digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (9)\n \nduration: 0 ms";
2 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build: 0 ms<br>number of output rows: 1"];
}
3 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 1<br>local merged chunks fetched: 0<br>shuffle write time: 0 ms<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 1<br>local bytes read: 59.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 1<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size: 16.0 B<br>local merged bytes read: 0.0 B<br>number of partitions: 1<br>remote reqs duration: 0 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written: 59.0 B"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (8)\n \nduration: 104 ms";
5 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 104 ms<br>peak memory: 0.0 B<br>number of output rows: 1<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
6 [labelType="html" label="<br><b>Project</b><br><br>"];
7 [labelType="html" label="<b>SortMergeJoin</b><br><br>number of output rows: 21,891<br>spill size: 0.0 B"];
}
subgraph cluster8 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: 118 ms";
9 [labelType="html" label="<br><b>Project</b><br><br>"];
10 [labelType="html" label="<b>SortMergeJoin</b><br><br>number of output rows: 21,869<br>spill size: 0.0 B"];
}
subgraph cluster11 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: 132 ms";
12 [labelType="html" label="<b>Sort</b><br><br>sort time: 9 ms<br>peak memory: 64.5 MiB<br>spill size: 0.0 B"];
}
13 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 173.0 KiB<br>number of coalesced partitions: 1"];
14 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 21,121<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>6 ms (1 ms, 2 ms, 2 ms (stage 206.0: task 244))<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 21,121<br>local bytes read: 164.6 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 3<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>825.0 KiB (25.9 KiB, 399.6 KiB, 399.6 KiB (stage 206.0: task 245))<br>local merged bytes read: 0.0 B<br>number of partitions: 10<br>remote reqs duration: 0 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>164.6 KiB (6.3 KiB, 79.0 KiB, 79.3 KiB (stage 206.0: task 245))"];
subgraph cluster15 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n217 ms (10 ms, 89 ms, 118 ms (stage 206.0: task 244))";
16 [labelType="html" label="<br><b>Project</b><br><br>"];
}
17 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 21,121<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 8.3 MiB"];
subgraph cluster18 {
isCluster="true";
label="WholeStageCodegen (5)\n \nduration: 2.9 m";
19 [labelType="html" label="<b>Sort</b><br><br>sort time: 0 ms<br>peak memory: 64.1 MiB<br>spill size: 0.0 B"];
}
20 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 5.5 KiB<br>number of coalesced partitions: 1"];
21 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 1,216<br>local merged chunks fetched: 0<br>shuffle write time: 2 ms<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 1,216<br>local bytes read: 5.3 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 1<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size: 47.5 KiB<br>local merged bytes read: 0.0 B<br>number of partitions: 10<br>remote reqs duration: 0 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written: 5.3 KiB"];
subgraph cluster22 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 13 ms";
23 [labelType="html" label="<br><b>Project</b><br><br>"];
24 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 1,216"];
}
25 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 1,216<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 111.6 KiB"];
subgraph cluster26 {
isCluster="true";
label="WholeStageCodegen (7)\n \nduration: 112 ms";
27 [labelType="html" label="<b>Sort</b><br><br>sort time: 0 ms<br>peak memory: 64.1 MiB<br>spill size: 0.0 B"];
}
28 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 4.8 KiB<br>number of coalesced partitions: 1"];
29 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 486<br>local merged chunks fetched: 0<br>shuffle write time: 2 ms<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 486<br>local bytes read: 4.6 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 1<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size: 19.0 KiB<br>local merged bytes read: 0.0 B<br>number of partitions: 10<br>remote reqs duration: 0 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written: 4.6 KiB"];
subgraph cluster30 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: 7 ms";
31 [labelType="html" label="<br><b>Project</b><br><br>"];
32 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 486"];
}
33 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 486<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 50.8 KiB"];
2->0;
3->2;
5->3;
6->5;
7->6;
9->7;
10->9;
12->10;
13->12;
14->13;
16->14;
17->16;
19->10;
20->19;
21->20;
23->21;
24->23;
25->24;
27->7;
28->27;
29->28;
31->29;
32->31;
33->32;
}
34
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (9)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=4987]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
SortMergeJoin [COL_9CE78B38_05A8_4BDE_9330_F7DF8166291D#50348], [MOLECULES_ONERE_440476_COL_9979D704_E827_4785_AA6A_46B46DBF4847#50513], LeftOuter
WholeStageCodegen (8)
Project [COL_9CE78B38_05A8_4BDE_9330_F7DF8166291D#50348]
SortMergeJoin [COL_9CE78B38_05A8_4BDE_9330_F7DF8166291D#50348], [01_DMI_DECOUPAG_440467_COL_C898C1FE_14C4_493A_878B_315EB757695B#50377], LeftOuter
WholeStageCodegen (6)
Sort [COL_9CE78B38_05A8_4BDE_9330_F7DF8166291D#50348 ASC NULLS FIRST], false, 0
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_9CE78B38_05A8_4BDE_9330_F7DF8166291D#50348, 10), ENSURE_REQUIREMENTS, [plan_id=4785]
Project [NO_ADMIN#47479 AS COL_9CE78B38_05A8_4BDE_9330_F7DF8166291D#50348]
WholeStageCodegen (1)
FileScan csv [NO_ADMIN#47479] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/VISUALVALOSEJOU_440300/420780652.2025.1..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<NO_ADMIN:string>
Sort [01_DMI_DECOUPAG_440467_COL_C898C1FE_14C4_493A_878B_315EB757695B#50377 ASC NULLS FIRST], false, 0
WholeStageCodegen (5)
AQEShuffleRead coalesced
Exchange hashpartitioning(01_DMI_DECOUPAG_440467_COL_C898C1FE_14C4_493A_878B_315EB757695B#50377, 10), ENSURE_REQUIREMENTS, [plan_id=4798]
Project [str_extract_middle(_c0#48890, 12, 20) AS 01_DMI_DECOUPAG_440467_COL_C898C1FE_14C4_493A_878B_315EB757695B#50377]
Filter isnotnull(str_extract_middle(_c0#48890, 12, 20))
WholeStageCodegen (2)
FileScan csv [_c0#48890] Batched: false, DataFilters: [isnotnull(str_extract_middle(_c0#48890, 12, 20))], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/DMI_M12_2025_440461/DMI-M12-2025 - BIS...., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<_c0:string>
Sort [MOLECULES_ONERE_440476_COL_9979D704_E827_4785_AA6A_46B46DBF4847#50513 ASC NULLS FIRST], false, 0
WholeStageCodegen (7)
AQEShuffleRead coalesced
Exchange hashpartitioning(MOLECULES_ONERE_440476_COL_9979D704_E827_4785_AA6A_46B46DBF4847#50513, 10), ENSURE_REQUIREMENTS, [plan_id=4815]
Project [str_extract_middle(_c0#48984, 12, 20) AS MOLECULES_ONERE_440476_COL_9979D704_E827_4785_AA6A_46B46DBF4847#50513]
Filter isnotnull(str_extract_middle(_c0#48984, 12, 20))
WholeStageCodegen (3)
FileScan csv [_c0#48984] Batched: false, DataFilters: [isnotnull(str_extract_middle(_c0#48984, 12, 20))], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/MOLECULES_ONERE_440457/MO-M12-2025.txt], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<_c0:string>