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. --- .../src/test/resources/sqlgen/window_with_the_same_window_with_agg.sql | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sql/hive/src/test/resources/sqlgen/window_with_the_same_window_with_agg.sql') diff --git a/sql/hive/src/test/resources/sqlgen/window_with_the_same_window_with_agg.sql b/sql/hive/src/test/resources/sqlgen/window_with_the_same_window_with_agg.sql index 65d3d3aeb6..7b99539a05 100644 --- a/sql/hive/src/test/resources/sqlgen/window_with_the_same_window_with_agg.sql +++ b/sql/hive/src/test/resources/sqlgen/window_with_the_same_window_with_agg.sql @@ -4,4 +4,4 @@ DENSE_RANK() OVER (DISTRIBUTE BY key SORT BY key, value) AS dr, COUNT(key) FROM parquet_t1 GROUP BY key, value -------------------------------------------------------------------------------- -SELECT `gen_attr` AS `key`, `gen_attr` AS `value`, `gen_attr` AS `dr`, `gen_attr` AS `count(key)` FROM (SELECT `gen_attr`, `gen_attr`, `gen_attr`, `gen_attr` FROM (SELECT gen_subquery_1.`gen_attr`, gen_subquery_1.`gen_attr`, gen_subquery_1.`gen_attr`, DENSE_RANK() OVER (PARTITION BY `gen_attr` ORDER BY `gen_attr` ASC, `gen_attr` ASC ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS `gen_attr` FROM (SELECT `gen_attr`, `gen_attr`, count(`gen_attr`) 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`, `gen_attr`) AS gen_subquery_1) AS gen_subquery_2) AS parquet_t1 +SELECT `gen_attr_0` AS `key`, `gen_attr_1` AS `value`, `gen_attr_2` AS `dr`, `gen_attr_3` AS `count(key)` FROM (SELECT `gen_attr_0`, `gen_attr_1`, `gen_attr_2`, `gen_attr_3` FROM (SELECT gen_subquery_1.`gen_attr_0`, gen_subquery_1.`gen_attr_1`, gen_subquery_1.`gen_attr_3`, DENSE_RANK() OVER (PARTITION BY `gen_attr_0` ORDER BY `gen_attr_0` ASC, `gen_attr_1` ASC ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS `gen_attr_2` FROM (SELECT `gen_attr_0`, `gen_attr_1`, count(`gen_attr_0`) AS `gen_attr_3` FROM (SELECT `key` AS `gen_attr_0`, `value` AS `gen_attr_1` FROM `default`.`parquet_t1`) AS gen_subquery_0 GROUP BY `gen_attr_0`, `gen_attr_1`) AS gen_subquery_1) AS gen_subquery_2) AS parquet_t1 -- cgit v1.2.3