cloud-fan commented on code in PR #48649:
URL: https://github.com/apache/spark/pull/48649#discussion_r1831878699
##########
sql/core/src/test/resources/sql-tests/analyzer-results/pipe-operators.sql.out:
##########
@@ -2769,6 +2741,239 @@ org.apache.spark.sql.catalyst.ExtendedAnalysisException
}
+-- !query
+table windowTestData
+|> select cate, sum(val) over w
+ window w as (partition by cate order by val)
+-- !query analysis
+Project [cate#x, sum(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST
RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
++- Project [cate#x, val#x, sum(val) OVER (PARTITION BY cate ORDER BY val ASC
NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL, sum(val)
OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED
PRECEDING AND CURRENT ROW)#xL]
+ +- Window [sum(val#x) windowspecdefinition(cate#x, val#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
sum(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN
UNBOUNDED PRECEDING AND CURRENT ROW)#xL], [cate#x], [val#x ASC NULLS FIRST]
+ +- Project [cate#x, val#x]
+ +- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x, cast(val_long#xL as
bigint) AS val_long#xL, cast(val_double#x as double) AS val_double#x,
cast(val_date#x as date) AS val_date#x, cast(val_timestamp#x as timestamp) AS
val_timestamp#x, cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, sum(val) over w
+ window w as (order by val_timestamp range between unbounded preceding and
current row)
+-- !query analysis
+Project [cate#x, sum(val) OVER (ORDER BY val_timestamp ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
++- Project [cate#x, val#x, val_timestamp#x, sum(val) OVER (ORDER BY
val_timestamp ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT
ROW)#xL, sum(val) OVER (ORDER BY val_timestamp ASC NULLS FIRST RANGE BETWEEN
UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
+ +- Window [sum(val#x) windowspecdefinition(val_timestamp#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
sum(val) OVER (ORDER BY val_timestamp ASC NULLS FIRST RANGE BETWEEN UNBOUNDED
PRECEDING AND CURRENT ROW)#xL], [val_timestamp#x ASC NULLS FIRST]
+ +- Project [cate#x, val#x, val_timestamp#x]
+ +- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x, cast(val_long#xL as
bigint) AS val_long#xL, cast(val_double#x as double) AS val_double#x,
cast(val_date#x as date) AS val_date#x, cast(val_timestamp#x as timestamp) AS
val_timestamp#x, cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, val
+ window w as (partition by cate order by val)
+-- !query analysis
+Project [cate#x, val#x]
++- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x, cast(val_long#xL as bigint) AS
val_long#xL, cast(val_double#x as double) AS val_double#x, cast(val_date#x as
date) AS val_date#x, cast(val_timestamp#x as timestamp) AS val_timestamp#x,
cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, val, sum(val) over w as sum_val
+ window w as (partition by cate)
+|> select cate, val, sum_val, first_value(cate) over w
+ window w as (order by val)
+-- !query analysis
+Project [cate#x, val#x, sum_val#xL, first_value(cate) OVER (ORDER BY val ASC
NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#x]
++- Project [cate#x, val#x, sum_val#xL, first_value(cate) OVER (ORDER BY val
ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#x,
first_value(cate) OVER (ORDER BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED
PRECEDING AND CURRENT ROW)#x]
+ +- Window [first_value(cate#x, false) windowspecdefinition(val#x ASC NULLS
FIRST, specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$()))
AS first_value(cate) OVER (ORDER BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED
PRECEDING AND CURRENT ROW)#x], [val#x ASC NULLS FIRST]
+ +- Project [cate#x, val#x, sum_val#xL]
+ +- Project [cate#x, val#x, sum_val#xL]
+ +- Project [cate#x, val#x, _we0#xL, pipeselect(_we0#xL) AS
sum_val#xL]
+ +- Window [sum(val#x) windowspecdefinition(cate#x,
specifiedwindowframe(RowFrame, unboundedpreceding$(), unboundedfollowing$()))
AS _we0#xL], [cate#x]
+ +- Project [cate#x, val#x]
+ +- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL,
val_double#x, val_date#x, val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x,
cast(val_long#xL as bigint) AS val_long#xL, cast(val_double#x as double) AS
val_double#x, cast(val_date#x as date) AS val_date#x, cast(val_timestamp#x as
timestamp) AS val_timestamp#x, cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL,
val_double#x, val_date#x, val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, val, sum(val) over w1, first_value(cate) over w2
+ window w1 as (partition by cate), w2 as (order by val)
+-- !query analysis
+Project [cate#x, val#x, sum(val) OVER (PARTITION BY cate ROWS BETWEEN
UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING)#xL, first_value(cate) OVER (ORDER
BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#x]
++- Project [cate#x, val#x, sum(val) OVER (PARTITION BY cate ROWS BETWEEN
UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING)#xL, first_value(cate) OVER (ORDER
BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#x,
sum(val) OVER (PARTITION BY cate ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED
FOLLOWING)#xL, first_value(cate) OVER (ORDER BY val ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#x]
+ +- Window [first_value(cate#x, false) windowspecdefinition(val#x ASC NULLS
FIRST, specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$()))
AS first_value(cate) OVER (ORDER BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED
PRECEDING AND CURRENT ROW)#x], [val#x ASC NULLS FIRST]
+ +- Window [sum(val#x) windowspecdefinition(cate#x,
specifiedwindowframe(RowFrame, unboundedpreceding$(), unboundedfollowing$()))
AS sum(val) OVER (PARTITION BY cate ROWS BETWEEN UNBOUNDED PRECEDING AND
UNBOUNDED FOLLOWING)#xL], [cate#x]
+ +- Project [cate#x, val#x]
+ +- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x, cast(val_long#xL as
bigint) AS val_long#xL, cast(val_double#x as double) AS val_double#x,
cast(val_date#x as date) AS val_date#x, cast(val_timestamp#x as timestamp) AS
val_timestamp#x, cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, val, sum(val) over w, first_value(val) over w
+ window w1 as (partition by cate order by val)
+-- !query analysis
+org.apache.spark.sql.AnalysisException
+{
+ "errorClass" : "MISSING_WINDOW_SPECIFICATION",
+ "sqlState" : "42P20",
+ "messageParameters" : {
+ "docroot" : "https://spark.apache.org/docs/latest";,
+ "windowName" : "w"
+ }
+}
+
+
+-- !query
+(select col from st)
+|> select col.i1, sum(col.i2) over w
+ window w as (partition by col.i1 order by col.i2)
+-- !query analysis
+Project [i1#x, sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS
FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
++- Project [i1#x, _w0#x, _w1#x, sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY
col.i2 ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL,
sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
+ +- Window [sum(_w0#x) windowspecdefinition(_w1#x, _w0#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL], [_w1#x], [_w0#x ASC NULLS
FIRST]
+ +- Project [col#x.i1 AS i1#x, col#x.i2 AS _w0#x, col#x.i1 AS _w1#x]
+ +- Project [col#x]
+ +- SubqueryAlias spark_catalog.default.st
+ +- Relation spark_catalog.default.st[x#x,col#x] parquet
+
+
+-- !query
+table st
+|> select st.col.i1, sum(st.col.i2) over w
+ window w as (partition by st.col.i1 order by st.col.i2)
+-- !query analysis
+Project [i1#x, sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS
FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
++- Project [i1#x, _w0#x, _w1#x, sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY
col.i2 ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL,
sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
+ +- Window [sum(_w0#x) windowspecdefinition(_w1#x, _w0#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL], [_w1#x], [_w0#x ASC NULLS
FIRST]
+ +- Project [col#x.i1 AS i1#x, col#x.i2 AS _w0#x, col#x.i1 AS _w1#x]
+ +- SubqueryAlias spark_catalog.default.st
+ +- Relation spark_catalog.default.st[x#x,col#x] parquet
+
+
+-- !query
+table st
+|> select spark_catalog.default.st.col.i1,
sum(spark_catalog.default.st.col.i2) over w
+ window w as (partition by spark_catalog.default.st.col.i1 order by
spark_catalog.default.st.col.i2)
+-- !query analysis
+Project [i1#x, sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS
FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
++- Project [i1#x, _w0#x, _w1#x, sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY
col.i2 ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL,
sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
+ +- Window [sum(_w0#x) windowspecdefinition(_w1#x, _w0#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
sum(col.i2) OVER (PARTITION BY col.i1 ORDER BY col.i2 ASC NULLS FIRST RANGE
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL], [_w1#x], [_w0#x ASC NULLS
FIRST]
+ +- Project [col#x.i1 AS i1#x, col#x.i2 AS _w0#x, col#x.i1 AS _w1#x]
+ +- SubqueryAlias spark_catalog.default.st
+ +- Relation spark_catalog.default.st[x#x,col#x] parquet
+
+
+-- !query
+table windowTestData
+|> select cate, sum(val) over val
+ window val as (partition by cate order by val)
+-- !query analysis
+Project [cate#x, sum(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST
RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL]
++- Project [cate#x, val#x, sum(val) OVER (PARTITION BY cate ORDER BY val ASC
NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)#xL, sum(val)
OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN UNBOUNDED
PRECEDING AND CURRENT ROW)#xL]
+ +- Window [sum(val#x) windowspecdefinition(cate#x, val#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
sum(val) OVER (PARTITION BY cate ORDER BY val ASC NULLS FIRST RANGE BETWEEN
UNBOUNDED PRECEDING AND CURRENT ROW)#xL], [cate#x], [val#x ASC NULLS FIRST]
+ +- Project [cate#x, val#x]
+ +- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x, cast(val_long#xL as
bigint) AS val_long#xL, cast(val_double#x as double) AS val_double#x,
cast(val_date#x as date) AS val_date#x, cast(val_timestamp#x as timestamp) AS
val_timestamp#x, cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x, val_date#x,
val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, val, first_value(cate) over w as first_val
+|> select cate, val, sum(val) over w as sum_val
+ window w as (order by val)
+-- !query analysis
+Project [cate#x, val#x, sum_val#xL]
++- Project [cate#x, val#x, _we0#xL, pipeselect(_we0#xL) AS sum_val#xL]
+ +- Window [sum(val#x) windowspecdefinition(val#x ASC NULLS FIRST,
specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS
_we0#xL], [val#x ASC NULLS FIRST]
+ +- Project [cate#x, val#x]
+ +- Project [cate#x, val#x, first_val#x]
+ +- Project [cate#x, val#x, _we0#x, pipeselect(_we0#x) AS
first_val#x]
+ +- Window [first_value(cate#x, false)
windowspecdefinition(val#x ASC NULLS FIRST, specifiedwindowframe(RangeFrame,
unboundedpreceding$(), currentrow$())) AS _we0#x], [val#x ASC NULLS FIRST]
+ +- Project [cate#x, val#x]
+ +- SubqueryAlias windowtestdata
+ +- View (`windowTestData`, [val#x, val_long#xL,
val_double#x, val_date#x, val_timestamp#x, cate#x])
+ +- Project [cast(val#x as int) AS val#x,
cast(val_long#xL as bigint) AS val_long#xL, cast(val_double#x as double) AS
val_double#x, cast(val_date#x as date) AS val_date#x, cast(val_timestamp#x as
timestamp) AS val_timestamp#x, cast(cate#x as string) AS cate#x]
+ +- Project [val#x, val_long#xL, val_double#x,
val_date#x, val_timestamp#x, cate#x]
+ +- SubqueryAlias testData
+ +- LocalRelation [val#x, val_long#xL,
val_double#x, val_date#x, val_timestamp#x, cate#x]
+
+
+-- !query
+table windowTestData
+|> select cate, sum(val) over w
+-- !query analysis
+org.apache.spark.sql.catalyst.ExtendedAnalysisException
+{
+ "errorClass" : "MISSING_WINDOW_SPECIFICATION",
+ "sqlState" : "42P20",
+ "messageParameters" : {
+ "docroot" : "https://spark.apache.org/docs/latest";,
+ "windowName" : "w"
+ }
+}
+
+
+-- !query
+table windowTestData
+|> select cate, val, sum(val) over w1, first_value(cate) over w2
+ window w1 as (partition by cate)
+ window w2 as (order by val)
Review Comment:
hmm, is it a bug? @srielau
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
