digraph G {
0 [labelType="html" label="<br><b>CollectLimit</b><br><br>"];
1 [labelType="html" label="<br><b>Project</b><br><br>"];
subgraph cluster2 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n32 ms (9 ms, 23 ms, 23 ms (stage 293.0: task 250))";
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>229 ms (4 ms, 4 ms, 221 ms (stage 294.0: task 251))<br>metadata time: 0 ms<br>size of files read: 9.4 MiB<br>number of output rows: 4,096"];
1->0;
3->1;
4->3;
5->4;
}
6
CollectLimit 1500
Project [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#22634, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#22635, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#22636, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#22637, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#22638, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#22639, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#22640, COL_AE628ECA_E5BA_4F07_8939_98F393782191#22641, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#22642, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#22643, COL_A687F590_7636_41E9_B432_F96E84FA5822#22644, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#22645, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#22646, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#22647, COL_46900168_36DE_4076_8267_A418814B0376#22648, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#22649, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#22756, to_json(str_to_words(COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755), Some(Etc/UTC)) AS COL_37C87C6F_353F_41BB_95A5_184EE9E09EA1#22813]
Project [DOCUMENT_ID_3241#22510 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#22634, METADOCUMENT_ID_3242#22514 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#22635, PATIENT_ID_3243#22516 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#22636, VISIT_ID_3244#22520 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#22637, VISIT_UNIT_ID_3245#22521 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#22638, UPDATED_AT_3246#22519 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#22639, UNIT_3247#22518 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#22640, DELEGATE_UNIT_3248#22509 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#22641, HIERARCHY_UNIT_3249#22513 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#22642, TITLE_3250#22517 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#22643, DOCUMENT_TYPE_3251#22511 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#22644, CREATED_AT_3252#22508 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#22645, BODY_3253#22507 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#22646, AUTHOR_3254#22506 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#22647, PATIENT_AGE_3255#22515 AS COL_46900168_36DE_4076_8267_A418814B0376#22648, FORMAT_3256#22512 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#22649, str_replace_regex(BODY_3253#22507, <p[^>]*>(.*?)<\/p>, ) AS COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755, str_extract_by_regex(str_replace_extend(BODY_3253#22507, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#22756]
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [AUTHOR_3254#22506,BODY_3253#22507,CREATED_AT_3252#22508,DELEGATE_UNIT_3248#22509,DOCUMENT_ID_3241#22510,DOCUMENT_TYPE_3251#22511,FORMAT_3256#22512,HIERARCHY_UNIT_3249#22513,METADOCUMENT_ID_3242#22514,PATIENT_AGE_3255#22515,PATIENT_ID_3243#22516,TITLE_3250#22517,UNIT_3247#22518,UPDATED_AT_3246#22519,VISIT_ID_3244#22520,VISIT_UNIT_ID_3245#22521] 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#22506, BODY_3253#22507, CREATED_AT_3252#22508, DELEGATE_UNIT_3248#22509, DOCUMENT_ID_3241#22510, DOCUMENT_TYPE_3251#22511, FORMAT_3256#22512, HIERARCHY_UNIT_3249#22513, METADOCUMENT_ID_3242#22514, PATIENT_AGE_3255#22515, PATIENT_ID_3243#22516, TITLE_3250#22517, UNIT_3247#22518, UPDATED_AT_3246#22519, VISIT_ID_3244#22520, VISIT_UNIT_ID_3245#22521]
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#22506, BODY_3253#22507, CREATED_AT_3252#22508, DELEGATE_UNIT_3248#22509, DOCUMENT_ID_3241#22510, DOCUMENT_TYPE_3251#22511, FORMAT_3256#22512, HIERARCHY_UNIT_3249#22513, METADOCUMENT_ID_3242#22514, PATIENT_AGE_3255#22515, PATIENT_ID_3243#22516, TITLE_3250#22517, UNIT_3247#22518, UPDATED_AT_3246#22519, VISIT_ID_3244#22520, VISIT_UNIT_ID_3245#22521]
(3) Project [codegen id : 1]
Output [18]: [DOCUMENT_ID_3241#22510 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#22634, METADOCUMENT_ID_3242#22514 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#22635, PATIENT_ID_3243#22516 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#22636, VISIT_ID_3244#22520 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#22637, VISIT_UNIT_ID_3245#22521 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#22638, UPDATED_AT_3246#22519 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#22639, UNIT_3247#22518 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#22640, DELEGATE_UNIT_3248#22509 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#22641, HIERARCHY_UNIT_3249#22513 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#22642, TITLE_3250#22517 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#22643, DOCUMENT_TYPE_3251#22511 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#22644, CREATED_AT_3252#22508 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#22645, BODY_3253#22507 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#22646, AUTHOR_3254#22506 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#22647, PATIENT_AGE_3255#22515 AS COL_46900168_36DE_4076_8267_A418814B0376#22648, FORMAT_3256#22512 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#22649, str_replace_regex(BODY_3253#22507, <p[^>]*>(.*?)<\/p>, ) AS COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755, str_extract_by_regex(str_replace_extend(BODY_3253#22507, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#22756]
Input [16]: [AUTHOR_3254#22506, BODY_3253#22507, CREATED_AT_3252#22508, DELEGATE_UNIT_3248#22509, DOCUMENT_ID_3241#22510, DOCUMENT_TYPE_3251#22511, FORMAT_3256#22512, HIERARCHY_UNIT_3249#22513, METADOCUMENT_ID_3242#22514, PATIENT_AGE_3255#22515, PATIENT_ID_3243#22516, TITLE_3250#22517, UNIT_3247#22518, UPDATED_AT_3246#22519, VISIT_ID_3244#22520, VISIT_UNIT_ID_3245#22521]
(4) Project
Output [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#22634, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#22635, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#22636, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#22637, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#22638, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#22639, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#22640, COL_AE628ECA_E5BA_4F07_8939_98F393782191#22641, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#22642, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#22643, COL_A687F590_7636_41E9_B432_F96E84FA5822#22644, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#22645, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#22646, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#22647, COL_46900168_36DE_4076_8267_A418814B0376#22648, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#22649, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#22756, to_json(str_to_words(COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755), Some(Etc/UTC)) AS COL_37C87C6F_353F_41BB_95A5_184EE9E09EA1#22813]
Input [18]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#22634, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#22635, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#22636, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#22637, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#22638, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#22639, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#22640, COL_AE628ECA_E5BA_4F07_8939_98F393782191#22641, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#22642, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#22643, COL_A687F590_7636_41E9_B432_F96E84FA5822#22644, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#22645, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#22646, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#22647, COL_46900168_36DE_4076_8267_A418814B0376#22648, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#22649, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#22756]
(5) CollectLimit
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#22634, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#22635, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#22636, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#22637, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#22638, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#22639, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#22640, COL_AE628ECA_E5BA_4F07_8939_98F393782191#22641, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#22642, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#22643, COL_A687F590_7636_41E9_B432_F96E84FA5822#22644, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#22645, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#22646, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#22647, COL_46900168_36DE_4076_8267_A418814B0376#22648, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#22649, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#22755, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#22756, COL_37C87C6F_353F_41BB_95A5_184EE9E09EA1#22813]
Arguments: 1500