comparison mercurial/wireprotov2server.py @ 40924:08cfa77d7288

wireprotov2: unify file revision collection and linknode derivation

The old mechanism for choosing which file revisions to send in the
haveparents=True case was buggy in multiple ways - the most severe
of which being that file revisions were excluded when they shouldn't
have been.

This commit unifies the logic for deriving the filenodes that will
be sent by the "filesdata" command. We now consistently read files
data from manifests. The "haveparents" argument now controls whether
we iterate ctx.files() or use the full manifest to derive relevant
files.

The logic here is still woefully lacking to fully support shallow
clones. It will require an API break to fully address. This commit
should at least make the server APIs emit proper data, which is
strictly better than before.

Differential Revision: https://phab.mercurial-scm.org/D5406

40923:3ed77780f4a6

    # is a race between a client making a push that obsoletes a changeset and
    # another client fetching files data for that changeset. If a client has a
    # changeset, it should probably be allowed to access files data for that
    # changeset.

    cl = repo.changelog
    clnode = cl.node
    outgoing = resolvenodes(repo, revisions)
    filematcher = makefilematcher(repo, pathfilter)

    # Figure out what needs to be emitted.
    changedpaths = set()
    # path -> {fnode: linknode}
    fnodes = collections.defaultdict(dict)

    for node in outgoing:
        ctx = repo[node]
        changedpaths.update(ctx.files())

    changedpaths = sorted(p for p in changedpaths if filematcher(p))

    # If ancestors are known, we send file revisions having a linkrev in the
    # outgoing set of changeset revisions.
    if haveparents:
        outgoingclrevs = set(cl.rev(n) for n in outgoing)

        for path in changedpaths:
            try:
                store = getfilestore(repo, proto, path)
            except FileAccessError as e:
                raise error.WireprotoCommandError(e.msg, e.args)

            for rev in store:
                linkrev = store.linkrev(rev)

                if linkrev in outgoingclrevs:
                    fnodes[path].setdefault(store.node(rev), clnode(linkrev))

    # If ancestors aren't known, we walk the manifests and send all
    # encountered file revisions.
    else:
        for node in outgoing:
            mctx = repo[node].manifestctx()

            for path, fnode in mctx.read().items():
                if filematcher(path):
                    fnodes[path].setdefault(fnode, node)

    yield {
        b'totalpaths': len(fnodes),
        b'totalitems': sum(len(v) for v in fnodes.values())
    }

40924:08cfa77d7288

    # is a race between a client making a push that obsoletes a changeset and
    # another client fetching files data for that changeset. If a client has a
    # changeset, it should probably be allowed to access files data for that
    # changeset.

    outgoing = resolvenodes(repo, revisions)
    filematcher = makefilematcher(repo, pathfilter)

    # path -> {fnode: linknode}
    fnodes = collections.defaultdict(dict)

    # We collect the set of relevant file revisions by iterating the changeset
    # revisions and either walking the set of files recorded in the changeset
    # or by walking the manifest at that revision. There is probably room for a
    # storage-level API to request this data, as it can be expensive to compute
    # and would benefit from caching or alternate storage from what revlogs
    # provide.
    for node in outgoing:
        ctx = repo[node]
        mctx = ctx.manifestctx()
        md = mctx.read()

        if haveparents:
            checkpaths = ctx.files()
        else:
            checkpaths = md.keys()

        for path in checkpaths:
            fnode = md[path]

            if path in fnodes and fnode in fnodes[path]:
                continue

            if not filematcher(path):
                continue

            fnodes[path].setdefault(fnode, node)

    yield {
        b'totalpaths': len(fnodes),
        b'totalitems': sum(len(v) for v in fnodes.values())
    }