |
 			            dirstate_flag_has_meaningful_data);
 			t->mode = mode;
 			t->size = size;
 		} else {
 			t->flags = (dirstate_flag_wc_tracked |
 			            dirstate_flag_p1_tracked |
 			            dirstate_flag_has_meaningful_data |
 			            dirstate_flag_has_mtime);
 			t->mode = mode;
 			t->size = size;
 			t->mtime_s = mtime;
 		}
 	} else {
 		PyErr_Format(PyExc_RuntimeError,
 		             "unknown state: `%c` (%d, %d, %d)", state, mode,
 		             size, mtime, NULL);
 		Py_DECREF(t);
 		return NULL;
 	}
 
 	return t;
 }
 
 /* This will never change since it's bound to V1, unlike `dirstate_item_new` */
 static PyObject *dirstate_item_from_v1_meth(PyTypeObject *subtype,
                                             PyObject *args)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	char state;
 	int size, mode, mtime;
 	if (!PyArg_ParseTuple(args, "ciii", &state, &mode, &size, &mtime)) {
 		return NULL;
 	}
 	return (PyObject *)dirstate_item_from_v1_data(state, mode, size, mtime);
 };
 
 static PyObject *dirstate_item_from_v2_meth(PyTypeObject *subtype,
                                             PyObject *args)
 {
 	dirstateItemObject *t =
 	    PyObject_New(dirstateItemObject, &dirstateItemType);
 	if (!t) {
 		return NULL;
 	}
 	if (!PyArg_ParseTuple(args, "iiii", &t->flags, &t->size, &t->mtime_s,
 	                      &t->mtime_ns)) {
 		return NULL;
 	}
 	if (t->flags & dirstate_flag_expected_state_is_modified) {
 		t->flags &= ~(dirstate_flag_expected_state_is_modified |
 		              dirstate_flag_has_meaningful_data |
 		              dirstate_flag_has_mtime);
 	}
 	t->mode = 0;
 	if (t->flags & dirstate_flag_has_meaningful_data) {
 		if (t->flags & dirstate_flag_mode_exec_perm) {
 			t->mode = 0755;
 		} else {
 			t->mode = 0644;
 		}
 		if (t->flags & dirstate_flag_mode_is_symlink) {
 			t->mode |= S_IFLNK;
 		} else {
 			t->mode |= S_IFREG;
 		}
 	}
 	return (PyObject *)t;
 };
 
 /* This means the next status call will have to actually check its content
    to make sure it is correct. */
 static PyObject *dirstate_item_set_possibly_dirty(dirstateItemObject *self)
 {
 	self->flags &= ~dirstate_flag_has_mtime;
 	Py_RETURN_NONE;
 }
 
 /* See docstring of the python implementation for details */
 static PyObject *dirstate_item_set_clean(dirstateItemObject *self,
                                          PyObject *args)
 {
 	int size, mode, mtime_s, mtime_ns, mtime_second_ambiguous;
 	PyObject *mtime;
 	mtime_s = 0;
 	mtime_ns = 0;
 	mtime_second_ambiguous = 0;
 	if (!PyArg_ParseTuple(args, "iiO", &mode, &size, &mtime)) {
 		return NULL;
 	}
 	if (mtime != Py_None) {
 		if (!PyArg_ParseTuple(mtime, "iii", &mtime_s, &mtime_ns,
 		                      &mtime_second_ambiguous)) {
 			return NULL;
 		}
 	} else {
 		self->flags &= ~dirstate_flag_has_mtime;
 	}
 	self->flags = dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
 	              dirstate_flag_has_meaningful_data |
 	              dirstate_flag_has_mtime;
 	if (mtime_second_ambiguous) {
 		self->flags |= dirstate_flag_mtime_second_ambiguous;
 	}
 	self->mode = mode;
 	self->size = size;
 	self->mtime_s = mtime_s;
 	self->mtime_ns = mtime_ns;
 	Py_RETURN_NONE;
 }
 
 static PyObject *dirstate_item_set_tracked(dirstateItemObject *self)
 {
 	self->flags |= dirstate_flag_wc_tracked;
 	self->flags &= ~dirstate_flag_has_mtime;
 	Py_RETURN_NONE;
 }
 
 static PyObject *dirstate_item_set_untracked(dirstateItemObject *self)
 {
 	self->flags &= ~dirstate_flag_wc_tracked;
+	self->flags &= ~dirstate_flag_has_meaningful_data;
+	self->flags &= ~dirstate_flag_has_mtime;
 	self->mode = 0;
 	self->size = 0;
 	self->mtime_s = 0;
 	self->mtime_ns = 0;
 	Py_RETURN_NONE;
 }
 
 static PyObject *dirstate_item_drop_merge_data(dirstateItemObject *self)
 {
 	if (self->flags & dirstate_flag_p2_info) {
 		self->flags &= ~(dirstate_flag_p2_info |
 		                 dirstate_flag_has_meaningful_data |
 		                 dirstate_flag_has_mtime);
 		self->mode = 0;
 		self->size = 0;
 		self->mtime_s = 0;
 		self->mtime_ns = 0;
 	}
 	Py_RETURN_NONE;
 }
 static PyMethodDef dirstate_item_methods[] = {
     {"v2_data", (PyCFunction)dirstate_item_v2_data, METH_NOARGS,
      "return data suitable for v2 serialization"},
     {"v1_state", (PyCFunction)dirstate_item_v1_state, METH_NOARGS,
      "return a \"state\" suitable for v1 serialization"},
     {"v1_mode", (PyCFunction)dirstate_item_v1_mode, METH_NOARGS,
      "return a \"mode\" suitable for v1 serialization"},
     {"v1_size", (PyCFunction)dirstate_item_v1_size, METH_NOARGS,
      "return a \"size\" suitable for v1 serialization"},
     {"v1_mtime", (PyCFunction)dirstate_item_v1_mtime, METH_NOARGS,
      "return a \"mtime\" suitable for v1 serialization"},
     {"mtime_likely_equal_to", (PyCFunction)dirstate_item_mtime_likely_equal_to,
      METH_O, "True if the stored mtime is likely equal to the given mtime"},
     {"from_v1_data", (PyCFunction)dirstate_item_from_v1_meth,
      METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V1 data"},
     {"from_v2_data", (PyCFunction)dirstate_item_from_v2_meth,
      METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V2 data"},
     {"set_possibly_dirty", (PyCFunction)dirstate_item_set_possibly_dirty,
      METH_NOARGS, "mark a file as \"possibly dirty\""},
     {"set_clean", (PyCFunction)dirstate_item_set_clean, METH_VARARGS,
      "mark a file as \"clean\""},
     {"set_tracked", (PyCFunction)dirstate_item_set_tracked, METH_NOARGS,
      "mark a file as \"tracked\""},
     {"set_untracked", (PyCFunction)dirstate_item_set_untracked, METH_NOARGS,
      "mark a file as \"untracked\""},
     {"drop_merge_data", (PyCFunction)dirstate_item_drop_merge_data, METH_NOARGS,
      "remove all \"merge-only\" from a DirstateItem"},
     {NULL} /* Sentinel */
 };
 
 static PyObject *dirstate_item_get_mode(dirstateItemObject *self)
 {
 	return PyLong_FromLong(dirstate_item_c_v1_mode(self));
 };
 
 static PyObject *dirstate_item_get_size(dirstateItemObject *self)
 {
 	return PyLong_FromLong(dirstate_item_c_v1_size(self));
 };
 
 static PyObject *dirstate_item_get_mtime(dirstateItemObject *self)
 {
 	return PyLong_FromLong(dirstate_item_c_v1_mtime(self));
 };
 
 static PyObject *dirstate_item_get_state(dirstateItemObject *self)
 {
 	char state = dirstate_item_c_v1_state(self);
 	return PyBytes_FromStringAndSize(&state, 1);
 };
 
 static PyObject *dirstate_item_get_has_fallback_exec(dirstateItemObject *self)
 {
 	if (dirstate_item_c_has_fallback_exec(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_fallback_exec(dirstateItemObject *self)
 {
 	if (dirstate_item_c_has_fallback_exec(self)) {
 		if (self->flags & dirstate_flag_fallback_exec) {
 			Py_RETURN_TRUE;
 		} else {
 			Py_RETURN_FALSE;
 		}
 	} else {
 		Py_RETURN_NONE;
 	}
 };
 
 static int dirstate_item_set_fallback_exec(dirstateItemObject *self,
                                            PyObject *value)
 {
 	if ((value == Py_None) || (value == NULL)) {
 		self->flags &= ~dirstate_flag_has_fallback_exec;
 	} else {
 		self->flags |= dirstate_flag_has_fallback_exec;
 		if (PyObject_IsTrue(value)) {
 			self->flags |= dirstate_flag_fallback_exec;
 		} else {
 			self->flags &= ~dirstate_flag_fallback_exec;
 		}
 	}
 	return 0;
 };
 
 static PyObject *
 dirstate_item_get_has_fallback_symlink(dirstateItemObject *self)
 {
 	if (dirstate_item_c_has_fallback_symlink(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_fallback_symlink(dirstateItemObject *self)
 {
 	if (dirstate_item_c_has_fallback_symlink(self)) {
 		if (self->flags & dirstate_flag_fallback_symlink) {
 			Py_RETURN_TRUE;
 		} else {
 			Py_RETURN_FALSE;
 		}
 	} else {
 		Py_RETURN_NONE;
 	}
 };
 
 static int dirstate_item_set_fallback_symlink(dirstateItemObject *self,
                                               PyObject *value)
 {
 	if ((value == Py_None) || (value == NULL)) {
 		self->flags &= ~dirstate_flag_has_fallback_symlink;
 	} else {
 		self->flags |= dirstate_flag_has_fallback_symlink;
 		if (PyObject_IsTrue(value)) {
 			self->flags |= dirstate_flag_fallback_symlink;
 		} else {
 			self->flags &= ~dirstate_flag_fallback_symlink;
 		}
 	}
 	return 0;
 };
 
 static PyObject *dirstate_item_get_tracked(dirstateItemObject *self)
 {
 	if (dirstate_item_c_tracked(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 static PyObject *dirstate_item_get_p1_tracked(dirstateItemObject *self)
 {
 	if (self->flags & dirstate_flag_p1_tracked) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_added(dirstateItemObject *self)
 {
 	if (dirstate_item_c_added(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_p2_info(dirstateItemObject *self)
 {
 	if (self->flags & dirstate_flag_wc_tracked &&
 	    self->flags & dirstate_flag_p2_info) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_merged(dirstateItemObject *self)
 {
 	if (dirstate_item_c_merged(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_from_p2(dirstateItemObject *self)
 {
 	if (dirstate_item_c_from_p2(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_maybe_clean(dirstateItemObject *self)
 {
 	if (!(self->flags & dirstate_flag_wc_tracked)) {
 		Py_RETURN_FALSE;
 	} else if (!(self->flags & dirstate_flag_p1_tracked)) {
 		Py_RETURN_FALSE;
 	} else if (self->flags & dirstate_flag_p2_info) {
 		Py_RETURN_FALSE;
 	} else {
 		Py_RETURN_TRUE;
 	}
 };
 
 static PyObject *dirstate_item_get_any_tracked(dirstateItemObject *self)
 {
 	if (dirstate_item_c_any_tracked(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_removed(dirstateItemObject *self)
 {
 	if (dirstate_item_c_removed(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyGetSetDef dirstate_item_getset[] = {
     {"mode", (getter)dirstate_item_get_mode, NULL, "mode", NULL},
     {"size", (getter)dirstate_item_get_size, NULL, "size", NULL},
     {"mtime", (getter)dirstate_item_get_mtime, NULL, "mtime", NULL},
     {"state", (getter)dirstate_item_get_state, NULL, "state", NULL},
     {"has_fallback_exec", (getter)dirstate_item_get_has_fallback_exec, NULL,
      "has_fallback_exec", NULL},
     {"fallback_exec", (getter)dirstate_item_get_fallback_exec,
      (setter)dirstate_item_set_fallback_exec, "fallback_exec", NULL},
     {"has_fallback_symlink", (getter)dirstate_item_get_has_fallback_symlink,
      NULL, "has_fallback_symlink", NULL},
     {"fallback_symlink", (getter)dirstate_item_get_fallback_symlink,
      (setter)dirstate_item_set_fallback_symlink, "fallback_symlink", NULL},
     {"tracked", (getter)dirstate_item_get_tracked, NULL, "tracked", NULL},
     {"p1_tracked", (getter)dirstate_item_get_p1_tracked, NULL, "p1_tracked",
      NULL},
     {"added", (getter)dirstate_item_get_added, NULL, "added", NULL},
     {"p2_info", (getter)dirstate_item_get_p2_info, NULL, "p2_info", NULL},
     {"merged", (getter)dirstate_item_get_merged, NULL, "merged", NULL},
     {"from_p2", (getter)dirstate_item_get_from_p2, NULL, "from_p2", NULL},
     {"maybe_clean", (getter)dirstate_item_get_maybe_clean, NULL, "maybe_clean",
      NULL},
     {"any_tracked", (getter)dirstate_item_get_any_tracked, NULL, "any_tracked",
      NULL},
     {"removed", (getter)dirstate_item_get_removed, NULL, "removed", NULL},
     {NULL} /* Sentinel */
 };
 
 PyTypeObject dirstateItemType = {
     PyVarObject_HEAD_INIT(NULL, 0)     /* header */
     "dirstate_tuple",                  /* tp_name */
     sizeof(dirstateItemObject),        /* tp_basicsize */
     0,                                 /* tp_itemsize */
     (destructor)dirstate_item_dealloc, /* tp_dealloc */
     0,                                 /* tp_print */
     0,                                 /* tp_getattr */
     0,                                 /* tp_setattr */
     0,                                 /* tp_compare */
     0,                                 /* tp_repr */
     0,                                 /* tp_as_number */
     0,                                 /* tp_as_sequence */
     0,                                 /* tp_as_mapping */
     0,                                 /* tp_hash  */
     0,                                 /* tp_call */
     0,                                 /* tp_str */
     0,                                 /* tp_getattro */
     0,                                 /* tp_setattro */
     0,                                 /* tp_as_buffer */
     Py_TPFLAGS_DEFAULT,                /* tp_flags */
     "dirstate tuple",                  /* tp_doc */
     0,                                 /* tp_traverse */
     0,                                 /* tp_clear */
     0,                                 /* tp_richcompare */
     0,                                 /* tp_weaklistoffset */
     0,                                 /* tp_iter */
     0,                                 /* tp_iternext */
     dirstate_item_methods,             /* tp_methods */
     0,                                 /* tp_members */
     dirstate_item_getset,              /* tp_getset */
     0,                                 /* tp_base */
     0,                                 /* tp_dict */
     0,                                 /* tp_descr_get */
     0,                                 /* tp_descr_set */
     0,                                 /* tp_dictoffset */
     0,                                 /* tp_init */
     0,                                 /* tp_alloc */
     dirstate_item_new,                 /* tp_new */
 };
 
 static PyObject *parse_dirstate(PyObject *self, PyObject *args)
 {
 	PyObject *dmap, *cmap, *parents = NULL, *ret = NULL;
 	PyObject *fname = NULL, *cname = NULL, *entry = NULL;
 	char state, *cur, *str, *cpos;
 	int mode, size, mtime;
 	unsigned int flen, pos = 40;
 	Py_ssize_t len = 40;
 	Py_ssize_t readlen;
 
 	if (!PyArg_ParseTuple(args, "O!O!y#:parse_dirstate", &PyDict_Type,
 	                      &dmap, &PyDict_Type, &cmap, &str, &readlen)) {
 		goto quit;
 	}
 
 	len = readlen;
 
 	/* read parents */
 	if (len < 40) {
 		PyErr_SetString(PyExc_ValueError,
 		                "too little data for parents");
 		goto quit;
 	}
 
 	parents = Py_BuildValue("y#y#", str, (Py_ssize_t)20, str + 20,
 	                        (Py_ssize_t)20);
 	if (!parents) {
 		goto quit;
 	}
 
 	/* read filenames */
 	while (pos >= 40 && pos < len) {
 		if (pos + 17 > len) {
 			PyErr_SetString(PyExc_ValueError,
 			                "overflow in dirstate");
 			goto quit;
 		}
 		cur = str + pos;
 		/* unpack header */
 		state = *cur;
 		mode = getbe32(cur + 1);
 		size = getbe32(cur + 5);
 		mtime = getbe32(cur + 9);
 		flen = getbe32(cur + 13);
 		pos += 17;
 		cur += 17;
 		if (flen > len - pos) {
 			PyErr_SetString(PyExc_ValueError,
 			                "overflow in dirstate");
 			goto quit;
 		}
 
 		entry = (PyObject *)dirstate_item_from_v1_data(state, mode,
 		                                               size, mtime);
 		if (!entry)
 			goto quit;
 		cpos = memchr(cur, 0, flen);
 		if (cpos) {
 			fname = PyBytes_FromStringAndSize(cur, cpos - cur);
 			cname = PyBytes_FromStringAndSize(
 			    cpos + 1, flen - (cpos - cur) - 1);
 			if (!fname || !cname ||
 			    PyDict_SetItem(cmap, fname, cname) == -1 ||
 			    PyDict_SetItem(dmap, fname, entry) == -1) {
 				goto quit;
 			}
 			Py_DECREF(cname);
 		} else {
 			fname = PyBytes_FromStringAndSize(cur, flen);
 			if (!fname ||
 			    PyDict_SetItem(dmap, fname, entry) == -1) {
 				goto quit;
 			}
 		}
 		Py_DECREF(fname);
 		Py_DECREF(entry);
 		fname = cname = entry = NULL;
 		pos += flen;
 	}
 
 	ret = parents;
 	Py_INCREF(ret);
 quit:
 	Py_XDECREF(fname);
 	Py_XDECREF(cname);
 	Py_XDECREF(entry);
 	Py_XDECREF(parents);
 	return ret;
 }
 
 /*
  * Efficiently pack a dirstate object into its on-disk format.
  */
 static PyObject *pack_dirstate(PyObject *self, PyObject *args)
 {
 	PyObject *packobj = NULL;
 	PyObject *map, *copymap, *pl, *mtime_unset = NULL;
 	Py_ssize_t nbytes, pos, l;
 	PyObject *k, *v = NULL, *pn;
 	char *p, *s;
 
 	if (!PyArg_ParseTuple(args, "O!O!O!:pack_dirstate", &PyDict_Type, &map,
 	                      &PyDict_Type, &copymap, &PyTuple_Type, &pl)) {
 		return NULL;
 	}
 
 	if (PyTuple_Size(pl) != 2) {
 		PyErr_SetString(PyExc_TypeError, "expected 2-element tuple");
 		return NULL;
 	}
 
 	/* Figure out how much we need to allocate. */
 	for (nbytes = 40, pos = 0; PyDict_Next(map, &pos, &k, &v);) {
 		PyObject *c;
 		if (!PyBytes_Check(k)) {
 			PyErr_SetString(PyExc_TypeError, "expected string key");
 			goto bail;
 		}
 		nbytes += PyBytes_GET_SIZE(k) + 17;
 		c = PyDict_GetItem(copymap, k);
 		if (c) {
 			if (!PyBytes_Check(c)) {
 				PyErr_SetString(PyExc_TypeError,
 				                "expected string key");
 				goto bail;
 			}
 			nbytes += PyBytes_GET_SIZE(c) + 1;
 		}
 	}
 
 	packobj = PyBytes_FromStringAndSize(NULL, nbytes);
 	if (packobj == NULL) {
 		goto bail;
 	}
 
 	p = PyBytes_AS_STRING(packobj);
 
 	pn = PyTuple_GET_ITEM(pl, 0);
 	if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) {
 		PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash");
 		goto bail;
 	}
 	memcpy(p, s, l);
 	p += 20;
 	pn = PyTuple_GET_ITEM(pl, 1);
 	if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) {
 		PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash");
 		goto bail;
 	}
 	memcpy(p, s, l);
 	p += 20;
 
 	for (pos = 0; PyDict_Next(map, &pos, &k, &v);) {
 		dirstateItemObject *tuple;
 		char state;
 		int mode, size, mtime;
 		Py_ssize_t len, l;
 		PyObject *o;
 		char *t;
 
 		if (!dirstate_tuple_check(v)) {
 			PyErr_SetString(PyExc_TypeError,
 			                "expected a dirstate tuple");
 			goto bail;
 		}
 		tuple = (dirstateItemObject *)v;
 
 		state = dirstate_item_c_v1_state(tuple);
 		mode = dirstate_item_c_v1_mode(tuple);
 		size = dirstate_item_c_v1_size(tuple);
 		mtime = dirstate_item_c_v1_mtime(tuple);
 		*p++ = state;
 		putbe32((uint32_t)mode, p);
 		putbe32((uint32_t)size, p + 4);
 		putbe32((uint32_t)mtime, p + 8);
 		t = p + 12;
 		p += 16;
 		len = PyBytes_GET_SIZE(k);
 		memcpy(p, PyBytes_AS_STRING(k), len);
 		p += len;
 		o = PyDict_GetItem(copymap, k);
 		if (o) {
 			*p++ = '\0';
 			l = PyBytes_GET_SIZE(o);
 			memcpy(p, PyBytes_AS_STRING(o), l);
 			p += l;
 			len += l + 1;
 		}
 		putbe32((uint32_t)len, t);
 	}
 
 	pos = p - PyBytes_AS_STRING(packobj);
 	if (pos != nbytes) {
 		PyErr_Format(PyExc_SystemError, "bad dirstate size: %ld != %ld",
 		             (long)pos, (long)nbytes);
 		goto bail;
 	}
 
 	return packobj;
 bail:
 	Py_XDECREF(mtime_unset);
 	Py_XDECREF(packobj);
 	Py_XDECREF(v);
 	return NULL;
 }
 
 #define BUMPED_FIX 1
 #define USING_SHA_256 2
 #define FM1_HEADER_SIZE (4 + 8 + 2 + 2 + 1 + 1 + 1)
 
 static PyObject *readshas(const char *source, unsigned char num,
                           Py_ssize_t hashwidth)
 {
 	int i;
 	PyObject *list = PyTuple_New(num);
 	if (list == NULL) {
 		return NULL;
 	}
 	for (i = 0; i < num; i++) {
 		PyObject *hash = PyBytes_FromStringAndSize(source, hashwidth);
 		if (hash == NULL) {
 			Py_DECREF(list);
 			return NULL;
 		}
 		PyTuple_SET_ITEM(list, i, hash);
 		source += hashwidth;
 	}
 	return list;
 }
 
 static PyObject *fm1readmarker(const char *databegin, const char *dataend,
                                uint32_t *msize)
 {
 	const char *data = databegin;
 	const char *meta;
 
 	double mtime;
 	int16_t tz;
 	uint16_t flags;
 	unsigned char nsuccs, nparents, nmetadata;
 	Py_ssize_t hashwidth = 20;
 
 	PyObject *prec = NULL, *parents = NULL, *succs = NULL;
 	PyObject *metadata = NULL, *ret = NULL;
 	int i;
 
 	if (data + FM1_HEADER_SIZE > dataend) {
 		goto overflow;
 	}
 
 	*msize = getbe32(data);
 	data += 4;
 	mtime = getbefloat64(data);
 	data += 8;
 	tz = getbeint16(data);
 	data += 2;
 	flags = getbeuint16(data);
 	data += 2;
 
 	if (flags & USING_SHA_256) {
 		hashwidth = 32;
 	}
 
 	nsuccs = (unsigned char)(*data++);
 	nparents = (unsigned char)(*data++);
 	nmetadata = (unsigned char)(*data++);
 
 	if (databegin + *msize > dataend) {
 		goto overflow;
 	}
 	dataend = databegin + *msize; /* narrow down to marker size */
 
 	if (data + hashwidth > dataend) {
 		goto overflow;
 	}
 	prec = PyBytes_FromStringAndSize(data, hashwidth);
 	data += hashwidth;
 	if (prec == NULL) {
 		goto bail;
 	}
 
 	if (data + nsuccs * hashwidth > dataend) {
 		goto overflow;
 	}
 	succs = readshas(data, nsuccs, hashwidth);
 	if (succs == NULL) {
 		goto bail;
 	}
 	data += nsuccs * hashwidth;
 
 	if (nparents == 1 || nparents == 2) {
 		if (data + nparents * hashwidth > dataend) {
 			goto overflow;
 		}
 		parents = readshas(data, nparents, hashwidth);
 		if (parents == NULL) {
 			goto bail;
 		}
 		data += nparents * hashwidth;
 	} else {
 		parents = Py_None;
 		Py_INCREF(parents);
 	}
 
 	if (data + 2 * nmetadata > dataend) {
 		goto overflow;
 	}
 	meta = data + (2 * nmetadata);
 	metadata = PyTuple_New(nmetadata);
 	if (metadata == NULL) {
 		goto bail;
 	}
 	for (i = 0; i < nmetadata; i++) {
 		PyObject *tmp, *left = NULL, *right = NULL;
 		Py_ssize_t leftsize = (unsigned char)(*data++);
 		Py_ssize_t rightsize = (unsigned char)(*data++);
 		if (meta + leftsize + rightsize > dataend) {
 			goto overflow;
 		}
 		left = PyBytes_FromStringAndSize(meta, leftsize);
 		meta += leftsize;
 		right = PyBytes_FromStringAndSize(meta, rightsize);
 		meta += rightsize;
 		tmp = PyTuple_New(2);
 		if (!left || !right || !tmp) {
 			Py_XDECREF(left);
 			Py_XDECREF(right);
 			Py_XDECREF(tmp);
 			goto bail;
 		}
 		PyTuple_SET_ITEM(tmp, 0, left);
 		PyTuple_SET_ITEM(tmp, 1, right);
 		PyTuple_SET_ITEM(metadata, i, tmp);
 	}
 	ret = Py_BuildValue("(OOHO(di)O)", prec, succs, flags, metadata, mtime,
 	                    (int)tz * 60, parents);
 	goto bail; /* return successfully */
 
 overflow:
 	PyErr_SetString(PyExc_ValueError, "overflow in obsstore");
 bail:
 	Py_XDECREF(prec);
 	Py_XDECREF(succs);
 	Py_XDECREF(metadata);
 	Py_XDECREF(parents);
 	return ret;
 }
 
 static PyObject *fm1readmarkers(PyObject *self, PyObject *args)
 {
 	const char *data, *dataend;
 	Py_ssize_t datalen, offset, stop;
 	PyObject *markers = NULL;
 
 	if (!PyArg_ParseTuple(args, "y#nn", &data, &datalen, &offset, &stop)) {
 		return NULL;
 	}
 	if (offset < 0) {
 		PyErr_SetString(PyExc_ValueError,
 		                "invalid negative offset in fm1readmarkers");
 		return NULL;
 	}
 	if (stop > datalen) {
 		PyErr_SetString(
 		    PyExc_ValueError,
 		    "stop longer than data length in fm1readmarkers");
 		return NULL;
 	}
 	dataend = data + datalen;
 	data += offset;
 	markers = PyList_New(0);
 	if (!markers) {
 		return NULL;
 	}
 	while (offset < stop) {
 		uint32_t msize;
 		int error;
 		PyObject *record = fm1readmarker(data, dataend, &msize);
 		if (!record) {
 			goto bail;
 		}
 		error = PyList_Append(markers, record);
 		Py_DECREF(record);
 		if (error) {
 			goto bail;
 		}
 		data += msize;
 		offset += msize;
 	}
 	return markers;
 bail:
 	Py_DECREF(markers);
 	return NULL;
 }
 
 static char parsers_doc[] = "Efficient content parsing.";
 
 PyObject *encodedir(PyObject *self, PyObject *args);
 PyObject *pathencode(PyObject *self, PyObject *args);
 PyObject *lowerencode(PyObject *self, PyObject *args);
 PyObject *parse_index2(PyObject *self, PyObject *args, PyObject *kwargs);
 
 static PyMethodDef methods[] = {
     {"pack_dirstate", pack_dirstate, METH_VARARGS, "pack a dirstate\n"},
     {"parse_dirstate", parse_dirstate, METH_VARARGS, "parse a dirstate\n"},
     {"parse_index2", (PyCFunction)parse_index2, METH_VARARGS | METH_KEYWORDS,
      "parse a revlog index\n"},
     {"isasciistr", isasciistr, METH_VARARGS, "check if an ASCII string\n"},
     {"asciilower", asciilower, METH_VARARGS, "lowercase an ASCII string\n"},
     {"asciiupper", asciiupper, METH_VARARGS, "uppercase an ASCII string\n"},
     {"dict_new_presized", dict_new_presized, METH_VARARGS,
      "construct a dict with an expected size\n"},
     {"make_file_foldmap", make_file_foldmap, METH_VARARGS,
      "make file foldmap\n"},
     {"jsonescapeu8fast", jsonescapeu8fast, METH_VARARGS,
      "escape a UTF-8 byte string to JSON (fast path)\n"},
     {"encodedir", encodedir, METH_VARARGS, "encodedir a path\n"},
     {"pathencode", pathencode, METH_VARARGS, "fncache-encode a path\n"},
     {"lowerencode", lowerencode, METH_VARARGS, "lower-encode a path\n"},
     {"fm1readmarkers", fm1readmarkers, METH_VARARGS,
      "parse v1 obsolete markers\n"},
     {NULL, NULL}};
 
 void dirs_module_init(PyObject *mod);
 void manifest_module_init(PyObject *mod);
 void revlog_module_init(PyObject *mod);
 
 static const int version = 20;
 
 static void module_init(PyObject *mod)
 {
 	PyModule_AddIntConstant(mod, "version", version);
 
 	/* This module constant has two purposes.  First, it lets us unit test
 	 * the ImportError raised without hard-coding any error text.  This
 	 * means we can change the text in the future without breaking tests,
 	 * even across changesets without a recompile.  Second, its presence
 	 * can be used to determine whether the version-checking logic is
 	 * present, which also helps in testing across changesets without a
 	 * recompile.  Note that this means the pure-Python version of parsers
 	 * should not have this module constant. */
 	PyModule_AddStringConstant(mod, "versionerrortext", versionerrortext);
 
 	dirs_module_init(mod);
 	manifest_module_init(mod);
 	revlog_module_init(mod);
 
 	if (PyType_Ready(&dirstateItemType) < 0) {
 		return;
 	}
 	Py_INCREF(&dirstateItemType);
 	PyModule_AddObject(mod, "DirstateItem", (PyObject *)&dirstateItemType);
 }
 
 static int check_python_version(void)
 {
 	PyObject *sys = PyImport_ImportModule("sys"), *ver;
 	long hexversion;
 	if (!sys) {
 		return -1;
 	}
 	ver = PyObject_GetAttrString(sys, "hexversion");
 	Py_DECREF(sys);
 	if (!ver) {
 		return -1;
 	}
 	hexversion = PyLong_AsLong(ver);
 	Py_DECREF(ver);
 	/* sys.hexversion is a 32-bit number by default, so the -1 case
 	 * should only occur in unusual circumstances (e.g. if sys.hexversion
 	 * is manually set to an invalid value). */
 	if ((hexversion == -1) || (hexversion >> 16 != PY_VERSION_HEX >> 16)) {
 		PyErr_Format(PyExc_ImportError,
 		             "%s: The Mercurial extension "
 		             "modules were compiled with Python " PY_VERSION
 		             ", but "
 		             "Mercurial is currently using Python with "
 		             "sys.hexversion=%ld: "
 		             "Python %s\n at: %s",
 		             versionerrortext, hexversion, Py_GetVersion(),
 		             Py_GetProgramFullPath());
 		return -1;
 	}
 	return 0;
 }
 
 static struct PyModuleDef parsers_module = {PyModuleDef_HEAD_INIT, "parsers",
                                             parsers_doc, -1, methods};
 
 PyMODINIT_FUNC PyInit_parsers(void)
 {
 	PyObject *mod;
 
 	if (check_python_version() == -1)
 		return NULL;
 	mod = PyModule_Create(&parsers_module);
 	module_init(mod);
 	return mod;
 }

mercurial/rewriteutil.py

@@ -1,251 +1,257 b''
 # rewriteutil.py - utility functions for rewriting changesets
 #
 # Copyright 2017 Octobus <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import re
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
 )
 
 from . import (
     error,
     node,
     obsolete,
     obsutil,
     revset,
     scmutil,
     util,
 )
 
 
 NODE_RE = re.compile(br'\b[0-9a-f]{6,64}\b')
 
 
 def _formatrevs(repo, revs, maxrevs=4):
     """returns a string summarizing revisions in a decent size
 
     If there are few enough revisions, we list them all. Otherwise we display a
     summary of the form:
 
         1ea73414a91b and 5 others
     """
     tonode = repo.changelog.node
     numrevs = len(revs)
     if numrevs < maxrevs:
         shorts = [node.short(tonode(r)) for r in revs]
         summary = b', '.join(shorts)
     else:
         first = revs.first()
         summary = _(b'%s and %d others')
         summary %= (node.short(tonode(first)), numrevs - 1)
     return summary
 
 
-def precheck(repo, revs, action=b'rewrite'):
+def precheck(repo, revs, action=b'rewrite', check_divergence=True):
     """check if revs can be rewritten
     action is used to control the error message.
 
+    check_divergence allows skipping the divergence checks in cases like adding
+    a prune marker (A, ()) to obsstore (which can't be diverging).
+
     Make sure this function is called after taking the lock.
     """
     if nullrev in revs:
         msg = _(b"cannot %s the null revision") % action
         hint = _(b"no changeset checked out")
         raise error.InputError(msg, hint=hint)
 
     if any(util.safehasattr(r, 'rev') for r in revs):
         repo.ui.develwarn(b"rewriteutil.precheck called with ctx not revs")
         revs = (r.rev() for r in revs)
 
     if len(repo[None].parents()) > 1:
         raise error.StateError(
             _(b"cannot %s changesets while merging") % action
         )
 
     publicrevs = repo.revs(b'%ld and public()', revs)
     if publicrevs:
         summary = _formatrevs(repo, publicrevs)
         msg = _(b"cannot %s public changesets: %s") % (action, summary)
         hint = _(b"see 'hg help phases' for details")
         raise error.InputError(msg, hint=hint)
 
     newunstable = disallowednewunstable(repo, revs)
     if newunstable:
         hint = _(b"see 'hg help evolution.instability'")
         raise error.InputError(
             _(b"cannot %s changeset, as that will orphan %d descendants")
             % (action, len(newunstable)),
             hint=hint,
         )
 
+    if not check_divergence:
+        return
+
     if not obsolete.isenabled(repo, obsolete.allowdivergenceopt):
         new_divergence = _find_new_divergence(repo, revs)
         if new_divergence:
             local_ctx, other_ctx, base_ctx = new_divergence
             msg = _(
                 b'cannot %s %s, as that creates content-divergence with %s'
             ) % (
                 action,
                 local_ctx,
                 other_ctx,
             )
             if local_ctx.rev() != base_ctx.rev():
                 msg += _(b', from %s') % base_ctx
             if repo.ui.verbose:
                 if local_ctx.rev() != base_ctx.rev():
                     msg += _(
                         b'\n    changeset %s is a successor of ' b'changeset %s'
                     ) % (local_ctx, base_ctx)
                 msg += _(
                     b'\n    changeset %s already has a successor in '
                     b'changeset %s\n'
                     b'    rewriting changeset %s would create '
                     b'"content-divergence"\n'
                     b'    set experimental.evolution.allowdivergence=True to '
                     b'skip this check'
                 ) % (base_ctx, other_ctx, local_ctx)
                 raise error.InputError(
                     msg,
                     hint=_(
                         b"see 'hg help evolution.instability' for details on content-divergence"
                     ),
                 )
             else:
                 raise error.InputError(
                     msg,
                     hint=_(
                         b"add --verbose for details or see "
                         b"'hg help evolution.instability'"
                     ),
                 )
 
 
 def disallowednewunstable(repo, revs):
     """Checks whether editing the revs will create new unstable changesets and
     are we allowed to create them.
 
     To allow new unstable changesets, set the config:
         `experimental.evolution.allowunstable=True`
     """
     allowunstable = obsolete.isenabled(repo, obsolete.allowunstableopt)
     if allowunstable:
         return revset.baseset()
     return repo.revs(b"(%ld::) - %ld", revs, revs)
 
 
 def _find_new_divergence(repo, revs):
     obsrevs = repo.revs(b'%ld and obsolete()', revs)
     for r in obsrevs:
         div = find_new_divergence_from(repo, repo[r])
         if div:
             return (repo[r], repo[div[0]], repo.unfiltered()[div[1]])
     return None
 
 
 def find_new_divergence_from(repo, ctx):
     """return divergent revision if rewriting an obsolete cset (ctx) will
     create divergence
 
     Returns (<other node>, <common ancestor node>) or None
     """
     if not ctx.obsolete():
         return None
     # We need to check two cases that can cause divergence:
     # case 1: the rev being rewritten has a non-obsolete successor (easily
     #     detected by successorssets)
     sset = obsutil.successorssets(repo, ctx.node())
     if sset:
         return (sset[0][0], ctx.node())
     else:
         # case 2: one of the precursors of the rev being revived has a
         #     non-obsolete successor (we need divergentsets for this)
         divsets = obsutil.divergentsets(repo, ctx)
         if divsets:
             nsuccset = divsets[0][b'divergentnodes']
             prec = divsets[0][b'commonpredecessor']
             return (nsuccset[0], prec)
         return None
 
 
 def skip_empty_successor(ui, command):
     empty_successor = ui.config(b'rewrite', b'empty-successor')
     if empty_successor == b'skip':
         return True
     elif empty_successor == b'keep':
         return False
     else:
         raise error.ConfigError(
             _(
                 b"%s doesn't know how to handle config "
                 b"rewrite.empty-successor=%s (only 'skip' and 'keep' are "
                 b"supported)"
             )
             % (command, empty_successor)
         )
 
 
 def update_hash_refs(repo, commitmsg, pending=None):
     """Replace all obsolete commit hashes in the message with the current hash.
 
     If the obsolete commit was split or is divergent, the hash is not replaced
     as there's no way to know which successor to choose.
 
     For commands that update a series of commits in the current transaction, the
     new obsolete markers can be considered by setting ``pending`` to a mapping
     of ``pending[oldnode] = [successor_node1, successor_node2,..]``.
     """
     if not pending:
         pending = {}
     cache = {}
     hashes = re.findall(NODE_RE, commitmsg)
     unfi = repo.unfiltered()
     for h in hashes:
         try:
             fullnode = scmutil.resolvehexnodeidprefix(unfi, h)
         except error.WdirUnsupported:
             # Someone has an fffff... in a commit message we're
             # rewriting. Don't try rewriting that.
             continue
         if fullnode is None:
             continue
         ctx = unfi[fullnode]
         if not ctx.obsolete():
             successors = pending.get(fullnode)
             if successors is None:
                 continue
             # obsutil.successorssets() returns a list of list of nodes
             successors = [successors]
         else:
             successors = obsutil.successorssets(repo, ctx.node(), cache=cache)
 
         # We can't make any assumptions about how to update the hash if the
         # cset in question was split or diverged.
         if len(successors) == 1 and len(successors[0]) == 1:
             successor = successors[0][0]
             if successor is not None:
                 newhash = hex(successor)
                 commitmsg = commitmsg.replace(h, newhash[: len(h)])
             else:
                 repo.ui.note(
                     _(
                         b'The stale commit message reference to %s could '
                         b'not be updated\n(The referenced commit was dropped)\n'
                     )
                     % h
                 )
         else:
             repo.ui.note(
                 _(
                     b'The stale commit message reference to %s could '
                     b'not be updated\n'
                 )
                 % h
             )
 
     return commitmsg

mercurial/tags.py

@@ -1,913 +1,913 b''
 # tags.py - read tag info from local repository
 #
 # Copyright 2009 Olivia Mackall <[e-mail]>
 # Copyright 2009 Greg Ward <[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.
 
 # Currently this module only deals with reading and caching tags.
 # Eventually, it could take care of updating (adding/removing/moving)
 # tags too.
 
 
 import errno
 import io
 
 from .node import (
     bin,
     hex,
     nullrev,
     short,
 )
 from .i18n import _
 from . import (
     encoding,
     error,
     match as matchmod,
     scmutil,
     util,
 )
 from .utils import stringutil
 
 # Tags computation can be expensive and caches exist to make it fast in
 # the common case.
 #
 # The "hgtagsfnodes1" cache file caches the .hgtags filenode values for
 # each revision in the repository. The file is effectively an array of
 # fixed length records. Read the docs for "hgtagsfnodescache" for technical
 # details.
 #
 # The .hgtags filenode cache grows in proportion to the length of the
 # changelog. The file is truncated when the # changelog is stripped.
 #
 # The purpose of the filenode cache is to avoid the most expensive part
 # of finding global tags, which is looking up the .hgtags filenode in the
 # manifest for each head. This can take dozens or over 100ms for
 # repositories with very large manifests. Multiplied by dozens or even
 # hundreds of heads and there is a significant performance concern.
 #
 # There also exist a separate cache file for each repository filter.
 # These "tags-*" files store information about the history of tags.
 #
 # The tags cache files consists of a cache validation line followed by
 # a history of tags.
 #
 # The cache validation line has the format:
 #
 #   <tiprev> <tipnode> [<filteredhash>]
 #
 # <tiprev> is an integer revision and <tipnode> is a 40 character hex
 # node for that changeset. These redundantly identify the repository
 # tip from the time the cache was written. In addition, <filteredhash>,
 # if present, is a 40 character hex hash of the contents of the filtered
 # revisions for this filter. If the set of filtered revs changes, the
 # hash will change and invalidate the cache.
 #
 # The history part of the tags cache consists of lines of the form:
 #
 #   <node> <tag>
 #
 # (This format is identical to that of .hgtags files.)
 #
 # <tag> is the tag name and <node> is the 40 character hex changeset
 # the tag is associated with.
 #
 # Tags are written sorted by tag name.
 #
 # Tags associated with multiple changesets have an entry for each changeset.
 # The most recent changeset (in terms of revlog ordering for the head
 # setting it) for each tag is last.
 
 
 def fnoderevs(ui, repo, revs):
     """return the list of '.hgtags' fnodes used in a set revisions
 
     This is returned as list of unique fnodes. We use a list instead of a set
     because order matters when it comes to tags."""
     unfi = repo.unfiltered()
     tonode = unfi.changelog.node
     nodes = [tonode(r) for r in revs]
     fnodes = _getfnodes(ui, repo, nodes)
     fnodes = _filterfnodes(fnodes, nodes)
     return fnodes
 
 
 def _nulltonone(repo, value):
     """convert nullid to None
 
     For tag value, nullid means "deleted". This small utility function helps
     translating that to None."""
     if value == repo.nullid:
         return None
     return value
 
 
 def difftags(ui, repo, oldfnodes, newfnodes):
     """list differences between tags expressed in two set of file-nodes
 
     The list contains entries in the form: (tagname, oldvalue, new value).
     None is used to expressed missing value:
         ('foo', None, 'abcd') is a new tag,
         ('bar', 'ef01', None) is a deletion,
         ('baz', 'abcd', 'ef01') is a tag movement.
     """
     if oldfnodes == newfnodes:
         return []
     oldtags = _tagsfromfnodes(ui, repo, oldfnodes)
     newtags = _tagsfromfnodes(ui, repo, newfnodes)
 
     # list of (tag, old, new): None means missing
     entries = []
     for tag, (new, __) in newtags.items():
         new = _nulltonone(repo, new)
         old, __ = oldtags.pop(tag, (None, None))
         old = _nulltonone(repo, old)
         if old != new:
             entries.append((tag, old, new))
     # handle deleted tags
     for tag, (old, __) in oldtags.items():
         old = _nulltonone(repo, old)
         if old is not None:
             entries.append((tag, old, None))
     entries.sort()
     return entries
 
 
 def writediff(fp, difflist):
     """write tags diff information to a file.
 
     Data are stored with a line based format:
 
         <action> <hex-node> <tag-name>\n
 
     Action are defined as follow:
        -R tag is removed,
        +A tag is added,
        -M tag is moved (old value),
        +M tag is moved (new value),
 
     Example:
 
          +A 875517b4806a848f942811a315a5bce30804ae85 t5
 
     See documentation of difftags output for details about the input.
     """
     add = b'+A %s %s\n'
     remove = b'-R %s %s\n'
     updateold = b'-M %s %s\n'
     updatenew = b'+M %s %s\n'
     for tag, old, new in difflist:
         # translate to hex
         if old is not None:
             old = hex(old)
         if new is not None:
             new = hex(new)
         # write to file
         if old is None:
             fp.write(add % (new, tag))
         elif new is None:
             fp.write(remove % (old, tag))
         else:
             fp.write(updateold % (old, tag))
             fp.write(updatenew % (new, tag))
 
 
 def findglobaltags(ui, repo):
     """Find global tags in a repo: return a tagsmap
 
     tagsmap: tag name to (node, hist) 2-tuples.
 
     The tags cache is read and updated as a side-effect of calling.
     """
     (heads, tagfnode, valid, cachetags, shouldwrite) = _readtagcache(ui, repo)
     if cachetags is not None:
         assert not shouldwrite
         # XXX is this really 100% correct?  are there oddball special
         # cases where a global tag should outrank a local tag but won't,
         # because cachetags does not contain rank info?
         alltags = {}
         _updatetags(cachetags, alltags)
         return alltags
 
     for head in reversed(heads):  # oldest to newest
         assert repo.changelog.index.has_node(
             head
         ), b"tag cache returned bogus head %s" % short(head)
     fnodes = _filterfnodes(tagfnode, reversed(heads))
     alltags = _tagsfromfnodes(ui, repo, fnodes)
 
     # and update the cache (if necessary)
     if shouldwrite:
         _writetagcache(ui, repo, valid, alltags)
     return alltags
 
 
 def _filterfnodes(tagfnode, nodes):
     """return a list of unique fnodes
 
     The order of this list matches the order of "nodes". Preserving this order
     is important as reading tags in different order provides different
     results."""
     seen = set()  # set of fnode
     fnodes = []
     for no in nodes:  # oldest to newest
         fnode = tagfnode.get(no)
         if fnode and fnode not in seen:
             seen.add(fnode)
             fnodes.append(fnode)
     return fnodes
 
 
 def _tagsfromfnodes(ui, repo, fnodes):
     """return a tagsmap from a list of file-node
 
     tagsmap: tag name to (node, hist) 2-tuples.
 
     The order of the list matters."""
     alltags = {}
     fctx = None
     for fnode in fnodes:
         if fctx is None:
             fctx = repo.filectx(b'.hgtags', fileid=fnode)
         else:
             fctx = fctx.filectx(fnode)
         filetags = _readtags(ui, repo, fctx.data().splitlines(), fctx)
         _updatetags(filetags, alltags)
     return alltags
 
 
 def readlocaltags(ui, repo, alltags, tagtypes):
     '''Read local tags in repo. Update alltags and tagtypes.'''
     try:
         data = repo.vfs.read(b"localtags")
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return
 
     # localtags is in the local encoding; re-encode to UTF-8 on
     # input for consistency with the rest of this module.
     filetags = _readtags(
         ui, repo, data.splitlines(), b"localtags", recode=encoding.fromlocal
     )
 
     # remove tags pointing to invalid nodes
     cl = repo.changelog
     for t in list(filetags):
         try:
             cl.rev(filetags[t][0])
         except (LookupError, ValueError):
             del filetags[t]
 
     _updatetags(filetags, alltags, b'local', tagtypes)
 
 
 def _readtaghist(ui, repo, lines, fn, recode=None, calcnodelines=False):
     """Read tag definitions from a file (or any source of lines).
 
     This function returns two sortdicts with similar information:
 
     - the first dict, bintaghist, contains the tag information as expected by
       the _readtags function, i.e. a mapping from tag name to (node, hist):
         - node is the node id from the last line read for that name,
         - hist is the list of node ids previously associated with it (in file
           order). All node ids are binary, not hex.
 
     - the second dict, hextaglines, is a mapping from tag name to a list of
       [hexnode, line number] pairs, ordered from the oldest to the newest node.
 
     When calcnodelines is False the hextaglines dict is not calculated (an
     empty dict is returned). This is done to improve this function's
     performance in cases where the line numbers are not needed.
     """
 
     bintaghist = util.sortdict()
     hextaglines = util.sortdict()
     count = 0
 
     def dbg(msg):
         ui.debug(b"%s, line %d: %s\n" % (fn, count, msg))
 
     for nline, line in enumerate(lines):
         count += 1
         if not line:
             continue
         try:
             (nodehex, name) = line.split(b" ", 1)
         except ValueError:
             dbg(b"cannot parse entry")
             continue
         name = name.strip()
         if recode:
             name = recode(name)
         try:
             nodebin = bin(nodehex)
         except TypeError:
             dbg(b"node '%s' is not well formed" % nodehex)
             continue
 
         # update filetags
         if calcnodelines:
             # map tag name to a list of line numbers
             if name not in hextaglines:
                 hextaglines[name] = []
             hextaglines[name].append([nodehex, nline])
             continue
         # map tag name to (node, hist)
         if name not in bintaghist:
             bintaghist[name] = []
         bintaghist[name].append(nodebin)
     return bintaghist, hextaglines
 
 
 def _readtags(ui, repo, lines, fn, recode=None, calcnodelines=False):
     """Read tag definitions from a file (or any source of lines).
 
     Returns a mapping from tag name to (node, hist).
 
     "node" is the node id from the last line read for that name. "hist"
     is the list of node ids previously associated with it (in file order).
     All node ids are binary, not hex.
     """
     filetags, nodelines = _readtaghist(
         ui, repo, lines, fn, recode=recode, calcnodelines=calcnodelines
     )
     # util.sortdict().__setitem__ is much slower at replacing then inserting
     # new entries. The difference can matter if there are thousands of tags.
     # Create a new sortdict to avoid the performance penalty.
     newtags = util.sortdict()
     for tag, taghist in filetags.items():
         newtags[tag] = (taghist[-1], taghist[:-1])
     return newtags
 
 
 def _updatetags(filetags, alltags, tagtype=None, tagtypes=None):
     """Incorporate the tag info read from one file into dictionnaries
 
     The first one, 'alltags', is a "tagmaps" (see 'findglobaltags' for details).
 
     The second one, 'tagtypes', is optional and will be updated to track the
     "tagtype" of entries in the tagmaps. When set, the 'tagtype' argument also
     needs to be set."""
     if tagtype is None:
         assert tagtypes is None
 
     for name, nodehist in filetags.items():
         if name not in alltags:
             alltags[name] = nodehist
             if tagtype is not None:
                 tagtypes[name] = tagtype
             continue
 
         # we prefer alltags[name] if:
         #  it supersedes us OR
         #  mutual supersedes and it has a higher rank
         # otherwise we win because we're tip-most
         anode, ahist = nodehist
         bnode, bhist = alltags[name]
         if (
             bnode != anode
             and anode in bhist
             and (bnode not in ahist or len(bhist) > len(ahist))
         ):
             anode = bnode
         elif tagtype is not None:
             tagtypes[name] = tagtype
         ahist.extend([n for n in bhist if n not in ahist])
         alltags[name] = anode, ahist
 
 
 def _filename(repo):
     """name of a tagcache file for a given repo or repoview"""
     filename = b'tags2'
     if repo.filtername:
         filename = b'%s-%s' % (filename, repo.filtername)
     return filename
 
 
 def _readtagcache(ui, repo):
     """Read the tag cache.
 
     Returns a tuple (heads, fnodes, validinfo, cachetags, shouldwrite).
 
     If the cache is completely up-to-date, "cachetags" is a dict of the
     form returned by _readtags() and "heads", "fnodes", and "validinfo" are
     None and "shouldwrite" is False.
 
     If the cache is not up to date, "cachetags" is None. "heads" is a list
     of all heads currently in the repository, ordered from tip to oldest.
     "validinfo" is a tuple describing cache validation info. This is used
     when writing the tags cache. "fnodes" is a mapping from head to .hgtags
     filenode. "shouldwrite" is True.
 
     If the cache is not up to date, the caller is responsible for reading tag
     info from each returned head. (See findglobaltags().)
     """
     try:
         cachefile = repo.cachevfs(_filename(repo), b'r')
         # force reading the file for static-http
         cachelines = iter(cachefile)
     except IOError:
         cachefile = None
 
     cacherev = None
     cachenode = None
     cachehash = None
     if cachefile:
         try:
             validline = next(cachelines)
             validline = validline.split()
             cacherev = int(validline[0])
             cachenode = bin(validline[1])
             if len(validline) > 2:
                 cachehash = bin(validline[2])
         except Exception:
             # corruption of the cache, just recompute it.
             pass
 
     tipnode = repo.changelog.tip()
     tiprev = len(repo.changelog) - 1
 
     # Case 1 (common): tip is the same, so nothing has changed.
     # (Unchanged tip trivially means no changesets have been added.
     # But, thanks to localrepository.destroyed(), it also means none
     # have been destroyed by strip or rollback.)
     if (
         cacherev == tiprev
         and cachenode == tipnode
         and cachehash == scmutil.filteredhash(repo, tiprev)
     ):
         tags = _readtags(ui, repo, cachelines, cachefile.name)
         cachefile.close()
         return (None, None, None, tags, False)
     if cachefile:
         cachefile.close()  # ignore rest of file
 
     valid = (tiprev, tipnode, scmutil.filteredhash(repo, tiprev))
 
     repoheads = repo.heads()
     # Case 2 (uncommon): empty repo; get out quickly and don't bother
     # writing an empty cache.
     if repoheads == [repo.nullid]:
         return ([], {}, valid, {}, False)
 
     # Case 3 (uncommon): cache file missing or empty.
 
     # Case 4 (uncommon): tip rev decreased.  This should only happen
     # when we're called from localrepository.destroyed().  Refresh the
     # cache so future invocations will not see disappeared heads in the
     # cache.
 
     # Case 5 (common): tip has changed, so we've added/replaced heads.
 
     # As it happens, the code to handle cases 3, 4, 5 is the same.
 
     # N.B. in case 4 (nodes destroyed), "new head" really means "newly
     # exposed".
     if not len(repo.file(b'.hgtags')):
         # No tags have ever been committed, so we can avoid a
         # potentially expensive search.
         return ([], {}, valid, None, True)
 
     # Now we have to lookup the .hgtags filenode for every new head.
     # This is the most expensive part of finding tags, so performance
     # depends primarily on the size of newheads.  Worst case: no cache
     # file, so newheads == repoheads.
     # Reversed order helps the cache ('repoheads' is in descending order)
     cachefnode = _getfnodes(ui, repo, reversed(repoheads))
 
     # Caller has to iterate over all heads, but can use the filenodes in
     # cachefnode to get to each .hgtags revision quickly.
     return (repoheads, cachefnode, valid, None, True)
 
 
 def _getfnodes(ui, repo, nodes):
     """return .hgtags fnodes for a list of changeset nodes
 
     Return value is a {node: fnode} mapping. There will be no entry for nodes
     without a '.hgtags' file.
     """
     starttime = util.timer()
     fnodescache = hgtagsfnodescache(repo.unfiltered())
     cachefnode = {}
     validated_fnodes = set()
     unknown_entries = set()
     for node in nodes:
         fnode = fnodescache.getfnode(node)
         flog = repo.file(b'.hgtags')
         if fnode != repo.nullid:
             if fnode not in validated_fnodes:
                 if flog.hasnode(fnode):
                     validated_fnodes.add(fnode)
                 else:
                     unknown_entries.add(node)
             cachefnode[node] = fnode
 
     if unknown_entries:
         fixed_nodemap = fnodescache.refresh_invalid_nodes(unknown_entries)
         for node, fnode in fixed_nodemap.items():
             if fnode != repo.nullid:
                 cachefnode[node] = fnode
 
     fnodescache.write()
 
     duration = util.timer() - starttime
     ui.log(
         b'tagscache',
         b'%d/%d cache hits/lookups in %0.4f seconds\n',
         fnodescache.hitcount,
         fnodescache.lookupcount,
         duration,
     )
     return cachefnode
 
 
 def _writetagcache(ui, repo, valid, cachetags):
     filename = _filename(repo)
     try:
         cachefile = repo.cachevfs(filename, b'w', atomictemp=True)
     except (OSError, IOError):
         return
 
     ui.log(
         b'tagscache',
         b'writing .hg/cache/%s with %d tags\n',
         filename,
         len(cachetags),
     )
 
     if valid[2]:
         cachefile.write(
             b'%d %s %s\n' % (valid[0], hex(valid[1]), hex(valid[2]))
         )
     else:
         cachefile.write(b'%d %s\n' % (valid[0], hex(valid[1])))
 
     # Tag names in the cache are in UTF-8 -- which is the whole reason
     # we keep them in UTF-8 throughout this module.  If we converted
     # them local encoding on input, we would lose info writing them to
     # the cache.
     for (name, (node, hist)) in sorted(cachetags.items()):
         for n in hist:
             cachefile.write(b"%s %s\n" % (hex(n), name))
         cachefile.write(b"%s %s\n" % (hex(node), name))
 
     try:
         cachefile.close()
     except (OSError, IOError):
         pass
 
 
 def tag(repo, names, node, message, local, user, date, editor=False):
     """tag a revision with one or more symbolic names.
 
     names is a list of strings or, when adding a single tag, names may be a
     string.
 
     if local is True, the tags are stored in a per-repository file.
     otherwise, they are stored in the .hgtags file, and a new
     changeset is committed with the change.
 
     keyword arguments:
 
     local: whether to store tags in non-version-controlled file
     (default False)
 
     message: commit message to use if committing
 
     user: name of user to use if committing
 
     date: date tuple to use if committing"""
 
     if not local:
         m = matchmod.exact([b'.hgtags'])
         st = repo.status(match=m, unknown=True, ignored=True)
         if any(
             (
                 st.modified,
                 st.added,
                 st.removed,
                 st.deleted,
                 st.unknown,
                 st.ignored,
             )
         ):
             raise error.Abort(
                 _(b'working copy of .hgtags is changed'),
                 hint=_(b'please commit .hgtags manually'),
             )
 
     with repo.wlock():
         repo.tags()  # instantiate the cache
         _tag(repo, names, node, message, local, user, date, editor=editor)
 
 
 def _tag(
     repo, names, node, message, local, user, date, extra=None, editor=False
 ):
     if isinstance(names, bytes):
         names = (names,)
 
     branches = repo.branchmap()
     for name in names:
         repo.hook(b'pretag', throw=True, node=hex(node), tag=name, local=local)
         if name in branches:
             repo.ui.warn(
                 _(b"warning: tag %s conflicts with existing branch name\n")
                 % name
             )
 
     def writetags(fp, names, munge, prevtags):
         fp.seek(0, io.SEEK_END)
         if prevtags and not prevtags.endswith(b'\n'):
             fp.write(b'\n')
         for name in names:
             if munge:
                 m = munge(name)
             else:
                 m = name
 
             if repo._tagscache.tagtypes and name in repo._tagscache.tagtypes:
                 old = repo.tags().get(name, repo.nullid)
                 fp.write(b'%s %s\n' % (hex(old), m))
             fp.write(b'%s %s\n' % (hex(node), m))
         fp.close()
 
     prevtags = b''
     if local:
         try:
             fp = repo.vfs(b'localtags', b'r+')
         except IOError:
             fp = repo.vfs(b'localtags', b'a')
         else:
             prevtags = fp.read()
 
         # local tags are stored in the current charset
         writetags(fp, names, None, prevtags)
         for name in names:
             repo.hook(b'tag', node=hex(node), tag=name, local=local)
         return
 
     try:
         fp = repo.wvfs(b'.hgtags', b'rb+')
     except IOError as e:
         if e.errno != errno.ENOENT:
             raise
         fp = repo.wvfs(b'.hgtags', b'ab')
     else:
         prevtags = fp.read()
 
     # committed tags are stored in UTF-8
     writetags(fp, names, encoding.fromlocal, prevtags)
 
     fp.close()
 
     repo.invalidatecaches()
 
     if b'.hgtags' not in repo.dirstate:
         repo[None].add([b'.hgtags'])
 
     m = matchmod.exact([b'.hgtags'])
     tagnode = repo.commit(
         message, user, date, extra=extra, match=m, editor=editor
     )
 
     for name in names:
         repo.hook(b'tag', node=hex(node), tag=name, local=local)
 
     return tagnode
 
 
 _fnodescachefile = b'hgtagsfnodes1'
 _fnodesrecsize = 4 + 20  # changeset fragment + filenode
 _fnodesmissingrec = b'\xff' * 24
 
 
 class hgtagsfnodescache:
     """Persistent cache mapping revisions to .hgtags filenodes.
 
     The cache is an array of records. Each item in the array corresponds to
     a changelog revision. Values in the array contain the first 4 bytes of
     the node hash and the 20 bytes .hgtags filenode for that revision.
 
     The first 4 bytes are present as a form of verification. Repository
     stripping and rewriting may change the node at a numeric revision in the
     changelog. The changeset fragment serves as a verifier to detect
     rewriting. This logic is shared with the rev branch cache (see
     branchmap.py).
 
     The instance holds in memory the full cache content but entries are
     only parsed on read.
 
     Instances behave like lists. ``c[i]`` works where i is a rev or
     changeset node. Missing indexes are populated automatically on access.
     """
 
     def __init__(self, repo):
         assert repo.filtername is None
 
         self._repo = repo
 
         # Only for reporting purposes.
         self.lookupcount = 0
         self.hitcount = 0
 
         try:
             data = repo.cachevfs.read(_fnodescachefile)
         except (OSError, IOError):
             data = b""
         self._raw = bytearray(data)
 
         # The end state of self._raw is an array that is of the exact length
         # required to hold a record for every revision in the repository.
         # We truncate or extend the array as necessary. self._dirtyoffset is
         # defined to be the start offset at which we need to write the output
         # file. This offset is also adjusted when new entries are calculated
         # for array members.
         cllen = len(repo.changelog)
         wantedlen = cllen * _fnodesrecsize
         rawlen = len(self._raw)
 
         self._dirtyoffset = None
 
         rawlentokeep = min(
             wantedlen, (rawlen // _fnodesrecsize) * _fnodesrecsize
         )
         if rawlen > rawlentokeep:
             # There's no easy way to truncate array instances. This seems
             # slightly less evil than copying a potentially large array slice.
             for i in range(rawlen - rawlentokeep):
                 self._raw.pop()
             rawlen = len(self._raw)
             self._dirtyoffset = rawlen
         if rawlen < wantedlen:
             if self._dirtyoffset is None:
                 self._dirtyoffset = rawlen
             # TODO: zero fill entire record, because it's invalid not missing?
             self._raw.extend(b'\xff' * (wantedlen - rawlen))
 
     def getfnode(self, node, computemissing=True):
         """Obtain the filenode of the .hgtags file at a specified revision.
 
         If the value is in the cache, the entry will be validated and returned.
         Otherwise, the filenode will be computed and returned unless
         "computemissing" is False.  In that case, None will be returned if
         the entry is missing or False if the entry is invalid without
         any potentially expensive computation being performed.
 
         If an .hgtags does not exist at the specified revision, nullid is
         returned.
         """
         if node == self._repo.nullid:
             return node
 
         ctx = self._repo[node]
         rev = ctx.rev()
 
         self.lookupcount += 1
 
         offset = rev * _fnodesrecsize
         record = b'%s' % self._raw[offset : offset + _fnodesrecsize]
         properprefix = node[0:4]
 
         # Validate and return existing entry.
         if record != _fnodesmissingrec and len(record) == _fnodesrecsize:
             fileprefix = record[0:4]
 
             if fileprefix == properprefix:
                 self.hitcount += 1
                 return record[4:]
 
             # Fall through.
 
         # If we get here, the entry is either missing or invalid.
 
         if not computemissing:
             if record != _fnodesmissingrec:
                 return False
             return None
 
         fnode = self._computefnode(node)
         self._writeentry(offset, properprefix, fnode)
         return fnode
 
     def _computefnode(self, node):
         """Finds the tag filenode for a node which is missing or invalid
         in cache"""
         ctx = self._repo[node]
         rev = ctx.rev()
         fnode = None
         cl = self._repo.changelog
         p1rev, p2rev = cl._uncheckedparentrevs(rev)
         p1node = cl.node(p1rev)
         p1fnode = self.getfnode(p1node, computemissing=False)
         if p2rev != nullrev:
             # There is some no-merge changeset where p1 is null and p2 is set
             # Processing them as merge is just slower, but still gives a good
             # result.
-            p2node = cl.node(p1rev)
+            p2node = cl.node(p2rev)
             p2fnode = self.getfnode(p2node, computemissing=False)
             if p1fnode != p2fnode:
                 # we cannot rely on readfast because we don't know against what
                 # parent the readfast delta is computed
                 p1fnode = None
         if p1fnode:
             mctx = ctx.manifestctx()
             fnode = mctx.readfast().get(b'.hgtags')
             if fnode is None:
                 fnode = p1fnode
         if fnode is None:
             # Populate missing entry.
             try:
                 fnode = ctx.filenode(b'.hgtags')
             except error.LookupError:
                 # No .hgtags file on this revision.
                 fnode = self._repo.nullid
         return fnode
 
     def setfnode(self, node, fnode):
         """Set the .hgtags filenode for a given changeset."""
         assert len(fnode) == 20
         ctx = self._repo[node]
 
         # Do a lookup first to avoid writing if nothing has changed.
         if self.getfnode(ctx.node(), computemissing=False) == fnode:
             return
 
         self._writeentry(ctx.rev() * _fnodesrecsize, node[0:4], fnode)
 
     def refresh_invalid_nodes(self, nodes):
         """recomputes file nodes for a given set of nodes which has unknown
         filenodes for them in the cache
         Also updates the in-memory cache with the correct filenode.
         Caller needs to take care about calling `.write()` so that updates are
         persisted.
         Returns a map {node: recomputed fnode}
         """
         fixed_nodemap = {}
         for node in nodes:
             fnode = self._computefnode(node)
             fixed_nodemap[node] = fnode
             self.setfnode(node, fnode)
         return fixed_nodemap
 
     def _writeentry(self, offset, prefix, fnode):
         # Slices on array instances only accept other array.
         entry = bytearray(prefix + fnode)
         self._raw[offset : offset + _fnodesrecsize] = entry
         # self._dirtyoffset could be None.
         self._dirtyoffset = min(self._dirtyoffset or 0, offset or 0)
 
     def write(self):
         """Perform all necessary writes to cache file.
 
         This may no-op if no writes are needed or if a write lock could
         not be obtained.
         """
         if self._dirtyoffset is None:
             return
 
         data = self._raw[self._dirtyoffset :]
         if not data:
             return
 
         repo = self._repo
 
         try:
             lock = repo.lock(wait=False)
         except error.LockError:
             repo.ui.log(
                 b'tagscache',
                 b'not writing .hg/cache/%s because '
                 b'lock cannot be acquired\n' % _fnodescachefile,
             )
             return
 
         try:
             f = repo.cachevfs.open(_fnodescachefile, b'ab')
             try:
                 # if the file has been truncated
                 actualoffset = f.tell()
                 if actualoffset < self._dirtyoffset:
                     self._dirtyoffset = actualoffset
                     data = self._raw[self._dirtyoffset :]
                 f.seek(self._dirtyoffset)
                 f.truncate()
                 repo.ui.log(
                     b'tagscache',
                     b'writing %d bytes to cache/%s\n'
                     % (len(data), _fnodescachefile),
                 )
                 f.write(data)
                 self._dirtyoffset = None
             finally:
                 f.close()
         except (IOError, OSError) as inst:
             repo.ui.log(
                 b'tagscache',
                 b"couldn't write cache/%s: %s\n"
                 % (_fnodescachefile, stringutil.forcebytestr(inst)),
             )
         finally:
             lock.release()

tests/test-clone-stream.t

@@ -1,819 +1,825 b''
 #require serve no-reposimplestore no-chg
 
 #testcases stream-legacy stream-bundle2
 
 #if stream-legacy
   $ cat << EOF >> $HGRCPATH
   > [server]
   > bundle2.stream = no
   > EOF
 #endif
 
 Initialize repository
 
   $ hg init server
   $ cd server
   $ sh $TESTDIR/testlib/stream_clone_setup.sh
   adding 00changelog-ab349180a0405010.nd
   adding 00changelog.d
   adding 00changelog.i
   adding 00changelog.n
   adding 00manifest.d
   adding 00manifest.i
   adding container/isam-build-centos7/bazel-coverage-generator-sandboxfs-compatibility-0758e3e4f6057904d44399bd666faba9e7f40686.patch
   adding data/foo.d
   adding data/foo.i
   adding data/foo.n
   adding data/undo.babar
   adding data/undo.d
   adding data/undo.foo.d
   adding data/undo.foo.i
   adding data/undo.foo.n
   adding data/undo.i
   adding data/undo.n
   adding data/undo.py
   adding foo.d
   adding foo.i
   adding foo.n
   adding meta/foo.d
   adding meta/foo.i
   adding meta/foo.n
   adding meta/undo.babar
   adding meta/undo.d
   adding meta/undo.foo.d
   adding meta/undo.foo.i
   adding meta/undo.foo.n
   adding meta/undo.i
   adding meta/undo.n
   adding meta/undo.py
   adding savanah/foo.d
   adding savanah/foo.i
   adding savanah/foo.n
   adding savanah/undo.babar
   adding savanah/undo.d
   adding savanah/undo.foo.d
   adding savanah/undo.foo.i
   adding savanah/undo.foo.n
   adding savanah/undo.i
   adding savanah/undo.n
   adding savanah/undo.py
   adding store/C\xc3\xa9lesteVille_is_a_Capital_City (esc)
   adding store/foo.d
   adding store/foo.i
   adding store/foo.n
   adding store/undo.babar
   adding store/undo.d
   adding store/undo.foo.d
   adding store/undo.foo.i
   adding store/undo.foo.n
   adding store/undo.i
   adding store/undo.n
   adding store/undo.py
   adding undo.babar
   adding undo.d
   adding undo.foo.d
   adding undo.foo.i
   adding undo.foo.n
   adding undo.i
   adding undo.n
   adding undo.py
 
   $ hg --config server.uncompressed=false serve -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
 Check local clone
 ==================
 
 The logic is close enough of uncompressed.
 This is present here to reuse the testing around file with "special" names.
 
   $ hg clone server local-clone
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Check that the clone went well
 
   $ hg verify -R local-clone
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 3 changesets with 1088 changes to 1088 files
 
 Check uncompressed
 ==================
 
 Cannot stream clone when server.uncompressed is set
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=stream_out'
   200 Script output follows
   
   1
 
 #if stream-legacy
   $ hg debugcapabilities http://localhost:$HGPORT
   Main capabilities:
     batch
     branchmap
     $USUAL_BUNDLE2_CAPS_SERVER$
     changegroupsubset
     compression=$BUNDLE2_COMPRESSIONS$
     getbundle
     httpheader=1024
     httpmediatype=0.1rx,0.1tx,0.2tx
     known
     lookup
     pushkey
     unbundle=HG10GZ,HG10BZ,HG10UN
     unbundlehash
   Bundle2 capabilities:
     HG20
     bookmarks
     changegroup
       01
       02
     checkheads
       related
     digests
       md5
       sha1
       sha512
     error
       abort
       unsupportedcontent
       pushraced
       pushkey
     hgtagsfnodes
     listkeys
     phases
       heads
     pushkey
     remote-changegroup
       http
       https
 
   $ hg clone --stream -U http://localhost:$HGPORT server-disabled
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 1088 changes to 1088 files
   new changesets 96ee1d7354c4:5223b5e3265f
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=getbundle' content-type --bodyfile body --hgproto 0.2 --requestheader "x-hgarg-1=bundlecaps=HG20%2Cbundle2%3DHG20%250Abookmarks%250Achangegroup%253D01%252C02%250Adigests%253Dmd5%252Csha1%252Csha512%250Aerror%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250Ahgtagsfnodes%250Alistkeys%250Aphases%253Dheads%250Apushkey%250Aremote-changegroup%253Dhttp%252Chttps&cg=0&common=0000000000000000000000000000000000000000&heads=c17445101a72edac06facd130d14808dfbd5c7c2&stream=1"
   200 Script output follows
   content-type: application/mercurial-0.2
   
 
   $ f --size body --hexdump --bytes 100
   body: size=232
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: cf 0b 45 52 52 4f 52 3a 41 42 4f 52 54 00 00 00 |..ERROR:ABORT...|
   0020: 00 01 01 07 3c 04 72 6d 65 73 73 61 67 65 73 74 |....<.rmessagest|
   0030: 72 65 61 6d 20 64 61 74 61 20 72 65 71 75 65 73 |ream data reques|
   0040: 74 65 64 20 62 75 74 20 73 65 72 76 65 72 20 64 |ted but server d|
   0050: 6f 65 73 20 6e 6f 74 20 61 6c 6c 6f 77 20 74 68 |oes not allow th|
   0060: 69 73 20 66                                     |is f|
 
 #endif
 #if stream-bundle2
   $ hg debugcapabilities http://localhost:$HGPORT
   Main capabilities:
     batch
     branchmap
     $USUAL_BUNDLE2_CAPS_SERVER$
     changegroupsubset
     compression=$BUNDLE2_COMPRESSIONS$
     getbundle
     httpheader=1024
     httpmediatype=0.1rx,0.1tx,0.2tx
     known
     lookup
     pushkey
     unbundle=HG10GZ,HG10BZ,HG10UN
     unbundlehash
   Bundle2 capabilities:
     HG20
     bookmarks
     changegroup
       01
       02
     checkheads
       related
     digests
       md5
       sha1
       sha512
     error
       abort
       unsupportedcontent
       pushraced
       pushkey
     hgtagsfnodes
     listkeys
     phases
       heads
     pushkey
     remote-changegroup
       http
       https
 
   $ hg clone --stream -U http://localhost:$HGPORT server-disabled
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 1088 changes to 1088 files
   new changesets 96ee1d7354c4:5223b5e3265f
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=getbundle' content-type --bodyfile body --hgproto 0.2 --requestheader "x-hgarg-1=bundlecaps=HG20%2Cbundle2%3DHG20%250Abookmarks%250Achangegroup%253D01%252C02%250Adigests%253Dmd5%252Csha1%252Csha512%250Aerror%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250Ahgtagsfnodes%250Alistkeys%250Aphases%253Dheads%250Apushkey%250Aremote-changegroup%253Dhttp%252Chttps&cg=0&common=0000000000000000000000000000000000000000&heads=c17445101a72edac06facd130d14808dfbd5c7c2&stream=1"
   200 Script output follows
   content-type: application/mercurial-0.2
   
 
   $ f --size body --hexdump --bytes 100
   body: size=232
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: cf 0b 45 52 52 4f 52 3a 41 42 4f 52 54 00 00 00 |..ERROR:ABORT...|
   0020: 00 01 01 07 3c 04 72 6d 65 73 73 61 67 65 73 74 |....<.rmessagest|
   0030: 72 65 61 6d 20 64 61 74 61 20 72 65 71 75 65 73 |ream data reques|
   0040: 74 65 64 20 62 75 74 20 73 65 72 76 65 72 20 64 |ted but server d|
   0050: 6f 65 73 20 6e 6f 74 20 61 6c 6c 6f 77 20 74 68 |oes not allow th|
   0060: 69 73 20 66                                     |is f|
 
 #endif
 
   $ killdaemons.py
   $ cd server
   $ hg serve -p $HGPORT -d --pid-file=hg.pid --error errors.txt
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
 Basic clone
 
 #if stream-legacy
   $ hg clone --stream -U http://localhost:$HGPORT clone1
   streaming all changes
   1090 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   searching for changes
   no changes found
   $ cat server/errors.txt
 #endif
 #if stream-bundle2
   $ hg clone --stream -U http://localhost:$HGPORT clone1
   streaming all changes
   1093 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1093 files to transfer, 98.9 KB of data (zstd !)
   transferred 98.9 KB in * seconds (* */sec) (glob) (zstd !)
 
   $ ls -1 clone1/.hg/cache
   branch2-base
   branch2-immutable
   branch2-served
   branch2-served.hidden
   branch2-visible
   branch2-visible-hidden
   rbc-names-v1
   rbc-revs-v1
   tags2
   tags2-served
   $ cat server/errors.txt
 #endif
 
 getbundle requests with stream=1 are uncompressed
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=getbundle' content-type --bodyfile body --hgproto '0.1 0.2 comp=zlib,none' --requestheader "x-hgarg-1=bundlecaps=HG20%2Cbundle2%3DHG20%250Abookmarks%250Achangegroup%253D01%252C02%250Adigests%253Dmd5%252Csha1%252Csha512%250Aerror%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250Ahgtagsfnodes%250Alistkeys%250Aphases%253Dheads%250Apushkey%250Aremote-changegroup%253Dhttp%252Chttps&cg=0&common=0000000000000000000000000000000000000000&heads=c17445101a72edac06facd130d14808dfbd5c7c2&stream=1"
   200 Script output follows
   content-type: application/mercurial-0.2
   
 
 #if no-zstd no-rust
   $ f --size --hex --bytes 256 body
   body: size=119123
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: 62 07 53 54 52 45 41 4d 32 00 00 00 00 03 00 09 |b.STREAM2.......|
   0020: 06 09 04 0c 26 62 79 74 65 63 6f 75 6e 74 31 30 |....&bytecount10|
   0030: 34 31 31 35 66 69 6c 65 63 6f 75 6e 74 31 30 39 |4115filecount109|
   0040: 33 72 65 71 75 69 72 65 6d 65 6e 74 73 67 65 6e |3requirementsgen|
   0050: 65 72 61 6c 64 65 6c 74 61 25 32 43 72 65 76 6c |eraldelta%2Crevl|
   0060: 6f 67 76 31 25 32 43 73 70 61 72 73 65 72 65 76 |ogv1%2Csparserev|
   0070: 6c 6f 67 00 00 80 00 73 08 42 64 61 74 61 2f 30 |log....s.Bdata/0|
   0080: 2e 69 00 03 00 01 00 00 00 00 00 00 00 02 00 00 |.i..............|
   0090: 00 01 00 00 00 00 00 00 00 01 ff ff ff ff ff ff |................|
   00a0: ff ff 80 29 63 a0 49 d3 23 87 bf ce fe 56 67 92 |...)c.I.#....Vg.|
   00b0: 67 2c 69 d1 ec 39 00 00 00 00 00 00 00 00 00 00 |g,i..9..........|
   00c0: 00 00 75 30 73 26 45 64 61 74 61 2f 30 30 63 68 |..u0s&Edata/00ch|
   00d0: 61 6e 67 65 6c 6f 67 2d 61 62 33 34 39 31 38 30 |angelog-ab349180|
   00e0: 61 30 34 30 35 30 31 30 2e 6e 64 2e 69 00 03 00 |a0405010.nd.i...|
   00f0: 01 00 00 00 00 00 00 00 05 00 00 00 04 00 00 00 |................|
 #endif
 #if zstd no-rust
   $ f --size --hex --bytes 256 body
   body: size=116310 (no-bigendian !)
   body: size=116305 (bigendian !)
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: 7c 07 53 54 52 45 41 4d 32 00 00 00 00 03 00 09 ||.STREAM2.......|
   0020: 06 09 04 0c 40 62 79 74 65 63 6f 75 6e 74 31 30 |....@bytecount10|
   0030: 31 32 37 36 66 69 6c 65 63 6f 75 6e 74 31 30 39 |1276filecount109| (no-bigendian !)
   0030: 31 32 37 31 66 69 6c 65 63 6f 75 6e 74 31 30 39 |1271filecount109| (bigendian !)
   0040: 33 72 65 71 75 69 72 65 6d 65 6e 74 73 67 65 6e |3requirementsgen|
   0050: 65 72 61 6c 64 65 6c 74 61 25 32 43 72 65 76 6c |eraldelta%2Crevl|
   0060: 6f 67 2d 63 6f 6d 70 72 65 73 73 69 6f 6e 2d 7a |og-compression-z|
   0070: 73 74 64 25 32 43 72 65 76 6c 6f 67 76 31 25 32 |std%2Crevlogv1%2|
   0080: 43 73 70 61 72 73 65 72 65 76 6c 6f 67 00 00 80 |Csparserevlog...|
   0090: 00 73 08 42 64 61 74 61 2f 30 2e 69 00 03 00 01 |.s.Bdata/0.i....|
   00a0: 00 00 00 00 00 00 00 02 00 00 00 01 00 00 00 00 |................|
   00b0: 00 00 00 01 ff ff ff ff ff ff ff ff 80 29 63 a0 |.............)c.|
   00c0: 49 d3 23 87 bf ce fe 56 67 92 67 2c 69 d1 ec 39 |I.#....Vg.g,i..9|
   00d0: 00 00 00 00 00 00 00 00 00 00 00 00 75 30 73 26 |............u0s&|
   00e0: 45 64 61 74 61 2f 30 30 63 68 61 6e 67 65 6c 6f |Edata/00changelo|
   00f0: 67 2d 61 62 33 34 39 31 38 30 61 30 34 30 35 30 |g-ab349180a04050|
 #endif
 #if zstd rust no-dirstate-v2
   $ f --size --hex --bytes 256 body
   body: size=116310
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: 7c 07 53 54 52 45 41 4d 32 00 00 00 00 03 00 09 ||.STREAM2.......|
   0020: 06 09 04 0c 40 62 79 74 65 63 6f 75 6e 74 31 30 |....@bytecount10|
   0030: 31 32 37 36 66 69 6c 65 63 6f 75 6e 74 31 30 39 |1276filecount109|
   0040: 33 72 65 71 75 69 72 65 6d 65 6e 74 73 67 65 6e |3requirementsgen|
   0050: 65 72 61 6c 64 65 6c 74 61 25 32 43 72 65 76 6c |eraldelta%2Crevl|
   0060: 6f 67 2d 63 6f 6d 70 72 65 73 73 69 6f 6e 2d 7a |og-compression-z|
   0070: 73 74 64 25 32 43 72 65 76 6c 6f 67 76 31 25 32 |std%2Crevlogv1%2|
   0080: 43 73 70 61 72 73 65 72 65 76 6c 6f 67 00 00 80 |Csparserevlog...|
   0090: 00 73 08 42 64 61 74 61 2f 30 2e 69 00 03 00 01 |.s.Bdata/0.i....|
   00a0: 00 00 00 00 00 00 00 02 00 00 00 01 00 00 00 00 |................|
   00b0: 00 00 00 01 ff ff ff ff ff ff ff ff 80 29 63 a0 |.............)c.|
   00c0: 49 d3 23 87 bf ce fe 56 67 92 67 2c 69 d1 ec 39 |I.#....Vg.g,i..9|
   00d0: 00 00 00 00 00 00 00 00 00 00 00 00 75 30 73 26 |............u0s&|
   00e0: 45 64 61 74 61 2f 30 30 63 68 61 6e 67 65 6c 6f |Edata/00changelo|
   00f0: 67 2d 61 62 33 34 39 31 38 30 61 30 34 30 35 30 |g-ab349180a04050|
 #endif
 #if zstd dirstate-v2
   $ f --size --hex --bytes 256 body
   body: size=109549
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: c0 07 53 54 52 45 41 4d 32 00 00 00 00 03 00 09 |..STREAM2.......|
   0020: 05 09 04 0c 85 62 79 74 65 63 6f 75 6e 74 39 35 |.....bytecount95|
   0030: 38 39 37 66 69 6c 65 63 6f 75 6e 74 31 30 33 30 |897filecount1030|
   0040: 72 65 71 75 69 72 65 6d 65 6e 74 73 64 6f 74 65 |requirementsdote|
   0050: 6e 63 6f 64 65 25 32 43 65 78 70 2d 64 69 72 73 |ncode%2Cexp-dirs|
   0060: 74 61 74 65 2d 76 32 25 32 43 66 6e 63 61 63 68 |tate-v2%2Cfncach|
   0070: 65 25 32 43 67 65 6e 65 72 61 6c 64 65 6c 74 61 |e%2Cgeneraldelta|
   0080: 25 32 43 70 65 72 73 69 73 74 65 6e 74 2d 6e 6f |%2Cpersistent-no|
   0090: 64 65 6d 61 70 25 32 43 72 65 76 6c 6f 67 2d 63 |demap%2Crevlog-c|
   00a0: 6f 6d 70 72 65 73 73 69 6f 6e 2d 7a 73 74 64 25 |ompression-zstd%|
   00b0: 32 43 72 65 76 6c 6f 67 76 31 25 32 43 73 70 61 |2Crevlogv1%2Cspa|
   00c0: 72 73 65 72 65 76 6c 6f 67 25 32 43 73 74 6f 72 |rserevlog%2Cstor|
   00d0: 65 00 00 80 00 73 08 42 64 61 74 61 2f 30 2e 69 |e....s.Bdata/0.i|
   00e0: 00 03 00 01 00 00 00 00 00 00 00 02 00 00 00 01 |................|
   00f0: 00 00 00 00 00 00 00 01 ff ff ff ff ff ff ff ff |................|
 #endif
 
 --uncompressed is an alias to --stream
 
 #if stream-legacy
   $ hg clone --uncompressed -U http://localhost:$HGPORT clone1-uncompressed
   streaming all changes
   1090 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   searching for changes
   no changes found
 #endif
 #if stream-bundle2
   $ hg clone --uncompressed -U http://localhost:$HGPORT clone1-uncompressed
   streaming all changes
   1093 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1093 files to transfer, 98.9 KB of data (zstd !)
   transferred 98.9 KB in * seconds (* */sec) (glob) (zstd !)
 #endif
 
 Clone with background file closing enabled
 
 #if stream-legacy
   $ hg --debug --config worker.backgroundclose=true --config worker.backgroundcloseminfilecount=1 clone --stream -U http://localhost:$HGPORT clone-background | grep -v adding
   using http://localhost:$HGPORT/
   sending capabilities command
   sending branchmap command
   streaming all changes
   sending stream_out command
   1090 files to transfer, 102 KB of data (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   starting 4 threads for background file closing
   updating the branch cache
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   query 1; heads
   sending batch command
   searching for changes
   all remote heads known locally
   no changes found
   sending getbundle command
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "listkeys" (params: 1 mandatory) supported
   bundle2-input-part: "phase-heads" supported
   bundle2-input-part: total payload size 24
   bundle2-input-bundle: 2 parts total
   checking for updated bookmarks
   updating the branch cache
   (sent 5 HTTP requests and * bytes; received * bytes in responses) (glob)
 #endif
 #if stream-bundle2
   $ hg --debug --config worker.backgroundclose=true --config worker.backgroundcloseminfilecount=1 clone --stream -U http://localhost:$HGPORT clone-background | grep -v adding
   using http://localhost:$HGPORT/
   sending capabilities command
   query 1; heads
   sending batch command
   streaming all changes
   sending getbundle command
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "stream2" (params: 3 mandatory) supported
   applying stream bundle
   1093 files to transfer, 102 KB of data (no-zstd !)
   1093 files to transfer, 98.9 KB of data (zstd !)
   starting 4 threads for background file closing
   starting 4 threads for background file closing
   updating the branch cache
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   bundle2-input-part: total payload size 118984 (no-zstd !)
   transferred 98.9 KB in * seconds (* */sec) (glob) (zstd !)
   bundle2-input-part: total payload size 116145 (zstd no-bigendian !)
   bundle2-input-part: total payload size 116140 (zstd bigendian !)
   bundle2-input-part: "listkeys" (params: 1 mandatory) supported
   bundle2-input-bundle: 2 parts total
   checking for updated bookmarks
   updating the branch cache
   (sent 3 HTTP requests and * bytes; received * bytes in responses) (glob)
 #endif
 
 Cannot stream clone when there are secret changesets
 
   $ hg -R server phase --force --secret -r tip
   $ hg clone --stream -U http://localhost:$HGPORT secret-denied
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 1025 changes to 1025 files
   new changesets 96ee1d7354c4:c17445101a72
 
   $ killdaemons.py
 
 Streaming of secrets can be overridden by server config
 
   $ cd server
   $ hg serve --config server.uncompressedallowsecret=true -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
 #if stream-legacy
   $ hg clone --stream -U http://localhost:$HGPORT secret-allowed
   streaming all changes
   1090 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   searching for changes
   no changes found
 #endif
 #if stream-bundle2
   $ hg clone --stream -U http://localhost:$HGPORT secret-allowed
   streaming all changes
   1093 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1093 files to transfer, 98.9 KB of data (zstd !)
   transferred 98.9 KB in * seconds (* */sec) (glob) (zstd !)
 #endif
 
   $ killdaemons.py
 
 Verify interaction between preferuncompressed and secret presence
 
   $ cd server
   $ hg serve --config server.preferuncompressed=true -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
   $ hg clone -U http://localhost:$HGPORT preferuncompressed-secret
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 1025 changes to 1025 files
   new changesets 96ee1d7354c4:c17445101a72
 
   $ killdaemons.py
 
 Clone not allowed when full bundles disabled and can't serve secrets
 
   $ cd server
   $ hg serve --config server.disablefullbundle=true -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
   $ hg clone --stream http://localhost:$HGPORT secret-full-disabled
   warning: stream clone requested but server has them disabled
   requesting all changes
   remote: abort: server has pull-based clones disabled
   abort: pull failed on remote
   (remove --pull if specified or upgrade Mercurial)
   [100]
 
 Local stream clone with secrets involved
 (This is just a test over behavior: if you have access to the repo's files,
 there is no security so it isn't important to prevent a clone here.)
 
   $ hg clone -U --stream server local-secret
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 1025 changes to 1025 files
   new changesets 96ee1d7354c4:c17445101a72
 
 Stream clone while repo is changing:
 
   $ mkdir changing
   $ cd changing
 
 extension for delaying the server process so we reliably can modify the repo
 while cloning
 
   $ cat > stream_steps.py <<EOF
   > import os
   > import sys
   > from mercurial import (
   >     encoding,
   >     extensions,
   >     streamclone,
   >     testing,
   > )
   > WALKED_FILE_1 = encoding.environ[b'HG_TEST_STREAM_WALKED_FILE_1']
   > WALKED_FILE_2 = encoding.environ[b'HG_TEST_STREAM_WALKED_FILE_2']
   > 
   > def _test_sync_point_walk_1(orig, repo):
   >     testing.write_file(WALKED_FILE_1)
   > 
   > def _test_sync_point_walk_2(orig, repo):
   >     assert repo._currentlock(repo._lockref) is None
   >     testing.wait_file(WALKED_FILE_2)
   > 
   > extensions.wrapfunction(
   >     streamclone,
   >     '_test_sync_point_walk_1',
   >     _test_sync_point_walk_1
   > )
   > extensions.wrapfunction(
   >     streamclone,
   >     '_test_sync_point_walk_2',
   >     _test_sync_point_walk_2
   > )
   > EOF
 
 prepare repo with small and big file to cover both code paths in emitrevlogdata
 
   $ hg init repo
   $ touch repo/f1
   $ $TESTDIR/seq.py 50000 > repo/f2
   $ hg -R repo ci -Aqm "0"
   $ HG_TEST_STREAM_WALKED_FILE_1="$TESTTMP/sync_file_walked_1"
   $ export HG_TEST_STREAM_WALKED_FILE_1
   $ HG_TEST_STREAM_WALKED_FILE_2="$TESTTMP/sync_file_walked_2"
   $ export HG_TEST_STREAM_WALKED_FILE_2
   $ HG_TEST_STREAM_WALKED_FILE_3="$TESTTMP/sync_file_walked_3"
   $ export HG_TEST_STREAM_WALKED_FILE_3
 #   $ cat << EOF >> $HGRCPATH
 #   > [hooks]
 #   > pre-clone=rm -f "$TESTTMP/sync_file_walked_*"
 #   > EOF
   $ hg serve -R repo -p $HGPORT1 -d --error errors.log --pid-file=hg.pid --config extensions.stream_steps="$RUNTESTDIR/testlib/ext-stream-clone-steps.py"
   $ cat hg.pid >> $DAEMON_PIDS
 
 clone while modifying the repo between stating file with write lock and
 actually serving file content
 
   $ (hg clone -q --stream -U http://localhost:$HGPORT1 clone; touch "$HG_TEST_STREAM_WALKED_FILE_3") &
   $ $RUNTESTDIR/testlib/wait-on-file 10 $HG_TEST_STREAM_WALKED_FILE_1
   $ echo >> repo/f1
   $ echo >> repo/f2
   $ hg -R repo ci -m "1" --config ui.timeout.warn=-1
   $ touch $HG_TEST_STREAM_WALKED_FILE_2
   $ $RUNTESTDIR/testlib/wait-on-file 10 $HG_TEST_STREAM_WALKED_FILE_3
   $ hg -R clone id
   000000000000
   $ cat errors.log
   $ cd ..
 
 Stream repository with bookmarks
 --------------------------------
 
 (revert introduction of secret changeset)
 
   $ hg -R server phase --draft 'secret()'
 
 add a bookmark
 
   $ hg -R server bookmark -r tip some-bookmark
 
 clone it
 
 #if stream-legacy
   $ hg clone --stream http://localhost:$HGPORT with-bookmarks
   streaming all changes
   1090 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   searching for changes
   no changes found
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 #if stream-bundle2
   $ hg clone --stream http://localhost:$HGPORT with-bookmarks
   streaming all changes
   1096 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1096 files to transfer, 99.1 KB of data (zstd !)
   transferred 99.1 KB in * seconds (* */sec) (glob) (zstd !)
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
   $ hg verify -R with-bookmarks
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 3 changesets with 1088 changes to 1088 files
   $ hg -R with-bookmarks bookmarks
      some-bookmark             2:5223b5e3265f
 
 Stream repository with phases
 -----------------------------
 
 Clone as publishing
 
   $ hg -R server phase -r 'all()'
   0: draft
   1: draft
   2: draft
 
 #if stream-legacy
   $ hg clone --stream http://localhost:$HGPORT phase-publish
   streaming all changes
   1090 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   searching for changes
   no changes found
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 #if stream-bundle2
   $ hg clone --stream http://localhost:$HGPORT phase-publish
   streaming all changes
   1096 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1096 files to transfer, 99.1 KB of data (zstd !)
   transferred 99.1 KB in * seconds (* */sec) (glob) (zstd !)
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
   $ hg verify -R phase-publish
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 3 changesets with 1088 changes to 1088 files
   $ hg -R phase-publish phase -r 'all()'
   0: public
   1: public
   2: public
 
 Clone as non publishing
 
   $ cat << EOF >> server/.hg/hgrc
   > [phases]
   > publish = False
   > EOF
   $ killdaemons.py
   $ hg -R server serve -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
 
 #if stream-legacy
 
 With v1 of the stream protocol, changeset are always cloned as public. It make
 stream v1 unsuitable for non-publishing repository.
 
   $ hg clone --stream http://localhost:$HGPORT phase-no-publish
   streaming all changes
   1090 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1090 files to transfer, 98.8 KB of data (zstd !)
   transferred 98.8 KB in * seconds (* */sec) (glob) (zstd !)
   searching for changes
   no changes found
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R phase-no-publish phase -r 'all()'
   0: public
   1: public
   2: public
 #endif
 #if stream-bundle2
   $ hg clone --stream http://localhost:$HGPORT phase-no-publish
   streaming all changes
   1097 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1097 files to transfer, 99.1 KB of data (zstd !)
   transferred 99.1 KB in * seconds (* */sec) (glob) (zstd !)
   updating to branch default
   1088 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R phase-no-publish phase -r 'all()'
   0: draft
   1: draft
   2: draft
 #endif
   $ hg verify -R phase-no-publish
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 3 changesets with 1088 changes to 1088 files
 
   $ killdaemons.py
 
 #if stream-legacy
 
 With v1 of the stream protocol, changeset are always cloned as public. There's
 no obsolescence markers exchange in stream v1.
 
 #endif
 #if stream-bundle2
 
 Stream repository with obsolescence
 -----------------------------------
 
 Clone non-publishing with obsolescence
 
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > evolution=all
   > EOF
 
   $ cd server
   $ echo foo > foo
   $ hg -q commit -m 'about to be pruned'
   $ hg debugobsolete `hg log -r . -T '{node}'` -d '0 0' -u test --record-parents
   1 new obsolescence markers
   obsoleted 1 changesets
   $ hg up null -q
   $ hg log -T '{rev}: {phase}\n'
   2: draft
   1: draft
   0: draft
   $ hg serve -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
   $ hg clone -U --stream http://localhost:$HGPORT with-obsolescence
   streaming all changes
   1098 files to transfer, 102 KB of data (no-zstd !)
   transferred 102 KB in * seconds (* */sec) (glob) (no-zstd !)
   1098 files to transfer, 99.5 KB of data (zstd !)
   transferred 99.5 KB in * seconds (* */sec) (glob) (zstd !)
   $ hg -R with-obsolescence log -T '{rev}: {phase}\n'
   2: draft
   1: draft
   0: draft
   $ hg debugobsolete -R with-obsolescence
   8c206a663911c1f97f2f9d7382e417ae55872cfa 0 {5223b5e3265f0df40bb743da62249413d74ac70f} (Thu Jan 01 00:00:00 1970 +0000) {'user': 'test'}
   $ hg verify -R with-obsolescence
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 4 changesets with 1089 changes to 1088 files
 
   $ hg clone -U --stream --config experimental.evolution=0 http://localhost:$HGPORT with-obsolescence-no-evolution
   streaming all changes
   remote: abort: server has obsolescence markers, but client cannot receive them via stream clone
   abort: pull failed on remote
   [100]
 
   $ killdaemons.py
 
 #endif
+
+Cloning a repo with no requirements doesn't give some obscure error
+
+  $ mkdir -p empty-repo/.hg
+  $ hg clone -q --stream ssh://user@dummy/empty-repo empty-repo2
+  $ hg --cwd empty-repo2 verify -q

tests/test-tags.t

@@ -1,935 +1,990 b''
 setup
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > blackbox=
   > mock=$TESTDIR/mockblackbox.py
   > [blackbox]
   > track = command, commandfinish, tagscache
   > EOF
 
 Helper functions:
 
   $ cacheexists() {
   >   [ -f .hg/cache/tags2-visible ] && echo "tag cache exists" || echo "no tag cache"
   > }
 
   $ fnodescacheexists() {
   >   [ -f .hg/cache/hgtagsfnodes1 ] && echo "fnodes cache exists" || echo "no fnodes cache"
   > }
 
   $ dumptags() {
   >     rev=$1
   >     echo "rev $rev: .hgtags:"
   >     hg cat -r$rev .hgtags
   > }
 
 # XXX need to test that the tag cache works when we strip an old head
 # and add a new one rooted off non-tip: i.e. node and rev of tip are the
 # same, but stuff has changed behind tip.
 
 Setup:
 
   $ hg init t
   $ cd t
   $ cacheexists
   no tag cache
   $ fnodescacheexists
   no fnodes cache
   $ hg id
   000000000000 tip
   $ cacheexists
   no tag cache
   $ fnodescacheexists
   no fnodes cache
   $ echo a > a
   $ hg add a
   $ hg commit -m "test"
   $ hg co
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg identify
   acb14030fe0a tip
   $ hg identify -r 'wdir()'
   acb14030fe0a tip
   $ cacheexists
   tag cache exists
 No fnodes cache because .hgtags file doesn't exist
 (this is an implementation detail)
   $ fnodescacheexists
   no fnodes cache
 
 Try corrupting the cache
 
   $ printf 'a b' > .hg/cache/tags2-visible
   $ hg identify
   acb14030fe0a tip
   $ cacheexists
   tag cache exists
   $ fnodescacheexists
   no fnodes cache
   $ hg identify
   acb14030fe0a tip
 
 Create local tag with long name:
 
   $ T=`hg identify --debug --id`
   $ hg tag -l "This is a local tag with a really long name!"
   $ hg tags
   tip                                0:acb14030fe0a
   This is a local tag with a really long name!     0:acb14030fe0a
   $ rm .hg/localtags
 
 Create a tag behind hg's back:
 
   $ echo "$T first" > .hgtags
   $ cat .hgtags
   acb14030fe0a21b60322c440ad2d20cf7685a376 first
   $ hg add .hgtags
   $ hg commit -m "add tags"
   $ hg tags
   tip                                1:b9154636be93
   first                              0:acb14030fe0a
   $ hg identify
   b9154636be93 tip
 
 We should have a fnodes cache now that we have a real tag
 The cache should have an empty entry for rev 0 and a valid entry for rev 1.
 
 
   $ fnodescacheexists
   fnodes cache exists
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=48
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff b9 15 46 36 26 b7 b4 a7 |..........F6&...|
   0020: 73 e0 9e e3 c5 2f 51 0e 19 e0 5e 1f f9 66 d8 59 |s..../Q...^..f.Y|
   $ hg debugtagscache
   0 acb14030fe0a21b60322c440ad2d20cf7685a376 missing
   1 b9154636be938d3d431e75a7c906504a079bfe07 26b7b4a773e09ee3c52f510e19e05e1ff966d859
 
 Repeat with cold tag cache:
 
   $ rm -f .hg/cache/tags2-visible .hg/cache/hgtagsfnodes1
   $ hg identify
   b9154636be93 tip
 
   $ fnodescacheexists
   fnodes cache exists
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=48
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff b9 15 46 36 26 b7 b4 a7 |..........F6&...|
   0020: 73 e0 9e e3 c5 2f 51 0e 19 e0 5e 1f f9 66 d8 59 |s..../Q...^..f.Y|
 
 And again, but now unable to write tag cache or lock file:
 
 #if unix-permissions no-fsmonitor
 
   $ rm -f .hg/cache/tags2-visible .hg/cache/hgtagsfnodes1
   $ chmod 555 .hg/cache
   $ hg identify
   b9154636be93 tip
   $ chmod 755 .hg/cache
 
 (this block should be protected by no-fsmonitor, because "chmod 555 .hg"
 makes watchman fail at accessing to files under .hg)
 
   $ chmod 555 .hg
   $ hg identify
   b9154636be93 tip
   $ chmod 755 .hg
 #endif
 
 Tag cache debug info written to blackbox log
 
   $ rm -f .hg/cache/tags2-visible .hg/cache/hgtagsfnodes1
   $ hg identify
   b9154636be93 tip
   $ hg blackbox -l 6
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> writing 48 bytes to cache/hgtagsfnodes1
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> 0/2 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> blackbox -l 6
 
 Failure to acquire lock results in no write
 
   $ rm -f .hg/cache/tags2-visible .hg/cache/hgtagsfnodes1
   $ echo 'foo:1' > .hg/store/lock
   $ hg identify
   b9154636be93 tip
   $ hg blackbox -l 6
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> not writing .hg/cache/hgtagsfnodes1 because lock cannot be acquired
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> 0/2 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> blackbox -l 6
 
   $ fnodescacheexists
   no fnodes cache
 
   $ rm .hg/store/lock
 
   $ rm -f .hg/cache/tags2-visible .hg/cache/hgtagsfnodes1
   $ hg identify
   b9154636be93 tip
 
 Create a branch:
 
   $ echo bb > a
   $ hg status
   M a
   $ hg identify
   b9154636be93+ tip
   $ hg co first
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg id
   acb14030fe0a+ first
   $ hg id -r 'wdir()'
   acb14030fe0a+ first
   $ hg -v id
   acb14030fe0a+ first
   $ hg status
   M a
   $ echo 1 > b
   $ hg add b
   $ hg commit -m "branch"
   created new head
 
 Creating a new commit shouldn't append the .hgtags fnodes cache until
 tags info is accessed
 
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=48
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff b9 15 46 36 26 b7 b4 a7 |..........F6&...|
   0020: 73 e0 9e e3 c5 2f 51 0e 19 e0 5e 1f f9 66 d8 59 |s..../Q...^..f.Y|
 
   $ hg id
   c8edf04160c7 tip
 
 First 4 bytes of record 3 are changeset fragment
 
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=72
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff b9 15 46 36 26 b7 b4 a7 |..........F6&...|
   0020: 73 e0 9e e3 c5 2f 51 0e 19 e0 5e 1f f9 66 d8 59 |s..../Q...^..f.Y|
   0030: c8 ed f0 41 00 00 00 00 00 00 00 00 00 00 00 00 |...A............|
   0040: 00 00 00 00 00 00 00 00                         |........|
 
 Merge the two heads:
 
   $ hg merge 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg blackbox -l3
   1970-01-01 00:00:00.000 bob @c8edf04160c7f731e4589d66ab3ab3486a64ac28 (5000)> merge 1
   1970-01-01 00:00:00.000 bob @c8edf04160c7f731e4589d66ab3ab3486a64ac28+b9154636be938d3d431e75a7c906504a079bfe07 (5000)> merge 1 exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @c8edf04160c7f731e4589d66ab3ab3486a64ac28+b9154636be938d3d431e75a7c906504a079bfe07 (5000)> blackbox -l3
   $ hg id
   c8edf04160c7+b9154636be93+ tip
   $ hg status
   M .hgtags
   $ hg commit -m "merge"
 
 Create a fake head, make sure tag not visible afterwards:
 
   $ cp .hgtags tags
   $ hg tag last
   $ hg rm .hgtags
   $ hg commit -m "remove"
 
   $ mv tags .hgtags
   $ hg add .hgtags
   $ hg commit -m "readd"
   $ 
   $ hg tags
   tip                                6:35ff301afafe
   first                              0:acb14030fe0a
 
 Add invalid tags:
 
   $ echo "spam" >> .hgtags
   $ echo >> .hgtags
   $ echo "foo bar" >> .hgtags
   $ echo "a5a5 invalid" >> .hg/localtags
   $ cat .hgtags
   acb14030fe0a21b60322c440ad2d20cf7685a376 first
   spam
   
   foo bar
   $ hg commit -m "tags"
 
 Report tag parse error on other head:
 
   $ hg up 3
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 'x y' >> .hgtags
   $ hg commit -m "head"
   created new head
 
   $ hg tags --debug
   .hgtags@75d9f02dfe28, line 2: cannot parse entry
   .hgtags@75d9f02dfe28, line 4: node 'foo' is not well formed
   .hgtags@c4be69a18c11, line 2: node 'x' is not well formed
   tip                                8:c4be69a18c11e8bc3a5fdbb576017c25f7d84663
   first                              0:acb14030fe0a21b60322c440ad2d20cf7685a376
   $ hg tip
   changeset:   8:c4be69a18c11
   tag:         tip
   parent:      3:ac5e980c4dc0
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     head
   
 
 Test tag precedence rules:
 
   $ cd ..
   $ hg init t2
   $ cd t2
   $ echo foo > foo
   $ hg add foo
   $ hg ci -m 'add foo'      # rev 0
   $ hg tag bar              # rev 1
   $ echo >> foo
   $ hg ci -m 'change foo 1' # rev 2
   $ hg up -C 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg tag -r 1 -f bar      # rev 3
   $ hg up -C 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo >> foo
   $ hg ci -m 'change foo 2' # rev 4
   created new head
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
 Repeat in case of cache effects:
 
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
 Detailed dump of tag info:
 
   $ hg heads -q             # expect 4, 3, 2
   4:0c192d7d5e6b
   3:6fa450212aeb
   2:7a94127795a3
   $ dumptags 2
   rev 2: .hgtags:
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   $ dumptags 3
   rev 3: .hgtags:
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   78391a272241d70354aa14c874552cad6b51bb42 bar
   $ dumptags 4
   rev 4: .hgtags:
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 
 Dump cache:
 
   $ cat .hg/cache/tags2-visible
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   78391a272241d70354aa14c874552cad6b51bb42 bar
 
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=120
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0030: 7a 94 12 77 0c 04 f2 a8 af 31 de 17 fa b7 42 28 |z..w.....1....B(|
   0040: 78 ee 5a 2d ad bc 94 3d 6f a4 50 21 7d 3b 71 8c |x.Z-...=o.P!};q.|
   0050: 96 4e f3 7b 89 e5 50 eb da fd 57 89 e7 6c e1 b0 |.N.{..P...W..l..|
   0060: 0c 19 2d 7d 0c 04 f2 a8 af 31 de 17 fa b7 42 28 |..-}.....1....B(|
   0070: 78 ee 5a 2d ad bc 94 3d                         |x.Z-...=|
 
 Corrupt the .hgtags fnodes cache
 Extra junk data at the end should get overwritten on next cache update
 
   $ echo extra >> .hg/cache/hgtagsfnodes1
   $ echo dummy1 > foo
   $ hg commit -m throwaway1
 
   $ hg tags
   tip                                5:8dbfe60eff30
   bar                                1:78391a272241
 
   $ hg blackbox -l 6
   1970-01-01 00:00:00.000 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> tags
   1970-01-01 00:00:00.000 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> writing 24 bytes to cache/hgtagsfnodes1
   1970-01-01 00:00:00.000 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> 3/4 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> tags exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> blackbox -l 6
 
 On junk data + missing cache entries, hg also overwrites the junk.
 
   $ rm -f .hg/cache/tags2-visible
   >>> import os
   >>> with open(".hg/cache/hgtagsfnodes1", "ab+") as fp:
   ...     fp.seek(-10, os.SEEK_END) and None
   ...     fp.truncate() and None
 
   $ hg debugtagscache | tail -2
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   5 8dbfe60eff306a54259cfe007db9e330e7ecf866 missing
   $ hg tags
   tip                                5:8dbfe60eff30
   bar                                1:78391a272241
   $ hg debugtagscache | tail -2
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   5 8dbfe60eff306a54259cfe007db9e330e7ecf866 0c04f2a8af31de17fab7422878ee5a2dadbc943d
 
 If the 4 bytes of node hash for a record don't match an existing node, the entry
 is flagged as invalid.
 
   >>> import os
   >>> with open(".hg/cache/hgtagsfnodes1", "rb+") as fp:
   ...     fp.seek(-24, os.SEEK_END) and None
   ...     fp.write(b'\xde\xad') and None
 
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=144
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0030: 7a 94 12 77 0c 04 f2 a8 af 31 de 17 fa b7 42 28 |z..w.....1....B(|
   0040: 78 ee 5a 2d ad bc 94 3d 6f a4 50 21 7d 3b 71 8c |x.Z-...=o.P!};q.|
   0050: 96 4e f3 7b 89 e5 50 eb da fd 57 89 e7 6c e1 b0 |.N.{..P...W..l..|
   0060: 0c 19 2d 7d 0c 04 f2 a8 af 31 de 17 fa b7 42 28 |..-}.....1....B(|
   0070: 78 ee 5a 2d ad bc 94 3d de ad e6 0e 0c 04 f2 a8 |x.Z-...=........|
   0080: af 31 de 17 fa b7 42 28 78 ee 5a 2d ad bc 94 3d |.1....B(x.Z-...=|
 
   $ hg debugtagscache | tail -2
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   5 8dbfe60eff306a54259cfe007db9e330e7ecf866 invalid
 
   $ hg tags
   tip                                5:8dbfe60eff30
   bar                                1:78391a272241
 
 BUG: If the filenode part of an entry in hgtagsfnodes is corrupt and
 tags2-visible is missing, `hg tags` aborts.  Corrupting the leading 4 bytes of
 node hash (as above) doesn't seem to trigger the issue.  Also note that the
 debug command hides the corruption, both with and without tags2-visible.
 
   $ mv .hg/cache/hgtagsfnodes1 .hg/cache/hgtagsfnodes1.bak
   $ hg debugupdatecaches
 
   >>> import os
   >>> with open(".hg/cache/hgtagsfnodes1", "rb+") as fp:
   ...     fp.seek(-16, os.SEEK_END) and None
   ...     fp.write(b'\xde\xad') and None
 
   $ f --size --hexdump .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=144
   0000: bb d1 79 df 00 00 00 00 00 00 00 00 00 00 00 00 |..y.............|
   0010: 00 00 00 00 00 00 00 00 78 39 1a 27 0c 04 f2 a8 |........x9.'....|
   0020: af 31 de 17 fa b7 42 28 78 ee 5a 2d ad bc 94 3d |.1....B(x.Z-...=|
   0030: 7a 94 12 77 0c 04 f2 a8 af 31 de 17 fa b7 42 28 |z..w.....1....B(|
   0040: 78 ee 5a 2d ad bc 94 3d 6f a4 50 21 7d 3b 71 8c |x.Z-...=o.P!};q.|
   0050: 96 4e f3 7b 89 e5 50 eb da fd 57 89 e7 6c e1 b0 |.N.{..P...W..l..|
   0060: 0c 19 2d 7d 0c 04 f2 a8 af 31 de 17 fa b7 42 28 |..-}.....1....B(|
   0070: 78 ee 5a 2d ad bc 94 3d 8d bf e6 0e 0c 04 f2 a8 |x.Z-...=........|
   0080: de ad de 17 fa b7 42 28 78 ee 5a 2d ad bc 94 3d |......B(x.Z-...=|
 
   $ hg debugtagscache | tail -2
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   5 8dbfe60eff306a54259cfe007db9e330e7ecf866 0c04f2a8deadde17fab7422878ee5a2dadbc943d (unknown node)
 
   $ rm -f .hg/cache/tags2-visible
   $ hg debugtagscache | tail -2
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   5 8dbfe60eff306a54259cfe007db9e330e7ecf866 0c04f2a8deadde17fab7422878ee5a2dadbc943d (unknown node)
 
   $ hg tags
   tip                                5:8dbfe60eff30
   bar                                1:78391a272241
 
 BUG: Unless this file is restored, the `hg tags` in the next unix-permissions
 conditional will fail: "abort: data/.hgtags.i@0c04f2a8dead: no match found"
 
   $ mv .hg/cache/hgtagsfnodes1.bak .hg/cache/hgtagsfnodes1
 
 #if unix-permissions no-root
 Errors writing to .hgtags fnodes cache are silently ignored
 
   $ echo dummy2 > foo
   $ hg commit -m throwaway2
 
   $ chmod a-w .hg/cache/hgtagsfnodes1
   $ rm -f .hg/cache/tags2-visible
 
   $ hg tags
   tip                                6:b968051b5cf3
   bar                                1:78391a272241
 
   $ hg blackbox -l 6
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> couldn't write cache/hgtagsfnodes1: [Errno *] * (glob)
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> 2/4 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> blackbox -l 6
 
   $ chmod a+w .hg/cache/hgtagsfnodes1
 
   $ rm -f .hg/cache/tags2-visible
   $ hg tags
   tip                                6:b968051b5cf3
   bar                                1:78391a272241
 
   $ hg blackbox -l 6
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> writing 24 bytes to cache/hgtagsfnodes1
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> 2/4 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> blackbox -l 6
 
   $ f --size .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=168
 
   $ hg -q --config extensions.strip= strip -r 6 --no-backup
 #endif
 
 Stripping doesn't truncate the tags cache until new data is available
 
   $ rm -f .hg/cache/hgtagsfnodes1 .hg/cache/tags2-visible
   $ hg tags
   tip                                5:8dbfe60eff30
   bar                                1:78391a272241
 
   $ f --size .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=144
 
   $ hg -q --config extensions.strip= strip -r 5 --no-backup
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
   $ hg blackbox -l 5
   1970-01-01 00:00:00.000 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> writing 24 bytes to cache/hgtagsfnodes1
   1970-01-01 00:00:00.000 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> 2/4 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> tags exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> blackbox -l 5
 
   $ f --size .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=120
 
   $ echo dummy > foo
   $ hg commit -m throwaway3
 
   $ hg tags
   tip                                5:035f65efb448
   bar                                1:78391a272241
 
   $ hg blackbox -l 6
   1970-01-01 00:00:00.000 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> tags
   1970-01-01 00:00:00.000 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> writing 24 bytes to cache/hgtagsfnodes1
   1970-01-01 00:00:00.000 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> 3/4 cache hits/lookups in * seconds (glob)
   1970-01-01 00:00:00.000 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> writing .hg/cache/tags2-visible with 1 tags
   1970-01-01 00:00:00.000 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> tags exited 0 after * seconds (glob)
   1970-01-01 00:00:00.000 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> blackbox -l 6
   $ f --size .hg/cache/hgtagsfnodes1
   .hg/cache/hgtagsfnodes1: size=144
 
   $ hg -q --config extensions.strip= strip -r 5 --no-backup
 
 Test tag removal:
 
   $ hg tag --remove bar     # rev 5
   $ hg tip -vp
   changeset:   5:5f6e8655b1c7
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   files:       .hgtags
   description:
   Removed tag bar
   
   
   diff -r 0c192d7d5e6b -r 5f6e8655b1c7 .hgtags
   --- a/.hgtags	Thu Jan 01 00:00:00 1970 +0000
   +++ b/.hgtags	Thu Jan 01 00:00:00 1970 +0000
   @@ -1,1 +1,3 @@
    bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   +78391a272241d70354aa14c874552cad6b51bb42 bar
   +0000000000000000000000000000000000000000 bar
   
   $ hg tags
   tip                                5:5f6e8655b1c7
   $ hg tags                 # again, try to expose cache bugs
   tip                                5:5f6e8655b1c7
 
 Remove nonexistent tag:
 
   $ hg tag --remove foobar
   abort: tag 'foobar' does not exist
   [10]
   $ hg tip
   changeset:   5:5f6e8655b1c7
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Removed tag bar
   
 
 Undo a tag with rollback:
 
   $ hg rollback             # destroy rev 5 (restore bar)
   repository tip rolled back to revision 4 (undo commit)
   working directory now based on revision 4
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
 Test tag rank:
 
   $ cd ..
   $ hg init t3
   $ cd t3
   $ echo foo > foo
   $ hg add foo
   $ hg ci -m 'add foo'       # rev 0
   $ hg tag -f bar            # rev 1 bar -> 0
   $ hg tag -f bar            # rev 2 bar -> 1
   $ hg tag -fr 0 bar         # rev 3 bar -> 0
   $ hg tag -fr 1 bar         # rev 4 bar -> 1
   $ hg tag -fr 0 bar         # rev 5 bar -> 0
   $ hg tags
   tip                                5:85f05169d91d
   bar                                0:bbd179dfa0a7
   $ hg co 3
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo barbar > foo
   $ hg ci -m 'change foo'    # rev 6
   created new head
   $ hg tags
   tip                                6:735c3ca72986
   bar                                0:bbd179dfa0a7
 
 Don't allow moving tag without -f:
 
   $ hg tag -r 3 bar
   abort: tag 'bar' already exists (use -f to force)
   [10]
   $ hg tags
   tip                                6:735c3ca72986
   bar                                0:bbd179dfa0a7
 
 Strip 1: expose an old head:
 
   $ hg --config extensions.mq= strip 5
   saved backup bundle to $TESTTMP/t3/.hg/strip-backup/*-backup.hg (glob)
   $ hg tags                  # partly stale cache
   tip                                5:735c3ca72986
   bar                                1:78391a272241
   $ hg tags                  # up-to-date cache
   tip                                5:735c3ca72986
   bar                                1:78391a272241
 
 Strip 2: destroy whole branch, no old head exposed
 
   $ hg --config extensions.mq= strip 4
   saved backup bundle to $TESTTMP/t3/.hg/strip-backup/*-backup.hg (glob)
   $ hg tags                  # partly stale
   tip                                4:735c3ca72986
   bar                                0:bbd179dfa0a7
   $ rm -f .hg/cache/tags2-visible
   $ hg tags                  # cold cache
   tip                                4:735c3ca72986
   bar                                0:bbd179dfa0a7
 
 Test tag rank with 3 heads:
 
   $ cd ..
   $ hg init t4
   $ cd t4
   $ echo foo > foo
   $ hg add
   adding foo
   $ hg ci -m 'add foo'                 # rev 0
   $ hg tag bar                         # rev 1 bar -> 0
   $ hg tag -f bar                      # rev 2 bar -> 1
   $ hg up -qC 0
   $ hg tag -fr 2 bar                   # rev 3 bar -> 2
   $ hg tags
   tip                                3:197c21bbbf2c
   bar                                2:6fa450212aeb
   $ hg up -qC 0
   $ hg tag -m 'retag rev 0' -fr 0 bar  # rev 4 bar -> 0, but bar stays at 2
 
 Bar should still point to rev 2:
 
   $ hg tags
   tip                                4:3b4b14ed0202
   bar                                2:6fa450212aeb
 
 Test that removing global/local tags does not get confused when trying
 to remove a tag of type X which actually only exists as a type Y:
 
   $ cd ..
   $ hg init t5
   $ cd t5
   $ echo foo > foo
   $ hg add
   adding foo
   $ hg ci -m 'add foo'                 # rev 0
 
   $ hg tag -r 0 -l localtag
   $ hg tag --remove localtag
   abort: tag 'localtag' is not a global tag
   [10]
   $ 
   $ hg tag -r 0 globaltag
   $ hg tag --remove -l globaltag
   abort: tag 'globaltag' is not a local tag
   [10]
   $ hg tags -v
   tip                                1:a0b6fe111088
   localtag                           0:bbd179dfa0a7 local
   globaltag                          0:bbd179dfa0a7
 
 Templated output:
 
  (immediate values)
 
   $ hg tags -T '{pad(tag, 9)} {rev}:{node} ({type})\n'
   tip       1:a0b6fe111088c8c29567d3876cc466aa02927cae ()
   localtag  0:bbd179dfa0a71671c253b3ae0aa1513b60d199fa (local)
   globaltag 0:bbd179dfa0a71671c253b3ae0aa1513b60d199fa ()
 
  (ctx/revcache dependent)
 
   $ hg tags -T '{pad(tag, 9)} {rev} {file_adds}\n'
   tip       1 .hgtags
   localtag  0 foo
   globaltag 0 foo
 
   $ hg tags -T '{pad(tag, 9)} {rev}:{node|shortest}\n'
   tip       1:a0b6
   localtag  0:bbd1
   globaltag 0:bbd1
 
 Test for issue3911
 
   $ hg tag -r 0 -l localtag2
   $ hg tag -l --remove localtag2
   $ hg tags -v
   tip                                1:a0b6fe111088
   localtag                           0:bbd179dfa0a7 local
   globaltag                          0:bbd179dfa0a7
 
   $ hg tag -r 1 -f localtag
   $ hg tags -v
   tip                                2:5c70a037bb37
   localtag                           1:a0b6fe111088
   globaltag                          0:bbd179dfa0a7
 
   $ hg tags -v
   tip                                2:5c70a037bb37
   localtag                           1:a0b6fe111088
   globaltag                          0:bbd179dfa0a7
 
   $ hg tag -r 1 localtag2
   $ hg tags -v
   tip                                3:bbfb8cd42be2
   localtag2                          1:a0b6fe111088
   localtag                           1:a0b6fe111088
   globaltag                          0:bbd179dfa0a7
 
   $ hg tags -v
   tip                                3:bbfb8cd42be2
   localtag2                          1:a0b6fe111088
   localtag                           1:a0b6fe111088
   globaltag                          0:bbd179dfa0a7
 
   $ cd ..
 
 Create a repository with tags data to test .hgtags fnodes transfer
 
   $ hg init tagsserver
   $ cd tagsserver
   $ touch foo
   $ hg -q commit -A -m initial
   $ hg tag -m 'tag 0.1' 0.1
   $ echo second > foo
   $ hg commit -m second
   $ hg tag -m 'tag 0.2' 0.2
   $ hg tags
   tip                                3:40f0358cb314
   0.2                                2:f63cc8fe54e4
   0.1                                0:96ee1d7354c4
   $ cd ..
 
 Cloning should pull down hgtags fnodes mappings and write the cache file
 
   $ hg clone --pull tagsserver tagsclient
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 4 changesets with 4 changes to 2 files
   new changesets 96ee1d7354c4:40f0358cb314
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Missing tags2* files means the cache wasn't written through the normal mechanism.
 
   $ ls tagsclient/.hg/cache
   branch2-base
   branch2-immutable
   branch2-served
   branch2-served.hidden
   branch2-visible
   branch2-visible-hidden
   hgtagsfnodes1
   rbc-names-v1
   rbc-revs-v1
   tags2
   tags2-served
 
 Cache should contain the head only, even though other nodes have tags data
 
   $ f --size --hexdump tagsclient/.hg/cache/hgtagsfnodes1
   tagsclient/.hg/cache/hgtagsfnodes1: size=96
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0030: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0040: ff ff ff ff ff ff ff ff 40 f0 35 8c 19 e0 a7 d3 |........@.5.....|
   0050: 8a 5c 6a 82 4d cf fb a5 87 d0 2f a3 1e 4f 2f 8a |.\j.M...../..O/.|
 
 Running hg tags should produce tags2* file and not change cache
 
   $ hg -R tagsclient tags
   tip                                3:40f0358cb314
   0.2                                2:f63cc8fe54e4
   0.1                                0:96ee1d7354c4
 
   $ ls tagsclient/.hg/cache
   branch2-base
   branch2-immutable
   branch2-served
   branch2-served.hidden
   branch2-visible
   branch2-visible-hidden
   hgtagsfnodes1
   rbc-names-v1
   rbc-revs-v1
   tags2
   tags2-served
   tags2-visible
 
   $ f --size --hexdump tagsclient/.hg/cache/hgtagsfnodes1
   tagsclient/.hg/cache/hgtagsfnodes1: size=96
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0030: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0040: ff ff ff ff ff ff ff ff 40 f0 35 8c 19 e0 a7 d3 |........@.5.....|
   0050: 8a 5c 6a 82 4d cf fb a5 87 d0 2f a3 1e 4f 2f 8a |.\j.M...../..O/.|
 
 Check that the bundle includes cache data
 
   $ hg -R tagsclient bundle --all ./test-cache-in-bundle-all-rev.hg
   4 changesets found
   $ hg debugbundle ./test-cache-in-bundle-all-rev.hg
   Stream params: {Compression: BZ}
   changegroup -- {nbchanges: 4, version: 02} (mandatory: True)
       96ee1d7354c4ad7372047672c36a1f561e3a6a4c
       c4dab0c2fd337eb9191f80c3024830a4889a8f34
       f63cc8fe54e4d326f8d692805d70e092f851ddb1
       40f0358cb314c824a5929ee527308d90e023bc10
   hgtagsfnodes -- {} (mandatory: True)
   cache:rev-branch-cache -- {} (mandatory: False)
 
 Check that local clone includes cache data
 
   $ hg clone tagsclient tags-local-clone
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ (cd tags-local-clone/.hg/cache/; ls -1 tag*)
   tags2
   tags2-served
   tags2-visible
 
 Avoid writing logs on trying to delete an already deleted tag
   $ hg init issue5752
   $ cd issue5752
   $ echo > a
   $ hg commit -Am 'add a'
   adding a
   $ hg tag a
   $ hg tags
   tip                                1:bd7ee4f3939b
   a                                  0:a8a82d372bb3
   $ hg log
   changeset:   1:bd7ee4f3939b
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Added tag a for changeset a8a82d372bb3
   
   changeset:   0:a8a82d372bb3
   tag:         a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
   $ hg tag --remove a
   $ hg log
   changeset:   2:e7feacc7ec9e
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Removed tag a
   
   changeset:   1:bd7ee4f3939b
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Added tag a for changeset a8a82d372bb3
   
   changeset:   0:a8a82d372bb3
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
   $ hg tag --remove a
   abort: tag 'a' is already removed
   [10]
   $ hg log
   changeset:   2:e7feacc7ec9e
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Removed tag a
   
   changeset:   1:bd7ee4f3939b
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Added tag a for changeset a8a82d372bb3
   
   changeset:   0:a8a82d372bb3
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
   $ cat .hgtags
   a8a82d372bb35b42ff736e74f07c23bcd99c371f a
   a8a82d372bb35b42ff736e74f07c23bcd99c371f a
   0000000000000000000000000000000000000000 a
+
+  $ cd ..
+
+.hgtags fnode should be properly resolved at merge revision (issue6673)
+
+  $ hg init issue6673
+  $ cd issue6673
+
+  $ touch a
+  $ hg ci -qAm a
+  $ hg branch -q stable
+  $ hg ci -m branch
+
+  $ hg up -q default
+  $ hg merge -q stable
+  $ hg ci -m merge
+
+ add tag to stable branch:
+
+  $ hg up -q stable
+  $ echo a >> a
+  $ hg ci -m a
+  $ hg tag whatever
+  $ hg log -GT'{rev} {tags}\n'
+  @  4 tip
+  |
+  o  3 whatever
+  |
+  | o  2
+  |/|
+  o |  1
+  |/
+  o  0
+  
+
+ merge tagged stable into default:
+
+  $ hg up -q default
+  $ hg merge -q  stable
+  $ hg ci -m merge
+  $ hg log -GT'{rev} {tags}\n'
+  @    5 tip
+  |\
+  | o  4
+  | |
+  | o  3 whatever
+  | |
+  o |  2
+  |\|
+  | o  1
+  |/
+  o  0
+  
+
+  $ cd ..