fix case_clause when HitId and DocId do not match when include_docs=true
Sometimes, a clouseau index may become out of sync with the db or
become corrupt under certain conditions (heap exhaustion, garbage collection).
This leads to certain HitIds that get returned which may not exist
in the current db. Before this fix, we assume the Hit's Id will
automatically match an Id return from:
fabric:all_docs(DbName, fun callback/2, [], [{keys, DocIds}, {include_docs, true}]).
When the document does not exist, {error, false} is returned for the row.
This fix accounts for this scenario and possible other scenarios
by returning an error to the user and also logging the error when the
Hit Id does not match what is returned from the _all_docs call.
diff --git a/src/dreyfus/src/dreyfus_httpd.erl b/src/dreyfus/src/dreyfus_httpd.erl
index 007dace..a925966 100644
--- a/src/dreyfus/src/dreyfus_httpd.erl
+++ b/src/dreyfus/src/dreyfus_httpd.erl
@@ -532,16 +532,18 @@
if IncludeDocs ->
chttpd_stats:incr_reads(length(Hits)),
{ok, JsonDocs} = dreyfus_fabric:get_json_docs(DbName, Ids),
- lists:zipwith(fun(Hit, {Id, Doc}) ->
+ lists:zipwith(fun
+ (Hit, {Id, Doc}) ->
case Hit of
- {Id, Order, Fields} ->
- {[{id, Id}, {order, Order}, {fields, {Fields}}, Doc]};
- {Id, Order, Fields, Highlights} ->
+ {HitId, Order, Fields} ->
+ Doc1 = hits_id_validator(HitId, {Id, Doc}),
+ {[{id, Id}, {order, Order}, {fields, {Fields}}, Doc1]};
+ {HitId, Order, Fields, Highlights} ->
+ Doc1 = hits_id_validator(HitId, {Id, Doc}),
{[{id, Id}, {order, Order}, {fields, {Fields}},
- {highlights, {Highlights}}, Doc]}
+ {highlights, {Highlights}}, Doc1]}
end
- end, HitData, JsonDocs);
-
+ end, HitData, JsonDocs);
true ->
lists:map(fun(Hit) ->
case Hit of
@@ -553,6 +555,21 @@
end, HitData)
end.
+
+% _all_docs returned {error, false} meaning document doesn't exist
+hits_id_validator(HitId, {error, false}) ->
+ couch_log:error("HitId: ~p does not exist in db. Index may be out of sync or corrupt", [HitId]),
+ {error, <<"not_found">>};
+hits_id_validator(HitId, {error, Reason}) ->
+ couch_log:error("HitId: ~p does not exist in db. Reason: ~p", [HitId, Reason]),
+ {error, Reason};
+hits_id_validator(HitId, {DocId, Doc}) when DocId =:= HitId ->
+ Doc;
+hits_id_validator(HitId, {DocId, _}) ->
+ couch_log:error("HitId: ~p DocId: ~p mismatch. Index maybe out of sync or corrupt.", [HitId, DocId]),
+ {error, <<"docid mismatch">>}.
+
+
get_hit_data(Hit) ->
Id = couch_util:get_value(<<"_id">>, Hit#hit.fields),
Fields = lists:keydelete(<<"_id">>, 1, Hit#hit.fields),
@@ -612,3 +629,20 @@
timer:sleep(RetryPause),
handle_search_req(Req, Db, DDoc, RetryCount + 1, RetryPause * 2)
end.
+
+
+-ifdef(TEST).
+-include_lib("eunit/include/eunit.hrl").
+
+hits_id_validator_test() ->
+ Doc = {doc, {[
+ {<<"_id">>, <<"foo">>},
+ {<<"_rev">>, <<"1-4c6114c65e295552ab1019e2b046b10e">>},
+ {<<"foo">>, <<"bar">>}
+ ]}},
+ ?assertEqual(Doc, hits_id_validator(<<"foo">>, {<<"foo">>, Doc})),
+ ?assertEqual({error, <<"not_found">>}, hits_id_validator(<<"foo>">>, {error, false})),
+ ?assertEqual({error, some_reason}, hits_id_validator(<<"foo>">>, {error, some_reason})),
+ ?assertEqual({error, <<"docid mismatch">>}, hits_id_validator(<<"bar">>, {<<"foo">>, Doc})).
+
+-endif.
