[SPARK-21366][SQL][TEST] Add sql test for window functions

jiangxb1987 · cloud-fan · commit 399aa016e8f4 · 2017-07-11T21:53:10.000+08:00
## What changes were proposed in this pull request? Add sql test for window functions, also remove uncecessary test cases in `WindowQuerySuite`. ## How was this patch tested? Added `window.sql` and the corresponding output file. Author: Xingbo Jiang <xingbo.jiang@databricks.com> Closes #18591 from jiangxb1987/window. (cherry picked from commit 66d2168) Signed-off-by: Wenchen Fan <wenchen@databricks.com>
diff --git a/sql/core/src/test/resources/sql-tests/inputs/window.sql b/sql/core/src/test/resources/sql-tests/inputs/window.sql
@@ -0,0 +1,69 @@
+-- Test data.
+CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
+(null, "a"), (1, "a"), (1, "a"), (2, "a"), (1, "b"), (2, "b"), (3, "b"), (null, null), (3, null)
+AS testData(val, cate);
+
+-- RowsBetween
+SELECT val, cate, count(val) OVER(PARTITION BY cate ORDER BY val ROWS CURRENT ROW) FROM testData
+ORDER BY cate, val;
+SELECT val, cate, sum(val) OVER(PARTITION BY cate ORDER BY val
+ROWS BETWEEN UNBOUNDED PRECEDING AND 1 FOLLOWING) FROM testData ORDER BY cate, val;
+
+-- RangeBetween
+SELECT val, cate, count(val) OVER(PARTITION BY cate ORDER BY val RANGE 1 PRECEDING) FROM testData
+ORDER BY cate, val;
+SELECT val, cate, sum(val) OVER(PARTITION BY cate ORDER BY val
+RANGE BETWEEN CURRENT ROW AND 1 FOLLOWING) FROM testData ORDER BY cate, val;
+
+-- RangeBetween with reverse OrderBy
+SELECT val, cate, sum(val) OVER(PARTITION BY cate ORDER BY val DESC
+RANGE BETWEEN CURRENT ROW AND 1 FOLLOWING) FROM testData ORDER BY cate, val;
+
+-- Window functions
+SELECT val, cate,
+max(val) OVER w AS max,
+min(val) OVER w AS min,
+min(val) OVER w AS min,
+count(val) OVER w AS count,
+sum(val) OVER w AS sum,
+avg(val) OVER w AS avg,
+stddev(val) OVER w AS stddev,
+first_value(val) OVER w AS first_value,
+first_value(val, true) OVER w AS first_value_ignore_null,
+first_value(val, false) OVER w AS first_value_contain_null,
+last_value(val) OVER w AS last_value,
+last_value(val, true) OVER w AS last_value_ignore_null,
+last_value(val, false) OVER w AS last_value_contain_null,
+rank() OVER w AS rank,
+dense_rank() OVER w AS dense_rank,
+cume_dist() OVER w AS cume_dist,
+percent_rank() OVER w AS percent_rank,
+ntile(2) OVER w AS ntile,
+row_number() OVER w AS row_number,
+var_pop(val) OVER w AS var_pop,
+var_samp(val) OVER w AS var_samp,
+approx_count_distinct(val) OVER w AS approx_count_distinct
+FROM testData
+WINDOW w AS (PARTITION BY cate ORDER BY val)
+ORDER BY cate, val;
+
+-- Null inputs
+SELECT val, cate, avg(null) OVER(PARTITION BY cate ORDER BY val) FROM testData ORDER BY cate, val;
+
+-- OrderBy not specified
+SELECT val, cate, row_number() OVER(PARTITION BY cate) FROM testData ORDER BY cate, val;
+
+-- Over clause is empty
+SELECT val, cate, sum(val) OVER(), avg(val) OVER() FROM testData ORDER BY cate, val;
+
+-- first_value()/last_value() over ()
+SELECT val, cate,
+first_value(false) OVER w AS first_value,
+first_value(true, true) OVER w AS first_value_ignore_null,
+first_value(false, false) OVER w AS first_value_contain_null,
+last_value(false) OVER w AS last_value,
+last_value(true, true) OVER w AS last_value_ignore_null,
+last_value(false, false) OVER w AS last_value_contain_null
+FROM testData
+WINDOW w AS ()
+ORDER BY cate, val;
diff --git a/sql/core/src/test/resources/sql-tests/results/window.sql.out b/sql/core/src/test/resources/sql-tests/results/window.sql.out
@@ -0,0 +1,204 @@
+-- Automatically generated by SQLQueryTestSuite
+-- Number of queries: 11
+
+
+-- !query 0
+CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
+(null, "a"), (1, "a"), (1, "a"), (2, "a"), (1, "b"), (2, "b"), (3, "b"), (null, null), (3, null)
+AS testData(val, cate)
+-- !query 0 schema
+struct<>
+-- !query 0 output
+
+
+
+-- !query 1
+SELECT val, cate, count(val) OVER(PARTITION BY cate ORDER BY val ROWS CURRENT ROW) FROM testData
+ORDER BY cate, val
+-- !query 1 schema
+struct<val:int,cate:string,count(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST ROWS BETWEEN CURRENT ROW AND CURRENT ROW):bigint>
+-- !query 1 output
+NULL	NULL	0
+3	NULL	1
+NULL	a	0
+1	a	1
+1	a	1
+2	a	1
+1	b	1
+2	b	1
+3	b	1
+
+
+-- !query 2
+SELECT val, cate, sum(val) OVER(PARTITION BY cate ORDER BY val
+ROWS BETWEEN UNBOUNDED PRECEDING AND 1 FOLLOWING) FROM testData ORDER BY cate, val
+-- !query 2 schema
+struct<val:int,cate:string,sum(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST ROWS BETWEEN UNBOUNDED PRECEDING AND 1 FOLLOWING):bigint>
+-- !query 2 output
+NULL	NULL	3
+3	NULL	3
+NULL	a	1
+1	a	2
+1	a	4
+2	a	4
+1	b	3
+2	b	6
+3	b	6
+
+
+-- !query 3
+SELECT val, cate, count(val) OVER(PARTITION BY cate ORDER BY val RANGE 1 PRECEDING) FROM testData
+ORDER BY cate, val
+-- !query 3 schema
+struct<val:int,cate:string,count(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN 1 PRECEDING AND CURRENT ROW):bigint>
+-- !query 3 output
+NULL	NULL	0
+3	NULL	1
+NULL	a	0
+1	a	2
+1	a	2
+2	a	3
+1	b	1
+2	b	2
+3	b	2
+
+
+-- !query 4
+SELECT val, cate, sum(val) OVER(PARTITION BY cate ORDER BY val
+RANGE BETWEEN CURRENT ROW AND 1 FOLLOWING) FROM testData ORDER BY cate, val
+-- !query 4 schema
+struct<val:int,cate:string,sum(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN CURRENT ROW AND 1 FOLLOWING):bigint>
+-- !query 4 output
+NULL	NULL	NULL
+3	NULL	3
+NULL	a	NULL
+1	a	4
+1	a	4
+2	a	2
+1	b	3
+2	b	5
+3	b	3
+
+
+-- !query 5
+SELECT val, cate, sum(val) OVER(PARTITION BY cate ORDER BY val DESC
+RANGE BETWEEN CURRENT ROW AND 1 FOLLOWING) FROM testData ORDER BY cate, val
+-- !query 5 schema
+struct<val:int,cate:string,sum(val) OVER (PARTITION BY cate ORDER BY val DESC NULLS LAST RANGE BETWEEN CURRENT ROW AND 1 FOLLOWING):bigint>
+-- !query 5 output
+NULL	NULL	NULL
+3	NULL	3
+NULL	a	NULL
+1	a	2
+1	a	2
+2	a	4
+1	b	1
+2	b	3
+3	b	5
+
+
+-- !query 6
+SELECT val, cate,
+max(val) OVER w AS max,
+min(val) OVER w AS min,
+min(val) OVER w AS min,
+count(val) OVER w AS count,
+sum(val) OVER w AS sum,
+avg(val) OVER w AS avg,
+stddev(val) OVER w AS stddev,
+first_value(val) OVER w AS first_value,
+first_value(val, true) OVER w AS first_value_ignore_null,
+first_value(val, false) OVER w AS first_value_contain_null,
+last_value(val) OVER w AS last_value,
+last_value(val, true) OVER w AS last_value_ignore_null,
+last_value(val, false) OVER w AS last_value_contain_null,
+rank() OVER w AS rank,
+dense_rank() OVER w AS dense_rank,
+cume_dist() OVER w AS cume_dist,
+percent_rank() OVER w AS percent_rank,
+ntile(2) OVER w AS ntile,
+row_number() OVER w AS row_number,
+var_pop(val) OVER w AS var_pop,
+var_samp(val) OVER w AS var_samp,
+approx_count_distinct(val) OVER w AS approx_count_distinct
+FROM testData
+WINDOW w AS (PARTITION BY cate ORDER BY val)
+ORDER BY cate, val
+-- !query 6 schema
+struct<val:int,cate:string,max:int,min:int,min:int,count:bigint,sum:bigint,avg:double,stddev:double,first_value:int,first_value_ignore_null:int,first_value_contain_null:int,last_value:int,last_value_ignore_null:int,last_value_contain_null:int,rank:int,dense_rank:int,cume_dist:double,percent_rank:double,ntile:int,row_number:int,var_pop:double,var_samp:double,approx_count_distinct:bigint>
+-- !query 6 output
+NULL	NULL	NULL	NULL	NULL	0	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	1	1	0.5	0.0	1	1	NULL	NULL	0
+3	NULL	3	3	3	1	3	3.0	NaN	NULL	3	NULL	3	3	3	2	2	1.0	1.0	2	2	0.0	NaN	1
+NULL	a	NULL	NULL	NULL	0	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	1	1	0.25	0.0	1	1	NULL	NULL	0
+1	a	1	1	1	2	2	1.0	0.0	NULL	1	NULL	1	1	1	2	2	0.75	0.3333333333333333	1	2	0.0	0.0	1
+1	a	1	1	1	2	2	1.0	0.0	NULL	1	NULL	1	1	1	2	2	0.75	0.3333333333333333	2	3	0.0	0.0	1
+2	a	2	1	1	3	4	1.3333333333333333	0.5773502691896258	NULL	1	NULL	2	2	2	4	3	1.0	1.0	2	4	0.22222222222222224	0.33333333333333337	2
+1	b	1	1	1	1	1	1.0	NaN	1	1	1	1	1	1	1	1	0.3333333333333333	0.0	1	1	0.0	NaN	1
+2	b	2	1	1	2	3	1.5	0.7071067811865476	1	1	1	2	2	2	2	2	0.6666666666666666	0.5	1	2	0.25	0.5	2
+3	b	3	1	1	3	6	2.0	1.0	1	1	1	3	3	3	3	3	1.0	1.0	2	3	0.6666666666666666	1.0	3
+
+
+-- !query 7
+SELECT val, cate, avg(null) OVER(PARTITION BY cate ORDER BY val) FROM testData ORDER BY cate, val
+-- !query 7 schema
+struct<val:int,cate:string,avg(CAST(NULL AS DOUBLE)) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW):double>
+-- !query 7 output
+NULL	NULL	NULL
+3	NULL	NULL
+NULL	a	NULL
+1	a	NULL
+1	a	NULL
+2	a	NULL
+1	b	NULL
+2	b	NULL
+3	b	NULL
+
+
+-- !query 8
+SELECT val, cate, row_number() OVER(PARTITION BY cate) FROM testData ORDER BY cate, val
+-- !query 8 schema
+struct<>
+-- !query 8 output
+org.apache.spark.sql.AnalysisException
+Window function row_number() requires window to be ordered, please add ORDER BY clause. For example SELECT row_number()(value_expr) OVER (PARTITION BY window_partition ORDER BY window_ordering) from table;
+
+
+-- !query 9
+SELECT val, cate, sum(val) OVER(), avg(val) OVER() FROM testData ORDER BY cate, val
+-- !query 9 schema
+struct<val:int,cate:string,sum(CAST(val AS BIGINT)) OVER (ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING):bigint,avg(CAST(val AS BIGINT)) OVER (ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING):double>
+-- !query 9 output
+NULL	NULL	13	1.8571428571428572
+3	NULL	13	1.8571428571428572
+NULL	a	13	1.8571428571428572
+1	a	13	1.8571428571428572
+1	a	13	1.8571428571428572
+2	a	13	1.8571428571428572
+1	b	13	1.8571428571428572
+2	b	13	1.8571428571428572
+3	b	13	1.8571428571428572
+
+
+-- !query 10
+SELECT val, cate,
+first_value(false) OVER w AS first_value,
+first_value(true, true) OVER w AS first_value_ignore_null,
+first_value(false, false) OVER w AS first_value_contain_null,
+last_value(false) OVER w AS last_value,
+last_value(true, true) OVER w AS last_value_ignore_null,
+last_value(false, false) OVER w AS last_value_contain_null
+FROM testData
+WINDOW w AS ()
+ORDER BY cate, val
+-- !query 10 schema
+struct<val:int,cate:string,first_value:boolean,first_value_ignore_null:boolean,first_value_contain_null:boolean,last_value:boolean,last_value_ignore_null:boolean,last_value_contain_null:boolean>
+-- !query 10 output
+NULL	NULL	false	true	false	false	true	false
+3	NULL	false	true	false	false	true	false
+NULL	a	false	true	false	false	true	false
+1	a	false	true	false	false	true	false
+1	a	false	true	false	false	true	false
+2	a	false	true	false	false	true	false
+1	b	false	true	false	false	true	false
+2	b	false	true	false	false	true	false
+3	b	false	true	false	false	true	false
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/WindowQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/WindowQuerySuite.scala
@@ -232,31 +232,4 @@ class WindowQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleto
         Row("Manufacturer#5", "almond azure blanched chiffon midnight", 23, 315.9225931564038, 315.9225931564038, 46, 99807.08486666666, -0.9978877469246935, -5664.856666666666)))
       // scalastyle:on
   }
-
-  test("null arguments") {
-    checkAnswer(sql("""
-        |select  p_mfgr, p_name, p_size,
-        |sum(null) over(distribute by p_mfgr sort by p_name) as sum,
-        |avg(null) over(distribute by p_mfgr sort by p_name) as avg
-        |from part
-      """.stripMargin),
-      sql("""
-        |select  p_mfgr, p_name, p_size,
-        |null as sum,
-        |null as avg
-        |from part
-        """.stripMargin))
-  }
-
-  test("SPARK-16646: LAST_VALUE(FALSE) OVER ()") {
-    checkAnswer(sql("SELECT LAST_VALUE(FALSE) OVER ()"), Row(false))
-    checkAnswer(sql("SELECT LAST_VALUE(FALSE, FALSE) OVER ()"), Row(false))
-    checkAnswer(sql("SELECT LAST_VALUE(TRUE, TRUE) OVER ()"), Row(true))
-  }
-
-  test("SPARK-16646: FIRST_VALUE(FALSE) OVER ()") {
-    checkAnswer(sql("SELECT FIRST_VALUE(FALSE) OVER ()"), Row(false))
-    checkAnswer(sql("SELECT FIRST_VALUE(FALSE, FALSE) OVER ()"), Row(false))
-    checkAnswer(sql("SELECT FIRST_VALUE(TRUE, TRUE) OVER ()"), Row(true))
-  }
 }
