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))\n14 ms (6 ms, 8 ms, 8 ms (stage 601.0: task 603))";
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>270 ms (2 ms, 5 ms, 263 ms (stage 602.0: task 604))<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#51559, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#51560, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#51561, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#51562, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#51563, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#51564, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#51565, COL_AE628ECA_E5BA_4F07_8939_98F393782191#51566, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#51567, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#51568, COL_A687F590_7636_41E9_B432_F96E84FA5822#51569, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#51570, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#51571, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#51572, COL_46900168_36DE_4076_8267_A418814B0376#51573, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#51574, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591, str_replace_regex(COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591, <[^<>]+>, ) AS COL_291B5D76_C464_449C_833D_1B12D9EFB9F4#51665, to_json(str_to_words(COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591), Some(Etc/UTC)) AS COL_9FC317CC_EE21_4F02_AFAC_D56CF1521310#51666]
Project [DOCUMENT_ID_3241#51435 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#51559, METADOCUMENT_ID_3242#51439 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#51560, PATIENT_ID_3243#51441 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#51561, VISIT_ID_3244#51445 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#51562, VISIT_UNIT_ID_3245#51446 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#51563, UPDATED_AT_3246#51444 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#51564, UNIT_3247#51443 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#51565, DELEGATE_UNIT_3248#51434 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#51566, HIERARCHY_UNIT_3249#51438 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#51567, TITLE_3250#51442 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#51568, DOCUMENT_TYPE_3251#51436 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#51569, CREATED_AT_3252#51433 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#51570, BODY_3253#51432 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#51571, AUTHOR_3254#51431 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#51572, PATIENT_AGE_3255#51440 AS COL_46900168_36DE_4076_8267_A418814B0376#51573, FORMAT_3256#51437 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#51574, str_replace_regex(BODY_3253#51432, <br\s*\/?>, ) AS COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591]
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [AUTHOR_3254#51431,BODY_3253#51432,CREATED_AT_3252#51433,DELEGATE_UNIT_3248#51434,DOCUMENT_ID_3241#51435,DOCUMENT_TYPE_3251#51436,FORMAT_3256#51437,HIERARCHY_UNIT_3249#51438,METADOCUMENT_ID_3242#51439,PATIENT_AGE_3255#51440,PATIENT_ID_3243#51441,TITLE_3250#51442,UNIT_3247#51443,UPDATED_AT_3246#51444,VISIT_ID_3244#51445,VISIT_UNIT_ID_3245#51446] 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#51431, BODY_3253#51432, CREATED_AT_3252#51433, DELEGATE_UNIT_3248#51434, DOCUMENT_ID_3241#51435, DOCUMENT_TYPE_3251#51436, FORMAT_3256#51437, HIERARCHY_UNIT_3249#51438, METADOCUMENT_ID_3242#51439, PATIENT_AGE_3255#51440, PATIENT_ID_3243#51441, TITLE_3250#51442, UNIT_3247#51443, UPDATED_AT_3246#51444, VISIT_ID_3244#51445, VISIT_UNIT_ID_3245#51446]
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#51431, BODY_3253#51432, CREATED_AT_3252#51433, DELEGATE_UNIT_3248#51434, DOCUMENT_ID_3241#51435, DOCUMENT_TYPE_3251#51436, FORMAT_3256#51437, HIERARCHY_UNIT_3249#51438, METADOCUMENT_ID_3242#51439, PATIENT_AGE_3255#51440, PATIENT_ID_3243#51441, TITLE_3250#51442, UNIT_3247#51443, UPDATED_AT_3246#51444, VISIT_ID_3244#51445, VISIT_UNIT_ID_3245#51446]
(3) Project [codegen id : 1]
Output [17]: [DOCUMENT_ID_3241#51435 AS COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#51559, METADOCUMENT_ID_3242#51439 AS COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#51560, PATIENT_ID_3243#51441 AS COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#51561, VISIT_ID_3244#51445 AS COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#51562, VISIT_UNIT_ID_3245#51446 AS COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#51563, UPDATED_AT_3246#51444 AS COL_8A9046D2_1D72_45E3_B655_D46E004711DC#51564, UNIT_3247#51443 AS COL_A3AD19B8_0E44_4535_990D_3E89D0346083#51565, DELEGATE_UNIT_3248#51434 AS COL_AE628ECA_E5BA_4F07_8939_98F393782191#51566, HIERARCHY_UNIT_3249#51438 AS COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#51567, TITLE_3250#51442 AS COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#51568, DOCUMENT_TYPE_3251#51436 AS COL_A687F590_7636_41E9_B432_F96E84FA5822#51569, CREATED_AT_3252#51433 AS COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#51570, BODY_3253#51432 AS COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#51571, AUTHOR_3254#51431 AS COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#51572, PATIENT_AGE_3255#51440 AS COL_46900168_36DE_4076_8267_A418814B0376#51573, FORMAT_3256#51437 AS COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#51574, str_replace_regex(BODY_3253#51432, <br\s*\/?>, ) AS COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591]
Input [16]: [AUTHOR_3254#51431, BODY_3253#51432, CREATED_AT_3252#51433, DELEGATE_UNIT_3248#51434, DOCUMENT_ID_3241#51435, DOCUMENT_TYPE_3251#51436, FORMAT_3256#51437, HIERARCHY_UNIT_3249#51438, METADOCUMENT_ID_3242#51439, PATIENT_AGE_3255#51440, PATIENT_ID_3243#51441, TITLE_3250#51442, UNIT_3247#51443, UPDATED_AT_3246#51444, VISIT_ID_3244#51445, VISIT_UNIT_ID_3245#51446]
(4) Project
Output [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#51559, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#51560, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#51561, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#51562, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#51563, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#51564, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#51565, COL_AE628ECA_E5BA_4F07_8939_98F393782191#51566, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#51567, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#51568, COL_A687F590_7636_41E9_B432_F96E84FA5822#51569, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#51570, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#51571, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#51572, COL_46900168_36DE_4076_8267_A418814B0376#51573, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#51574, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591, str_replace_regex(COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591, <[^<>]+>, ) AS COL_291B5D76_C464_449C_833D_1B12D9EFB9F4#51665, to_json(str_to_words(COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591), Some(Etc/UTC)) AS COL_9FC317CC_EE21_4F02_AFAC_D56CF1521310#51666]
Input [17]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#51559, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#51560, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#51561, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#51562, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#51563, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#51564, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#51565, COL_AE628ECA_E5BA_4F07_8939_98F393782191#51566, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#51567, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#51568, COL_A687F590_7636_41E9_B432_F96E84FA5822#51569, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#51570, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#51571, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#51572, COL_46900168_36DE_4076_8267_A418814B0376#51573, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#51574, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591]
(5) CollectLimit
Input [19]: [COL_B8C4154A_9C1F_4379_B2D0_37CB2E2E8163#51559, COL_E64A43C0_92EB_4340_A5E8_C7C27526AB67#51560, COL_93CB3020_C35B_4048_83FD_5071BBD0FA14#51561, COL_7C0A6459_9870_4E69_A193_D12DCD19B4D8#51562, COL_8FADC0CC_2246_48BF_96B6_37B8BA1E1C0D#51563, COL_8A9046D2_1D72_45E3_B655_D46E004711DC#51564, COL_A3AD19B8_0E44_4535_990D_3E89D0346083#51565, COL_AE628ECA_E5BA_4F07_8939_98F393782191#51566, COL_BB50D21B_057C_4291_B5BF_6CE5E982EC4F#51567, COL_70DA6BEE_221D_4064_99F0_A228C6EA03D1#51568, COL_A687F590_7636_41E9_B432_F96E84FA5822#51569, COL_B885B9B6_22DC_43A3_A9BA_7E5273012413#51570, COL_B4024986_B57D_48FD_A06D_AA53298E7CAF#51571, COL_2B0D0A0B_E8F4_4E84_AD0F_67F5167E0998#51572, COL_46900168_36DE_4076_8267_A418814B0376#51573, COL_E95AE405_48D5_4107_B391_1BC4DED5B99A#51574, COL_145BD05D_B40A_4119_ACB5_8A24ACDCE160#51591, COL_291B5D76_C464_449C_833D_1B12D9EFB9F4#51665, COL_9FC317CC_EE21_4F02_AFAC_D56CF1521310#51666]
Arguments: 1500