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

@@ -217,11 +217,11 b' class bundlemanifest(bundlerevlog, manif'
                 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)

mercurial/filelog.py

@@ -11,18 +11,112 b' 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")),
-                                      censorable=True)
+        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)
@@ -56,7 +150,7 b' class filelog(revlog.revlog):'
             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
@@ -68,7 +162,7 b' class filelog(revlog.revlog):'
         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
 
@@ -83,3 +177,91 b' class filelog(revlog.revlog):'
             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

@@ -92,7 +92,7 b' class unionrevlog(revlog.revlog):'
 
         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.
         """
@@ -163,13 +163,15 b' class unionmanifest(unionrevlog, manifes'
     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)