digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (10)\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 (9)\n \nduration: 19 ms";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build: 18 ms<br>number of output rows: 1"];
6 [labelType="html" label="<br><b>Project</b><br><br>"];
7 [labelType="html" label="<b>SortMergeJoin</b><br><br>number of output rows: 21,131"];
}
subgraph cluster8 {
isCluster="true";
label="WholeStageCodegen (7)\n \nduration: 20 ms";
9 [labelType="html" label="<b>Sort</b><br><br>sort time: 2 ms<br>peak memory: 16.5 MiB<br>spill size: 0.0 B"];
}
10 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 148.0 KiB<br>number of coalesced partitions: 1"];
11 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 21,127<br>local merged chunks fetched: 0<br>shuffle write time: 1 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: 21,127<br>local bytes read: 141.1 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: 660.1 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: 141.1 KiB"];
subgraph cluster12 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: 38 ms";
13 [labelType="html" label="<br><b>Project</b><br><br>"];
14 [labelType="html" label="<b>SortMergeJoin</b><br><br>number of output rows: 21,127<br>spill size: 0.0 B"];
}
subgraph cluster15 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: 96 ms";
16 [labelType="html" label="<b>Sort</b><br><br>sort time: 7 ms<br>peak memory: 16.5 MiB<br>spill size: 0.0 B"];
}
17 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 175.9 KiB<br>number of coalesced partitions: 1"];
18 [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>5 ms (1 ms, 1 ms, 2 ms (stage 21009.0: task 27237))<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: 166.3 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 3<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>660.0 KiB (20.7 KiB, 319.7 KiB, 319.7 KiB (stage 21009.0: task 27235))<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>166.3 KiB (6.7 KiB, 79.7 KiB, 79.9 KiB (stage 21009.0: task 27235))"];
subgraph cluster19 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n219 ms (20 ms, 97 ms, 102 ms (stage 21009.0: task 27236))";
20 [labelType="html" label="<br><b>Project</b><br><br>"];
}
21 [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 cluster22 {
isCluster="true";
label="WholeStageCodegen (5)\n \nduration: 1.1 m";
23 [labelType="html" label="<b>Sort</b><br><br>sort time: 0 ms<br>peak memory: 16.1 MiB<br>spill size: 0.0 B"];
24 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 0 ms<br>peak memory: 256.0 KiB<br>number of output rows: 445<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
}
25 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 5.0 KiB<br>number of coalesced partitions: 1"];
26 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 445<br>local merged chunks fetched: 0<br>shuffle write time: 1 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: 445<br>local bytes read: 4.8 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: 13.9 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: 4.8 KiB"];
subgraph cluster27 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 19 ms";
28 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 13 ms<br>peak memory: 256.0 KiB<br>number of output rows: 445<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
29 [labelType="html" label="<br><b>Project</b><br><br>"];
}
30 [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 cluster31 {
isCluster="true";
label="WholeStageCodegen (8)\n \nduration: 38 ms";
32 [labelType="html" label="<b>Sort</b><br><br>sort time: 0 ms<br>peak memory: 16.1 MiB<br>spill size: 0.0 B"];
33 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 0 ms<br>peak memory: 256.0 KiB<br>number of output rows: 464<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
}
34 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 5.2 KiB<br>number of coalesced partitions: 1"];
35 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 464<br>local merged chunks fetched: 0<br>shuffle write time: 1 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: 464<br>local bytes read: 5.0 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: 14.5 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: 5.0 KiB"];
subgraph cluster36 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: 10 ms";
37 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 7 ms<br>peak memory: 256.0 KiB<br>number of output rows: 464<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
38 [labelType="html" label="<br><b>Project</b><br><br>"];
}
39 [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;
11->10;
13->11;
14->13;
16->14;
17->16;
18->17;
20->18;
21->20;
23->14;
24->23;
25->24;
26->25;
28->26;
29->28;
30->29;
32->7;
33->32;
34->33;
35->34;
37->35;
38->37;
39->38;
}
40
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (10)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=1032107]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
SortMergeJoin [COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875], [01_MOLECULES_ON_237708_COL_EE4AB0B4_F37E_40C0_9292_9E68BF166E36#1687000], FullOuter
WholeStageCodegen (9)
Sort [COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875 ASC NULLS FIRST], false, 0
WholeStageCodegen (7)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875, 10), ENSURE_REQUIREMENTS, [plan_id=1032025]
Project [COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875]
SortMergeJoin [COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875], [01_DMI_DECOUPAG_237714_COL_1D1ABD09_1E00_4FA7_81FE_A558E22F6A6D#1686889], FullOuter
WholeStageCodegen (6)
Sort [COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875 ASC NULLS FIRST], false, 0
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875, 10), ENSURE_REQUIREMENTS, [plan_id=1031804]
Project [str_remove_space(NO_ADMIN#1681215, ALL) AS COL_7948E047_29EE_472A_BFFC_723098878DAD#1686875]
WholeStageCodegen (1)
FileScan csv [NO_ADMIN#1681215] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/VISUALVALOSEJOU_237544/420780652.2025.1..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<NO_ADMIN:string>
Sort [01_DMI_DECOUPAG_237714_COL_1D1ABD09_1E00_4FA7_81FE_A558E22F6A6D#1686889 ASC NULLS FIRST], false, 0
HashAggregate(keys=[COL_9D7AAEDE_94EE_40AF_8530_BC9D1F27742A#1683798], functions=[])
WholeStageCodegen (5)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_9D7AAEDE_94EE_40AF_8530_BC9D1F27742A#1683798, 10), ENSURE_REQUIREMENTS, [plan_id=1031817]
HashAggregate(keys=[COL_9D7AAEDE_94EE_40AF_8530_BC9D1F27742A#1683798], functions=[])
Project [str_remove_space(str_extract_middle(_c0#1683678, 12, 20), ALL) AS COL_9D7AAEDE_94EE_40AF_8530_BC9D1F27742A#1683798]
WholeStageCodegen (2)
FileScan csv [_c0#1683678] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/DMI_M12_2025_237543/DMI-M12-2025 - BIS...., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<_c0:string>
Sort [01_MOLECULES_ON_237708_COL_EE4AB0B4_F37E_40C0_9292_9E68BF166E36#1687000 ASC NULLS FIRST], false, 0
HashAggregate(keys=[COL_45066C9F_40FD_4BE1_ACAF_6139C274CECB#1682949], functions=[])
WholeStageCodegen (8)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_45066C9F_40FD_4BE1_ACAF_6139C274CECB#1682949, 10), ENSURE_REQUIREMENTS, [plan_id=1031837]
HashAggregate(keys=[COL_45066C9F_40FD_4BE1_ACAF_6139C274CECB#1682949], functions=[])
Project [str_remove_space(str_extract_middle(_c0#1682799, 12, 20), ALL) AS COL_45066C9F_40FD_4BE1_ACAF_6139C274CECB#1682949]
WholeStageCodegen (3)
FileScan csv [_c0#1682799] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/MOLECULES_ONERE_237545/MO-M12-2025.txt], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<_c0:string>