D5405: wireprotov2: send linknodes to emitfilerevisions()

[indygreg (Gregory Szorc)]

indygreg created this revision.
Herald added a subscriber: mercurial-devel.
Herald added a reviewer: hg-reviewers.

REVISION SUMMARY
  Previously, linknodes were calculated within emitfilerevisions() by
  using filectx.introrev(), which would always use the linkrev/linknode
  as recorded by storage. This is wrong for cases where the receiver
  doesn't have the changeset the linknode refers to.
  
  This commit changes the logic for linknode emission so the mapping
  of filenode to linknode is computed by the caller and passed into
  emitfilerevisions().
  
  As part of the change, linknodes for "filesdata" in the
  haveparents=False case are now correct: the existing code performed a
  manifest walk and it was trivial to plug in the correct linknode.
  
  However, behavior for the haveparents=True case is still wrong
  because it relies on filtering linkrevs against the outgoing set in
  order to determine what to send. This will be fixed in a subsequent
  commit.
  
  The change test test-wireproto-exchangev2-shallow.t is a bit wonky.
  The test repo has 6 revisions. The changed test is performing a shallow
  clone with depth=1. So, only file data for revision 5 is present
  locally. So, the new behavior of associating the linknode with
  revision 5 for every file revision seems correct. Of course, when
  backfilling old revisions, we'll want to update the linknode. But
  this problem requires wire protocol support and we'll cross that
  bridge later.

REPOSITORY
  rHG Mercurial

REVISION DETAIL
  https://phab.mercurial-scm.org/D5405

AFFECTED FILES
  mercurial/wireprotov2server.py
  tests/test-wireproto-command-filesdata.t
  tests/test-wireproto-exchangev2-shallow.t

CHANGE DETAILS

diff --git a/tests/test-wireproto-exchangev2-shallow.t b/tests/test-wireproto-exchangev2-shallow.t
--- a/tests/test-wireproto-exchangev2-shallow.t
+++ b/tests/test-wireproto-exchangev2-shallow.t
@@ -196,34 +196,34 @@
      node = I\x1d\xa1\xbb\x89\xeax\xc0\xc0\xa2s[\x16\xce}\x93\x1d\xc8\xe2\r (esc)
     p1rev = -1
     p2rev = -1
-  linkrev = 4
+  linkrev = 5
     flags = 2
   
        id = 4
      path = dir0/d
    revnum = 0
      node = S\x82\x06\xdc\x97\x1eR\x15@\xd6\x84:\xbf\xe6\xd1`2\xf6\xd4& (esc)
     p1rev = -1
     p2rev = -1
-  linkrev = 1
+  linkrev = 5
     flags = 0
   
        id = 5
      path = dir1/e
    revnum = 0
      node = ]\xf3\xac\xd8\xd0\xc7\xfaP\x98\xd0'\x9a\x044\xc3\x02\x9e+x\xe1 (esc)
     p1rev = -1
     p2rev = -1
-  linkrev = 4
+  linkrev = 5
     flags = 2
   
        id = 6
      path = dir1/f
    revnum = 0
      node = (\xc7v\xae\x08\xd0\xd5^\xb4\x06H\xb4\x01\xb9\x0f\xf5DH4\x8e (esc)
     p1rev = -1
     p2rev = -1
-  linkrev = 4
+  linkrev = 5
     flags = 2
 
 Test a shallow clone with only some files
@@ -342,16 +342,16 @@
      node = I\x1d\xa1\xbb\x89\xeax\xc0\xc0\xa2s[\x16\xce}\x93\x1d\xc8\xe2\r (esc)
     p1rev = -1
     p2rev = -1
-  linkrev = 4
+  linkrev = 5
     flags = 2
   
        id = 2
      path = dir0/d
    revnum = 0
      node = S\x82\x06\xdc\x97\x1eR\x15@\xd6\x84:\xbf\xe6\xd1`2\xf6\xd4& (esc)
     p1rev = -1
     p2rev = -1
-  linkrev = 1
+  linkrev = 5
     flags = 0
 
 Cloning an old revision with depth=1 works
diff --git a/tests/test-wireproto-command-filesdata.t b/tests/test-wireproto-command-filesdata.t
--- a/tests/test-wireproto-command-filesdata.t
+++ b/tests/test-wireproto-command-filesdata.t
@@ -1239,7 +1239,6 @@
 
 Request for changeset where recorded linknode isn't in DAG ancestry will get
 rewritten accordingly
-TODO this is buggy
 
   $ sendhttpv2peer << EOF
   > command filesdata
@@ -1263,7 +1262,7 @@
       b'totalitems': 1
     },
     {
-      b'linknode': b'\xb1l\xce)g\xc1t\x9e\xf4\xf4\xe3\x08j\x80l\xfb\xad\x8a:\xf7',
+      b'linknode': b'G\xfc0X\t\x11#,\xb2dg[@(\x19\xde\xdd\xf6\xc6\xf0',
       b'node': b'.\xd2\xa3\x91*\x0b$P C\xea\xe8N\xe4\xb2y\xc1\x8b\x90\xdd'
     }
   ]
diff --git a/mercurial/wireprotov2server.py b/mercurial/wireprotov2server.py
--- a/mercurial/wireprotov2server.py
+++ b/mercurial/wireprotov2server.py
@@ -984,9 +984,7 @@
 
     return fl
 
-def emitfilerevisions(repo, path, revisions, fields):
-    clnode = repo.changelog.node
-
+def emitfilerevisions(repo, path, revisions, linknodes, fields):
     for revision in revisions:
         d = {
             b'node': revision.node,
@@ -996,13 +994,7 @@
             d[b'parents'] = [revision.p1node, revision.p2node]
 
         if b'linknode' in fields:
-            # TODO by creating the filectx against a specific file revision
-            # instead of changeset, linkrev() is always used. This is wrong for
-            # cases where linkrev() may refer to a hidden changeset. We need an
-            # API for performing linkrev adjustment that takes this into
-            # account.
-            fctx = repo.filectx(path, fileid=revision.node)
-            d[b'linknode'] = clnode(fctx.introrev())
+            d[b'linknode'] = linknodes[revision.node]
 
         followingmeta = []
         followingdata = []
@@ -1086,23 +1078,34 @@
     except FileAccessError as e:
         raise error.WireprotoCommandError(e.msg, e.args)
 
+    clnode = repo.changelog.node
+    linknodes = {}
+
     # Validate requested nodes.
     for node in nodes:
         try:
             store.rev(node)
         except error.LookupError:
             raise error.WireprotoCommandError('unknown file node: %s',
                                               (hex(node),))
 
+        # TODO by creating the filectx against a specific file revision
+        # instead of changeset, linkrev() is always used. This is wrong for
+        # cases where linkrev() may refer to a hidden changeset. But since this
+        # API doesn't know anything about changesets, we're not sure how to
+        # disambiguate the linknode. Perhaps we should delete this API?
+        fctx = repo.filectx(path, fileid=node)
+        linknodes[node] = clnode(fctx.introrev())
+
     revisions = store.emitrevisions(nodes,
                                     revisiondata=b'revision' in fields,
                                     assumehaveparentrevisions=haveparents)
 
     yield {
         b'totalitems': len(nodes),
     }
 
-    for o in emitfilerevisions(repo, path, revisions, fields):
+    for o in emitfilerevisions(repo, path, revisions, linknodes, fields):
         yield o
 
 def filesdatacapabilities(repo, proto):
@@ -1154,12 +1157,14 @@
     # changeset.
 
     cl = repo.changelog
+    clnode = cl.node
     outgoing = resolvenodes(repo, revisions)
     filematcher = makefilematcher(repo, pathfilter)
 
     # Figure out what needs to be emitted.
     changedpaths = set()
-    fnodes = collections.defaultdict(set)
+    # path -> {fnode: linknode}
+    fnodes = collections.defaultdict(dict)
 
     for node in outgoing:
         ctx = repo[node]
@@ -1182,7 +1187,7 @@
                 linkrev = store.linkrev(rev)
 
                 if linkrev in outgoingclrevs:
-                    fnodes[path].add(store.node(rev))
+                    fnodes[path].setdefault(store.node(rev), clnode(linkrev))
 
     # If ancestors aren't known, we walk the manifests and send all
     # encountered file revisions.
@@ -1192,7 +1197,7 @@
 
             for path, fnode in mctx.read().items():
                 if filematcher(path):
-                    fnodes[path].add(fnode)
+                    fnodes[path].setdefault(fnode, node)
 
     yield {
         b'totalpaths': len(fnodes),
@@ -1210,11 +1215,11 @@
             b'totalitems': len(filenodes),
         }
 
-        revisions = store.emitrevisions(filenodes,
+        revisions = store.emitrevisions(filenodes.keys(),
                                         revisiondata=b'revision' in fields,
                                         assumehaveparentrevisions=haveparents)
 
-        for o in emitfilerevisions(repo, path, revisions, fields):
+        for o in emitfilerevisions(repo, path, revisions, filenodes, fields):
             yield o
 
 @wireprotocommand(



To: indygreg, #hg-reviewers
Cc: mercurial-devel