From aa7b8fd014f8b1a3855330806efa40cec1fc11d6 Mon Sep 17 00:00:00 2001
From: Giambattista Bloisi <giambattista.bloisi@openaire.eu>
Date: Mon, 21 Oct 2024 18:05:01 +0200
Subject: [PATCH] Use workingDir parameter for temporary data of ORCID
 enrichment

---
 .../enrich/orcid/enrich_graph_orcid_parameters.json  |  6 ++++++
 .../orcid/SparkEnrichGraphWithOrcidAuthors.scala     | 12 +++++++-----
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/enrich_graph_orcid_parameters.json b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/enrich_graph_orcid_parameters.json
index 765c0e8ff8..772e1381f5 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/enrich_graph_orcid_parameters.json
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/enrich_graph_orcid_parameters.json
@@ -22,5 +22,11 @@
     "paramLongName": "targetPath",
     "paramDescription": "the output path of the graph enriched",
     "paramRequired": true
+  },
+  {
+    "paramName": "wp",
+    "paramLongName": "workingDir",
+    "paramDescription": "the working dir",
+    "paramRequired": true
   }
 ]
\ No newline at end of file
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/SparkEnrichGraphWithOrcidAuthors.scala b/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/SparkEnrichGraphWithOrcidAuthors.scala
index 0824c2a71e..847a5f090f 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/SparkEnrichGraphWithOrcidAuthors.scala
+++ b/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/SparkEnrichGraphWithOrcidAuthors.scala
@@ -47,13 +47,15 @@ class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String]
     log.info(s"orcidPath is '$orcidPath'")
     val targetPath = parser.get("targetPath")
     log.info(s"targetPath is '$targetPath'")
+    val workingDir = parser.get("workingDir")
+    log.info(s"targetPath is '$workingDir'")
 
-    createTemporaryData(graphPath, orcidPath, targetPath)
-    analisys(targetPath)
-    generateGraph(graphPath, targetPath)
+    createTemporaryData(graphPath, orcidPath, workingDir)
+    analisys(workingDir)
+    generateGraph(graphPath, workingDir, targetPath)
   }
 
-  private def generateGraph(graphPath: String, targetPath: String): Unit = {
+  private def generateGraph(graphPath: String, workingDir: String, targetPath: String): Unit = {
 
     ModelSupport.entityTypes.asScala
       .filter(e => ModelSupport.isResult(e._1))
@@ -63,7 +65,7 @@ class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String]
 
         val matched = spark.read
           .schema(Encoders.bean(classOf[ORCIDAuthorEnricherResult]).schema)
-          .parquet(s"${targetPath}/${resultType}_matched")
+          .parquet(s"${workingDir}/${resultType}_matched")
           .selectExpr("id", "enriched_author")
 
         spark.read