digraph G {
0 [labelType="html" label="<br><b>CollectLimit</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n6 ms (3 ms, 3 ms, 3 ms (stage 454.0: task 455))";
2 [labelType="html" label="<br><b>Project</b><br><br>"];
3 [labelType="html" label="<br><b>Project</b><br><br>"];
4 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 4,096<br>number of input batches: 1"];
}
5 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>160 ms (2 ms, 3 ms, 155 ms (stage 455.0: task 456))<br>metadata time: 0 ms<br>size of files read: 9.4 MiB<br>number of output rows: 4,096"];
2->0;
3->2;
4->3;
5->4;
}
6
CollectLimit 1500
Project [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#39582, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#39583, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#39584, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#39585, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#39586, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#39587, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#39588, COL_AE628ECA_E5BA_4F07_8939_98F393782191#39589, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#39590, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#39591, COL_A687F590_7636_41E9_B432_F96E84FA5822#39592, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#39593, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#39594, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#39595, COL_46900168_36DE_4076_8267_A418814B0376#39596, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#39597, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#39614, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#39632, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651, str_replace_regex(COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651, <[^<>]+>, ) AS COL_291B5D76_C464_449C_833D_1B12D9EFB9F4#39711]
Project [DOCUMENT_ID_3241#39458 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#39582, METADOCUMENT_ID_3242#39462 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#39583, PATIENT_ID_3243#39464 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#39584, VISIT_ID_3244#39468 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#39585, VISIT_UNIT_ID_3245#39469 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#39586, UPDATED_AT_3246#39467 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#39587, UNIT_3247#39466 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#39588, DELEGATE_UNIT_3248#39457 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#39589, HIERARCHY_UNIT_3249#39461 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#39590, TITLE_3250#39465 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#39591, DOCUMENT_TYPE_3251#39459 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#39592, CREATED_AT_3252#39456 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#39593, BODY_3253#39455 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#39594, AUTHOR_3254#39454 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#39595, PATIENT_AGE_3255#39463 AS COL_46900168_36DE_4076_8267_A418814B0376#39596, FORMAT_3256#39460 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#39597, str_replace_regex(BODY_3253#39455, <br\s*\/?>, ) AS COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#39614, str_extract_by_regex(str_replace_extend(BODY_3253#39455, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#39632, str_replace_regex(BODY_3253#39455, <br\s*\/?>, ) AS COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651]
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [AUTHOR_3254#39454,BODY_3253#39455,CREATED_AT_3252#39456,DELEGATE_UNIT_3248#39457,DOCUMENT_ID_3241#39458,DOCUMENT_TYPE_3251#39459,FORMAT_3256#39460,HIERARCHY_UNIT_3249#39461,METADOCUMENT_ID_3242#39462,PATIENT_AGE_3255#39463,PATIENT_ID_3243#39464,TITLE_3250#39465,UNIT_3247#39466,UPDATED_AT_3246#39467,VISIT_ID_3244#39468,VISIT_UNIT_ID_3245#39469] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/uet/DOCUMENT_3240], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<AUTHOR_3254:string,BODY_3253:string,CREATED_AT_3252:timestamp,DELEGATE_UNIT_3248:string,DO...
== Physical Plan ==
CollectLimit (5)
+- * Project (4)
+- * Project (3)
+- * ColumnarToRow (2)
+- Scan parquet (1)
(1) Scan parquet
Output [16]: [AUTHOR_3254#39454, BODY_3253#39455, CREATED_AT_3252#39456, DELEGATE_UNIT_3248#39457, DOCUMENT_ID_3241#39458, DOCUMENT_TYPE_3251#39459, FORMAT_3256#39460, HIERARCHY_UNIT_3249#39461, METADOCUMENT_ID_3242#39462, PATIENT_AGE_3255#39463, PATIENT_ID_3243#39464, TITLE_3250#39465, UNIT_3247#39466, UPDATED_AT_3246#39467, VISIT_ID_3244#39468, VISIT_UNIT_ID_3245#39469]
Batched: true
Location: InMemoryFileIndex [file:/data/output/cache/parquet/uet/DOCUMENT_3240]
ReadSchema: struct<AUTHOR_3254:string,BODY_3253:string,CREATED_AT_3252:timestamp,DELEGATE_UNIT_3248:string,DOCUMENT_ID_3241:string,DOCUMENT_TYPE_3251:string,FORMAT_3256: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 [16]: [AUTHOR_3254#39454, BODY_3253#39455, CREATED_AT_3252#39456, DELEGATE_UNIT_3248#39457, DOCUMENT_ID_3241#39458, DOCUMENT_TYPE_3251#39459, FORMAT_3256#39460, HIERARCHY_UNIT_3249#39461, METADOCUMENT_ID_3242#39462, PATIENT_AGE_3255#39463, PATIENT_ID_3243#39464, TITLE_3250#39465, UNIT_3247#39466, UPDATED_AT_3246#39467, VISIT_ID_3244#39468, VISIT_UNIT_ID_3245#39469]
(3) Project [codegen id : 1]
Output [19]: [DOCUMENT_ID_3241#39458 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#39582, METADOCUMENT_ID_3242#39462 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#39583, PATIENT_ID_3243#39464 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#39584, VISIT_ID_3244#39468 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#39585, VISIT_UNIT_ID_3245#39469 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#39586, UPDATED_AT_3246#39467 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#39587, UNIT_3247#39466 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#39588, DELEGATE_UNIT_3248#39457 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#39589, HIERARCHY_UNIT_3249#39461 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#39590, TITLE_3250#39465 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#39591, DOCUMENT_TYPE_3251#39459 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#39592, CREATED_AT_3252#39456 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#39593, BODY_3253#39455 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#39594, AUTHOR_3254#39454 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#39595, PATIENT_AGE_3255#39463 AS COL_46900168_36DE_4076_8267_A418814B0376#39596, FORMAT_3256#39460 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#39597, str_replace_regex(BODY_3253#39455, <br\s*\/?>, ) AS COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#39614, str_extract_by_regex(str_replace_extend(BODY_3253#39455, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#39632, str_replace_regex(BODY_3253#39455, <br\s*\/?>, ) AS COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651]
Input [16]: [AUTHOR_3254#39454, BODY_3253#39455, CREATED_AT_3252#39456, DELEGATE_UNIT_3248#39457, DOCUMENT_ID_3241#39458, DOCUMENT_TYPE_3251#39459, FORMAT_3256#39460, HIERARCHY_UNIT_3249#39461, METADOCUMENT_ID_3242#39462, PATIENT_AGE_3255#39463, PATIENT_ID_3243#39464, TITLE_3250#39465, UNIT_3247#39466, UPDATED_AT_3246#39467, VISIT_ID_3244#39468, VISIT_UNIT_ID_3245#39469]
(4) Project [codegen id : 1]
Output [20]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#39582, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#39583, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#39584, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#39585, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#39586, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#39587, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#39588, COL_AE628ECA_E5BA_4F07_8939_98F393782191#39589, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#39590, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#39591, COL_A687F590_7636_41E9_B432_F96E84FA5822#39592, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#39593, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#39594, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#39595, COL_46900168_36DE_4076_8267_A418814B0376#39596, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#39597, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#39614, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#39632, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651, str_replace_regex(COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651, <[^<>]+>, ) AS COL_291B5D76_C464_449C_833D_1B12D9EFB9F4#39711]
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#39582, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#39583, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#39584, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#39585, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#39586, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#39587, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#39588, COL_AE628ECA_E5BA_4F07_8939_98F393782191#39589, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#39590, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#39591, COL_A687F590_7636_41E9_B432_F96E84FA5822#39592, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#39593, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#39594, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#39595, COL_46900168_36DE_4076_8267_A418814B0376#39596, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#39597, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#39614, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#39632, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651]
(5) CollectLimit
Input [20]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#39582, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#39583, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#39584, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#39585, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#39586, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#39587, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#39588, COL_AE628ECA_E5BA_4F07_8939_98F393782191#39589, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#39590, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#39591, COL_A687F590_7636_41E9_B432_F96E84FA5822#39592, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#39593, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#39594, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#39595, COL_46900168_36DE_4076_8267_A418814B0376#39596, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#39597, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#39614, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#39632, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#39651, COL_291B5D76_C464_449C_833D_1B12D9EFB9F4#39711]
Arguments: 1500