Mercurial > public > mercurial-scm > hg-stable

diff mercurial/wireprotov2server.py @ 40942:08cfa77d7288

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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
author Gregory Szorc <gregory.szorc@gmail.com>
date Mon, 10 Dec 2018 18:55:08 +0000
parents 3ed77780f4a6
children 5cc5a5561c3f
line wrap: on
line diff
--- a/mercurial/wireprotov2server.py	Mon Dec 10 18:04:12 2018 +0000
+++ b/mercurial/wireprotov2server.py	Mon Dec 10 18:55:08 2018 +0000
@@ -1156,48 +1156,38 @@
     # 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)
 
+    # 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]
-        changedpaths.update(ctx.files())
-
-    changedpaths = sorted(p for p in changedpaths if filematcher(p))
+        mctx = ctx.manifestctx()
+        md = mctx.read()
 
-    # 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)
+        if haveparents:
+            checkpaths = ctx.files()
+        else:
+            checkpaths = md.keys()
 
-            for rev in store:
-                linkrev = store.linkrev(rev)
-
-                if linkrev in outgoingclrevs:
-                    fnodes[path].setdefault(store.node(rev), clnode(linkrev))
+        for path in checkpaths:
+            fnode = md[path]
 
-    # If ancestors aren't known, we walk the manifests and send all
-    # encountered file revisions.
-    else:
-        for node in outgoing:
-            mctx = repo[node].manifestctx()
+            if path in fnodes and fnode in fnodes[path]:
+                continue
 
-            for path, fnode in mctx.read().items():
-                if filematcher(path):
-                    fnodes[path].setdefault(fnode, node)
+            if not filematcher(path):
+                continue
+
+            fnodes[path].setdefault(fnode, node)
 
     yield {
         b'totalpaths': len(fnodes),