digraph G {
subgraph cluster0 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n0 ms (0 ms, 0 ms, 0 ms (stage 15.0: task 70))";
1 [labelType="html" label="<br><b>Project</b><br><br>"];
2 [labelType="html" label="<br><b>SerializeFromObject</b><br><br>"];
3 [labelType="html" label="<br><b>MapElements</b><br><br>"];
4 [labelType="html" label="<br><b>DeserializeToObject</b><br><br>"];
5 [labelType="html" label="<br><b>Project</b><br><br>"];
6 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 6"];
7 [labelType="html" label="<b>Scan ExistingRDD Delta Table State #31 - hdlfs://7646b954-15f6-4bdc-91a5-2644c1a43a19.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-dl-stream-service/prp/demand-profile-v3/_delta_log</b><br><br>number of output rows: 9"];
}
2->1;
3->2;
4->3;
5->4;
6->5;
7->6;
}
8
Project [path#753, partitionValues#754, size#755L, modificationTime#756L, dataChange#757, null AS stats#776, tags#759, deletionVector#760, baseRowId#761L, defaultRowCommitVersion#762L, clusteringProvider#763]
SerializeFromObject [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).path, true, false, true) AS path#753, externalmaptocatalyst(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -1), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -1), StringType, ObjectType(class java.lang.String)), true, false, true), lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -2), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -2), StringType, ObjectType(class java.lang.String)), true, false, true), knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).partitionValues) AS partitionValues#754, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).size AS size#755L, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).modificationTime AS modificationTime#756L, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).dataChange AS dataChange#757, externalmaptocatalyst(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -3), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -3), StringType, ObjectType(class java.lang.String)), true, false, true), lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -4), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -4), StringType, ObjectType(class java.lang.String)), true, false, true), knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).tags) AS tags#759, if (isnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector)) null else named_struct(storageType, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).storageType, true, false, true), pathOrInlineDv, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).pathOrInlineDv, true, false, true), offset, unwrapoption(IntegerType, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).offset), sizeInBytes, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).sizeInBytes, cardinality, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).cardinality, maxRowIndex, unwrapoption(LongType, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).maxRowIndex)) AS deletionVector#760, unwrapoption(LongType, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).baseRowId) AS baseRowId#761L, unwrapoption(LongType, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).defaultRowCommitVersion) AS defaultRowCommitVersion#762L, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, unwrapoption(ObjectType(class java.lang.String), knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).clusteringProvider), true, false, true) AS clusteringProvider#763]
MapElements org.apache.spark.sql.Dataset$$Lambda$5811/0x00007f301da515e0@2e0988b3, obj#752: org.apache.spark.sql.delta.actions.AddFile
DeserializeToObject newInstance(class scala.Tuple1), obj#751: scala.Tuple1
Project [add#493]
Filter isnotnull(add#493)
Scan ExistingRDD Delta Table State #31 - hdlfs://7646b954-15f6-4bdc-91a5-2644c1a43a19.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-dl-stream-service/prp/demand-profile-v3/_delta_log[txn#492,add#493,remove#494,metaData#495,protocol#496,cdc#497,checkpointMetadata#498,sidecar#499,domainMetadata#500,commitInfo#501]
WholeStageCodegen (1)
== Physical Plan ==
* Project (7)
+- * SerializeFromObject (6)
+- * MapElements (5)
+- * DeserializeToObject (4)
+- * Project (3)
+- * Filter (2)
+- * Scan ExistingRDD Delta Table State #31 - hdlfs://7646b954-15f6-4bdc-91a5-2644c1a43a19.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-dl-stream-service/prp/demand-profile-v3/_delta_log (1)
(1) Scan ExistingRDD Delta Table State #31 - hdlfs://7646b954-15f6-4bdc-91a5-2644c1a43a19.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-dl-stream-service/prp/demand-profile-v3/_delta_log [codegen id : 1]
Output [10]: [txn#492, add#493, remove#494, metaData#495, protocol#496, cdc#497, checkpointMetadata#498, sidecar#499, domainMetadata#500, commitInfo#501]
Arguments: [txn#492, add#493, remove#494, metaData#495, protocol#496, cdc#497, checkpointMetadata#498, sidecar#499, domainMetadata#500, commitInfo#501], Delta Table State #31 - hdlfs://7646b954-15f6-4bdc-91a5-2644c1a43a19.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-dl-stream-service/prp/demand-profile-v3/_delta_log MapPartitionsRDD[47] at $anonfun$recordDeltaOperationInternal$1 at DatabricksLogging.scala:128, ExistingRDD, UnknownPartitioning(0)
(2) Filter [codegen id : 1]
Input [10]: [txn#492, add#493, remove#494, metaData#495, protocol#496, cdc#497, checkpointMetadata#498, sidecar#499, domainMetadata#500, commitInfo#501]
Condition : isnotnull(add#493)
(3) Project [codegen id : 1]
Output [1]: [add#493]
Input [10]: [txn#492, add#493, remove#494, metaData#495, protocol#496, cdc#497, checkpointMetadata#498, sidecar#499, domainMetadata#500, commitInfo#501]
(4) DeserializeToObject [codegen id : 1]
Input [1]: [add#493]
Arguments: newInstance(class scala.Tuple1), obj#751: scala.Tuple1
(5) MapElements [codegen id : 1]
Input [1]: [obj#751]
Arguments: org.apache.spark.sql.Dataset$$Lambda$5811/0x00007f301da515e0@2e0988b3, obj#752: org.apache.spark.sql.delta.actions.AddFile
(6) SerializeFromObject [codegen id : 1]
Input [1]: [obj#752]
Arguments: [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).path, true, false, true) AS path#753, externalmaptocatalyst(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -1), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -1), StringType, ObjectType(class java.lang.String)), true, false, true), lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -2), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -2), StringType, ObjectType(class java.lang.String)), true, false, true), knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).partitionValues) AS partitionValues#754, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).size AS size#755L, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).modificationTime AS modificationTime#756L, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).dataChange AS dataChange#757, externalmaptocatalyst(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -3), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_key, ObjectType(class java.lang.Object), true, -3), StringType, ObjectType(class java.lang.String)), true, false, true), lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -4), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(ExternalMapToCatalyst_value, ObjectType(class java.lang.Object), true, -4), StringType, ObjectType(class java.lang.String)), true, false, true), knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).tags) AS tags#759, if (isnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector)) null else named_struct(storageType, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).storageType, true, false, true), pathOrInlineDv, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).pathOrInlineDv, true, false, true), offset, unwrapoption(IntegerType, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).offset), sizeInBytes, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).sizeInBytes, cardinality, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).cardinality, maxRowIndex, unwrapoption(LongType, knownnotnull(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).deletionVector).maxRowIndex)) AS deletionVector#760, unwrapoption(LongType, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).baseRowId) AS baseRowId#761L, unwrapoption(LongType, knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).defaultRowCommitVersion) AS defaultRowCommitVersion#762L, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, unwrapoption(ObjectType(class java.lang.String), knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.actions.AddFile, true])).clusteringProvider), true, false, true) AS clusteringProvider#763]
(7) Project [codegen id : 1]
Output [11]: [path#753, partitionValues#754, size#755L, modificationTime#756L, dataChange#757, null AS stats#776, tags#759, deletionVector#760, baseRowId#761L, defaultRowCommitVersion#762L, clusteringProvider#763]
Input [10]: [path#753, partitionValues#754, size#755L, modificationTime#756L, dataChange#757, tags#759, deletionVector#760, baseRowId#761L, defaultRowCommitVersion#762L, clusteringProvider#763]