adopting dhp-schemas:8.0.1 to support Auhtor's rawAffiliationString(s). Improved graph2hive implementation

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTransformation.scala

@@ -407,10 +407,9 @@ object DataciteToOAFTransformation {
         )
       }
       if (c.affiliation.isDefined)
-        a.setAffiliation(
+        a.setRawAffiliationString(
           c.affiliation.get
             .filter(af => af.nonEmpty)
-            .map(af => OafMapperUtils.field(af, dataInfo))
             .asJava
         )
       a.setRank(idx + 1)

dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/mag/MagDataModel.scala

@@ -313,7 +313,7 @@ case object ConversionUtil {
       if (f.author.DisplayName.isDefined)
         a.setFullname(f.author.DisplayName.get)
       if (f.affiliation != null)
-        a.setAffiliation(List(asField(f.affiliation)).asJava)
+        a.setRawAffiliationString(List(f.affiliation).asJava)
       a.setPid(
         List(
           createSP(
@@ -386,7 +386,7 @@ case object ConversionUtil {
       a.setFullname(f.author.DisplayName.get)
 
       if (f.affiliation != null)
-        a.setAffiliation(List(asField(f.affiliation)).asJava)
+        a.setRawAffiliationString(List(f.affiliation).asJava)
 
       a.setPid(
         List(

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hive/GraphHiveTableImporterJob.java

@@ -9,10 +9,7 @@ import java.util.Optional;
 import org.apache.commons.io.IOUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.MapFunction;
-import org.apache.spark.sql.Dataset;
-import org.apache.spark.sql.Encoders;
-import org.apache.spark.sql.SaveMode;
-import org.apache.spark.sql.SparkSession;
+import org.apache.spark.sql.*;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
@@ -25,8 +22,6 @@ public class GraphHiveTableImporterJob {
 
 	private static final Logger log = LoggerFactory.getLogger(GraphHiveTableImporterJob.class);
 
-	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
-
 	public static void main(String[] args) throws Exception {
 
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
@@ -74,7 +69,12 @@ public class GraphHiveTableImporterJob {
 	private static <T extends Oaf> void loadGraphTable(SparkSession spark, String inputPath, String hiveDbName,
 		Class<T> clazz, int numPartitions) {
 
-		Dataset<String> dataset = spark.read().textFile(inputPath);
+		final Encoder<T> clazzEncoder = Encoders.bean(clazz);
+
+		Dataset<Row> dataset = spark
+				.read()
+				.schema(clazzEncoder.schema())
+				.json(inputPath);
 
 		if (numPartitions > 0) {
 			log.info("repartitioning {} to {} partitions", clazz.getSimpleName(), numPartitions);
@@ -82,7 +82,6 @@ public class GraphHiveTableImporterJob {
 		}
 
 		dataset
-			.map((MapFunction<String, T>) s -> OBJECT_MAPPER.readValue(s, clazz), Encoders.bean(clazz))
 			.write()
 			.mode(SaveMode.Overwrite)
 			.saveAsTable(tableIdentifier(hiveDbName, clazz));

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java

@@ -94,7 +94,7 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
 					author.setFullname(String.format("%s, %s", author.getSurname(), author.getName()));
 				}
 
-				author.setAffiliation(prepareListFields(n, "./*[local-name()='affiliation']", info));
+				author.setRawAffiliationString(prepareListString(n, "./*[local-name()='affiliation']"));
 				author.setPid(preparePids(n, info));
 				author.setRank(pos++);
 				res.add(author);

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/GraphHiveImporterJobTest.java

@@ -73,14 +73,10 @@ public class GraphHiveImporterJobTest {
 		GraphHiveImporterJob
 			.main(
 				new String[] {
-					"-isSparkSessionManaged",
-					Boolean.FALSE.toString(),
-					"-inputPath",
-					getClass().getResource("/eu/dnetlib/dhp/oa/graph/sample").getPath(),
-					"-hiveMetastoreUris",
-					"",
-					"-hiveDbName",
-					dbName
+					"--isSparkSessionManaged", Boolean.FALSE.toString(),
+					"--inputPath", getClass().getResource("/eu/dnetlib/dhp/oa/graph/sample").getPath(),
+					"--hiveMetastoreUris", "",
+					"--hiveDbName", dbName
 				});
 
 		ModelSupport.oafTypes

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java

@@ -406,15 +406,15 @@ class MappersTest {
 		assertEquals("Baracchini", author.get().getSurname());
 		assertEquals("Theo", author.get().getName());
 
-		assertEquals(1, author.get().getAffiliation().size());
-		final Optional<Field<String>> opAff = author
+		assertEquals(1, author.get().getRawAffiliationString().size());
+		final Optional<String> opAff = author
 			.get()
-			.getAffiliation()
+			.getRawAffiliationString()
 			.stream()
 			.findFirst();
 		assertTrue(opAff.isPresent());
-		final Field<String> affiliation = opAff.get();
-		assertEquals("ISTI-CNR", affiliation.getValue());
+		final String affiliation = opAff.get();
+		assertEquals("ISTI-CNR", affiliation);
 
 		assertFalse(d.getSubject().isEmpty());
 		assertFalse(d.getInstance().isEmpty());

pom.xml

@@ -937,7 +937,7 @@
         <commons.logging.version>1.1.3</commons.logging.version>
         <commons-validator.version>1.7</commons-validator.version>
         <dateparser.version>1.0.7</dateparser.version>
-        <dhp-schemas.version>[7.0.1]</dhp-schemas.version>
+        <dhp-schemas.version>[8.0.1]</dhp-schemas.version>
         <dhp.cdh.version>cdh5.9.2</dhp.cdh.version>
         <dhp.commons.lang.version>3.5</dhp.commons.lang.version>
         <dhp.guava.version>11.0.2</dhp.guava.version>