digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
1 [labelType="html" label="<b>Execute InsertIntoHadoopFsRelationCommand</b><br><br>task commit time total (min, med, max (stageId: taskId))<br>2 ms (1 ms, 1 ms, 1 ms (stage 1024.0: task 1012))<br>number of written files: 2<br>job commit time: 8 ms<br>number of output rows: 60<br>number of dynamic part: 0<br>written output: 29.0 KiB"];
2 [labelType="html" label="<br><b>WriteFiles</b><br><br>"];
subgraph cluster3 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n58 ms (27 ms, 31 ms, 31 ms (stage 1024.0: task 1013))";
4 [labelType="html" label="<br><b>Project</b><br><br>"];
5 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 60"];
}
6 [labelType="html" label="<b>Window</b><br><br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 1024.0: task 1012))"];
subgraph cluster7 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n401 ms (198 ms, 203 ms, 203 ms (stage 1024.0: task 1013))";
8 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 1024.0: task 1012))<br>peak memory total (min, med, max (stageId: taskId))<br>128.1 MiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 1024.0: task 1012))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 1024.0: task 1012))"];
}
9 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 2<br>partition data size total (min, med, max (stageId: taskId))<br>2.5 MiB (1071.3 KiB, 1529.3 KiB, 1529.3 KiB (driver))<br>number of coalesced partitions: 2"];
10 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 737<br>local merged chunks fetched: 0<br>shuffle write time: 7 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: 737<br>local bytes read total (min, med, max (stageId: taskId))<br>2.4 MiB (1031.5 KiB, 1440.3 KiB, 1440.3 KiB (stage 1024.0: task 1013))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 1024.0: task 1012))<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: 12.9 MiB<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: 2.4 MiB"];
11 [labelType="html" label="<br><b>Project</b><br><br>"];
subgraph cluster12 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n23.1 s (7 ms, 7 ms, 23.1 s (stage 1022.0: task 1010))";
13 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 737"];
}
14 [labelType="html" label="<br><b>Project</b><br><br>"];
15 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 1"];
subgraph cluster16 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n23.1 s (10 ms, 10 ms, 23.1 s (stage 1022.0: task 1010))";
17 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 9,522<br>number of input batches: 3"];
}
18 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>177 ms (3 ms, 3 ms, 171 ms (stage 1022.0: task 1010))<br>metadata time: 0 ms<br>size of files read: 9.9 MiB<br>number of output rows: 9,522"];
1->0;
2->1;
4->2;
5->4;
6->5;
8->6;
9->8;
10->9;
11->10;
13->11;
14->13;
15->14;
17->15;
18->17;
}
19
AdaptiveSparkPlan isFinalPlan=true
Execute InsertIntoHadoopFsRelationCommand file:/data/output/cache/parquet/datablock/DOCUMENT_TRAITE_3440, false, Parquet, [path=file:///data/output/cache/parquet/datablock/DOCUMENT_TRAITE_3440], Overwrite, [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D, COL_8A9046D2_1D72_45E3_B655_D46E004711DC, COL_A3AD19B8_0E44_4535_990D_3E89D0346083, COL_AE628ECA_E5BA_4F07_8939_98F393782191, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1, COL_A687F590_7636_41E9_B432_F96E84FA5822, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998, COL_46900168_36DE_4076_8267_A418814B0376, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59, COL_A805C849_5E36_4B9D_996E_AA54407924E2]
WriteFiles
Project [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, str_replace(COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933, |, ) AS COL_A805C849_5E36_4B9D_996E_AA54407924E2#104116]
Filter (COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885 <=> 1)
WholeStageCodegen (4)
Window [concatwithseparatorudaf(_w0#103934, com.adb.hdh.spark.job.scala.utils.ConcatWithSeparatorUDAF@13270fbd, class[value[0]: string], class[value[0]: string], true, true, 0, 0, None) windowspecdefinition(COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), unboundedfollowing$())) AS COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933], [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883], [COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST]
Sort [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381 ASC NULLS FIRST, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883 ASC NULLS FIRST, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST], false, 0
WholeStageCodegen (3)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, 10), ENSURE_REQUIREMENTS, [plan_id=15628]
Project [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.sentence_number_in_text)) AS COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term_number_in_text)) AS COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term_number_in_sentence)) AS COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, ARRAY_TO_STR_BEFORE_CONCAT(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term)) AS _w0#103934]
Generate explode(COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538), [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395], false, [COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558]
WholeStageCodegen (2)
Project [DOCUMENT_ID_3241#103193 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, METADOCUMENT_ID_3242#103197 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, PATIENT_ID_3243#103199 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, VISIT_ID_3244#103203 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, VISIT_UNIT_ID_3245#103204 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, UPDATED_AT_3246#103202 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, UNIT_3247#103201 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, DELEGATE_UNIT_3248#103192 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, HIERARCHY_UNIT_3249#103196 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, TITLE_3250#103200 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, DOCUMENT_TYPE_3251#103194 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, CREATED_AT_3252#103191 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, BODY_3253#103190 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, AUTHOR_3254#103189 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, PATIENT_AGE_3255#103198 AS COL_46900168_36DE_4076_8267_A418814B0376#103395, from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC)) AS COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538]
Filter (((DOCUMENT_ID_3241#103193 <=> 8BE75A8015FDF0D67EA8C8C6A4008D75E25BAEEF) AND (size(from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC)), true) > 0)) AND isnotnull(from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC))))
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [AUTHOR_3254#103189,BODY_3253#103190,CREATED_AT_3252#103191,DELEGATE_UNIT_3248#103192,DOCUMENT_ID_3241#103193,DOCUMENT_TYPE_3251#103194,HIERARCHY_UNIT_3249#103196,METADOCUMENT_ID_3242#103197,PATIENT_AGE_3255#103198,PATIENT_ID_3243#103199,TITLE_3250#103200,UNIT_3247#103201,UPDATED_AT_3246#103202,VISIT_ID_3244#103203,VISIT_UNIT_ID_3245#103204] Batched: true, DataFilters: [(DOCUMENT_ID_3241#103193 <=> 8BE75A8015FDF0D67EA8C8C6A4008D75E25BAEEF), (size(from_json(ArrayTyp..., Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/uet/DOCUMENT_3240], PartitionFilters: [], PushedFilters: [EqualNullSafe(DOCUMENT_ID_3241,8BE75A8015FDF0D67EA8C8C6A4008D75E25BAEEF)], ReadSchema: struct<AUTHOR_3254:string,BODY_3253:string,CREATED_AT_3252:timestamp,DELEGATE_UNIT_3248:string,DO...
== Physical Plan ==
AdaptiveSparkPlan (27)
+- == Final Plan ==
Execute InsertIntoHadoopFsRelationCommand (15)
+- WriteFiles (14)
+- * Project (13)
+- * Filter (12)
+- Window (11)
+- * Sort (10)
+- AQEShuffleRead (9)
+- ShuffleQueryStage (8), Statistics(sizeInBytes=12.9 MiB, rowCount=737)
+- Exchange (7)
+- Project (6)
+- * Generate (5)
+- Project (4)
+- Filter (3)
+- * ColumnarToRow (2)
+- Scan parquet (1)
+- == Initial Plan ==
Execute InsertIntoHadoopFsRelationCommand (26)
+- WriteFiles (25)
+- Project (24)
+- Filter (23)
+- Window (22)
+- Sort (21)
+- Exchange (20)
+- Project (19)
+- Generate (18)
+- Project (17)
+- Filter (16)
+- Scan parquet (1)
(1) Scan parquet
Output [15]: [AUTHOR_3254#103189, BODY_3253#103190, CREATED_AT_3252#103191, DELEGATE_UNIT_3248#103192, DOCUMENT_ID_3241#103193, DOCUMENT_TYPE_3251#103194, HIERARCHY_UNIT_3249#103196, METADOCUMENT_ID_3242#103197, PATIENT_AGE_3255#103198, PATIENT_ID_3243#103199, TITLE_3250#103200, UNIT_3247#103201, UPDATED_AT_3246#103202, VISIT_ID_3244#103203, VISIT_UNIT_ID_3245#103204]
Batched: true
Location: InMemoryFileIndex [file:/data/output/cache/parquet/uet/DOCUMENT_3240]
PushedFilters: [EqualNullSafe(DOCUMENT_ID_3241,8BE75A8015FDF0D67EA8C8C6A4008D75E25BAEEF)]
ReadSchema: struct<AUTHOR_3254:string,BODY_3253:string,CREATED_AT_3252:timestamp,DELEGATE_UNIT_3248:string,DOCUMENT_ID_3241:string,DOCUMENT_TYPE_3251:string,HIERARCHY_UNIT_3249:string,METADOCUMENT_ID_3242:string,PATIENT_AGE_3255:int,PATIENT_ID_3243:string,TITLE_3250:string,UNIT_3247:string,UPDATED_AT_3246:timestamp,VISIT_ID_3244:string,VISIT_UNIT_ID_3245:string>
(2) ColumnarToRow [codegen id : 1]
Input [15]: [AUTHOR_3254#103189, BODY_3253#103190, CREATED_AT_3252#103191, DELEGATE_UNIT_3248#103192, DOCUMENT_ID_3241#103193, DOCUMENT_TYPE_3251#103194, HIERARCHY_UNIT_3249#103196, METADOCUMENT_ID_3242#103197, PATIENT_AGE_3255#103198, PATIENT_ID_3243#103199, TITLE_3250#103200, UNIT_3247#103201, UPDATED_AT_3246#103202, VISIT_ID_3244#103203, VISIT_UNIT_ID_3245#103204]
(3) Filter
Input [15]: [AUTHOR_3254#103189, BODY_3253#103190, CREATED_AT_3252#103191, DELEGATE_UNIT_3248#103192, DOCUMENT_ID_3241#103193, DOCUMENT_TYPE_3251#103194, HIERARCHY_UNIT_3249#103196, METADOCUMENT_ID_3242#103197, PATIENT_AGE_3255#103198, PATIENT_ID_3243#103199, TITLE_3250#103200, UNIT_3247#103201, UPDATED_AT_3246#103202, VISIT_ID_3244#103203, VISIT_UNIT_ID_3245#103204]
Condition : (((DOCUMENT_ID_3241#103193 <=> 8BE75A8015FDF0D67EA8C8C6A4008D75E25BAEEF) AND (size(from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC)), true) > 0)) AND isnotnull(from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC))))
(4) Project
Output [16]: [DOCUMENT_ID_3241#103193 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, METADOCUMENT_ID_3242#103197 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, PATIENT_ID_3243#103199 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, VISIT_ID_3244#103203 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, VISIT_UNIT_ID_3245#103204 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, UPDATED_AT_3246#103202 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, UNIT_3247#103201 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, DELEGATE_UNIT_3248#103192 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, HIERARCHY_UNIT_3249#103196 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, TITLE_3250#103200 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, DOCUMENT_TYPE_3251#103194 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, CREATED_AT_3252#103191 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, BODY_3253#103190 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, AUTHOR_3254#103189 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, PATIENT_AGE_3255#103198 AS COL_46900168_36DE_4076_8267_A418814B0376#103395, from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC)) AS COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538]
Input [15]: [AUTHOR_3254#103189, BODY_3253#103190, CREATED_AT_3252#103191, DELEGATE_UNIT_3248#103192, DOCUMENT_ID_3241#103193, DOCUMENT_TYPE_3251#103194, HIERARCHY_UNIT_3249#103196, METADOCUMENT_ID_3242#103197, PATIENT_AGE_3255#103198, PATIENT_ID_3243#103199, TITLE_3250#103200, UNIT_3247#103201, UPDATED_AT_3246#103202, VISIT_ID_3244#103203, VISIT_UNIT_ID_3245#103204]
(5) Generate [codegen id : 2]
Input [16]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538]
Arguments: explode(COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538), [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395], false, [COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558]
(6) Project
Output [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.sentence_number_in_text)) AS COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term_number_in_text)) AS COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term_number_in_sentence)) AS COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, ARRAY_TO_STR_BEFORE_CONCAT(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term)) AS _w0#103934]
Input [16]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558]
(7) Exchange
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: hashpartitioning(COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, 10), ENSURE_REQUIREMENTS, [plan_id=15628]
(8) ShuffleQueryStage
Output [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: 0
(9) AQEShuffleRead
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: coalesced
(10) Sort [codegen id : 3]
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381 ASC NULLS FIRST, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883 ASC NULLS FIRST, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST], false, 0
(11) Window
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: [concatwithseparatorudaf(_w0#103934, com.adb.hdh.spark.job.scala.utils.ConcatWithSeparatorUDAF@13270fbd, class[value[0]: string], class[value[0]: string], true, true, 0, 0, None) windowspecdefinition(COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), unboundedfollowing$())) AS COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933], [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883], [COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST]
(12) Filter [codegen id : 4]
Input [20]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934, COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933]
Condition : (COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885 <=> 1)
(13) Project [codegen id : 4]
Output [17]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, str_replace(COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933, |, ) AS COL_A805C849_5E36_4B9D_996E_AA54407924E2#104116]
Input [20]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934, COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933]
(14) WriteFiles
Input [17]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_A805C849_5E36_4B9D_996E_AA54407924E2#104116]
(15) Execute InsertIntoHadoopFsRelationCommand
Input: []
Arguments: file:/data/output/cache/parquet/datablock/DOCUMENT_TRAITE_3440, false, Parquet, [path=file:///data/output/cache/parquet/datablock/DOCUMENT_TRAITE_3440], Overwrite, [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D, COL_8A9046D2_1D72_45E3_B655_D46E004711DC, COL_A3AD19B8_0E44_4535_990D_3E89D0346083, COL_AE628ECA_E5BA_4F07_8939_98F393782191, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1, COL_A687F590_7636_41E9_B432_F96E84FA5822, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998, COL_46900168_36DE_4076_8267_A418814B0376, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59, COL_A805C849_5E36_4B9D_996E_AA54407924E2]
(16) Filter
Input [15]: [AUTHOR_3254#103189, BODY_3253#103190, CREATED_AT_3252#103191, DELEGATE_UNIT_3248#103192, DOCUMENT_ID_3241#103193, DOCUMENT_TYPE_3251#103194, HIERARCHY_UNIT_3249#103196, METADOCUMENT_ID_3242#103197, PATIENT_AGE_3255#103198, PATIENT_ID_3243#103199, TITLE_3250#103200, UNIT_3247#103201, UPDATED_AT_3246#103202, VISIT_ID_3244#103203, VISIT_UNIT_ID_3245#103204]
Condition : (((DOCUMENT_ID_3241#103193 <=> 8BE75A8015FDF0D67EA8C8C6A4008D75E25BAEEF) AND (size(from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC)), true) > 0)) AND isnotnull(from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC))))
(17) Project
Output [16]: [DOCUMENT_ID_3241#103193 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, METADOCUMENT_ID_3242#103197 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, PATIENT_ID_3243#103199 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, VISIT_ID_3244#103203 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, VISIT_UNIT_ID_3245#103204 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, UPDATED_AT_3246#103202 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, UNIT_3247#103201 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, DELEGATE_UNIT_3248#103192 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, HIERARCHY_UNIT_3249#103196 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, TITLE_3250#103200 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, DOCUMENT_TYPE_3251#103194 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, CREATED_AT_3252#103191 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, BODY_3253#103190 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, AUTHOR_3254#103189 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, PATIENT_AGE_3255#103198 AS COL_46900168_36DE_4076_8267_A418814B0376#103395, from_json(ArrayType(StringType,false), to_json(str_to_words(str_replace_regex(str_replace_regex(BODY_3253#103190, <br\s*\/?>, ), <[^<>]+>, )), Some(Etc/UTC)), Some(Etc/UTC)) AS COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538]
Input [15]: [AUTHOR_3254#103189, BODY_3253#103190, CREATED_AT_3252#103191, DELEGATE_UNIT_3248#103192, DOCUMENT_ID_3241#103193, DOCUMENT_TYPE_3251#103194, HIERARCHY_UNIT_3249#103196, METADOCUMENT_ID_3242#103197, PATIENT_AGE_3255#103198, PATIENT_ID_3243#103199, TITLE_3250#103200, UNIT_3247#103201, UPDATED_AT_3246#103202, VISIT_ID_3244#103203, VISIT_UNIT_ID_3245#103204]
(18) Generate
Input [16]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538]
Arguments: explode(COL_9E6B0BF3_343E_49F2_87DB_EE022165520A#103538), [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395], false, [COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558]
(19) Project
Output [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.sentence_number_in_text)) AS COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term_number_in_text)) AS COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, str_to_integer(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term_number_in_sentence)) AS COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, ARRAY_TO_STR_BEFORE_CONCAT(get_json_object(COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558, $.term)) AS _w0#103934]
Input [16]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_9F4C7B82_8EA5_42B7_8724_EDC3D750C2D3#103558]
(20) Exchange
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: hashpartitioning(COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, 10), ENSURE_REQUIREMENTS, [plan_id=15595]
(21) Sort
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381 ASC NULLS FIRST, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883 ASC NULLS FIRST, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST], false, 0
(22) Window
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934]
Arguments: [concatwithseparatorudaf(_w0#103934, com.adb.hdh.spark.job.scala.utils.ConcatWithSeparatorUDAF@13270fbd, class[value[0]: string], class[value[0]: string], true, true, 0, 0, None) windowspecdefinition(COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), unboundedfollowing$())) AS COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933], [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883], [COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884 ASC NULLS LAST]
(23) Filter
Input [20]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934, COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933]
Condition : (COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885 <=> 1)
(24) Project
Output [17]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, str_replace(COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933, |, ) AS COL_A805C849_5E36_4B9D_996E_AA54407924E2#104116]
Input [20]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_1D0AC7FB_7DC0_4148_A57C_521D93651C80#103884, COL_16939028_D12C_4AE9_B6D9_4751D50C121A#103885, _w0#103934, COL_0547F461_BDD2_4D85_A674_DAB61BCAFE21#103933]
(25) WriteFiles
Input [17]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#103381, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#103382, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#103383, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#103384, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#103385, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#103386, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#103387, COL_AE628ECA_E5BA_4F07_8939_98F393782191#103388, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#103389, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#103390, COL_A687F590_7636_41E9_B432_F96E84FA5822#103391, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#103392, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#103393, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#103394, COL_46900168_36DE_4076_8267_A418814B0376#103395, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59#103883, COL_A805C849_5E36_4B9D_996E_AA54407924E2#104116]
(26) Execute InsertIntoHadoopFsRelationCommand
Input: []
Arguments: file:/data/output/cache/parquet/datablock/DOCUMENT_TRAITE_3440, false, Parquet, [path=file:///data/output/cache/parquet/datablock/DOCUMENT_TRAITE_3440], Overwrite, [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D, COL_8A9046D2_1D72_45E3_B655_D46E004711DC, COL_A3AD19B8_0E44_4535_990D_3E89D0346083, COL_AE628ECA_E5BA_4F07_8939_98F393782191, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1, COL_A687F590_7636_41E9_B432_F96E84FA5822, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998, COL_46900168_36DE_4076_8267_A418814B0376, COL_8C3C089C_BB84_4C3C_ABBA_C3CED60E9D59, COL_A805C849_5E36_4B9D_996E_AA54407924E2]
(27) AdaptiveSparkPlan
Output: []
Arguments: isFinalPlan=true