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 298.0: task 258))";
2 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 1,505"];
3 [labelType="html" label="<br><b>Project</b><br><br>"];
4 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 17"];
5 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 4,096<br>number of input batches: 1"];
}
6 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>246 ms (3 ms, 3 ms, 240 ms (stage 299.0: task 259))<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->5;
}
7
CollectLimit 1500
Generate explode(COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#23486), [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#23364, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#23365, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#23366, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#23367, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#23368, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#23369, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#23370, COL_AE628ECA_E5BA_4F07_8939_98F393782191#23371, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#23372, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#23373, COL_A687F590_7636_41E9_B432_F96E84FA5822#23374, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#23375, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#23376, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#23377, COL_46900168_36DE_4076_8267_A418814B0376#23378, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#23379, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#23485], false, [COL_A504A8EC_44DA_47A8_BC01_8F3D6A00E326#23506]
Project [DOCUMENT_ID_3241#23240 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#23364, METADOCUMENT_ID_3242#23244 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#23365, PATIENT_ID_3243#23246 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#23366, VISIT_ID_3244#23250 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#23367, VISIT_UNIT_ID_3245#23251 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#23368, UPDATED_AT_3246#23249 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#23369, UNIT_3247#23248 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#23370, DELEGATE_UNIT_3248#23239 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#23371, HIERARCHY_UNIT_3249#23243 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#23372, TITLE_3250#23247 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#23373, DOCUMENT_TYPE_3251#23241 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#23374, CREATED_AT_3252#23238 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#23375, BODY_3253#23237 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#23376, AUTHOR_3254#23236 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#23377, PATIENT_AGE_3255#23245 AS COL_46900168_36DE_4076_8267_A418814B0376#23378, FORMAT_3256#23242 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#23379, str_replace_regex(BODY_3253#23237, <p[^>]*>(.*?)<\/p>, ) AS COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#23485, str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#23486]
Filter ((size(str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>), true) > 0) AND isnotnull(str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>)))
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [AUTHOR_3254#23236,BODY_3253#23237,CREATED_AT_3252#23238,DELEGATE_UNIT_3248#23239,DOCUMENT_ID_3241#23240,DOCUMENT_TYPE_3251#23241,FORMAT_3256#23242,HIERARCHY_UNIT_3249#23243,METADOCUMENT_ID_3242#23244,PATIENT_AGE_3255#23245,PATIENT_ID_3243#23246,TITLE_3250#23247,UNIT_3247#23248,UPDATED_AT_3246#23249,VISIT_ID_3244#23250,VISIT_UNIT_ID_3245#23251] Batched: true, DataFilters: [(size(str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\..., 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 (6)
+- * Generate (5)
+- * Project (4)
+- * Filter (3)
+- * ColumnarToRow (2)
+- Scan parquet (1)
(1) Scan parquet
Output [16]: [AUTHOR_3254#23236, BODY_3253#23237, CREATED_AT_3252#23238, DELEGATE_UNIT_3248#23239, DOCUMENT_ID_3241#23240, DOCUMENT_TYPE_3251#23241, FORMAT_3256#23242, HIERARCHY_UNIT_3249#23243, METADOCUMENT_ID_3242#23244, PATIENT_AGE_3255#23245, PATIENT_ID_3243#23246, TITLE_3250#23247, UNIT_3247#23248, UPDATED_AT_3246#23249, VISIT_ID_3244#23250, VISIT_UNIT_ID_3245#23251]
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#23236, BODY_3253#23237, CREATED_AT_3252#23238, DELEGATE_UNIT_3248#23239, DOCUMENT_ID_3241#23240, DOCUMENT_TYPE_3251#23241, FORMAT_3256#23242, HIERARCHY_UNIT_3249#23243, METADOCUMENT_ID_3242#23244, PATIENT_AGE_3255#23245, PATIENT_ID_3243#23246, TITLE_3250#23247, UNIT_3247#23248, UPDATED_AT_3246#23249, VISIT_ID_3244#23250, VISIT_UNIT_ID_3245#23251]
(3) Filter [codegen id : 1]
Input [16]: [AUTHOR_3254#23236, BODY_3253#23237, CREATED_AT_3252#23238, DELEGATE_UNIT_3248#23239, DOCUMENT_ID_3241#23240, DOCUMENT_TYPE_3251#23241, FORMAT_3256#23242, HIERARCHY_UNIT_3249#23243, METADOCUMENT_ID_3242#23244, PATIENT_AGE_3255#23245, PATIENT_ID_3243#23246, TITLE_3250#23247, UNIT_3247#23248, UPDATED_AT_3246#23249, VISIT_ID_3244#23250, VISIT_UNIT_ID_3245#23251]
Condition : ((size(str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>), true) > 0) AND isnotnull(str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>)))
(4) Project [codegen id : 1]
Output [18]: [DOCUMENT_ID_3241#23240 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#23364, METADOCUMENT_ID_3242#23244 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#23365, PATIENT_ID_3243#23246 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#23366, VISIT_ID_3244#23250 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#23367, VISIT_UNIT_ID_3245#23251 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#23368, UPDATED_AT_3246#23249 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#23369, UNIT_3247#23248 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#23370, DELEGATE_UNIT_3248#23239 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#23371, HIERARCHY_UNIT_3249#23243 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#23372, TITLE_3250#23247 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#23373, DOCUMENT_TYPE_3251#23241 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#23374, CREATED_AT_3252#23238 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#23375, BODY_3253#23237 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#23376, AUTHOR_3254#23236 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#23377, PATIENT_AGE_3255#23245 AS COL_46900168_36DE_4076_8267_A418814B0376#23378, FORMAT_3256#23242 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#23379, str_replace_regex(BODY_3253#23237, <p[^>]*>(.*?)<\/p>, ) AS COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#23485, str_extract_by_regex(str_replace_extend(BODY_3253#23237, [</p>], [</p>.]), <p[^>]*>(.*?)<\/p>) AS COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#23486]
Input [16]: [AUTHOR_3254#23236, BODY_3253#23237, CREATED_AT_3252#23238, DELEGATE_UNIT_3248#23239, DOCUMENT_ID_3241#23240, DOCUMENT_TYPE_3251#23241, FORMAT_3256#23242, HIERARCHY_UNIT_3249#23243, METADOCUMENT_ID_3242#23244, PATIENT_AGE_3255#23245, PATIENT_ID_3243#23246, TITLE_3250#23247, UNIT_3247#23248, UPDATED_AT_3246#23249, VISIT_ID_3244#23250, VISIT_UNIT_ID_3245#23251]
(5) Generate [codegen id : 1]
Input [18]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#23364, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#23365, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#23366, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#23367, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#23368, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#23369, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#23370, COL_AE628ECA_E5BA_4F07_8939_98F393782191#23371, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#23372, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#23373, COL_A687F590_7636_41E9_B432_F96E84FA5822#23374, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#23375, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#23376, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#23377, COL_46900168_36DE_4076_8267_A418814B0376#23378, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#23379, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#23485, COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#23486]
Arguments: explode(COL_CBB80C89_C2E2_4CAE_9E96_1384D3814850#23486), [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#23364, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#23365, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#23366, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#23367, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#23368, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#23369, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#23370, COL_AE628ECA_E5BA_4F07_8939_98F393782191#23371, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#23372, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#23373, COL_A687F590_7636_41E9_B432_F96E84FA5822#23374, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#23375, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#23376, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#23377, COL_46900168_36DE_4076_8267_A418814B0376#23378, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#23379, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#23485], false, [COL_A504A8EC_44DA_47A8_BC01_8F3D6A00E326#23506]
(6) CollectLimit
Input [18]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#23364, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#23365, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#23366, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#23367, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#23368, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#23369, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#23370, COL_AE628ECA_E5BA_4F07_8939_98F393782191#23371, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#23372, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#23373, COL_A687F590_7636_41E9_B432_F96E84FA5822#23374, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#23375, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#23376, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#23377, COL_46900168_36DE_4076_8267_A418814B0376#23378, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#23379, COL_AECD41D8_DB05_475D_9E5C_621A9BFFB95E#23485, COL_A504A8EC_44DA_47A8_BC01_8F3D6A00E326#23506]
Arguments: 1500