digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (3)\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 (2)\n \nduration: 6 ms";
5 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 6 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="<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: 54<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
}
7 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 1932.0 B<br>number of coalesced partitions: 1"];
8 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 94<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>2 ms (1 ms, 1 ms, 1 ms (stage 1217.0: task 1666))<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: 94<br>local bytes read: 1858.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 2<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>2.2 KiB (1008.0 B, 1248.0 B, 1248.0 B (stage 1217.0: task 1662))<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>1858.0 B (867.0 B, 991.0 B, 991.0 B (stage 1217.0: task 1662))"];
subgraph cluster9 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n8.3 s (11 ms, 13 ms, 6.7 s (stage 1217.0: task 1662))";
10 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build total (min, med, max (stageId: taskId))<br>8.2 s (2 ms, 5 ms, 6.7 s (stage 1217.0: task 1662))<br>peak memory total (min, med, max (stageId: taskId))<br>2.5 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 1217.0: task 1665))<br>number of output rows: 94<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
11 [labelType="html" label="<br><b>Project</b><br><br>"];
12 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 41,179"];
13 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 2,996,009<br>number of input batches: 732"];
}
14 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>855 ms (2 ms, 5 ms, 683 ms (stage 1217.0: task 1662))<br>metadata time: 0 ms<br>size of files read: 150.9 MiB<br>number of output rows: 2,996,009"];
2->0;
3->2;
5->3;
6->5;
7->6;
8->7;
10->8;
11->10;
12->11;
13->12;
14->13;
}
15
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (3)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=30845]
HashAggregate(keys=[], functions=[partial_count(1)])
HashAggregate(keys=[COL_E75FD19A_D578_4037_B330_0F4E587CAF25#110042], functions=[])
WholeStageCodegen (2)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_E75FD19A_D578_4037_B330_0F4E587CAF25#110042, 10), ENSURE_REQUIREMENTS, [plan_id=30583]
HashAggregate(keys=[COL_E75FD19A_D578_4037_B330_0F4E587CAF25#110042], functions=[])
Project [str_join(array(str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#109735, 78, 5), null), ONLY_ONE), str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#109735, 68, 2), null), ONLY_ONE)), -) AS COL_E75FD19A_D578_4037_B330_0F4E587CAF25#110042]
Filter (str_if_with_rule((((str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#109735, 78, 5), null), ONLY_ONE) <=> SAS) OR (str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#109735, 78, 5), null), ONLY_ONE) <=> SUF)) OR (str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#109735, 78, 5), null), ONLY_ONE) <=> SUN)), 1, 0) <=> 1)
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [COL_B706A975_F287_4DC9_B631_A35735FE936F#109735,COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#109738] Batched: true, DataFilters: [(str_if_with_rule((((str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F3..., Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/datablock/00_A_LIGNES_RSF_345253], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<COL_B706A975_F287_4DC9_B631_A35735FE936F:string,COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38:s...