repoview: introduce a filter for serving hidden changesets

There are multiple usecase for being able to explicitly view or pull obsolete
from a server. We need to be able to do so without exposing the secret
changesets. We introduces a dedicated repository "view" to do so. Way to expose
this "view" to the user will come later.

To keep a behavior consistent with expected client/server behavior, the general
idea is for the obsolete access to be explicitly requested by the code
generating the request. In addition, the will be server side configuration to
restrict the access to this feature.

tests/test-remote-hidden.t

@@ -0,0 +1,97 b''
+========================================================
+Test the ability to access a hidden revision on a server
+========================================================
+
+#require serve
+
+  $ . $TESTDIR/testlib/obsmarker-common.sh
+  $ cat >> $HGRCPATH << EOF
+  > [phases]
+  > # public changeset are not obsolete
+  > publish=false
+  > [experimental]
+  > evolution=all
+  > [ui]
+  > logtemplate='{rev}:{node|short} {desc} [{phase}]\n'
+  > EOF
+
+Setup a simple repository with some hidden revisions
+----------------------------------------------------
+
+Testing the `served.hidden` view
+
+  $ hg init repo-with-hidden
+  $ cd repo-with-hidden
+
+  $ echo 0 > a
+  $ hg ci -qAm "c_Public"
+  $ hg phase --public
+  $ echo 1 > a
+  $ hg ci -m "c_Amend_Old"
+  $ echo 2 > a
+  $ hg ci -m "c_Amend_New" --amend
+  $ hg up ".^"
+  1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ echo 3 > a
+  $ hg ci -m "c_Pruned"
+  created new head
+  $ hg debugobsolete --record-parents `getid 'desc("c_Pruned")'` -d '0 0'
+  obsoleted 1 changesets
+  $ hg up ".^"
+  1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ echo 4 > a
+  $ hg ci -m "c_Secret" --secret
+  created new head
+  $ echo 5 > a
+  $ hg ci -m "c_Secret_Pruned" --secret
+  $ hg debugobsolete --record-parents `getid 'desc("c_Secret_Pruned")'` -d '0 0'
+  obsoleted 1 changesets
+  $ hg up null
+  0 files updated, 0 files merged, 1 files removed, 0 files unresolved
+
+  $ hg log -G -T '{rev}:{node|short} {desc} [{phase}]\n' --hidden
+  x  5:8d28cbe335f3 c_Secret_Pruned [secret]
+  |
+  o  4:1c6afd79eb66 c_Secret [secret]
+  |
+  | x  3:5d1575e42c25 c_Pruned [draft]
+  |/
+  | o  2:c33affeb3f6b c_Amend_New [draft]
+  |/
+  | x  1:be215fbb8c50 c_Amend_Old [draft]
+  |/
+  o  0:5f354f46e585 c_Public [public]
+  
+  $ hg debugobsolete
+  be215fbb8c5090028b00154c1fe877ad1b376c61 c33affeb3f6b4e9621d1839d6175ddc07708807c 0 (Thu Jan 01 00:00:00 1970 +0000) {'ef1': '9', 'operation': 'amend', 'user': 'test'}
+  5d1575e42c25b7f2db75cd4e0b881b1c35158fae 0 {5f354f46e5853535841ec7a128423e991ca4d59b} (Thu Jan 01 00:00:00 1970 +0000) {'user': 'test'}
+  8d28cbe335f311bc89332d7bbe8a07889b6914a0 0 {1c6afd79eb6663275bbe30097e162b1c24ced0f0} (Thu Jan 01 00:00:00 1970 +0000) {'user': 'test'}
+
+  $ cd ..
+
+Test the feature
+================
+
+Check that the `served.hidden` repoview
+---------------------------------------
+
+  $ hg -R repo-with-hidden serve -p $HGPORT -d --pid-file hg.pid --config web.view=served.hidden
+  $ cat hg.pid >> $DAEMON_PIDS
+
+changesets in secret and higher phases are not visible through hgweb
+
+  $ hg -R repo-with-hidden log --template "revision:    {rev}\\n" --rev "reverse(not secret())"
+  revision:    2
+  revision:    0
+  $ hg -R repo-with-hidden log --template "revision:    {rev}\\n" --rev "reverse(not secret())" --hidden
+  revision:    3
+  revision:    2
+  revision:    1
+  revision:    0
+  $ get-with-headers.py localhost:$HGPORT 'log?style=raw' | grep revision:
+  revision:    3
+  revision:    2
+  revision:    1
+  revision:    0
+
+  $ killdaemons.py

mercurial/branchmap.py

@@ -1,668 +1,669 b''
 # branchmap.py - logic to computes, maintain and stores branchmap for local repo
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import struct
 
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     encoding,
     error,
     pycompat,
     scmutil,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 calcsize = struct.calcsize
 pack_into = struct.pack_into
 unpack_from = struct.unpack_from
 
 
 ### Nearest subset relation
 # Nearest subset of filter X is a filter Y so that:
 # * Y is included in X,
 # * X - Y is as small as possible.
 # This create and ordering used for branchmap purpose.
 # the ordering may be partial
 subsettable = {None: 'visible',
                'visible-hidden': 'visible',
                'visible': 'served',
+               'served.hidden': 'served',
                'served': 'immutable',
                'immutable': 'base'}
 
 
 class BranchMapCache(object):
     """mapping of filtered views of repo with their branchcache"""
     def __init__(self):
         self._per_filter = {}
 
     def __getitem__(self, repo):
         self.updatecache(repo)
         return self._per_filter[repo.filtername]
 
     def updatecache(self, repo):
         """Update the cache for the given filtered view on a repository"""
         # This can trigger updates for the caches for subsets of the filtered
         # view, e.g. when there is no cache for this filtered view or the cache
         # is stale.
 
         cl = repo.changelog
         filtername = repo.filtername
         bcache = self._per_filter.get(filtername)
         if bcache is None or not bcache.validfor(repo):
             # cache object missing or cache object stale? Read from disk
             bcache = branchcache.fromfile(repo)
 
         revs = []
         if bcache is None:
             # no (fresh) cache available anymore, perhaps we can re-use
             # the cache for a subset, then extend that to add info on missing
             # revisions.
             subsetname = subsettable.get(filtername)
             if subsetname is not None:
                 subset = repo.filtered(subsetname)
                 bcache = self[subset].copy()
                 extrarevs = subset.changelog.filteredrevs - cl.filteredrevs
                 revs.extend(r for r in extrarevs if r <= bcache.tiprev)
             else:
                 # nothing to fall back on, start empty.
                 bcache = branchcache()
 
         revs.extend(cl.revs(start=bcache.tiprev + 1))
         if revs:
             bcache.update(repo, revs)
 
         assert bcache.validfor(repo), filtername
         self._per_filter[repo.filtername] = bcache
 
     def replace(self, repo, remotebranchmap):
         """Replace the branchmap cache for a repo with a branch mapping.
 
         This is likely only called during clone with a branch map from a
         remote.
 
         """
         cl = repo.changelog
         clrev = cl.rev
         clbranchinfo = cl.branchinfo
         rbheads = []
         closed = []
         for bheads in remotebranchmap.itervalues():
             rbheads += bheads
             for h in bheads:
                 r = clrev(h)
                 b, c = clbranchinfo(r)
                 if c:
                     closed.append(h)
 
         if rbheads:
             rtiprev = max((int(clrev(node)) for node in rbheads))
             cache = branchcache(
                 remotebranchmap, repo[rtiprev].node(), rtiprev,
                 closednodes=closed)
 
             # Try to stick it as low as possible
             # filter above served are unlikely to be fetch from a clone
             for candidate in ('base', 'immutable', 'served'):
                 rview = repo.filtered(candidate)
                 if cache.validfor(rview):
                     self._per_filter[candidate] = cache
                     cache.write(rview)
                     return
 
     def clear(self):
         self._per_filter.clear()
 
 def _unknownnode(node):
     """ raises ValueError when branchcache found a node which does not exists
     """
     raise ValueError(r'node %s does not exist' % pycompat.sysstr(hex(node)))
 
 class branchcache(object):
     """A dict like object that hold branches heads cache.
 
     This cache is used to avoid costly computations to determine all the
     branch heads of a repo.
 
     The cache is serialized on disk in the following format:
 
     <tip hex node> <tip rev number> [optional filtered repo hex hash]
     <branch head hex node> <open/closed state> <branch name>
     <branch head hex node> <open/closed state> <branch name>
     ...
 
     The first line is used to check if the cache is still valid. If the
     branch cache is for a filtered repo view, an optional third hash is
     included that hashes the hashes of all filtered revisions.
 
     The open/closed state is represented by a single letter 'o' or 'c'.
     This field can be used to avoid changelog reads when determining if a
     branch head closes a branch or not.
     """
 
     def __init__(self, entries=(), tipnode=nullid, tiprev=nullrev,
                  filteredhash=None, closednodes=None, hasnode=None):
         """ hasnode is a function which can be used to verify whether changelog
         has a given node or not. If it's not provided, we assume that every node
         we have exists in changelog """
         self.tipnode = tipnode
         self.tiprev = tiprev
         self.filteredhash = filteredhash
         # closednodes is a set of nodes that close their branch. If the branch
         # cache has been updated, it may contain nodes that are no longer
         # heads.
         if closednodes is None:
             self._closednodes = set()
         else:
             self._closednodes = closednodes
         self._entries = dict(entries)
         # whether closed nodes are verified or not
         self._closedverified = False
         # branches for which nodes are verified
         self._verifiedbranches = set()
         self._hasnode = hasnode
         if self._hasnode is None:
             self._hasnode = lambda x: True
 
     def _verifyclosed(self):
         """ verify the closed nodes we have """
         if self._closedverified:
             return
         for node in self._closednodes:
             if not self._hasnode(node):
                 _unknownnode(node)
 
         self._closedverified = True
 
     def _verifybranch(self, branch):
         """ verify head nodes for the given branch. If branch is None, verify
         for all the branches """
         if branch not in self._entries or branch in self._verifiedbranches:
             return
         for n in self._entries[branch]:
             if not self._hasnode(n):
                 _unknownnode(n)
 
         self._verifiedbranches.add(branch)
 
     def _verifyall(self):
         """ verifies nodes of all the branches """
         for b in self._entries:
             self._verifybranch(b)
 
     def __iter__(self):
         return iter(self._entries)
 
     def __setitem__(self, key, value):
         self._entries[key] = value
 
     def __getitem__(self, key):
         self._verifybranch(key)
         return self._entries[key]
 
     def __contains__(self, key):
         self._verifybranch(key)
         return key in self._entries
 
     def iteritems(self):
         self._verifyall()
         return self._entries.iteritems()
 
     def hasbranch(self, label):
         """ checks whether a branch of this name exists or not """
         self._verifybranch(label)
         return label in self._entries
 
     @classmethod
     def fromfile(cls, repo):
         f = None
         try:
             f = repo.cachevfs(cls._filename(repo))
             lineiter = iter(f)
             cachekey = next(lineiter).rstrip('\n').split(" ", 2)
             last, lrev = cachekey[:2]
             last, lrev = bin(last), int(lrev)
             filteredhash = None
             hasnode = repo.changelog.hasnode
             if len(cachekey) > 2:
                 filteredhash = bin(cachekey[2])
             bcache = cls(tipnode=last, tiprev=lrev, filteredhash=filteredhash,
                          hasnode=hasnode)
             if not bcache.validfor(repo):
                 # invalidate the cache
                 raise ValueError(r'tip differs')
             bcache.load(repo, lineiter)
         except (IOError, OSError):
             return None
 
         except Exception as inst:
             if repo.ui.debugflag:
                 msg = 'invalid branchheads cache'
                 if repo.filtername is not None:
                     msg += ' (%s)' % repo.filtername
                 msg += ': %s\n'
                 repo.ui.debug(msg % pycompat.bytestr(inst))
             bcache = None
 
         finally:
             if f:
                 f.close()
 
         return bcache
 
     def load(self, repo, lineiter):
         """ fully loads the branchcache by reading from the file using the line
         iterator passed"""
         for line in lineiter:
             line = line.rstrip('\n')
             if not line:
                 continue
             node, state, label = line.split(" ", 2)
             if state not in 'oc':
                 raise ValueError(r'invalid branch state')
             label = encoding.tolocal(label.strip())
             node = bin(node)
             self._entries.setdefault(label, []).append(node)
             if state == 'c':
                 self._closednodes.add(node)
 
     @staticmethod
     def _filename(repo):
         """name of a branchcache file for a given repo or repoview"""
         filename = "branch2"
         if repo.filtername:
             filename = '%s-%s' % (filename, repo.filtername)
         return filename
 
     def validfor(self, repo):
         """Is the cache content valid regarding a repo
 
         - False when cached tipnode is unknown or if we detect a strip.
         - True when cache is up to date or a subset of current repo."""
         try:
             return ((self.tipnode == repo.changelog.node(self.tiprev))
                     and (self.filteredhash ==
                          scmutil.filteredhash(repo, self.tiprev)))
         except IndexError:
             return False
 
     def _branchtip(self, heads):
         '''Return tuple with last open head in heads and false,
         otherwise return last closed head and true.'''
         tip = heads[-1]
         closed = True
         for h in reversed(heads):
             if h not in self._closednodes:
                 tip = h
                 closed = False
                 break
         return tip, closed
 
     def branchtip(self, branch):
         '''Return the tipmost open head on branch head, otherwise return the
         tipmost closed head on branch.
         Raise KeyError for unknown branch.'''
         return self._branchtip(self[branch])[0]
 
     def iteropen(self, nodes):
         return (n for n in nodes if n not in self._closednodes)
 
     def branchheads(self, branch, closed=False):
         self._verifybranch(branch)
         heads = self._entries[branch]
         if not closed:
             heads = list(self.iteropen(heads))
         return heads
 
     def iterbranches(self):
         for bn, heads in self.iteritems():
             yield (bn, heads) + self._branchtip(heads)
 
     def iterheads(self):
         """ returns all the heads """
         self._verifyall()
         return self._entries.itervalues()
 
     def copy(self):
         """return an deep copy of the branchcache object"""
         self._verifyall()
         return type(self)(
             self._entries, self.tipnode, self.tiprev, self.filteredhash,
             self._closednodes)
 
     def write(self, repo):
         try:
             f = repo.cachevfs(self._filename(repo), "w", atomictemp=True)
             cachekey = [hex(self.tipnode), '%d' % self.tiprev]
             if self.filteredhash is not None:
                 cachekey.append(hex(self.filteredhash))
             f.write(" ".join(cachekey) + '\n')
             nodecount = 0
             for label, nodes in sorted(self.iteritems()):
                 label = encoding.fromlocal(label)
                 for node in nodes:
                     nodecount += 1
                     if node in self._closednodes:
                         state = 'c'
                     else:
                         state = 'o'
                     f.write("%s %s %s\n" % (hex(node), state, label))
             f.close()
             repo.ui.log('branchcache',
                         'wrote %s branch cache with %d labels and %d nodes\n',
                         repo.filtername, len(self._entries), nodecount)
         except (IOError, OSError, error.Abort) as inst:
             # Abort may be raised by read only opener, so log and continue
             repo.ui.debug("couldn't write branch cache: %s\n" %
                           stringutil.forcebytestr(inst))
 
     def update(self, repo, revgen):
         """Given a branchhead cache, self, that may have extra nodes or be
         missing heads, and a generator of nodes that are strictly a superset of
         heads missing, this function updates self to be correct.
         """
         starttime = util.timer()
         cl = repo.changelog
         # collect new branch entries
         newbranches = {}
         getbranchinfo = repo.revbranchcache().branchinfo
         for r in revgen:
             branch, closesbranch = getbranchinfo(r)
             newbranches.setdefault(branch, []).append(r)
             if closesbranch:
                 self._closednodes.add(cl.node(r))
 
         # fetch current topological heads to speed up filtering
         topoheads = set(cl.headrevs())
 
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newheadrevs in newbranches.iteritems():
             bheads = self._entries.setdefault(branch, [])
             bheadset = set(cl.rev(node) for node in bheads)
 
             # This have been tested True on all internal usage of this function.
             # run it again in case of doubt
             # assert not (set(bheadrevs) & set(newheadrevs))
             bheadset.update(newheadrevs)
 
             # This prunes out two kinds of heads - heads that are superseded by
             # a head in newheadrevs, and newheadrevs that are not heads because
             # an existing head is their descendant.
             uncertain = bheadset - topoheads
             if uncertain:
                 floorrev = min(uncertain)
                 ancestors = set(cl.ancestors(newheadrevs, floorrev))
                 bheadset -= ancestors
             bheadrevs = sorted(bheadset)
             self[branch] = [cl.node(rev) for rev in bheadrevs]
             tiprev = bheadrevs[-1]
             if tiprev > self.tiprev:
                 self.tipnode = cl.node(tiprev)
                 self.tiprev = tiprev
 
         if not self.validfor(repo):
             # cache key are not valid anymore
             self.tipnode = nullid
             self.tiprev = nullrev
             for heads in self.iterheads():
                 tiprev = max(cl.rev(node) for node in heads)
                 if tiprev > self.tiprev:
                     self.tipnode = cl.node(tiprev)
                     self.tiprev = tiprev
         self.filteredhash = scmutil.filteredhash(repo, self.tiprev)
 
         duration = util.timer() - starttime
         repo.ui.log('branchcache', 'updated %s branch cache in %.4f seconds\n',
                     repo.filtername or b'None', duration)
 
         self.write(repo)
 
 
 class remotebranchcache(branchcache):
     """Branchmap info for a remote connection, should not write locally"""
     def write(self, repo):
         pass
 
 
 # Revision branch info cache
 
 _rbcversion = '-v1'
 _rbcnames = 'rbc-names' + _rbcversion
 _rbcrevs = 'rbc-revs' + _rbcversion
 # [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
 _rbcrecfmt = '>4sI'
 _rbcrecsize = calcsize(_rbcrecfmt)
 _rbcnodelen = 4
 _rbcbranchidxmask = 0x7fffffff
 _rbccloseflag = 0x80000000
 
 class revbranchcache(object):
     """Persistent cache, mapping from revision number to branch name and close.
     This is a low level cache, independent of filtering.
 
     Branch names are stored in rbc-names in internal encoding separated by 0.
     rbc-names is append-only, and each branch name is only stored once and will
     thus have a unique index.
 
     The branch info for each revision is stored in rbc-revs as constant size
     records. The whole file is read into memory, but it is only 'parsed' on
     demand. The file is usually append-only but will be truncated if repo
     modification is detected.
     The record for each revision contains the first 4 bytes of the
     corresponding node hash, and the record is only used if it still matches.
     Even a completely trashed rbc-revs fill thus still give the right result
     while converging towards full recovery ... assuming no incorrectly matching
     node hashes.
     The record also contains 4 bytes where 31 bits contains the index of the
     branch and the last bit indicate that it is a branch close commit.
     The usage pattern for rbc-revs is thus somewhat similar to 00changelog.i
     and will grow with it but be 1/8th of its size.
     """
 
     def __init__(self, repo, readonly=True):
         assert repo.filtername is None
         self._repo = repo
         self._names = [] # branch names in local encoding with static index
         self._rbcrevs = bytearray()
         self._rbcsnameslen = 0 # length of names read at _rbcsnameslen
         try:
             bndata = repo.cachevfs.read(_rbcnames)
             self._rbcsnameslen = len(bndata) # for verification before writing
             if bndata:
                 self._names = [encoding.tolocal(bn)
                                for bn in bndata.split('\0')]
         except (IOError, OSError):
             if readonly:
                 # don't try to use cache - fall back to the slow path
                 self.branchinfo = self._branchinfo
 
         if self._names:
             try:
                 data = repo.cachevfs.read(_rbcrevs)
                 self._rbcrevs[:] = data
             except (IOError, OSError) as inst:
                 repo.ui.debug("couldn't read revision branch cache: %s\n" %
                               stringutil.forcebytestr(inst))
         # remember number of good records on disk
         self._rbcrevslen = min(len(self._rbcrevs) // _rbcrecsize,
                                len(repo.changelog))
         if self._rbcrevslen == 0:
             self._names = []
         self._rbcnamescount = len(self._names) # number of names read at
                                                # _rbcsnameslen
 
     def _clear(self):
         self._rbcsnameslen = 0
         del self._names[:]
         self._rbcnamescount = 0
         self._rbcrevslen = len(self._repo.changelog)
         self._rbcrevs = bytearray(self._rbcrevslen * _rbcrecsize)
         util.clearcachedproperty(self, '_namesreverse')
 
     @util.propertycache
     def _namesreverse(self):
         return dict((b, r) for r, b in enumerate(self._names))
 
     def branchinfo(self, rev):
         """Return branch name and close flag for rev, using and updating
         persistent cache."""
         changelog = self._repo.changelog
         rbcrevidx = rev * _rbcrecsize
 
         # avoid negative index, changelog.read(nullrev) is fast without cache
         if rev == nullrev:
             return changelog.branchinfo(rev)
 
         # if requested rev isn't allocated, grow and cache the rev info
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             return self._branchinfo(rev)
 
         # fast path: extract data from cache, use it if node is matching
         reponode = changelog.node(rev)[:_rbcnodelen]
         cachenode, branchidx = unpack_from(
             _rbcrecfmt, util.buffer(self._rbcrevs), rbcrevidx)
         close = bool(branchidx & _rbccloseflag)
         if close:
             branchidx &= _rbcbranchidxmask
         if cachenode == '\0\0\0\0':
             pass
         elif cachenode == reponode:
             try:
                 return self._names[branchidx], close
             except IndexError:
                 # recover from invalid reference to unknown branch
                 self._repo.ui.debug("referenced branch names not found"
                     " - rebuilding revision branch cache from scratch\n")
                 self._clear()
         else:
             # rev/node map has changed, invalidate the cache from here up
             self._repo.ui.debug("history modification detected - truncating "
                 "revision branch cache to revision %d\n" % rev)
             truncate = rbcrevidx + _rbcrecsize
             del self._rbcrevs[truncate:]
             self._rbcrevslen = min(self._rbcrevslen, truncate)
 
         # fall back to slow path and make sure it will be written to disk
         return self._branchinfo(rev)
 
     def _branchinfo(self, rev):
         """Retrieve branch info from changelog and update _rbcrevs"""
         changelog = self._repo.changelog
         b, close = changelog.branchinfo(rev)
         if b in self._namesreverse:
             branchidx = self._namesreverse[b]
         else:
             branchidx = len(self._names)
             self._names.append(b)
             self._namesreverse[b] = branchidx
         reponode = changelog.node(rev)
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, reponode, branchidx)
         return b, close
 
     def setdata(self, branch, rev, node, close):
         """add new data information to the cache"""
         if branch in self._namesreverse:
             branchidx = self._namesreverse[branch]
         else:
             branchidx = len(self._names)
             self._names.append(branch)
             self._namesreverse[branch] = branchidx
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, node, branchidx)
         # If no cache data were readable (non exists, bad permission, etc)
         # the cache was bypassing itself by setting:
         #
         #   self.branchinfo = self._branchinfo
         #
         # Since we now have data in the cache, we need to drop this bypassing.
         if r'branchinfo' in vars(self):
             del self.branchinfo
 
     def _setcachedata(self, rev, node, branchidx):
         """Writes the node's branch data to the in-memory cache data."""
         if rev == nullrev:
             return
         rbcrevidx = rev * _rbcrecsize
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             self._rbcrevs.extend('\0' *
                                  (len(self._repo.changelog) * _rbcrecsize -
                                   len(self._rbcrevs)))
         pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx)
         self._rbcrevslen = min(self._rbcrevslen, rev)
 
         tr = self._repo.currenttransaction()
         if tr:
             tr.addfinalize('write-revbranchcache', self.write)
 
     def write(self, tr=None):
         """Save branch cache if it is dirty."""
         repo = self._repo
         wlock = None
         step = ''
         try:
             if self._rbcnamescount < len(self._names):
                 step = ' names'
                 wlock = repo.wlock(wait=False)
                 if self._rbcnamescount != 0:
                     f = repo.cachevfs.open(_rbcnames, 'ab')
                     if f.tell() == self._rbcsnameslen:
                         f.write('\0')
                     else:
                         f.close()
                         repo.ui.debug("%s changed - rewriting it\n" % _rbcnames)
                         self._rbcnamescount = 0
                         self._rbcrevslen = 0
                 if self._rbcnamescount == 0:
                     # before rewriting names, make sure references are removed
                     repo.cachevfs.unlinkpath(_rbcrevs, ignoremissing=True)
                     f = repo.cachevfs.open(_rbcnames, 'wb')
                 f.write('\0'.join(encoding.fromlocal(b)
                                   for b in self._names[self._rbcnamescount:]))
                 self._rbcsnameslen = f.tell()
                 f.close()
                 self._rbcnamescount = len(self._names)
 
             start = self._rbcrevslen * _rbcrecsize
             if start != len(self._rbcrevs):
                 step = ''
                 if wlock is None:
                     wlock = repo.wlock(wait=False)
                 revs = min(len(repo.changelog),
                            len(self._rbcrevs) // _rbcrecsize)
                 f = repo.cachevfs.open(_rbcrevs, 'ab')
                 if f.tell() != start:
                     repo.ui.debug("truncating cache/%s to %d\n"
                                   % (_rbcrevs, start))
                     f.seek(start)
                     if f.tell() != start:
                         start = 0
                         f.seek(start)
                     f.truncate()
                 end = revs * _rbcrecsize
                 f.write(self._rbcrevs[start:end])
                 f.close()
                 self._rbcrevslen = revs
         except (IOError, OSError, error.Abort, error.LockError) as inst:
             repo.ui.debug("couldn't write revision branch cache%s: %s\n"
                           % (step, stringutil.forcebytestr(inst)))
         finally:
             if wlock is not None:
                 wlock.release()

mercurial/repoview.py

@@ -1,271 +1,280 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 .node import nullrev
 from . import (
     obsolete,
     phases,
     pycompat,
     tags as tagsmod,
 )
 
 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.branchmap.subsettable), you cannot set "public"
     changesets as "hideable". Doing so would break multiple code assertions and
     lead to crashes."""
     obsoletes = obsolete.getrevs(repo, '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, nodemap = cl.rev, cl.nodemap
         pinned.update(rev(t[0]) for t in tags.values() if t[0] in nodemap)
     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, 'visible')
-    secrets = repo._phasecache.getrevset(repo, phases.remotehiddenphases)
+    secrets = filterrevs(repo, 'served.hidden')
     if secrets:
-        return frozenset(hiddens | frozenset(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:]):
         getphase = repo._phasecache.phase
         maymutable = filterrevs(repo, '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:]:
         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.branchmap.subsettable
 # Otherwise your filter will have to recompute all its branches cache
 # from scratch (very slow).
 filtertable = {'visible': computehidden,
                'visible-hidden': computehidden,
+               'served.hidden': computesecret,
                'served': computeunserved,
                'immutable':  computemutable,
                'base':  computeimpactable}
 
 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:
         func = filtertable[filtername]
         if visibilityexceptions:
             return func(repo.unfiltered, visibilityexceptions)
         repo.filteredrevcache[filtername] = func(repo.unfiltered())
     return repo.filteredrevcache[filtername]
 
 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, r'_unfilteredrepo', repo)
         object.__setattr__(self, r'filtername', filtername)
         object.__setattr__(self, r'_clcachekey', None)
         object.__setattr__(self, r'_clcache', None)
         # revs which are exceptions and must not be hidden
         object.__setattr__(self, r'_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]
 
         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:
             cl = copy.copy(unfichangelog)
             cl.filteredrevs = revs
             object.__setattr__(self, r'_clcache', cl)
             object.__setattr__(self, r'_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 r'<%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]