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/agg3.sql | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sql/hive/src/test/resources/sqlgen/agg3.sql') diff --git a/sql/hive/src/test/resources/sqlgen/agg3.sql b/sql/hive/src/test/resources/sqlgen/agg3.sql index 437afa7790..14b19392cd 100644 --- a/sql/hive/src/test/resources/sqlgen/agg3.sql +++ b/sql/hive/src/test/resources/sqlgen/agg3.sql @@ -1,4 +1,4 @@ -- This file is automatically generated by LogicalPlanToSQLSuite. SELECT COUNT(value) FROM parquet_t1 GROUP BY key ORDER BY key, MAX(key) -------------------------------------------------------------------------------- -SELECT `gen_attr` AS `count(value)` FROM (SELECT `gen_attr` FROM (SELECT count(`gen_attr`) AS `gen_attr`, `gen_attr` AS `gen_attr`, max(`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` ORDER BY `gen_attr` ASC, `gen_attr` ASC) AS gen_subquery_1) AS gen_subquery_2 +SELECT `gen_attr_0` AS `count(value)` FROM (SELECT `gen_attr_0` FROM (SELECT count(`gen_attr_4`) AS `gen_attr_0`, `gen_attr_3` AS `gen_attr_1`, max(`gen_attr_3`) AS `gen_attr_2` FROM (SELECT `key` AS `gen_attr_3`, `value` AS `gen_attr_4` FROM `default`.`parquet_t1`) AS gen_subquery_0 GROUP BY `gen_attr_3` ORDER BY `gen_attr_1` ASC, `gen_attr_2` ASC) AS gen_subquery_1) AS gen_subquery_2 -- cgit v1.2.3