filelog: wrap revlog instead of inheriting it (API)

The revlog base class exposes a ton of methods. Inheriting the
revlog class for filelog will make it difficult to expose a
clean interface. There will be abstraction violations.

This commit breaks the inheritance of revlog by the filelog
class. Filelog instances now contain a reference to a revlog
instance. Various properties and methods are now proxied to
that instance.

There is precedence for doing this: manifestlog does something
similar. Although, manifestlog has a cleaner interface than
filelog. We'll get there with filelog...

The new filelog class exposes a handful of extra properties and
methods that aren't part of the declared filelog interface.
Every extra item was added in order to get a test to pass. The
set of tests that failed without these extra proxies has
significant overlap with the set of tests that don't work with
the simple store repo. There should be no surprise there.

Hopefully the hardest part about this commit to review are the
changes to bundlerepo and unionrepo. Both repository types
define a custom revlog or revlog-like class and then have a
custom filelog that inherits from both filelog and their custom
revlog. This code has been changed so the filelog types don't
inherit from revlog. Instead, they replace the revlog instance
on the created filelog. This is super hacky. I plan to fix this
in a future commit by parameterizing filelog.__init__.

Because Python function call overhead is a thing, this change
could impact performance by introducing a nearly empty proxy
function for various methods and properties. I would gladly
measure the performance impact of it, but I'm not sure what
operations have tight loops over filelog attribute lookups
or function calls. I know some of the DAG traversal code can
be sensitive about the performance of e.g. parentrevs(). However,
many of these functions are implemented on the revlog class and
therefore have direct access to self.parentrevs() and aren't
going through a proxy.

.. api::

   filelog.filelog is now a standalone class and doesn't inherit
   from revlog. Instead, it wraps a revlog instance at self._revlog.
   This change was made in an attempt to formalize storage APIs and
   prevent revlog implementation details leaking through to callers.

Differential Revision: https://phab.mercurial-scm.org/D3154

mercurial/bundlerepo.py

@@ -1,598 +1,598 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[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.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from __future__ import absolute_import
 
 import os
 import shutil
 import tempfile
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     bundle2,
     changegroup,
     changelog,
     cmdutil,
     discovery,
     error,
     exchange,
     filelog,
     localrepo,
     manifest,
     mdiff,
     node as nodemod,
     pathutil,
     phases,
     pycompat,
     revlog,
     util,
     vfs as vfsmod,
 )
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, cgunpacker, linkmapper):
         # How it works:
         # To retrieve a revision, we need to know the offset of the revision in
         # the bundle (an unbundle object). We store this offset in the index
         # (start). The base of the delta is stored in the base field.
         #
         # To differentiate a rev in the bundle from a rev in the revlog, we
         # check revision against repotiprev.
         opener = vfsmod.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = cgunpacker
         n = len(self)
         self.repotiprev = n - 1
         self.bundlerevs = set() # used by 'bundle()' revset expression
         for deltadata in cgunpacker.deltaiter():
             node, p1, p2, cs, deltabase, delta, flags = deltadata
 
             size = len(delta)
             start = cgunpacker.tell() - size
 
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             for p in (p1, p2):
                 if p not in self.nodemap:
                     raise error.LookupError(p, self.indexfile,
                                             _("unknown parent"))
 
             if deltabase not in self.nodemap:
                 raise LookupError(deltabase, self.indexfile,
                                   _('unknown delta base'))
 
             baserev = self.rev(deltabase)
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (revlog.offset_type(start, flags), size, -1, baserev, link,
                  self.rev(p1), self.rev(p2), node)
             self.index.insert(-1, e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             n += 1
 
     def _chunk(self, rev, df=None):
         # Warning: in case of bundle, the diff is against what we stored as
         # delta base, not against rev - 1
         # XXX: could use some caching
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             # hot path for bundle
             revb = self.index[rev2][3]
             if revb == rev1:
                 return self._chunk(rev2)
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.revision(rev1, raw=True),
                               self.revision(rev2, raw=True))
 
     def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = self.rev(node)
 
         if node == nullid:
             return ""
 
         rawtext = None
         chain = []
         iterrev = rev
         # reconstruct the revision if it is from a changegroup
         while iterrev > self.repotiprev:
             if self._cache and self._cache[1] == iterrev:
                 rawtext = self._cache[2]
                 break
             chain.append(iterrev)
             iterrev = self.index[iterrev][3]
         if rawtext is None:
             rawtext = self.baserevision(iterrev)
 
         while chain:
             delta = self._chunk(chain.pop())
             rawtext = mdiff.patches(rawtext, [delta])
 
         text, validatehash = self._processflags(rawtext, self.flags(rev),
                                                 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
         self._cache = (node, rev, rawtext)
         return text
 
     def baserevision(self, nodeorrev):
         # Revlog subclasses may override 'revision' method to modify format of
         # content retrieved from revlog. To use bundlerevlog with such class one
         # needs to override 'baserevision' and make more specific call here.
         return revlog.revlog.revision(self, nodeorrev, raw=True)
 
     def addrevision(self, *args, **kwargs):
         raise NotImplementedError
 
     def addgroup(self, *args, **kwargs):
         raise NotImplementedError
 
     def strip(self, *args, **kwargs):
         raise NotImplementedError
 
     def checksize(self):
         raise NotImplementedError
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, cgunpacker):
         changelog.changelog.__init__(self, opener)
         linkmapper = lambda x: x
         bundlerevlog.__init__(self, opener, self.indexfile, cgunpacker,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         # Although changelog doesn't override 'revision' method, some extensions
         # may replace this class with another that does. Same story with
         # manifest and filelog classes.
 
         # This bypasses filtering on changelog.node() and rev() because we need
         # revision text of the bundle base even if it is hidden.
         oldfilter = self.filteredrevs
         try:
             self.filteredrevs = ()
             return changelog.changelog.revision(self, nodeorrev, raw=True)
         finally:
             self.filteredrevs = oldfilter
 
 class bundlemanifest(bundlerevlog, manifest.manifestrevlog):
     def __init__(self, opener, cgunpacker, linkmapper, dirlogstarts=None,
                  dir=''):
         manifest.manifestrevlog.__init__(self, opener, dir=dir)
         bundlerevlog.__init__(self, opener, self.indexfile, cgunpacker,
                               linkmapper)
         if dirlogstarts is None:
             dirlogstarts = {}
             if self.bundle.version == "03":
                 dirlogstarts = _getfilestarts(self.bundle)
         self._dirlogstarts = dirlogstarts
         self._linkmapper = linkmapper
 
     def baserevision(self, nodeorrev):
         node = nodeorrev
         if isinstance(node, int):
             node = self.node(node)
 
         if node in self.fulltextcache:
             result = '%s' % self.fulltextcache[node]
         else:
             result = manifest.manifestrevlog.revision(self, nodeorrev, raw=True)
         return result
 
     def dirlog(self, d):
         if d in self._dirlogstarts:
             self.bundle.seek(self._dirlogstarts[d])
             return bundlemanifest(
                 self.opener, self.bundle, self._linkmapper,
                 self._dirlogstarts, dir=d)
         return super(bundlemanifest, self).dirlog(d)
 
-class bundlefilelog(bundlerevlog, filelog.filelog):
+class bundlefilelog(filelog.filelog):
     def __init__(self, opener, path, cgunpacker, linkmapper):
         filelog.filelog.__init__(self, opener, path)
-        bundlerevlog.__init__(self, opener, self.indexfile, cgunpacker,
-                              linkmapper)
+        self._revlog = bundlerevlog(opener, self.indexfile,
+                                    cgunpacker, linkmapper)
 
     def baserevision(self, nodeorrev):
         return filelog.filelog.revision(self, nodeorrev, raw=True)
 
 class bundlepeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 class bundlephasecache(phases.phasecache):
     def __init__(self, *args, **kwargs):
         super(bundlephasecache, self).__init__(*args, **kwargs)
         if util.safehasattr(self, 'opener'):
             self.opener = vfsmod.readonlyvfs(self.opener)
 
     def write(self):
         raise NotImplementedError
 
     def _write(self, fp):
         raise NotImplementedError
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
 def _getfilestarts(cgunpacker):
     filespos = {}
     for chunkdata in iter(cgunpacker.filelogheader, {}):
         fname = chunkdata['filename']
         filespos[fname] = cgunpacker.tell()
         for chunk in iter(lambda: cgunpacker.deltachunk(None), {}):
             pass
     return filespos
 
 class bundlerepository(localrepo.localrepository):
     """A repository instance that is a union of a local repo and a bundle.
 
     Instances represent a read-only repository composed of a local repository
     with the contents of a bundle file applied. The repository instance is
     conceptually similar to the state of a repository after an
     ``hg unbundle`` operation. However, the contents of the bundle are never
     applied to the actual base repository.
     """
     def __init__(self, ui, repopath, bundlepath):
         self._tempparent = None
         try:
             localrepo.localrepository.__init__(self, ui, repopath)
         except error.RepoError:
             self._tempparent = tempfile.mkdtemp()
             localrepo.instance(ui, self._tempparent, 1)
             localrepo.localrepository.__init__(self, ui, self._tempparent)
         self.ui.setconfig('phases', 'publish', False, 'bundlerepo')
 
         if repopath:
             self._url = 'bundle:' + util.expandpath(repopath) + '+' + bundlepath
         else:
             self._url = 'bundle:' + bundlepath
 
         self.tempfile = None
         f = util.posixfile(bundlepath, "rb")
         bundle = exchange.readbundle(ui, f, bundlepath)
 
         if isinstance(bundle, bundle2.unbundle20):
             self._bundlefile = bundle
             self._cgunpacker = None
 
             cgpart = None
             for part in bundle.iterparts(seekable=True):
                 if part.type == 'changegroup':
                     if cgpart:
                         raise NotImplementedError("can't process "
                                                   "multiple changegroups")
                     cgpart = part
 
                 self._handlebundle2part(bundle, part)
 
             if not cgpart:
                 raise error.Abort(_("No changegroups found"))
 
             # This is required to placate a later consumer, which expects
             # the payload offset to be at the beginning of the changegroup.
             # We need to do this after the iterparts() generator advances
             # because iterparts() will seek to end of payload after the
             # generator returns control to iterparts().
             cgpart.seek(0, os.SEEK_SET)
 
         elif isinstance(bundle, changegroup.cg1unpacker):
             if bundle.compressed():
                 f = self._writetempbundle(bundle.read, '.hg10un',
                                           header='HG10UN')
                 bundle = exchange.readbundle(ui, f, bundlepath, self.vfs)
 
             self._bundlefile = bundle
             self._cgunpacker = bundle
         else:
             raise error.Abort(_('bundle type %s cannot be read') %
                               type(bundle))
 
         # dict with the mapping 'filename' -> position in the changegroup.
         self._cgfilespos = {}
 
         self.firstnewrev = self.changelog.repotiprev + 1
         phases.retractboundary(self, None, phases.draft,
                                [ctx.node() for ctx in self[self.firstnewrev:]])
 
     def _handlebundle2part(self, bundle, part):
         if part.type != 'changegroup':
             return
 
         cgstream = part
         version = part.params.get('version', '01')
         legalcgvers = changegroup.supportedincomingversions(self)
         if version not in legalcgvers:
             msg = _('Unsupported changegroup version: %s')
             raise error.Abort(msg % version)
         if bundle.compressed():
             cgstream = self._writetempbundle(part.read, '.cg%sun' % version)
 
         self._cgunpacker = changegroup.getunbundler(version, cgstream, 'UN')
 
     def _writetempbundle(self, readfn, suffix, header=''):
         """Write a temporary file to disk
         """
         fdtemp, temp = self.vfs.mkstemp(prefix="hg-bundle-",
                                         suffix=suffix)
         self.tempfile = temp
 
         with os.fdopen(fdtemp, r'wb') as fptemp:
             fptemp.write(header)
             while True:
                 chunk = readfn(2**18)
                 if not chunk:
                     break
                 fptemp.write(chunk)
 
         return self.vfs.open(self.tempfile, mode="rb")
 
     @localrepo.unfilteredpropertycache
     def _phasecache(self):
         return bundlephasecache(self, self._phasedefaults)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         # consume the header if it exists
         self._cgunpacker.changelogheader()
         c = bundlechangelog(self.svfs, self._cgunpacker)
         self.manstart = self._cgunpacker.tell()
         return c
 
     def _constructmanifest(self):
         self._cgunpacker.seek(self.manstart)
         # consume the header if it exists
         self._cgunpacker.manifestheader()
         linkmapper = self.unfiltered().changelog.rev
         m = bundlemanifest(self.svfs, self._cgunpacker, linkmapper)
         self.filestart = self._cgunpacker.tell()
         return m
 
     def _consumemanifest(self):
         """Consumes the manifest portion of the bundle, setting filestart so the
         file portion can be read."""
         self._cgunpacker.seek(self.manstart)
         self._cgunpacker.manifestheader()
         for delta in self._cgunpacker.deltaiter():
             pass
         self.filestart = self._cgunpacker.tell()
 
     @localrepo.unfilteredpropertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @localrepo.unfilteredpropertycache
     def filestart(self):
         self.manifestlog
 
         # If filestart was not set by self.manifestlog, that means the
         # manifestlog implementation did not consume the manifests from the
         # changegroup (ex: it might be consuming trees from a separate bundle2
         # part instead). So we need to manually consume it.
         if r'filestart' not in self.__dict__:
             self._consumemanifest()
 
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self._cgfilespos:
             self._cgunpacker.seek(self.filestart)
             self._cgfilespos = _getfilestarts(self._cgunpacker)
 
         if f in self._cgfilespos:
             self._cgunpacker.seek(self._cgfilespos[f])
             linkmapper = self.unfiltered().changelog.rev
             return bundlefilelog(self.svfs, f, self._cgunpacker, linkmapper)
         else:
             return super(bundlerepository, self).file(f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self._bundlefile.close()
         if self.tempfile is not None:
             self.vfs.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def peer(self):
         return bundlepeer(self)
 
     def getcwd(self):
         return pycompat.getcwd() # always outside the repo
 
     # Check if parents exist in localrepo before setting
     def setparents(self, p1, p2=nullid):
         p1rev = self.changelog.rev(p1)
         p2rev = self.changelog.rev(p2)
         msg = _("setting parent to node %s that only exists in the bundle\n")
         if self.changelog.repotiprev < p1rev:
             self.ui.warn(msg % nodemod.hex(p1))
         if self.changelog.repotiprev < p2rev:
             self.ui.warn(msg % nodemod.hex(p2))
         return super(bundlerepository, self).setparents(p1, p2)
 
 def instance(ui, path, create):
     if create:
         raise error.Abort(_('cannot create new bundle repository'))
     # internal config: bundle.mainreporoot
     parentpath = ui.config("bundle", "mainreporoot")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(pycompat.getcwd())
         if parentpath is None:
             parentpath = ''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = pycompat.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     u = util.url(path)
     path = u.localpath()
     if u.scheme == 'bundle':
         s = path.split("+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
     return bundlerepository(ui, repopath, bundlename)
 
 class bundletransactionmanager(object):
     def transaction(self):
         return None
 
     def close(self):
         raise NotImplementedError
 
     def release(self):
         raise NotImplementedError
 
 def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None,
                      force=False):
     '''obtains a bundle of changes incoming from other
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "other" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "other" and the one returned
       here.
     '''
     tmp = discovery.findcommonincoming(repo, other, heads=onlyheads,
                                        force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return repo, [], other.close
 
     commonset = set(common)
     rheads = [x for x in rheads if x not in commonset]
 
     bundle = None
     bundlerepo = None
     localrepo = other.local()
     if bundlename or not localrepo:
         # create a bundle (uncompressed if other repo is not local)
 
         # developer config: devel.legacy.exchange
         legexc = ui.configlist('devel', 'legacy.exchange')
         forcebundle1 = 'bundle2' not in legexc and 'bundle1' in legexc
         canbundle2 = (not forcebundle1
                       and other.capable('getbundle')
                       and other.capable('bundle2'))
         if canbundle2:
             kwargs = {}
             kwargs[r'common'] = common
             kwargs[r'heads'] = rheads
             kwargs[r'bundlecaps'] = exchange.caps20to10(repo, role='client')
             kwargs[r'cg'] = True
             b2 = other.getbundle('incoming', **kwargs)
             fname = bundle = changegroup.writechunks(ui, b2._forwardchunks(),
                                                      bundlename)
         else:
             if other.capable('getbundle'):
                 cg = other.getbundle('incoming', common=common, heads=rheads)
             elif onlyheads is None and not other.capable('changegroupsubset'):
                 # compat with older servers when pulling all remote heads
                 cg = other.changegroup(incoming, "incoming")
                 rheads = None
             else:
                 cg = other.changegroupsubset(incoming, rheads, 'incoming')
             if localrepo:
                 bundletype = "HG10BZ"
             else:
                 bundletype = "HG10UN"
             fname = bundle = bundle2.writebundle(ui, cg, bundlename,
                                                      bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not localrepo:
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = bundlerepository(repo.baseui, repo.root,
                                                       fname)
             # this repo contains local and other now, so filter out local again
             common = repo.heads()
     if localrepo:
         # Part of common may be remotely filtered
         # So use an unfiltered version
         # The discovery process probably need cleanup to avoid that
         localrepo = localrepo.unfiltered()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     if bundlerepo:
         reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev:]]
         remotephases = other.listkeys('phases')
 
         pullop = exchange.pulloperation(bundlerepo, other, heads=reponodes)
         pullop.trmanager = bundletransactionmanager()
         exchange._pullapplyphases(pullop, remotephases)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         other.close()
 
     return (localrepo, csets, cleanup)

mercurial/filelog.py

@@ -1,85 +1,267 b''
 # filelog.py - file history class for mercurial
 #
 # 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
 
 from .thirdparty.zope import (
     interface as zi,
 )
 from . import (
+    error,
     repository,
     revlog,
 )
 
 @zi.implementer(repository.ifilestorage)
-class filelog(revlog.revlog):
+class filelog(object):
     def __init__(self, opener, path):
-        super(filelog, self).__init__(opener,
-                        "/".join(("data", path + ".i")),
+        self._revlog = revlog.revlog(opener,
+                                     '/'.join(('data', path + '.i')),
                                       censorable=True)
         # full name of the user visible file, relative to the repository root
         self.filename = path
+        self.index = self._revlog.index
+        self.version = self._revlog.version
+        self.storedeltachains = self._revlog.storedeltachains
+        self._generaldelta = self._revlog._generaldelta
+
+    def __len__(self):
+        return len(self._revlog)
+
+    def __iter__(self):
+        return self._revlog.__iter__()
+
+    def revs(self, start=0, stop=None):
+        return self._revlog.revs(start=start, stop=stop)
+
+    def parents(self, node):
+        return self._revlog.parents(node)
+
+    def parentrevs(self, rev):
+        return self._revlog.parentrevs(rev)
+
+    def rev(self, node):
+        return self._revlog.rev(node)
+
+    def node(self, rev):
+        return self._revlog.node(rev)
+
+    def lookup(self, node):
+        return self._revlog.lookup(node)
+
+    def linkrev(self, rev):
+        return self._revlog.linkrev(rev)
+
+    def flags(self, rev):
+        return self._revlog.flags(rev)
+
+    def commonancestorsheads(self, node1, node2):
+        return self._revlog.commonancestorsheads(node1, node2)
+
+    def descendants(self, revs):
+        return self._revlog.descendants(revs)
+
+    def headrevs(self):
+        return self._revlog.headrevs()
+
+    def heads(self, start=None, stop=None):
+        return self._revlog.heads(start, stop)
+
+    def children(self, node):
+        return self._revlog.children(node)
+
+    def deltaparent(self, rev):
+        return self._revlog.deltaparent(rev)
+
+    def candelta(self, baserev, rev):
+        return self._revlog.candelta(baserev, rev)
+
+    def iscensored(self, rev):
+        return self._revlog.iscensored(rev)
+
+    def rawsize(self, rev):
+        return self._revlog.rawsize(rev)
+
+    def checkhash(self, text, node, p1=None, p2=None, rev=None):
+        return self._revlog.checkhash(text, node, p1=p1, p2=p2, rev=rev)
+
+    def revision(self, node, _df=None, raw=False):
+        return self._revlog.revision(node, _df=_df, raw=raw)
+
+    def revdiff(self, rev1, rev2):
+        return self._revlog.revdiff(rev1, rev2)
+
+    def addrevision(self, revisiondata, transaction, linkrev, p1, p2,
+                    node=None, flags=revlog.REVIDX_DEFAULT_FLAGS,
+                    cachedelta=None):
+        return self._revlog.addrevision(revisiondata, transaction, linkrev,
+                                    p1, p2, node=node, flags=flags,
+                                    cachedelta=cachedelta)
+
+    def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
+        return self._revlog.addgroup(deltas, linkmapper, transaction,
+                                 addrevisioncb=addrevisioncb)
+
+    def getstrippoint(self, minlink):
+        return self._revlog.getstrippoint(minlink)
+
+    def strip(self, minlink, transaction):
+        return self._revlog.strip(minlink, transaction)
+
+    def files(self):
+        return self._revlog.files()
+
+    def checksize(self):
+        return self._revlog.checksize()
 
     def read(self, node):
         t = self.revision(node)
         if not t.startswith('\1\n'):
             return t
         s = t.index('\1\n', 2)
         return t[s + 2:]
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith('\1\n'):
             text = revlog.packmeta(meta, text)
         return self.addrevision(text, transaction, link, p1, p2)
 
     def renamed(self, node):
         if self.parents(node)[0] != revlog.nullid:
             return False
         t = self.revision(node)
         m = revlog.parsemeta(t)[0]
         if m and "copy" in m:
             return (m["copy"], revlog.bin(m["copyrev"]))
         return False
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.renamed(node):
             return len(self.read(node))
         if self.iscensored(rev):
             return 0
 
         # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
-        return super(filelog, self).size(rev)
+        return self._revlog.size(rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
 
         t = text
         if text.startswith('\1\n'):
             t = '\1\n\1\n' + text
 
-        samehashes = not super(filelog, self).cmp(node, t)
+        samehashes = not self._revlog.cmp(node, t)
         if samehashes:
             return False
 
         # censored files compare against the empty file
         if self.iscensored(self.rev(node)):
             return text != ''
 
         # renaming a file produces a different hash, even if the data
         # remains unchanged. Check if it's the case (slow):
         if self.renamed(node):
             t2 = self.read(node)
             return t2 != text
 
         return True
+
+    @property
+    def filename(self):
+        return self._revlog.filename
+
+    @filename.setter
+    def filename(self, value):
+        self._revlog.filename = value
+
+    # TODO these aren't part of the interface and aren't internal methods.
+    # Callers should be fixed to not use them.
+    @property
+    def indexfile(self):
+        return self._revlog.indexfile
+
+    @indexfile.setter
+    def indexfile(self, value):
+        self._revlog.indexfile = value
+
+    @property
+    def datafile(self):
+        return self._revlog.datafile
+
+    @property
+    def opener(self):
+        return self._revlog.opener
+
+    @property
+    def _lazydeltabase(self):
+        return self._revlog._lazydeltabase
+
+    @_lazydeltabase.setter
+    def _lazydeltabase(self, value):
+        self._revlog._lazydeltabase = value
+
+    @property
+    def _aggressivemergedeltas(self):
+        return self._revlog._aggressivemergedeltas
+
+    @_aggressivemergedeltas.setter
+    def _aggressivemergedeltas(self, value):
+        self._revlog._aggressivemergedeltas = value
+
+    @property
+    def _inline(self):
+        return self._revlog._inline
+
+    @property
+    def _withsparseread(self):
+        return getattr(self._revlog, '_withsparseread', False)
+
+    @property
+    def _srmingapsize(self):
+        return self._revlog._srmingapsize
+
+    @property
+    def _srdensitythreshold(self):
+        return self._revlog._srdensitythreshold
+
+    def _deltachain(self, rev, stoprev=None):
+        return self._revlog._deltachain(rev, stoprev)
+
+    def chainbase(self, rev):
+        return self._revlog.chainbase(rev)
+
+    def chainlen(self, rev):
+        return self._revlog.chainlen(rev)
+
+    def clone(self, tr, destrevlog, **kwargs):
+        if not isinstance(destrevlog, filelog):
+            raise error.ProgrammingError('expected filelog to clone()')
+
+        return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
+
+    def start(self, rev):
+        return self._revlog.start(rev)
+
+    def end(self, rev):
+        return self._revlog.end(rev)
+
+    def length(self, rev):
+        return self._revlog.length(rev)
+
+    def compress(self, data):
+        return self._revlog.compress(data)
+
+    def _addrevision(self, *args, **kwargs):
+        return self._revlog._addrevision(*args, **kwargs)

mercurial/unionrepo.py

@@ -1,259 +1,261 b''
 # unionrepo.py - repository class for viewing union of repository changesets
 #
 # Derived from bundlerepo.py
 # Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
 # Copyright 2013 Unity Technologies, Mads Kiilerich <[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.
 
 """Repository class for "in-memory pull" of one local repository to another,
 allowing operations like diff and log with revsets.
 """
 
 from __future__ import absolute_import
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     changelog,
     cmdutil,
     error,
     filelog,
     localrepo,
     manifest,
     mdiff,
     pathutil,
     pycompat,
     revlog,
     util,
     vfs as vfsmod,
 )
 
 class unionrevlog(revlog.revlog):
     def __init__(self, opener, indexfile, revlog2, linkmapper):
         # How it works:
         # To retrieve a revision, we just need to know the node id so we can
         # look it up in revlog2.
         #
         # To differentiate a rev in the second revlog from a rev in the revlog,
         # we check revision against repotiprev.
         opener = vfsmod.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.revlog2 = revlog2
 
         n = len(self)
         self.repotiprev = n - 1
         self.bundlerevs = set() # used by 'bundle()' revset expression
         for rev2 in self.revlog2:
             rev = self.revlog2.index[rev2]
             # rev numbers - in revlog2, very different from self.rev
             _start, _csize, _rsize, base, linkrev, p1rev, p2rev, node = rev
             flags = _start & 0xFFFF
 
             if linkmapper is None: # link is to same revlog
                 assert linkrev == rev2 # we never link back
                 link = n
             else: # rev must be mapped from repo2 cl to unified cl by linkmapper
                 link = linkmapper(linkrev)
 
             if linkmapper is not None: # link is to same revlog
                 base = linkmapper(base)
 
             if node in self.nodemap:
                 # this happens for the common revlog revisions
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             p1node = self.revlog2.node(p1rev)
             p2node = self.revlog2.node(p2rev)
 
             e = (flags, None, None, base,
                  link, self.rev(p1node), self.rev(p2node), node)
             self.index.insert(-1, e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             n += 1
 
     def _chunk(self, rev):
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         return self.revlog2._chunk(self.node(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             return self.revlog2.revdiff(
                 self.revlog2.rev(self.node(rev1)),
                 self.revlog2.rev(self.node(rev2)))
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return self.baserevdiff(rev1, rev2)
 
         return mdiff.textdiff(self.revision(rev1), self.revision(rev2))
 
-    def revision(self, nodeorrev, raw=False):
+    def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = self.rev(node)
 
         if node == nullid:
             return ""
 
         if rev > self.repotiprev:
             text = self.revlog2.revision(node)
             self._cache = (node, rev, text)
         else:
             text = self.baserevision(rev)
             # already cached
         return text
 
     def baserevision(self, nodeorrev):
         # Revlog subclasses may override 'revision' method to modify format of
         # content retrieved from revlog. To use unionrevlog with such class one
         # needs to override 'baserevision' and make more specific call here.
         return revlog.revlog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         # Exists for the same purpose as baserevision.
         return revlog.revlog.revdiff(self, rev1, rev2)
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
     def addgroup(self, deltas, transaction, addrevisioncb=None):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
     def checksize(self):
         raise NotImplementedError
 
 class unionchangelog(unionrevlog, changelog.changelog):
     def __init__(self, opener, opener2):
         changelog.changelog.__init__(self, opener)
         linkmapper = None
         changelog2 = changelog.changelog(opener2)
         unionrevlog.__init__(self, opener, self.indexfile, changelog2,
                              linkmapper)
 
     def baserevision(self, nodeorrev):
         # Although changelog doesn't override 'revision' method, some extensions
         # may replace this class with another that does. Same story with
         # manifest and filelog classes.
         return changelog.changelog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         return changelog.changelog.revdiff(self, rev1, rev2)
 
 class unionmanifest(unionrevlog, manifest.manifestrevlog):
     def __init__(self, opener, opener2, linkmapper):
         manifest.manifestrevlog.__init__(self, opener)
         manifest2 = manifest.manifestrevlog(opener2)
         unionrevlog.__init__(self, opener, self.indexfile, manifest2,
                              linkmapper)
 
     def baserevision(self, nodeorrev):
         return manifest.manifestrevlog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         return manifest.manifestrevlog.revdiff(self, rev1, rev2)
 
-class unionfilelog(unionrevlog, filelog.filelog):
+class unionfilelog(filelog.filelog):
     def __init__(self, opener, path, opener2, linkmapper, repo):
         filelog.filelog.__init__(self, opener, path)
         filelog2 = filelog.filelog(opener2, path)
-        unionrevlog.__init__(self, opener, self.indexfile, filelog2,
-                             linkmapper)
+        self._revlog = unionrevlog(opener, self.indexfile,
+                                   filelog2._revlog, linkmapper)
         self._repo = repo
+        self.repotiprev = self._revlog.repotiprev
+        self.revlog2 = self._revlog.revlog2
 
     def baserevision(self, nodeorrev):
         return filelog.filelog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         return filelog.filelog.revdiff(self, rev1, rev2)
 
     def iscensored(self, rev):
         """Check if a revision is censored."""
         if rev <= self.repotiprev:
             return filelog.filelog.iscensored(self, rev)
         node = self.node(rev)
         return self.revlog2.iscensored(self.revlog2.rev(node))
 
 class unionpeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 class unionrepository(localrepo.localrepository):
     def __init__(self, ui, path, path2):
         localrepo.localrepository.__init__(self, ui, path)
         self.ui.setconfig('phases', 'publish', False, 'unionrepo')
 
         self._url = 'union:%s+%s' % (util.expandpath(path),
                                      util.expandpath(path2))
         self.repo2 = localrepo.localrepository(ui, path2)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         return unionchangelog(self.svfs, self.repo2.svfs)
 
     def _clrev(self, rev2):
         """map from repo2 changelog rev to temporary rev in self.changelog"""
         node = self.repo2.changelog.node(rev2)
         return self.changelog.rev(node)
 
     def _constructmanifest(self):
         return unionmanifest(self.svfs, self.repo2.svfs,
                              self.unfiltered()._clrev)
 
     def url(self):
         return self._url
 
     def file(self, f):
         return unionfilelog(self.svfs, f, self.repo2.svfs,
                             self.unfiltered()._clrev, self)
 
     def close(self):
         self.repo2.close()
 
     def cancopy(self):
         return False
 
     def peer(self):
         return unionpeer(self)
 
     def getcwd(self):
         return pycompat.getcwd() # always outside the repo
 
 def instance(ui, path, create):
     if create:
         raise error.Abort(_('cannot create new union repository'))
     parentpath = ui.config("bundle", "mainreporoot")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(pycompat.getcwd())
         if parentpath is None:
             parentpath = ''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = pycompat.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     if path.startswith('union:'):
         s = path.split(":", 1)[1].split("+", 1)
         if len(s) == 1:
             repopath, repopath2 = parentpath, s[0]
         else:
             repopath, repopath2 = s
     else:
         repopath, repopath2 = parentpath, path
     return unionrepository(ui, repopath, repopath2)