row like group values to avoid rowconverter

Signed-off-by: jayzhan211 <[email protected]>

Author: jayzhan211

benchmarks/queries/clickbench/queries.sql

@@ -35,9 +35,4 @@ SELECT "URL", COUNT(*) AS c FROM hits GROUP BY "URL" ORDER BY c DESC LIMIT 10;
 SELECT 1, "URL", COUNT(*) AS c FROM hits GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
 SELECT "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3, COUNT(*) AS c FROM hits GROUP BY "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3 ORDER BY c DESC LIMIT 10;
 SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "URL" <> '' GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10;
-SELECT "Title", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "Title" <> '' GROUP BY "Title" ORDER BY PageViews DESC LIMIT 10;
-SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "IsLink" <> 0 AND "IsDownload" = 0 GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
-SELECT "TraficSourceID", "SearchEngineID", "AdvEngineID", CASE WHEN ("SearchEngineID" = 0 AND "AdvEngineID" = 0) THEN "Referer" ELSE '' END AS Src, "URL" AS Dst, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 GROUP BY "TraficSourceID", "SearchEngineID", "AdvEngineID", Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
-SELECT "URLHash", "EventDate"::INT::DATE, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "TraficSourceID" IN (-1, 6) AND "RefererHash" = 3594120000172545465 GROUP BY "URLHash", "EventDate"::INT::DATE ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
-SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "DontCountHits" = 0 AND "URLHash" = 2868770270353813622 GROUP BY "WindowClientWidth", "WindowClientHeight" ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
-SELECT DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) AS M, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-14' AND "EventDate"::INT::DATE <= '2013-07-15' AND "IsRefresh" = 0 AND "DontCountHits" = 0 GROUP BY DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) ORDER BY DATE_TRUNC('minute', M) LIMIT 10 OFFSET 1000;
+SELECT "Title", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "Title" <> '' GROUP BY "Title" ORDER BY PageViews DESC LIMIT 10;

datafusion/physical-expr-common/src/binary_map.rs

@@ -235,9 +235,9 @@ where
 }
 
 /// The size, in number of entries, of the initial hash table
-const INITIAL_MAP_CAPACITY: usize = 128;
+pub(crate) const INITIAL_MAP_CAPACITY: usize = 128;
 /// The initial size, in bytes, of the string data
-const INITIAL_BUFFER_CAPACITY: usize = 8 * 1024;
+pub(crate) const INITIAL_BUFFER_CAPACITY: usize = 8 * 1024;
 impl<O: OffsetSizeTrait, V> ArrowBytesMap<O, V>
 where
     V: Debug + PartialEq + Eq + Clone + Copy + Default,
@@ -574,7 +574,7 @@ where
 }
 
 /// Maximum size of a value that can be inlined in the hash table
-const SHORT_VALUE_LEN: usize = mem::size_of::<usize>();
+pub(crate) const SHORT_VALUE_LEN: usize = mem::size_of::<usize>();
 
 /// Entry in the hash table -- see [`ArrowBytesMap`] for more details
 #[derive(Debug, PartialEq, Eq, Hash, Clone, Copy)]