phases: provide a test and accessor for non-public phase roots

This decouples users from the implementation details of the phasecache.
Also document a historic artifact about the stored phaseroots.

Differential Revision: https://phab.mercurial-scm.org/D8694

mercurial/phases.py

@@ -1,897 +1,919 b''
 """ Mercurial phases support code
 
     ---
 
     Copyright 2011 Pierre-Yves David <[e-mail]>
                    Logilab SA        <[e-mail]>
                    Augie Fackler     <[e-mail]>
 
     This software may be used and distributed according to the terms
     of the GNU General Public License version 2 or any later version.
 
     ---
 
 This module implements most phase logic in mercurial.
 
 
 Basic Concept
 =============
 
 A 'changeset phase' is an indicator that tells us how a changeset is
 manipulated and communicated. The details of each phase is described
 below, here we describe the properties they have in common.
 
 Like bookmarks, phases are not stored in history and thus are not
 permanent and leave no audit trail.
 
 First, no changeset can be in two phases at once. Phases are ordered,
 so they can be considered from lowest to highest. The default, lowest
 phase is 'public' - this is the normal phase of existing changesets. A
 child changeset can not be in a lower phase than its parents.
 
 These phases share a hierarchy of traits:
 
             immutable shared
     public:     X        X
     draft:               X
     secret:
 
 Local commits are draft by default.
 
 Phase Movement and Exchange
 ===========================
 
 Phase data is exchanged by pushkey on pull and push. Some servers have
 a publish option set, we call such a server a "publishing server".
 Pushing a draft changeset to a publishing server changes the phase to
 public.
 
 A small list of fact/rules define the exchange of phase:
 
 * old client never changes server states
 * pull never changes server states
 * publish and old server changesets are seen as public by client
 * any secret changeset seen in another repository is lowered to at
   least draft
 
 Here is the final table summing up the 49 possible use cases of phase
 exchange:
 
                            server
                   old     publish      non-publish
                  N   X    N   D   P    N   D   P
     old client
     pull
      N           -   X/X  -   X/D X/P  -   X/D X/P
      X           -   X/X  -   X/D X/P  -   X/D X/P
     push
      X           X/X X/X  X/P X/P X/P  X/D X/D X/P
     new client
     pull
      N           -   P/X  -   P/D P/P  -   D/D P/P
      D           -   P/X  -   P/D P/P  -   D/D P/P
      P           -   P/X  -   P/D P/P  -   P/D P/P
     push
      D           P/X P/X  P/P P/P P/P  D/D D/D P/P
      P           P/X P/X  P/P P/P P/P  P/P P/P P/P
 
 Legend:
 
     A/B = final state on client / state on server
 
     * N = new/not present,
     * P = public,
     * D = draft,
     * X = not tracked (i.e., the old client or server has no internal
           way of recording the phase.)
 
     passive = only pushes
 
 
     A cell here can be read like this:
 
     "When a new client pushes a draft changeset (D) to a publishing
     server where it's not present (N), it's marked public on both
     sides (P/P)."
 
 Note: old client behave as a publishing server with draft only content
 - other people see it as public
 - content is pushed as draft
 
 """
 
 from __future__ import absolute_import
 
 import errno
 import struct
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
     wdirrev,
 )
 from .pycompat import (
     getattr,
     setattr,
 )
 from . import (
     error,
     pycompat,
     smartset,
     txnutil,
     util,
 )
 
 _fphasesentry = struct.Struct(b'>i20s')
 
 INTERNAL_FLAG = 64  # Phases for mercurial internal usage only
 HIDEABLE_FLAG = 32  # Phases that are hideable
 
 # record phase index
 public, draft, secret = range(3)
 internal = INTERNAL_FLAG | HIDEABLE_FLAG
 archived = HIDEABLE_FLAG
 allphases = list(range(internal + 1))
 trackedphases = allphases[1:]
 # record phase names
 cmdphasenames = [b'public', b'draft', b'secret']  # known to `hg phase` command
 phasenames = [None] * len(allphases)
 phasenames[: len(cmdphasenames)] = cmdphasenames
 phasenames[archived] = b'archived'
 phasenames[internal] = b'internal'
 # record phase property
 mutablephases = tuple(allphases[1:])
 remotehiddenphases = tuple(allphases[2:])
 localhiddenphases = tuple(p for p in allphases if p & HIDEABLE_FLAG)
 
 
 def supportinternal(repo):
     """True if the internal phase can be used on a repository"""
     return b'internal-phase' in repo.requirements
 
 
 def _readroots(repo, phasedefaults=None):
     """Read phase roots from disk
 
     phasedefaults is a list of fn(repo, roots) callable, which are
     executed if the phase roots file does not exist. When phases are
     being initialized on an existing repository, this could be used to
     set selected changesets phase to something else than public.
 
     Return (roots, dirty) where dirty is true if roots differ from
     what is being stored.
     """
     repo = repo.unfiltered()
     dirty = False
     roots = [set() for i in allphases]
     try:
         f, pending = txnutil.trypending(repo.root, repo.svfs, b'phaseroots')
         try:
             for line in f:
                 phase, nh = line.split()
                 roots[int(phase)].add(bin(nh))
         finally:
             f.close()
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         if phasedefaults:
             for f in phasedefaults:
                 roots = f(repo, roots)
         dirty = True
     return roots, dirty
 
 
 def binaryencode(phasemapping):
     """encode a 'phase -> nodes' mapping into a binary stream
 
     Since phases are integer the mapping is actually a python list:
     [[PUBLIC_HEADS], [DRAFTS_HEADS], [SECRET_HEADS]]
     """
     binarydata = []
     for phase, nodes in enumerate(phasemapping):
         for head in nodes:
             binarydata.append(_fphasesentry.pack(phase, head))
     return b''.join(binarydata)
 
 
 def binarydecode(stream):
     """decode a binary stream into a 'phase -> nodes' mapping
 
     Since phases are integer the mapping is actually a python list."""
     headsbyphase = [[] for i in allphases]
     entrysize = _fphasesentry.size
     while True:
         entry = stream.read(entrysize)
         if len(entry) < entrysize:
             if entry:
                 raise error.Abort(_(b'bad phase-heads stream'))
             break
         phase, node = _fphasesentry.unpack(entry)
         headsbyphase[phase].append(node)
     return headsbyphase
 
 
 def _sortedrange_insert(data, idx, rev, t):
     merge_before = False
     if idx:
         r1, t1 = data[idx - 1]
         merge_before = r1[-1] + 1 == rev and t1 == t
     merge_after = False
     if idx < len(data):
         r2, t2 = data[idx]
         merge_after = r2[0] == rev + 1 and t2 == t
 
     if merge_before and merge_after:
         data[idx - 1] = (pycompat.xrange(r1[0], r2[-1] + 1), t)
         data.pop(idx)
     elif merge_before:
         data[idx - 1] = (pycompat.xrange(r1[0], rev + 1), t)
     elif merge_after:
         data[idx] = (pycompat.xrange(rev, r2[-1] + 1), t)
     else:
         data.insert(idx, (pycompat.xrange(rev, rev + 1), t))
 
 
 def _sortedrange_split(data, idx, rev, t):
     r1, t1 = data[idx]
     if t == t1:
         return
     t = (t1[0], t[1])
     if len(r1) == 1:
         data.pop(idx)
         _sortedrange_insert(data, idx, rev, t)
     elif r1[0] == rev:
         data[idx] = (pycompat.xrange(rev + 1, r1[-1] + 1), t1)
         _sortedrange_insert(data, idx, rev, t)
     elif r1[-1] == rev:
         data[idx] = (pycompat.xrange(r1[0], rev), t1)
         _sortedrange_insert(data, idx + 1, rev, t)
     else:
         data[idx : idx + 1] = [
             (pycompat.xrange(r1[0], rev), t1),
             (pycompat.xrange(rev, rev + 1), t),
             (pycompat.xrange(rev + 1, r1[-1] + 1), t1),
         ]
 
 
 def _trackphasechange(data, rev, old, new):
     """add a phase move to the <data> list of ranges
 
     If data is None, nothing happens.
     """
     if data is None:
         return
 
     # If data is empty, create a one-revision range and done
     if not data:
         data.insert(0, (pycompat.xrange(rev, rev + 1), (old, new)))
         return
 
     low = 0
     high = len(data)
     t = (old, new)
     while low < high:
         mid = (low + high) // 2
         revs = data[mid][0]
 
         if rev in revs:
             _sortedrange_split(data, mid, rev, t)
             return
 
         if revs[0] == rev + 1:
             if mid and data[mid - 1][0][-1] == rev:
                 _sortedrange_split(data, mid - 1, rev, t)
             else:
                 _sortedrange_insert(data, mid, rev, t)
             return
 
         if revs[-1] == rev - 1:
             if mid + 1 < len(data) and data[mid + 1][0][0] == rev:
                 _sortedrange_split(data, mid + 1, rev, t)
             else:
                 _sortedrange_insert(data, mid + 1, rev, t)
             return
 
         if revs[0] > rev:
             high = mid
         else:
             low = mid + 1
 
     if low == len(data):
         data.append((pycompat.xrange(rev, rev + 1), t))
         return
 
     r1, t1 = data[low]
     if r1[0] > rev:
         data.insert(low, (pycompat.xrange(rev, rev + 1), t))
     else:
         data.insert(low + 1, (pycompat.xrange(rev, rev + 1), t))
 
 
 class phasecache(object):
     def __init__(self, repo, phasedefaults, _load=True):
         if _load:
             # Cheap trick to allow shallow-copy without copy module
             self.phaseroots, self.dirty = _readroots(repo, phasedefaults)
             self._loadedrevslen = 0
             self._phasesets = None
             self.filterunknown(repo)
             self.opener = repo.svfs
 
+    def hasnonpublicphases(self, repo):
+        """detect if there are revisions with non-public phase"""
+        repo = repo.unfiltered()
+        cl = repo.changelog
+        if len(cl) >= self._loadedrevslen:
+            self.invalidate()
+            self.loadphaserevs(repo)
+        return any(self.phaseroots[1:])
+
+    def nonpublicphaseroots(self, repo):
+        """returns the roots of all non-public phases
+
+        The roots are not minimized, so if the secret revisions are
+        descendants of draft revisions, their roots will still be present.
+        """
+        repo = repo.unfiltered()
+        cl = repo.changelog
+        if len(cl) >= self._loadedrevslen:
+            self.invalidate()
+            self.loadphaserevs(repo)
+        return set().union(*[roots for roots in self.phaseroots[1:] if roots])
+
     def getrevset(self, repo, phases, subset=None):
         """return a smartset for the given phases"""
         self.loadphaserevs(repo)  # ensure phase's sets are loaded
         phases = set(phases)
         publicphase = public in phases
 
         if publicphase:
             # In this case, phases keeps all the *other* phases.
             phases = set(allphases).difference(phases)
             if not phases:
                 return smartset.fullreposet(repo)
 
         # fast path: _phasesets contains the interesting sets,
         # might only need a union and post-filtering.
         revsneedscopy = False
         if len(phases) == 1:
             [p] = phases
             revs = self._phasesets[p]
             revsneedscopy = True  # Don't modify _phasesets
         else:
             # revs has the revisions in all *other* phases.
             revs = set.union(*[self._phasesets[p] for p in phases])
 
         def _addwdir(wdirsubset, wdirrevs):
             if wdirrev in wdirsubset and repo[None].phase() in phases:
                 if revsneedscopy:
                     wdirrevs = wdirrevs.copy()
                 # The working dir would never be in the # cache, but it was in
                 # the subset being filtered for its phase (or filtered out,
                 # depending on publicphase), so add it to the output to be
                 # included (or filtered out).
                 wdirrevs.add(wdirrev)
             return wdirrevs
 
         if not publicphase:
             if repo.changelog.filteredrevs:
                 revs = revs - repo.changelog.filteredrevs
 
             if subset is None:
                 return smartset.baseset(revs)
             else:
                 revs = _addwdir(subset, revs)
                 return subset & smartset.baseset(revs)
         else:
             if subset is None:
                 subset = smartset.fullreposet(repo)
 
             revs = _addwdir(subset, revs)
 
             if not revs:
                 return subset
             return subset.filter(lambda r: r not in revs)
 
     def copy(self):
         # Shallow copy meant to ensure isolation in
         # advance/retractboundary(), nothing more.
         ph = self.__class__(None, None, _load=False)
         ph.phaseroots = self.phaseroots[:]
         ph.dirty = self.dirty
         ph.opener = self.opener
         ph._loadedrevslen = self._loadedrevslen
         ph._phasesets = self._phasesets
         return ph
 
     def replace(self, phcache):
         """replace all values in 'self' with content of phcache"""
         for a in (
             b'phaseroots',
             b'dirty',
             b'opener',
             b'_loadedrevslen',
             b'_phasesets',
         ):
             setattr(self, a, getattr(phcache, a))
 
     def _getphaserevsnative(self, repo):
         repo = repo.unfiltered()
         nativeroots = []
         for phase in trackedphases:
             nativeroots.append(
                 pycompat.maplist(repo.changelog.rev, self.phaseroots[phase])
             )
         return repo.changelog.computephases(nativeroots)
 
     def _computephaserevspure(self, repo):
         repo = repo.unfiltered()
         cl = repo.changelog
         self._phasesets = [set() for phase in allphases]
         lowerroots = set()
         for phase in reversed(trackedphases):
             roots = pycompat.maplist(cl.rev, self.phaseroots[phase])
             if roots:
                 ps = set(cl.descendants(roots))
                 for root in roots:
                     ps.add(root)
                 ps.difference_update(lowerroots)
                 lowerroots.update(ps)
                 self._phasesets[phase] = ps
         self._loadedrevslen = len(cl)
 
     def loadphaserevs(self, repo):
         """ensure phase information is loaded in the object"""
         if self._phasesets is None:
             try:
                 res = self._getphaserevsnative(repo)
                 self._loadedrevslen, self._phasesets = res
             except AttributeError:
                 self._computephaserevspure(repo)
 
     def invalidate(self):
         self._loadedrevslen = 0
         self._phasesets = None
 
     def phase(self, repo, rev):
         # We need a repo argument here to be able to build _phasesets
         # if necessary. The repository instance is not stored in
         # phasecache to avoid reference cycles. The changelog instance
         # is not stored because it is a filecache() property and can
         # be replaced without us being notified.
         if rev == nullrev:
             return public
         if rev < nullrev:
             raise ValueError(_(b'cannot lookup negative revision'))
         if rev >= self._loadedrevslen:
             self.invalidate()
             self.loadphaserevs(repo)
         for phase in trackedphases:
             if rev in self._phasesets[phase]:
                 return phase
         return public
 
     def write(self):
         if not self.dirty:
             return
         f = self.opener(b'phaseroots', b'w', atomictemp=True, checkambig=True)
         try:
             self._write(f)
         finally:
             f.close()
 
     def _write(self, fp):
         for phase, roots in enumerate(self.phaseroots):
             for h in sorted(roots):
                 fp.write(b'%i %s\n' % (phase, hex(h)))
         self.dirty = False
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
         tr.addfilegenerator(b'phase', (b'phaseroots',), self._write)
         tr.hookargs[b'phases_moved'] = b'1'
 
     def registernew(self, repo, tr, targetphase, nodes):
         repo = repo.unfiltered()
         self._retractboundary(repo, tr, targetphase, nodes)
         if tr is not None and b'phases' in tr.changes:
             phasetracking = tr.changes[b'phases']
             torev = repo.changelog.rev
             phase = self.phase
             revs = [torev(node) for node in nodes]
             revs.sort()
             for rev in revs:
                 revphase = phase(repo, rev)
                 _trackphasechange(phasetracking, rev, None, revphase)
         repo.invalidatevolatilesets()
 
     def advanceboundary(self, repo, tr, targetphase, nodes, dryrun=None):
         """Set all 'nodes' to phase 'targetphase'
 
         Nodes with a phase lower than 'targetphase' are not affected.
 
         If dryrun is True, no actions will be performed
 
         Returns a set of revs whose phase is changed or should be changed
         """
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
         if tr is None:
             phasetracking = None
         else:
             phasetracking = tr.changes.get(b'phases')
 
         repo = repo.unfiltered()
 
         changes = set()  # set of revisions to be changed
         delroots = []  # set of root deleted by this path
         for phase in pycompat.xrange(targetphase + 1, len(allphases)):
             # filter nodes that are not in a compatible phase already
             nodes = [
                 n for n in nodes if self.phase(repo, repo[n].rev()) >= phase
             ]
             if not nodes:
                 break  # no roots to move anymore
 
             olds = self.phaseroots[phase]
 
             affected = repo.revs(b'%ln::%ln', olds, nodes)
             changes.update(affected)
             if dryrun:
                 continue
             for r in affected:
                 _trackphasechange(
                     phasetracking, r, self.phase(repo, r), targetphase
                 )
 
             roots = {
                 ctx.node()
                 for ctx in repo.set(b'roots((%ln::) - %ld)', olds, affected)
             }
             if olds != roots:
                 self._updateroots(phase, roots, tr)
                 # some roots may need to be declared for lower phases
                 delroots.extend(olds - roots)
         if not dryrun:
             # declare deleted root in the target phase
             if targetphase != 0:
                 self._retractboundary(repo, tr, targetphase, delroots)
             repo.invalidatevolatilesets()
         return changes
 
     def retractboundary(self, repo, tr, targetphase, nodes):
         oldroots = self.phaseroots[: targetphase + 1]
         if tr is None:
             phasetracking = None
         else:
             phasetracking = tr.changes.get(b'phases')
         repo = repo.unfiltered()
         if (
             self._retractboundary(repo, tr, targetphase, nodes)
             and phasetracking is not None
         ):
 
             # find the affected revisions
             new = self.phaseroots[targetphase]
             old = oldroots[targetphase]
             affected = set(repo.revs(b'(%ln::) - (%ln::)', new, old))
 
             # find the phase of the affected revision
             for phase in pycompat.xrange(targetphase, -1, -1):
                 if phase:
                     roots = oldroots[phase]
                     revs = set(repo.revs(b'%ln::%ld', roots, affected))
                     affected -= revs
                 else:  # public phase
                     revs = affected
                 for r in sorted(revs):
                     _trackphasechange(phasetracking, r, phase, targetphase)
         repo.invalidatevolatilesets()
 
     def _retractboundary(self, repo, tr, targetphase, nodes):
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
         if targetphase in (archived, internal) and not supportinternal(repo):
             name = phasenames[targetphase]
             msg = b'this repository does not support the %s phase' % name
             raise error.ProgrammingError(msg)
 
         repo = repo.unfiltered()
         torev = repo.changelog.rev
         tonode = repo.changelog.node
         currentroots = {torev(node) for node in self.phaseroots[targetphase]}
         finalroots = oldroots = set(currentroots)
         newroots = [torev(node) for node in nodes]
         newroots = [
             rev for rev in newroots if self.phase(repo, rev) < targetphase
         ]
 
         if newroots:
             if nullrev in newroots:
                 raise error.Abort(_(b'cannot change null revision phase'))
             currentroots.update(newroots)
 
             # Only compute new roots for revs above the roots that are being
             # retracted.
             minnewroot = min(newroots)
             aboveroots = [rev for rev in currentroots if rev >= minnewroot]
             updatedroots = repo.revs(b'roots(%ld::)', aboveroots)
 
             finalroots = {rev for rev in currentroots if rev < minnewroot}
             finalroots.update(updatedroots)
         if finalroots != oldroots:
             self._updateroots(
                 targetphase, {tonode(rev) for rev in finalroots}, tr
             )
             return True
         return False
 
     def filterunknown(self, repo):
         """remove unknown nodes from the phase boundary
 
         Nothing is lost as unknown nodes only hold data for their descendants.
         """
         filtered = False
         has_node = repo.changelog.index.has_node  # to filter unknown nodes
         for phase, nodes in enumerate(self.phaseroots):
             missing = sorted(node for node in nodes if not has_node(node))
             if missing:
                 for mnode in missing:
                     repo.ui.debug(
                         b'removing unknown node %s from %i-phase boundary\n'
                         % (short(mnode), phase)
                     )
                 nodes.symmetric_difference_update(missing)
                 filtered = True
         if filtered:
             self.dirty = True
         # filterunknown is called by repo.destroyed, we may have no changes in
         # root but _phasesets contents is certainly invalid (or at least we
         # have not proper way to check that). related to issue 3858.
         #
         # The other caller is __init__ that have no _phasesets initialized
         # anyway. If this change we should consider adding a dedicated
         # "destroyed" function to phasecache or a proper cache key mechanism
         # (see branchmap one)
         self.invalidate()
 
 
 def advanceboundary(repo, tr, targetphase, nodes, dryrun=None):
     """Add nodes to a phase changing other nodes phases if necessary.
 
     This function move boundary *forward* this means that all nodes
     are set in the target phase or kept in a *lower* phase.
 
     Simplify boundary to contains phase roots only.
 
     If dryrun is True, no actions will be performed
 
     Returns a set of revs whose phase is changed or should be changed
     """
     phcache = repo._phasecache.copy()
     changes = phcache.advanceboundary(
         repo, tr, targetphase, nodes, dryrun=dryrun
     )
     if not dryrun:
         repo._phasecache.replace(phcache)
     return changes
 
 
 def retractboundary(repo, tr, targetphase, nodes):
     """Set nodes back to a phase changing other nodes phases if
     necessary.
 
     This function move boundary *backward* this means that all nodes
     are set in the target phase or kept in a *higher* phase.
 
     Simplify boundary to contains phase roots only."""
     phcache = repo._phasecache.copy()
     phcache.retractboundary(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 
 def registernew(repo, tr, targetphase, nodes):
     """register a new revision and its phase
 
     Code adding revisions to the repository should use this function to
     set new changeset in their target phase (or higher).
     """
     phcache = repo._phasecache.copy()
     phcache.registernew(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 
 def listphases(repo):
     """List phases root for serialization over pushkey"""
     # Use ordered dictionary so behavior is deterministic.
     keys = util.sortdict()
     value = b'%i' % draft
     cl = repo.unfiltered().changelog
     for root in repo._phasecache.phaseroots[draft]:
         if repo._phasecache.phase(repo, cl.rev(root)) <= draft:
             keys[hex(root)] = value
 
     if repo.publishing():
         # Add an extra data to let remote know we are a publishing
         # repo. Publishing repo can't just pretend they are old repo.
         # When pushing to a publishing repo, the client still need to
         # push phase boundary
         #
         # Push do not only push changeset. It also push phase data.
         # New phase data may apply to common changeset which won't be
         # push (as they are common). Here is a very simple example:
         #
         # 1) repo A push changeset X as draft to repo B
         # 2) repo B make changeset X public
         # 3) repo B push to repo A. X is not pushed but the data that
         #    X as now public should
         #
         # The server can't handle it on it's own as it has no idea of
         # client phase data.
         keys[b'publishing'] = b'True'
     return keys
 
 
 def pushphase(repo, nhex, oldphasestr, newphasestr):
     """List phases root for serialization over pushkey"""
     repo = repo.unfiltered()
     with repo.lock():
         currentphase = repo[nhex].phase()
         newphase = abs(int(newphasestr))  # let's avoid negative index surprise
         oldphase = abs(int(oldphasestr))  # let's avoid negative index surprise
         if currentphase == oldphase and newphase < oldphase:
             with repo.transaction(b'pushkey-phase') as tr:
                 advanceboundary(repo, tr, newphase, [bin(nhex)])
             return True
         elif currentphase == newphase:
             # raced, but got correct result
             return True
         else:
             return False
 
 
 def subsetphaseheads(repo, subset):
     """Finds the phase heads for a subset of a history
 
     Returns a list indexed by phase number where each item is a list of phase
     head nodes.
     """
     cl = repo.changelog
 
     headsbyphase = [[] for i in allphases]
     # No need to keep track of secret phase; any heads in the subset that
     # are not mentioned are implicitly secret.
     for phase in allphases[:secret]:
         revset = b"heads(%%ln & %s())" % phasenames[phase]
         headsbyphase[phase] = [cl.node(r) for r in repo.revs(revset, subset)]
     return headsbyphase
 
 
 def updatephases(repo, trgetter, headsbyphase):
     """Updates the repo with the given phase heads"""
     # Now advance phase boundaries of all but secret phase
     #
     # run the update (and fetch transaction) only if there are actually things
     # to update. This avoid creating empty transaction during no-op operation.
 
     for phase in allphases[:-1]:
         revset = b'%ln - _phase(%s)'
         heads = [c.node() for c in repo.set(revset, headsbyphase[phase], phase)]
         if heads:
             advanceboundary(repo, trgetter(), phase, heads)
 
 
 def analyzeremotephases(repo, subset, roots):
     """Compute phases heads and root in a subset of node from root dict
 
     * subset is heads of the subset
     * roots is {<nodeid> => phase} mapping. key and value are string.
 
     Accept unknown element input
     """
     repo = repo.unfiltered()
     # build list from dictionary
     draftroots = []
     has_node = repo.changelog.index.has_node  # to filter unknown nodes
     for nhex, phase in pycompat.iteritems(roots):
         if nhex == b'publishing':  # ignore data related to publish option
             continue
         node = bin(nhex)
         phase = int(phase)
         if phase == public:
             if node != nullid:
                 repo.ui.warn(
                     _(
                         b'ignoring inconsistent public root'
                         b' from remote: %s\n'
                     )
                     % nhex
                 )
         elif phase == draft:
             if has_node(node):
                 draftroots.append(node)
         else:
             repo.ui.warn(
                 _(b'ignoring unexpected root from remote: %i %s\n')
                 % (phase, nhex)
             )
     # compute heads
     publicheads = newheads(repo, subset, draftroots)
     return publicheads, draftroots
 
 
 class remotephasessummary(object):
     """summarize phase information on the remote side
 
     :publishing: True is the remote is publishing
     :publicheads: list of remote public phase heads (nodes)
     :draftheads: list of remote draft phase heads (nodes)
     :draftroots: list of remote draft phase root (nodes)
     """
 
     def __init__(self, repo, remotesubset, remoteroots):
         unfi = repo.unfiltered()
         self._allremoteroots = remoteroots
 
         self.publishing = remoteroots.get(b'publishing', False)
 
         ana = analyzeremotephases(repo, remotesubset, remoteroots)
         self.publicheads, self.draftroots = ana
         # Get the list of all "heads" revs draft on remote
         dheads = unfi.set(b'heads(%ln::%ln)', self.draftroots, remotesubset)
         self.draftheads = [c.node() for c in dheads]
 
 
 def newheads(repo, heads, roots):
     """compute new head of a subset minus another
 
     * `heads`: define the first subset
     * `roots`: define the second we subtract from the first"""
     # prevent an import cycle
     # phases > dagop > patch > copies > scmutil > obsolete > obsutil > phases
     from . import dagop
 
     repo = repo.unfiltered()
     cl = repo.changelog
     rev = cl.index.get_rev
     if not roots:
         return heads
     if not heads or heads == [nullid]:
         return []
     # The logic operated on revisions, convert arguments early for convenience
     new_heads = {rev(n) for n in heads if n != nullid}
     roots = [rev(n) for n in roots]
     # compute the area we need to remove
     affected_zone = repo.revs(b"(%ld::%ld)", roots, new_heads)
     # heads in the area are no longer heads
     new_heads.difference_update(affected_zone)
     # revisions in the area have children outside of it,
     # They might be new heads
     candidates = repo.revs(
         b"parents(%ld + (%ld and merge())) and not null", roots, affected_zone
     )
     candidates -= affected_zone
     if new_heads or candidates:
         # remove candidate that are ancestors of other heads
         new_heads.update(candidates)
         prunestart = repo.revs(b"parents(%ld) and not null", new_heads)
         pruned = dagop.reachableroots(repo, candidates, prunestart)
         new_heads.difference_update(pruned)
 
     return pycompat.maplist(cl.node, sorted(new_heads))
 
 
 def newcommitphase(ui):
     """helper to get the target phase of new commit
 
     Handle all possible values for the phases.new-commit options.
 
     """
     v = ui.config(b'phases', b'new-commit')
     try:
         return phasenames.index(v)
     except ValueError:
         try:
             return int(v)
         except ValueError:
             msg = _(b"phases.new-commit: not a valid phase name ('%s')")
             raise error.ConfigError(msg % v)
 
 
 def hassecret(repo):
     """utility function that check if a repo have any secret changeset."""
     return bool(repo._phasecache.phaseroots[secret])
 
 
 def preparehookargs(node, old, new):
     if old is None:
         old = b''
     else:
         old = phasenames[old]
     return {b'node': node, b'oldphase': old, b'phase': phasenames[new]}

mercurial/repoview.py

@@ -1,471 +1,471 b''
 # repoview.py - Filtered view of a localrepo object
 #
 # Copyright 2012 Pierre-Yves David <[e-mail]>
 #                Logilab SA        <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import copy
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
 )
 from .pycompat import (
     delattr,
     getattr,
     setattr,
 )
 from . import (
     error,
     obsolete,
     phases,
     pycompat,
     tags as tagsmod,
     util,
 )
 from .utils import repoviewutil
 
 
 def hideablerevs(repo):
     """Revision candidates to be hidden
 
     This is a standalone function to allow extensions to wrap it.
 
     Because we use the set of immutable changesets as a fallback subset in
     branchmap (see mercurial.utils.repoviewutils.subsettable), you cannot set
     "public" changesets as "hideable". Doing so would break multiple code
     assertions and lead to crashes."""
     obsoletes = obsolete.getrevs(repo, b'obsolete')
     internals = repo._phasecache.getrevset(repo, phases.localhiddenphases)
     internals = frozenset(internals)
     return obsoletes | internals
 
 
 def pinnedrevs(repo):
     """revisions blocking hidden changesets from being filtered
     """
 
     cl = repo.changelog
     pinned = set()
     pinned.update([par.rev() for par in repo[None].parents()])
     pinned.update([cl.rev(bm) for bm in repo._bookmarks.values()])
 
     tags = {}
     tagsmod.readlocaltags(repo.ui, repo, tags, {})
     if tags:
         rev = cl.index.get_rev
         pinned.update(rev(t[0]) for t in tags.values())
         pinned.discard(None)
     return pinned
 
 
 def _revealancestors(pfunc, hidden, revs):
     """reveals contiguous chains of hidden ancestors of 'revs' by removing them
     from 'hidden'
 
     - pfunc(r): a funtion returning parent of 'r',
     - hidden: the (preliminary) hidden revisions, to be updated
     - revs: iterable of revnum,
 
     (Ancestors are revealed exclusively, i.e. the elements in 'revs' are
     *not* revealed)
     """
     stack = list(revs)
     while stack:
         for p in pfunc(stack.pop()):
             if p != nullrev and p in hidden:
                 hidden.remove(p)
                 stack.append(p)
 
 
 def computehidden(repo, visibilityexceptions=None):
     """compute the set of hidden revision to filter
 
     During most operation hidden should be filtered."""
     assert not repo.changelog.filteredrevs
 
     hidden = hideablerevs(repo)
     if hidden:
         hidden = set(hidden - pinnedrevs(repo))
         if visibilityexceptions:
             hidden -= visibilityexceptions
         pfunc = repo.changelog.parentrevs
         mutable = repo._phasecache.getrevset(repo, phases.mutablephases)
 
         visible = mutable - hidden
         _revealancestors(pfunc, hidden, visible)
     return frozenset(hidden)
 
 
 def computesecret(repo, visibilityexceptions=None):
     """compute the set of revision that can never be exposed through hgweb
 
     Changeset in the secret phase (or above) should stay unaccessible."""
     assert not repo.changelog.filteredrevs
     secrets = repo._phasecache.getrevset(repo, phases.remotehiddenphases)
     return frozenset(secrets)
 
 
 def computeunserved(repo, visibilityexceptions=None):
     """compute the set of revision that should be filtered when used a server
 
     Secret and hidden changeset should not pretend to be here."""
     assert not repo.changelog.filteredrevs
     # fast path in simple case to avoid impact of non optimised code
     hiddens = filterrevs(repo, b'visible')
     secrets = filterrevs(repo, b'served.hidden')
     if secrets:
         return frozenset(hiddens | secrets)
     else:
         return hiddens
 
 
 def computemutable(repo, visibilityexceptions=None):
     assert not repo.changelog.filteredrevs
     # fast check to avoid revset call on huge repo
-    if any(repo._phasecache.phaseroots[1:]):
+    if repo._phasecache.hasnonpublicphases(repo):
         getphase = repo._phasecache.phase
         maymutable = filterrevs(repo, b'base')
         return frozenset(r for r in maymutable if getphase(repo, r))
     return frozenset()
 
 
 def computeimpactable(repo, visibilityexceptions=None):
     """Everything impactable by mutable revision
 
     The immutable filter still have some chance to get invalidated. This will
     happen when:
 
     - you garbage collect hidden changeset,
     - public phase is moved backward,
     - something is changed in the filtering (this could be fixed)
 
     This filter out any mutable changeset and any public changeset that may be
     impacted by something happening to a mutable revision.
 
     This is achieved by filtered everything with a revision number egal or
     higher than the first mutable changeset is filtered."""
     assert not repo.changelog.filteredrevs
     cl = repo.changelog
     firstmutable = len(cl)
-    for roots in repo._phasecache.phaseroots[1:]:
+    roots = repo._phasecache.nonpublicphaseroots(repo)
         if roots:
             firstmutable = min(firstmutable, min(cl.rev(r) for r in roots))
     # protect from nullrev root
     firstmutable = max(0, firstmutable)
     return frozenset(pycompat.xrange(firstmutable, len(cl)))
 
 
 # function to compute filtered set
 #
 # When adding a new filter you MUST update the table at:
 #     mercurial.utils.repoviewutil.subsettable
 # Otherwise your filter will have to recompute all its branches cache
 # from scratch (very slow).
 filtertable = {
     b'visible': computehidden,
     b'visible-hidden': computehidden,
     b'served.hidden': computesecret,
     b'served': computeunserved,
     b'immutable': computemutable,
     b'base': computeimpactable,
 }
 
 # set of filter level that will include the working copy parent no matter what.
 filter_has_wc = {b'visible', b'visible-hidden'}
 
 _basefiltername = list(filtertable)
 
 
 def extrafilter(ui):
     """initialize extra filter and return its id
 
     If extra filtering is configured, we make sure the associated filtered view
     are declared and return the associated id.
     """
     frevs = ui.config(b'experimental', b'extra-filter-revs')
     if frevs is None:
         return None
 
     fid = pycompat.sysbytes(util.DIGESTS[b'sha1'](frevs).hexdigest())[:12]
 
     combine = lambda fname: fname + b'%' + fid
 
     subsettable = repoviewutil.subsettable
 
     if combine(b'base') not in filtertable:
         for name in _basefiltername:
 
             def extrafilteredrevs(repo, *args, **kwargs):
                 baserevs = filtertable[name](repo, *args, **kwargs)
                 extrarevs = frozenset(repo.revs(frevs))
                 return baserevs | extrarevs
 
             filtertable[combine(name)] = extrafilteredrevs
             if name in subsettable:
                 subsettable[combine(name)] = combine(subsettable[name])
     return fid
 
 
 def filterrevs(repo, filtername, visibilityexceptions=None):
     """returns set of filtered revision for this filter name
 
     visibilityexceptions is a set of revs which must are exceptions for
     hidden-state and must be visible. They are dynamic and hence we should not
     cache it's result"""
     if filtername not in repo.filteredrevcache:
         if repo.ui.configbool(b'devel', b'debug.repo-filters'):
             msg = b'computing revision filter for "%s"'
             msg %= filtername
             if repo.ui.tracebackflag and repo.ui.debugflag:
                 # XXX use ui.write_err
                 util.debugstacktrace(
                     msg,
                     f=repo.ui._fout,
                     otherf=repo.ui._ferr,
                     prefix=b'debug.filters: ',
                 )
             else:
                 repo.ui.debug(b'debug.filters: %s\n' % msg)
         func = filtertable[filtername]
         if visibilityexceptions:
             return func(repo.unfiltered, visibilityexceptions)
         repo.filteredrevcache[filtername] = func(repo.unfiltered())
     return repo.filteredrevcache[filtername]
 
 
 def wrapchangelog(unfichangelog, filteredrevs):
     cl = copy.copy(unfichangelog)
     cl.filteredrevs = filteredrevs
 
     class filteredchangelog(filteredchangelogmixin, cl.__class__):
         pass
 
     cl.__class__ = filteredchangelog
 
     return cl
 
 
 class filteredchangelogmixin(object):
     def tiprev(self):
         """filtered version of revlog.tiprev"""
         for i in pycompat.xrange(len(self) - 1, -2, -1):
             if i not in self.filteredrevs:
                 return i
 
     def __contains__(self, rev):
         """filtered version of revlog.__contains__"""
         return 0 <= rev < len(self) and rev not in self.filteredrevs
 
     def __iter__(self):
         """filtered version of revlog.__iter__"""
 
         def filterediter():
             for i in pycompat.xrange(len(self)):
                 if i not in self.filteredrevs:
                     yield i
 
         return filterediter()
 
     def revs(self, start=0, stop=None):
         """filtered version of revlog.revs"""
         for i in super(filteredchangelogmixin, self).revs(start, stop):
             if i not in self.filteredrevs:
                 yield i
 
     def _checknofilteredinrevs(self, revs):
         """raise the appropriate error if 'revs' contains a filtered revision
 
         This returns a version of 'revs' to be used thereafter by the caller.
         In particular, if revs is an iterator, it is converted into a set.
         """
         safehasattr = util.safehasattr
         if safehasattr(revs, '__next__'):
             # Note that inspect.isgenerator() is not true for iterators,
             revs = set(revs)
 
         filteredrevs = self.filteredrevs
         if safehasattr(revs, 'first'):  # smartset
             offenders = revs & filteredrevs
         else:
             offenders = filteredrevs.intersection(revs)
 
         for rev in offenders:
             raise error.FilteredIndexError(rev)
         return revs
 
     def headrevs(self, revs=None):
         if revs is None:
             try:
                 return self.index.headrevsfiltered(self.filteredrevs)
             # AttributeError covers non-c-extension environments and
             # old c extensions without filter handling.
             except AttributeError:
                 return self._headrevs()
 
         revs = self._checknofilteredinrevs(revs)
         return super(filteredchangelogmixin, self).headrevs(revs)
 
     def strip(self, *args, **kwargs):
         # XXX make something better than assert
         # We can't expect proper strip behavior if we are filtered.
         assert not self.filteredrevs
         super(filteredchangelogmixin, self).strip(*args, **kwargs)
 
     def rev(self, node):
         """filtered version of revlog.rev"""
         r = super(filteredchangelogmixin, self).rev(node)
         if r in self.filteredrevs:
             raise error.FilteredLookupError(
                 hex(node), self.indexfile, _(b'filtered node')
             )
         return r
 
     def node(self, rev):
         """filtered version of revlog.node"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(filteredchangelogmixin, self).node(rev)
 
     def linkrev(self, rev):
         """filtered version of revlog.linkrev"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(filteredchangelogmixin, self).linkrev(rev)
 
     def parentrevs(self, rev):
         """filtered version of revlog.parentrevs"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(filteredchangelogmixin, self).parentrevs(rev)
 
     def flags(self, rev):
         """filtered version of revlog.flags"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(filteredchangelogmixin, self).flags(rev)
 
 
 class repoview(object):
     """Provide a read/write view of a repo through a filtered changelog
 
     This object is used to access a filtered version of a repository without
     altering the original repository object itself. We can not alter the
     original object for two main reasons:
     - It prevents the use of a repo with multiple filters at the same time. In
       particular when multiple threads are involved.
     - It makes scope of the filtering harder to control.
 
     This object behaves very closely to the original repository. All attribute
     operations are done on the original repository:
     - An access to `repoview.someattr` actually returns `repo.someattr`,
     - A write to `repoview.someattr` actually sets value of `repo.someattr`,
     - A deletion of `repoview.someattr` actually drops `someattr`
       from `repo.__dict__`.
 
     The only exception is the `changelog` property. It is overridden to return
     a (surface) copy of `repo.changelog` with some revisions filtered. The
     `filtername` attribute of the view control the revisions that need to be
     filtered.  (the fact the changelog is copied is an implementation detail).
 
     Unlike attributes, this object intercepts all method calls. This means that
     all methods are run on the `repoview` object with the filtered `changelog`
     property. For this purpose the simple `repoview` class must be mixed with
     the actual class of the repository. This ensures that the resulting
     `repoview` object have the very same methods than the repo object. This
     leads to the property below.
 
         repoview.method() --> repo.__class__.method(repoview)
 
     The inheritance has to be done dynamically because `repo` can be of any
     subclasses of `localrepo`. Eg: `bundlerepo` or `statichttprepo`.
     """
 
     def __init__(self, repo, filtername, visibilityexceptions=None):
         object.__setattr__(self, '_unfilteredrepo', repo)
         object.__setattr__(self, 'filtername', filtername)
         object.__setattr__(self, '_clcachekey', None)
         object.__setattr__(self, '_clcache', None)
         # revs which are exceptions and must not be hidden
         object.__setattr__(self, '_visibilityexceptions', visibilityexceptions)
 
     # not a propertycache on purpose we shall implement a proper cache later
     @property
     def changelog(self):
         """return a filtered version of the changeset
 
         this changelog must not be used for writing"""
         # some cache may be implemented later
         unfi = self._unfilteredrepo
         unfichangelog = unfi.changelog
         # bypass call to changelog.method
         unfiindex = unfichangelog.index
         unfilen = len(unfiindex)
         unfinode = unfiindex[unfilen - 1][7]
         with util.timedcm('repo filter for %s', self.filtername):
             revs = filterrevs(unfi, self.filtername, self._visibilityexceptions)
         cl = self._clcache
         newkey = (unfilen, unfinode, hash(revs), unfichangelog._delayed)
         # if cl.index is not unfiindex, unfi.changelog would be
         # recreated, and our clcache refers to garbage object
         if cl is not None and (
             cl.index is not unfiindex or newkey != self._clcachekey
         ):
             cl = None
         # could have been made None by the previous if
         if cl is None:
             # Only filter if there's something to filter
             cl = wrapchangelog(unfichangelog, revs) if revs else unfichangelog
             object.__setattr__(self, '_clcache', cl)
             object.__setattr__(self, '_clcachekey', newkey)
         return cl
 
     def unfiltered(self):
         """Return an unfiltered version of a repo"""
         return self._unfilteredrepo
 
     def filtered(self, name, visibilityexceptions=None):
         """Return a filtered version of a repository"""
         if name == self.filtername and not visibilityexceptions:
             return self
         return self.unfiltered().filtered(name, visibilityexceptions)
 
     def __repr__(self):
         return '<%s:%s %r>' % (
             self.__class__.__name__,
             pycompat.sysstr(self.filtername),
             self.unfiltered(),
         )
 
     # everything access are forwarded to the proxied repo
     def __getattr__(self, attr):
         return getattr(self._unfilteredrepo, attr)
 
     def __setattr__(self, attr, value):
         return setattr(self._unfilteredrepo, attr, value)
 
     def __delattr__(self, attr):
         return delattr(self._unfilteredrepo, attr)
 
 
 # Python <3.4 easily leaks types via __mro__. See
 # https://bugs.python.org/issue17950. We cache dynamically created types
 # so they won't be leaked on every invocation of repo.filtered().
 _filteredrepotypes = weakref.WeakKeyDictionary()
 
 
 def newtype(base):
     """Create a new type with the repoview mixin and the given base class"""
     if base not in _filteredrepotypes:
 
         class filteredrepo(repoview, base):
             pass
 
         _filteredrepotypes[base] = filteredrepo
     return _filteredrepotypes[base]