storageutil: extract filelog.cmp() to a standalone function

As part of implementing an alternate storage backend, I found myself
reimplementing this code.

With a little massaging, we can extract filelog.cmp() to a standalone
function.

As part of this, the call to revlog.cmp() was inlined (it is just a
2-line function).

I also tweaked some variable names to improve readability. I'll
further tweak names in a subsequent commit.

Differential Revision: https://phab.mercurial-scm.org/D4801

mercurial/filelog.py

@@ -1,238 +1,219
 # 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 . import (
     error,
     repository,
     revlog,
 )
 from .utils import (
     interfaceutil,
     storageutil,
 )
 
 @interfaceutil.implementer(repository.ifilestorage)
 class filelog(object):
     def __init__(self, opener, path):
         self._revlog = revlog.revlog(opener,
                                      '/'.join(('data', path + '.i')),
                                      censorable=True)
         # Full name of the user visible file, relative to the repository root.
         # Used by LFS.
         self._revlog.filename = path
 
     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 storageutil.fileidlookup(self._revlog, node,
                                         self._revlog.indexfile)
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def commonancestorsheads(self, node1, node2):
         return self._revlog.commonancestorsheads(node1, node2)
 
     # Used by dagop.blockdescendants().
     def descendants(self, revs):
         return self._revlog.descendants(revs)
 
     def heads(self, start=None, stop=None):
         return self._revlog.heads(start, stop)
 
     # Used by hgweb, children extension.
     def children(self, node):
         return self._revlog.children(node)
 
     def iscensored(self, rev):
         return self._revlog.iscensored(rev)
 
     def revision(self, node, _df=None, raw=False):
         return self._revlog.revision(node, _df=_df, raw=raw)
 
     def emitrevisions(self, nodes, nodesorder=None,
                       revisiondata=False, assumehaveparentrevisions=False,
                       deltaprevious=False):
         return self._revlog.emitrevisions(
             nodes, nodesorder=nodesorder, revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltaprevious=deltaprevious)
 
     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 censorrevision(self, tr, node, tombstone=b''):
         return self._revlog.censorrevision(node, tombstone=tombstone)
 
     def files(self):
         return self._revlog.files()
 
     def read(self, node):
         return storageutil.filtermetadata(self.revision(node))
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith('\1\n'):
             text = storageutil.packmeta(meta, text)
         return self.addrevision(text, transaction, link, p1, p2)
 
     def renamed(self, node):
         return storageutil.filerevisioncopied(self, node)
 
     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 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 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
+        return storageutil.filerevisiondifferent(self, node, text)
 
     def verifyintegrity(self, state):
         return self._revlog.verifyintegrity(state)
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles, sharedfiles=sharedfiles,
             revisionscount=revisionscount, trackedsize=trackedsize,
             storedsize=storedsize)
 
     # TODO these aren't part of the interface and aren't internal methods.
     # Callers should be fixed to not use them.
 
     # Used by bundlefilelog, unionfilelog.
     @property
     def indexfile(self):
         return self._revlog.indexfile
 
     @indexfile.setter
     def indexfile(self, value):
         self._revlog.indexfile = value
 
     # Used by repo upgrade.
     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)
 
 class narrowfilelog(filelog):
     """Filelog variation to be used with narrow stores."""
 
     def __init__(self, opener, path, narrowmatch):
         super(narrowfilelog, self).__init__(opener, path)
         self._narrowmatch = narrowmatch
 
     def renamed(self, node):
         res = super(narrowfilelog, self).renamed(node)
 
         # Renames that come from outside the narrowspec are problematic
         # because we may lack the base text for the rename. This can result
         # in code attempting to walk the ancestry or compute a diff
         # encountering a missing revision. We address this by silently
         # removing rename metadata if the source file is outside the
         # narrow spec.
         #
         # A better solution would be to see if the base revision is available,
         # rather than assuming it isn't.
         #
         # An even better solution would be to teach all consumers of rename
         # metadata that the base revision may not be available.
         #
         # TODO consider better ways of doing this.
         if res and not self._narrowmatch(res[0]):
             return None
 
         return res
 
     def size(self, rev):
         # Because we have a custom renamed() that may lie, we need to call
         # the base renamed() to report accurate results.
         node = self.node(rev)
         if super(narrowfilelog, self).renamed(node):
             return len(self.read(node))
         else:
             return super(narrowfilelog, self).size(rev)
 
     def cmp(self, node, text):
         different = super(narrowfilelog, self).cmp(node, text)
 
         # Because renamed() may lie, we may get false positives for
         # different content. Check for this by comparing against the original
         # renamed() implementation.
         if different:
             if super(narrowfilelog, self).renamed(node):
                 t2 = self.read(node)
                 return t2 != text
 
         return different

mercurial/utils/storageutil.py

@@ -1,228 +1,254
 # storageutil.py - Storage functionality agnostic of backend implementation.
 #
 # Copyright 2018 Gregory Szorc <[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 hashlib
 import re
 
 from ..i18n import _
 from ..node import (
     bin,
     nullid,
     nullrev,
 )
 from .. import (
     error,
     pycompat,
 )
 
 _nullhash = hashlib.sha1(nullid)
 
 def hashrevisionsha1(text, p1, p2):
     """Compute the SHA-1 for revision data and its parents.
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     # As of now, if one of the parent node is null, p2 is null
     if p2 == nullid:
         # deep copy of a hash is faster than creating one
         s = _nullhash.copy()
         s.update(p1)
     else:
         # none of the parent nodes are nullid
         if p1 < p2:
             a = p1
             b = p2
         else:
             a = p2
             b = p1
         s = hashlib.sha1(a)
         s.update(b)
     s.update(text)
     return s.digest()
 
 METADATA_RE = re.compile(b'\x01\n')
 
 def parsemeta(text):
     """Parse metadata header from revision data.
 
     Returns a 2-tuple of (metadata, offset), where both can be None if there
     is no metadata.
     """
     # text can be buffer, so we can't use .startswith or .index
     if text[:2] != b'\x01\n':
         return None, None
     s = METADATA_RE.search(text, 2).start()
     mtext = text[2:s]
     meta = {}
     for l in mtext.splitlines():
         k, v = l.split(b': ', 1)
         meta[k] = v
     return meta, s + 2
 
 def packmeta(meta, text):
     """Add metadata to fulltext to produce revision text."""
     keys = sorted(meta)
     metatext = b''.join(b'%s: %s\n' % (k, meta[k]) for k in keys)
     return b'\x01\n%s\x01\n%s' % (metatext, text)
 
 def iscensoredtext(text):
     meta = parsemeta(text)[0]
     return meta and b'censored' in meta
 
 def filtermetadata(text):
     """Extract just the revision data from source text.
 
     Returns ``text`` unless it has a metadata header, in which case we return
     a new buffer without hte metadata.
     """
     if not text.startswith(b'\x01\n'):
         return text
 
     offset = text.index(b'\x01\n', 2)
     return text[offset + 2:]
 
 def filerevisioncopied(store, node):
     """Resolve file revision copy metadata.
 
     Returns ``False`` if the file has no copy metadata. Otherwise a
     2-tuple of the source filename and node.
     """
     if store.parents(node)[0] != nullid:
         return False
 
     meta = parsemeta(store.revision(node))[0]
 
     # copy and copyrev occur in pairs. In rare cases due to old bugs,
     # one can occur without the other. So ensure both are present to flag
     # as a copy.
     if meta and b'copy' in meta and b'copyrev' in meta:
         return meta[b'copy'], bin(meta[b'copyrev'])
 
     return False
 
+def filerevisiondifferent(store, node, filedata):
+    """Determines whether file data is equivalent to a stored node."""
+
+    if filedata.startswith(b'\x01\n'):
+        revisiontext = b'\x01\n\x01\n' + filedata
+    else:
+        revisiontext = filedata
+
+    p1, p2 = store.parents(node)
+
+    computednode = hashrevisionsha1(revisiontext, p1, p2)
+
+    if computednode == node:
+        return False
+
+    # Censored files compare against the empty file.
+    if store.iscensored(store.rev(node)):
+        return filedata != b''
+
+    # Renaming a file produces a different hash, even if the data
+    # remains unchanged. Check if that's the case.
+    if store.renamed(node):
+        return store.read(node) != filedata
+
+    return True
+
 def iterrevs(storelen, start=0, stop=None):
     """Iterate over revision numbers in a store."""
     step = 1
 
     if stop is not None:
         if start > stop:
             step = -1
         stop += step
         if stop > storelen:
             stop = storelen
     else:
         stop = storelen
 
     return pycompat.xrange(start, stop, step)
 
 def fileidlookup(store, fileid, identifier):
     """Resolve the file node for a value.
 
     ``store`` is an object implementing the ``ifileindex`` interface.
 
     ``fileid`` can be:
 
     * A 20 byte binary node.
     * An integer revision number
     * A 40 byte hex node.
     * A bytes that can be parsed as an integer representing a revision number.
 
     ``identifier`` is used to populate ``error.LookupError`` with an identifier
     for the store.
 
     Raises ``error.LookupError`` on failure.
     """
     if isinstance(fileid, int):
         try:
             return store.node(fileid)
         except IndexError:
             raise error.LookupError(fileid, identifier, _('no match found'))
 
     if len(fileid) == 20:
         try:
             store.rev(fileid)
             return fileid
         except error.LookupError:
             pass
 
     if len(fileid) == 40:
         try:
             rawnode = bin(fileid)
             store.rev(rawnode)
             return rawnode
         except TypeError:
             pass
 
     try:
         rev = int(fileid)
 
         if b'%d' % rev != fileid:
             raise ValueError
 
         try:
             return store.node(rev)
         except (IndexError, TypeError):
             pass
     except (ValueError, OverflowError):
         pass
 
     raise error.LookupError(fileid, identifier, _('no match found'))
 
 def resolvestripinfo(minlinkrev, tiprev, headrevs, linkrevfn, parentrevsfn):
     """Resolve information needed to strip revisions.
 
     Finds the minimum revision number that must be stripped in order to
     strip ``minlinkrev``.
 
     Returns a 2-tuple of the minimum revision number to do that and a set
     of all revision numbers that have linkrevs that would be broken
     by that strip.
 
     ``tiprev`` is the current tip-most revision. It is ``len(store) - 1``.
     ``headrevs`` is an iterable of head revisions.
     ``linkrevfn`` is a callable that receives a revision and returns a linked
     revision.
     ``parentrevsfn`` is a callable that receives a revision number and returns
     an iterable of its parent revision numbers.
     """
     brokenrevs = set()
     strippoint = tiprev + 1
 
     heads = {}
     futurelargelinkrevs = set()
     for head in headrevs:
         headlinkrev = linkrevfn(head)
         heads[head] = headlinkrev
         if headlinkrev >= minlinkrev:
             futurelargelinkrevs.add(headlinkrev)
 
     # This algorithm involves walking down the rev graph, starting at the
     # heads. Since the revs are topologically sorted according to linkrev,
     # once all head linkrevs are below the minlink, we know there are
     # no more revs that could have a linkrev greater than minlink.
     # So we can stop walking.
     while futurelargelinkrevs:
         strippoint -= 1
         linkrev = heads.pop(strippoint)
 
         if linkrev < minlinkrev:
             brokenrevs.add(strippoint)
         else:
             futurelargelinkrevs.remove(linkrev)
 
         for p in parentrevsfn(strippoint):
             if p != nullrev:
                 plinkrev = linkrevfn(p)
                 heads[p] = plinkrev
                 if plinkrev >= minlinkrev:
                     futurelargelinkrevs.add(plinkrev)
 
     return strippoint, brokenrevs