Ensure deterministic revisions for attachments

This re-fixes a corner case when recreating a document with an
attachment in a single multipart request. Since we don't detect that we
need a new revision until after the document has been serialized we need
to be able to deserialize the body so that we can generate the same
revisions regardless of the contents of the database. If we don't do
this then we end up including information from the position of the
attachment on disk in the revision calculation which can introduce
branches in the revision tree.

I've left this as a separate commit from the pluggable storage engine
work so that its called out clearly for us to revisit.

COUCHDB-3255

3 files changed, 21 insertions, 13 deletions

diff --git a/src/couch/src/couch_bt_engine.erl b/src/couch/src/couch_bt_engine.erl
index e7178d1ad..0680ffd5a 100644
--- a/src/couch/src/couch_bt_engine.erl
+++ b/src/couch/src/couch_bt_engine.erl
@@ -325,7 +325,15 @@ serialize_doc(#st{} = St, #doc{} = Doc) ->
     SummaryBin = ?term_to_bin({Body, Atts}),
     Md5 = couch_crypto:hash(md5, SummaryBin),
     Data = couch_file:assemble_file_chunk(SummaryBin, Md5),
-    Doc#doc{body = Data}.
+    % TODO: This is a terrible hack to get around the issues
+    %       in COUCHDB-3255. We'll need to come back and figure
+    %       out a better approach to handling the case when we
+    %       need to generate a new revision id after the doc
+    %       has been serialized.
+    Doc#doc{
+        body = Data,
+        meta = [{comp_body, Body} | Doc#doc.meta]
+    }.
 
 
 write_doc_body(St, #doc{} = Doc) ->
diff --git a/src/couch/src/couch_db.erl b/src/couch/src/couch_db.erl
index 95a14a115..5018d253b 100644
--- a/src/couch/src/couch_db.erl
+++ b/src/couch/src/couch_db.erl
@@ -942,7 +942,7 @@ prep_and_validate_replicated_updates(Db, [Bucket|RestBuckets], [OldInfo|RestOldI
 
 
 
-new_revid(#doc{body=Body0, revs={OldStart,OldRevs}, atts=Atts, deleted=Deleted}) ->
+new_revid(#doc{body=Body, revs={OldStart,OldRevs}, atts=Atts, deleted=Deleted}) ->
     DigestedAtts = lists:foldl(fun(Att, Acc) ->
         [N, T, M] = couch_att:fetch([name, type, md5], Att),
         case M == <<>> of
@@ -950,16 +950,6 @@ new_revid(#doc{body=Body0, revs={OldStart,OldRevs}, atts=Atts, deleted=Deleted})
             false -> [{N, T, M} | Acc]
         end
     end, [], Atts),
-    Body = case Body0 of
-        {summary, [_Len, _Md5, BodyAtts], _SizeInfo, _AttsFd} ->
-            {CompBody, _CompAtts} = binary_to_term(BodyAtts),
-            couch_compress:decompress(CompBody);
-        {summary, [_Len, BodyAtts], _SizeInfo, _AttsFd} ->
-            {CompBody, _CompAtts} = binary_to_term(BodyAtts),
-            couch_compress:decompress(CompBody);
-        Else ->
-            Else
-    end,
     case DigestedAtts of
         Atts2 when length(Atts) =/= length(Atts2) ->
             % We must have old style non-md5 attachments
diff --git a/src/couch/src/couch_db_updater.erl b/src/couch/src/couch_db_updater.erl
index dbf3a6e28..dd5b4e739 100644
--- a/src/couch/src/couch_db_updater.erl
+++ b/src/couch/src/couch_db_updater.erl
@@ -525,7 +525,17 @@ merge_rev_tree(OldInfo, NewDoc, Client, Limit, false)
             % Update the new doc based on revisions in OldInfo
             #doc_info{revs=[WinningRev | _]} = couch_doc:to_doc_info(OldInfo),
             #rev_info{rev={OldPos, OldRev}} = WinningRev,
-            NewRevId = couch_db:new_revid(NewDoc#doc{revs={OldPos, [OldRev]}}),
+            Body = case couch_util:get_value(comp_body, NewDoc#doc.meta) of
+                CompBody when is_binary(CompBody) ->
+                    couch_compress:decompress(CompBody);
+                _ ->
+                    NewDoc#doc.body
+            end,
+            RevIdDoc = NewDoc#doc{
+                revs = {OldPos, [OldRev]},
+                body = Body
+            },
+            NewRevId = couch_db:new_revid(RevIdDoc),
             NewDoc2 = NewDoc#doc{revs={OldPos + 1, [NewRevId, OldRev]}},
 
             % Merge our modified new doc into the tree