Use efficient set storage for field names3358-use-efficient-set

When indexing a set of fields for text search, we also create a special
field called $fieldnames. It contains values for all the fields that
need to be indexed. In order to do that, we need a unique list of the
form [[<<"$fieldnames">>, Name, [] | Rest]. The old code would add an
element to the list, and then check for membership via lists:member/2.
This is inefficient. Some documents can contain a large number of
fields, so we will use gb_sets to create a unique set of fields, and
then extract out the field names.

COUCHDB-3358

1 files changed, 6 insertions, 10 deletions

diff --git a/src/mango/src/mango_native_proc.erl b/src/mango/src/mango_native_proc.erl
index 6d0fb2400..ba17c4867 100644
--- a/src/mango/src/mango_native_proc.erl
+++ b/src/mango/src/mango_native_proc.erl
@@ -175,7 +175,7 @@ get_text_entries0(IdxProps, Doc) ->
     Fields = if not DefaultEnabled -> Fields0; true ->
         add_default_text_field(Fields0)
     end,
-    FieldNames = get_field_names(Fields, []),
+    FieldNames = get_field_names(Fields),
     Converted = convert_text_fields(Fields),
     FieldNames ++ Converted.
 
@@ -257,15 +257,11 @@ add_default_text_field([_ | Rest], Acc) ->
 
 
 %% index of all field names
-get_field_names([], FAcc) ->
-    FAcc;
-get_field_names([{Name, _Type, _Value} | Rest], FAcc) ->
-    case lists:member([<<"$fieldnames">>, Name, []], FAcc) of
-        true ->
-            get_field_names(Rest, FAcc);
-        false ->
-            get_field_names(Rest, [[<<"$fieldnames">>, Name, []] | FAcc])
-    end.
+get_field_names(Fields) ->
+    FieldNameSet = lists:foldl(fun({Name, _, _}, Set) ->
+        gb_sets:add([<<"$fieldnames">>, Name, []], Set)
+    end, gb_sets:new(), Fields),
+    gb_sets:to_list(FieldNameSet).
 
 
 convert_text_fields([]) ->