From 16ae3c9ccfefd313870618e508451250193b8278 Mon Sep 17 00:00:00 2001 From: Sandro La Bruzzo Date: Thu, 30 Jul 2020 09:25:32 +0200 Subject: [PATCH] updated changing in the workflow of provision in the phase of aggregation. Removed serialization in JSON RDD and used spark Dataset --- .../eu/dnetlib/dhp/sx/graph/SparkSplitOafTODLIEntities.scala | 5 +++++ .../java/eu/dnetlib/dhp/sx/graph/SparkXMLToOAFDataset.scala | 5 +++++ 2 files changed, 10 insertions(+) create mode 100644 dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkSplitOafTODLIEntities.scala create mode 100644 dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkXMLToOAFDataset.scala diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkSplitOafTODLIEntities.scala b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkSplitOafTODLIEntities.scala new file mode 100644 index 000000000..be1e43963 --- /dev/null +++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkSplitOafTODLIEntities.scala @@ -0,0 +1,5 @@ +package eu.dnetlib.dhp.sx.graph + +object SparkSplitOafTODLIEntities { + +} diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkXMLToOAFDataset.scala b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkXMLToOAFDataset.scala new file mode 100644 index 000000000..848b23253 --- /dev/null +++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkXMLToOAFDataset.scala @@ -0,0 +1,5 @@ +package eu.dnetlib.dhp.sx.graph + +object SparkXMLToOAFDataset { + +}