comparison mercurial/changegroup.py @ 23381:cc0ff93d0c0c stable

changegroup: fix file linkrevs during reorders (issue4462)

Previously, if reorder was true during the creation of a changegroup bundle,
it was possible that the manifest and filelogs would be reordered such that the
resulting bundle filelog had a linkrev that pointed to a commit that was not
the earliest instance of the filelog revision. For example:

With commits:

0<-1<---3<-4
  \       /
   --2<---

if 2 and 3 added the same version of a file, if the manifests of 2 and 3 have
their order reversed, but the changelog did not, it could produce a filelog with
linkrevs 0<-3 instead of 0<-2, which meant if commit 3 was stripped, it would
delete that file data from the repository and commit 2 would be corrupt (as
would any future pulls that tried to build upon that version of the file).

The fix is to make the linkrev fixup smarter. Previously it considered the first
manifest that added a file to be the first commit that added that file, which is
not true. Now, for every file revision we add to the bundle we make sure we
attach it to the earliest applicable linkrev.

23377:c00b156d6e76

        progress = self._progress

        # for progress output
        msgbundling = _('bundling')

        mfs = {} # needed manifests
        fnodes = {} # needed file nodes
        changedfiles = set()

        # Callback for the changelog, used to collect changed files and manifest
        # nodes.
        # Returns the linkrev node (identity in the changelog case).
        def lookupcl(x):
            c = cl.read(x)
            changedfiles.update(c[3])
            # record the first changeset introducing this manifest version
            mfs.setdefault(c[0], x)
            return x

        # Callback for the manifest, used to collect linkrevs for filelog
        # revisions.
        # Returns the linkrev node (collected in lookupcl).
        def lookupmf(x):
            clnode = mfs[x]
            if not fastpathlinkrev:
                mdata = mf.readfast(x)
                for f, n in mdata.iteritems():
                    if f in changedfiles:
                        # record the first changeset introducing this filelog
                        # version
                        fnodes.setdefault(f, {}).setdefault(n, clnode)
            return clnode

        mfnodes = self.prune(mf, mfs, commonrevs, source)
        for chunk in self.group(mfnodes, mf, lookupmf, units=_('manifests'),
                                reorder=reorder):

        mfs.clear()
        needed = set(cl.rev(x) for x in clnodes)

        def linknodes(filerevlog, fname):
            if fastpathlinkrev:
                llr = filerevlog.linkrev
                def genfilenodes():
                    for r in filerevlog:
                        linkrev = llr(r)
                        if linkrev in needed:

23381:cc0ff93d0c0c

        progress = self._progress

        # for progress output
        msgbundling = _('bundling')

        clrevorder = {}
        mfs = {} # needed manifests
        fnodes = {} # needed file nodes
        changedfiles = set()

        # Callback for the changelog, used to collect changed files and manifest
        # nodes.
        # Returns the linkrev node (identity in the changelog case).
        def lookupcl(x):
            c = cl.read(x)
            clrevorder[x] = len(clrevorder)
            changedfiles.update(c[3])
            # record the first changeset introducing this manifest version
            mfs.setdefault(c[0], x)
            return x

        # Callback for the manifest, used to collect linkrevs for filelog
        # revisions.
        # Returns the linkrev node (collected in lookupcl).
        def lookupmf(x):
            clnode = mfs[x]
            if not fastpathlinkrev or reorder:
                mdata = mf.readfast(x)
                for f, n in mdata.iteritems():
                    if f in changedfiles:
                        # record the first changeset introducing this filelog
                        # version
                        fclnodes = fnodes.setdefault(f, {})
                        fclnode = fclnodes.setdefault(n, clnode)
                        if clrevorder[clnode] < clrevorder[fclnode]:
                            fclnodes[n] = clnode
            return clnode

        mfnodes = self.prune(mf, mfs, commonrevs, source)
        for chunk in self.group(mfnodes, mf, lookupmf, units=_('manifests'),
                                reorder=reorder):

        mfs.clear()
        needed = set(cl.rev(x) for x in clnodes)

        def linknodes(filerevlog, fname):
            if fastpathlinkrev and not reorder:
                llr = filerevlog.linkrev
                def genfilenodes():
                    for r in filerevlog:
                        linkrev = llr(r)
                        if linkrev in needed: