From e487b5544c9c81ea348441a8e4f4456bb1c5a800 Mon Sep 17 00:00:00 2001
From: "miriam.baglioni" <miriam.baglioni@isti.cnr.it>
Date: Wed, 30 Jun 2021 12:57:11 +0200
Subject: [PATCH] added tests for the normalization of the dois

---
 .../dnetlib/doiboost/mag/MAGMappingTest.scala | 51 ++++++++++++++++++-
 1 file changed, 50 insertions(+), 1 deletion(-)

diff --git a/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/mag/MAGMappingTest.scala b/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/mag/MAGMappingTest.scala
index 88b1669f48..7eb50665e2 100644
--- a/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/mag/MAGMappingTest.scala
+++ b/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/mag/MAGMappingTest.scala
@@ -4,7 +4,7 @@ import java.sql.Timestamp
 
 import eu.dnetlib.dhp.schema.oaf.Publication
 import org.apache.htrace.fasterxml.jackson.databind.SerializationFeature
-import org.apache.spark.SparkConf
+import org.apache.spark.{SparkConf, SparkContext}
 import org.apache.spark.api.java.function.MapFunction
 import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
 import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
@@ -62,6 +62,55 @@ class MAGMappingTest {
     logger.debug(description)
 
   }
+  @Test
+  def normalizeDoiTest():Unit = {
+
+    import org.json4s.jackson.Serialization.write
+    import org.json4s.DefaultFormats
+
+    implicit val formats = DefaultFormats
+
+    val conf = new SparkConf().setAppName("test").setMaster("local[2]")
+    val sc = new SparkContext(conf)
+    val spark = SparkSession.builder.config(sc.getConf).getOrCreate()
+    val path = getClass.getResource("magPapers.json").getPath
+
+    import org.apache.spark.sql.Encoders
+    val schema = Encoders.product[MagPapers].schema
+
+    import spark.implicits._
+    val magPapers :Dataset[MagPapers] = spark.read.option("multiline",true).schema(schema).json(path).as[MagPapers]
+    val ret :Dataset[MagPapers] = SparkProcessMAG.getDistinctResults(magPapers)
+    assertTrue(ret.count == 10)
+    ret.take(10).foreach(mp => assertTrue(mp.Doi.equals(mp.Doi.toLowerCase())))
+
+    spark.close()
+  }
+
+  @Test
+  def normalizeDoiTest2():Unit = {
+
+    import org.json4s.jackson.Serialization.write
+    import org.json4s.DefaultFormats
+
+    implicit val formats = DefaultFormats
+
+    val conf = new SparkConf().setAppName("test").setMaster("local[2]")
+    val sc = new SparkContext(conf)
+    val spark = SparkSession.builder.config(sc.getConf).getOrCreate()
+    val path = getClass.getResource("duplicatedMagPapers.json").getPath
+
+    import org.apache.spark.sql.Encoders
+    val schema = Encoders.product[MagPapers].schema
+
+    import spark.implicits._
+    val magPapers :Dataset[MagPapers] = spark.read.option("multiline",true).schema(schema).json(path).as[MagPapers]
+    val ret :Dataset[MagPapers] = SparkProcessMAG.getDistinctResults(magPapers)
+    assertTrue(ret.count == 8)
+    ret.take(8).foreach(mp => assertTrue(mp.Doi.equals(mp.Doi.toLowerCase())))
+    spark.close()
+    //ret.take(8).foreach(mp => println(write(mp)))
+  }
 
 
 }