digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (2)\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: 3<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>1 ms (0 ms, 0 ms, 0 ms (stage 348.0: task 322))<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: 3<br>local bytes read: 171.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 3<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>48.0 B (16.0 B, 16.0 B, 16.0 B (stage 348.0: task 320))<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 total (min, med, max (stageId: taskId))<br>171.0 B (56.0 B, 56.0 B, 59.0 B (stage 348.0: task 321))"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n7.0 s (3 ms, 3 ms, 6.9 s (stage 348.0: task 321))";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>7.0 s (3 ms, 3 ms, 6.9 s (stage 348.0: task 321))<br>number of output rows: 3"];
6 [labelType="html" label="<br><b>Project</b><br><br>"];
7 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 335,343"];
8 [labelType="html" label="<br><b>Project</b><br><br>"];
9 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 3,508"];
10 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 9,522<br>number of input batches: 3"];
}
11 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>210 ms (3 ms, 3 ms, 204 ms (stage 348.0: task 321))<br>metadata time: 0 ms<br>size of files read: 9.4 MiB<br>number of output rows: 9,522"];
2->0;
3->2;
5->3;
6->5;
7->6;
8->7;
9->8;
10->9;
11->10;
}
12
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (2)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=4915]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
Generate explode(COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#28900), false, [COL_A504A8EC_44DA_47A8_BC01_8F3D6A00E326#28922]
Project [str_extract_by_regex(str_replace_extend(BODY_3253#28588, [</p>,<br/], [</p>.,\n]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#28900]
Filter ((size(str_extract_by_regex(str_replace_extend(BODY_3253#28588, [</p>,<br/], [</p>.,\n]), <p[^>]*>(.*?)<\/p>), true) > 0) AND isnotnull(str_extract_by_regex(str_replace_extend(BODY_3253#28588, [</p>,<br/], [</p>.,\n]), <p[^>]*>(.*?)<\/p>)))
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [BODY_3253#28588] Batched: true, DataFilters: [(size(str_extract_by_regex(str_replace_extend(BODY_3253#28588, [</p>,<br/], [</p>.,\n]), <p[^>]*..., Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/uet/DOCUMENT_3240], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<BODY_3253:string>