From 5b8e848bbfbc0c99a5faf758e40b188b0bbebb7b Mon Sep 17 00:00:00 2001 From: Dongjoon Hyun Date: Wed, 27 Jul 2016 13:23:59 +0800 Subject: [SPARK-16621][SQL] Generate stable SQLs in SQLBuilder ## What changes were proposed in this pull request? Currently, the generated SQLs have not-stable IDs for generated attributes. The stable generated SQL will give more benefit for understanding or testing the queries. This PR provides stable SQL generation by the followings. - Provide unique ids for generated subqueries, `gen_subquery_xxx`. - Provide unique and stable ids for generated attributes, `gen_attr_xxx`. **Before** ```scala scala> new org.apache.spark.sql.catalyst.SQLBuilder(sql("select 1")).toSQL res0: String = SELECT `gen_attr_0` AS `1` FROM (SELECT 1 AS `gen_attr_0`) AS gen_subquery_0 scala> new org.apache.spark.sql.catalyst.SQLBuilder(sql("select 1")).toSQL res1: String = SELECT `gen_attr_4` AS `1` FROM (SELECT 1 AS `gen_attr_4`) AS gen_subquery_0 ``` **After** ```scala scala> new org.apache.spark.sql.catalyst.SQLBuilder(sql("select 1")).toSQL res1: String = SELECT `gen_attr_0` AS `1` FROM (SELECT 1 AS `gen_attr_0`) AS gen_subquery_0 scala> new org.apache.spark.sql.catalyst.SQLBuilder(sql("select 1")).toSQL res2: String = SELECT `gen_attr_0` AS `1` FROM (SELECT 1 AS `gen_attr_0`) AS gen_subquery_0 ``` ## How was this patch tested? Pass the existing Jenkins tests. Author: Dongjoon Hyun Closes #14257 from dongjoon-hyun/SPARK-16621. --- sql/hive/src/test/resources/sqlgen/rollup_cube_4_1.sql | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sql/hive/src/test/resources/sqlgen/rollup_cube_4_1.sql') diff --git a/sql/hive/src/test/resources/sqlgen/rollup_cube_4_1.sql b/sql/hive/src/test/resources/sqlgen/rollup_cube_4_1.sql index be4908ea16..619a554875 100644 --- a/sql/hive/src/test/resources/sqlgen/rollup_cube_4_1.sql +++ b/sql/hive/src/test/resources/sqlgen/rollup_cube_4_1.sql @@ -2,4 +2,4 @@ SELECT count(*) as cnt, key % 5 as k1, key - 5 as k2, grouping_id() FROM parquet_t1 GROUP BY key % 5, key - 5 WITH ROLLUP -------------------------------------------------------------------------------- -SELECT `gen_attr` AS `cnt`, `gen_attr` AS `k1`, `gen_attr` AS `k2`, `gen_attr` AS `grouping_id()` FROM (SELECT count(1) AS `gen_attr`, (`gen_attr` % CAST(5 AS BIGINT)) AS `gen_attr`, (`gen_attr` - CAST(5 AS BIGINT)) AS `gen_attr`, grouping_id() AS `gen_attr` FROM (SELECT `key` AS `gen_attr`, `value` AS `gen_attr` FROM `default`.`parquet_t1`) AS gen_subquery_0 GROUP BY (`gen_attr` % CAST(5 AS BIGINT)), (`gen_attr` - CAST(5 AS BIGINT)) GROUPING SETS(((`gen_attr` % CAST(5 AS BIGINT)), (`gen_attr` - CAST(5 AS BIGINT))), ((`gen_attr` % CAST(5 AS BIGINT))), ())) AS gen_subquery_1 +SELECT `gen_attr_3` AS `cnt`, `gen_attr_4` AS `k1`, `gen_attr_5` AS `k2`, `gen_attr_6` AS `grouping_id()` FROM (SELECT count(1) AS `gen_attr_3`, (`gen_attr_7` % CAST(5 AS BIGINT)) AS `gen_attr_4`, (`gen_attr_7` - CAST(5 AS BIGINT)) AS `gen_attr_5`, grouping_id() AS `gen_attr_6` FROM (SELECT `key` AS `gen_attr_7`, `value` AS `gen_attr_8` FROM `default`.`parquet_t1`) AS gen_subquery_0 GROUP BY (`gen_attr_7` % CAST(5 AS BIGINT)), (`gen_attr_7` - CAST(5 AS BIGINT)) GROUPING SETS(((`gen_attr_7` % CAST(5 AS BIGINT)), (`gen_attr_7` - CAST(5 AS BIGINT))), ((`gen_attr_7` % CAST(5 AS BIGINT))), ())) AS gen_subquery_1 -- cgit v1.2.3