The following aggregation query failed when using HashAggregate with
controlled fallback (it falls back to bytes to bytes map once it has processed
0 input rows and to sort-based aggregation once it has
processed 1 input rows). The query is == Parsed Logical Plan ==
'Aggregate [scalaaggregatefunction('id, 'col0, 'col1, 'col2, 'col3, 'col4, 'col5, 'col6, 'col7, 'col8, 'col9, 'col10, 'col11, 'col12, 'col13, 'col14, 'col15, 'col16, 'col17, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false

== Analyzed Logical Plan ==
scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17): struct<id:int,col0:string,col1:binary,col2:null,col3:boolean,col4:tinyint,col5:smallint,col6:int,col7:bigint,col8:float,col9:double,col10:decimal(25,5),col11:decimal(6,5),col12:date,col13:timestamp,col14:array<int>,col15:map<string,bigint>,col16:struct<f1:float,f2:array<boolean>>,col17:mydensevector>
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false

== Optimized Logical Plan ==
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false

== Physical Plan ==
SortAggregate(key=[], functions=[scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549])
+- Exchange SinglePartition
 +- SortAggregate(key=[], functions=[partial_scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[id#172569, col0#172570, col1#172571, col2#172572, col3#172573, col4#172574, col5#172575, col6#172576, col7#172577L, col8#172578, col9#172579, col10#172580, col11#172581, col12#172582, col13#172583, col14#172584, col15#172585, col16#172586, col17#172587])
 +- *(1) Scan ExistingRDD[id#171895,col0#171896,col1#171897,col2#171898,col3#171899,col4#171900,col5#171901,col6#171902,col7#171903L,col8#171904,col9#171905,col10#171906,col11#171907,col12#171908,col13#171909,col14#171910,col15#171911,col16#171912,col17#171913]



Results do not match for query:
Timezone: sun.util.calendar.ZoneInfo[id="America/Los_Angeles",offset=-28800000,dstSavings=3600000,useDaylight=true,transitions=185,lastRule=java.util.SimpleTimeZone[id=America/Los_Angeles,offset=-28800000,dstSavings=3600000,useDaylight=true,startYear=0,startMode=3,startMonth=2,startDay=8,startDayOfWeek=1,startTime=7200000,startTimeMode=0,endMode=3,endMonth=10,endDay=1,endDayOfWeek=1,endTime=7200000,endTimeMode=0]]
Timezone Env: 

== Parsed Logical Plan ==
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false

== Analyzed Logical Plan ==
scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17): struct<id:int,col0:string,col1:binary,col2:null,col3:boolean,col4:tinyint,col5:smallint,col6:int,col7:bigint,col8:float,col9:double,col10:decimal(25,5),col11:decimal(6,5),col12:date,col13:timestamp,col14:array<int>,col15:map<string,bigint>,col16:struct<f1:float,f2:array<boolean>>,col17:mydensevector>
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false

== Optimized Logical Plan ==
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false

== Physical Plan ==
SortAggregate(key=[], functions=[scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029])
+- Exchange SinglePartition
 +- SortAggregate(key=[], functions=[partial_scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[id#172049, col0#172050, col1#172051, col2#172052, col3#172053, col4#172054, col5#172055, col6#172056, col7#172057L, col8#172058, col9#172059, col10#172060, col11#172061, col12#172062, col13#172063, col14#172064, col15#172065, col16#172066, col17#172067])
 +- *(1) Scan ExistingRDD[id#171895,col0#171896,col1#171897,col2#171898,col3#171899,col4#171900,col5#171901,col6#171902,col7#171903L,col8#171904,col9#171905,col10#171906,col11#171907,col12#171908,col13#171909,col14#171910,col15#171911,col16#171912,col17#171913]

== Results ==

== Results ==
!== Correct Answer - 1 == == Spark Answer - 1 ==
!struct<>
org.scalatest.exceptions.TestFailedException:
The following aggregation query failed when using HashAggregate with
controlled fallback (it falls back to bytes to bytes map once it has processed
0 input rows and to sort-based aggregation once it has
processed 1 input rows). The query is == Parsed Logical Plan ==
'Aggregate [scalaaggregatefunction('id, 'col0, 'col1, 'col2, 'col3, 'col4, 'col5, 'col6, 'col7, 'col8, 'col9, 'col10, 'col11, 'col12, 'col13, 'col14, 'col15, 'col16, 'col17, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false
== Analyzed Logical Plan ==
scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17): struct<id:int,col0:string,col1:binary,col2:null,col3:boolean,col4:tinyint,col5:smallint,col6:int,col7:bigint,col8:float,col9:double,col10:decimal(25,5),col11:decimal(6,5),col12:date,col13:timestamp,col14:array<int>,col15:map<string,bigint>,col16:struct<f1:float,f2:array<boolean>>,col17:mydensevector>
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false
== Optimized Logical Plan ==
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false
== Physical Plan ==
SortAggregate(key=[], functions=[scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172549])
+- Exchange SinglePartition
+- SortAggregate(key=[], functions=[partial_scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[id#172569, col0#172570, col1#172571, col2#172572, col3#172573, col4#172574, col5#172575, col6#172576, col7#172577L, col8#172578, col9#172579, col10#172580, col11#172581, col12#172582, col13#172583, col14#172584, col15#172585, col16#172586, col17#172587])
+- *(1) Scan ExistingRDD[id#171895,col0#171896,col1#171897,col2#171898,col3#171899,col4#171900,col5#171901,col6#171902,col7#171903L,col8#171904,col9#171905,col10#171906,col11#171907,col12#171908,col13#171909,col14#171910,col15#171911,col16#171912,col17#171913]
Results do not match for query:
Timezone: sun.util.calendar.ZoneInfo[id="America/Los_Angeles",offset=-28800000,dstSavings=3600000,useDaylight=true,transitions=185,lastRule=java.util.SimpleTimeZone[id=America/Los_Angeles,offset=-28800000,dstSavings=3600000,useDaylight=true,startYear=0,startMode=3,startMonth=2,startDay=8,startDayOfWeek=1,startTime=7200000,startTimeMode=0,endMode=3,endMonth=10,endDay=1,endDayOfWeek=1,endTime=7200000,endTimeMode=0]]
Timezone Env:
== Parsed Logical Plan ==
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false
== Analyzed Logical Plan ==
scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17): struct<id:int,col0:string,col1:binary,col2:null,col3:boolean,col4:tinyint,col5:smallint,col6:int,col7:bigint,col8:float,col9:double,col10:decimal(25,5),col11:decimal(6,5),col12:date,col13:timestamp,col14:array<int>,col15:map<string,bigint>,col16:struct<f1:float,f2:array<boolean>>,col17:mydensevector>
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false
== Optimized Logical Plan ==
Aggregate [scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0) AS scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029]
+- LogicalRDD [id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913], false
== Physical Plan ==
SortAggregate(key=[], functions=[scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[scalaaggregatefunction(id, col0, col1, col2, col3, col4, col5, col6, col7, col8, col9, col10, col11, col12, col13, col14, col15, col16, col17)#172029])
+- Exchange SinglePartition
+- SortAggregate(key=[], functions=[partial_scalaaggregatefunction(id#171895, col0#171896, col1#171897, col2#171898, col3#171899, col4#171900, col5#171901, col6#171902, col7#171903L, col8#171904, col9#171905, col10#171906, col11#171907, col12#171908, col13#171909, col14#171910, col15#171911, col16#171912, col17#171913, org.apache.spark.sql.hive.execution.ScalaAggregateFunction@24227104, 0, 0)], output=[id#172049, col0#172050, col1#172051, col2#172052, col3#172053, col4#172054, col5#172055, col6#172056, col7#172057L, col8#172058, col9#172059, col10#172060, col11#172061, col12#172062, col13#172063, col14#172064, col15#172065, col16#172066, col17#172067])
+- *(1) Scan ExistingRDD[id#171895,col0#171896,col1#171897,col2#171898,col3#171899,col4#171900,col5#171901,col6#171902,col7#171903L,col8#171904,col9#171905,col10#171906,col11#171907,col12#171908,col13#171909,col14#171910,col15#171911,col16#171912,col17#171913]
== Results ==
== Results ==
!== Correct Answer - 1 == == Spark Answer - 1 ==
!struct<>