Merge branch 'beta' into 8232-mdstore-synch-improve

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/usagestats/SparkAtomicActionUsageJob.java

@@ -8,13 +8,13 @@ import java.io.Serializable;
 import java.util.Arrays;
 import java.util.List;
 import java.util.Optional;
-
+import eu.dnetlib.dhp.schema.oaf.*;
 import org.apache.commons.io.IOUtils;
 import org.apache.hadoop.io.Text;
 import org.apache.hadoop.mapred.SequenceFileOutputFormat;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.MapFunction;
-import org.apache.spark.api.java.function.MapGroupsFunction;
+
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Encoders;
 import org.apache.spark.sql.SaveMode;
@@ -28,9 +28,6 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import eu.dnetlib.dhp.schema.action.AtomicAction;
 import eu.dnetlib.dhp.schema.common.ModelConstants;
-import eu.dnetlib.dhp.schema.oaf.DataInfo;
-import eu.dnetlib.dhp.schema.oaf.Measure;
-import eu.dnetlib.dhp.schema.oaf.Result;
 import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
 import scala.Tuple2;
 
@@ -76,41 +73,38 @@ public class SparkAtomicActionUsageJob implements Serializable {
 			isSparkSessionManaged,
 			spark -> {
 				removeOutputDir(spark, outputPath);
-				prepareResults(dbname, spark, workingPath);
+				prepareData(dbname, spark, workingPath + "/usageDb", "usage_stats", "result_id");
+				prepareData(dbname, spark, workingPath + "/projectDb", "project_stats", "id");
+				prepareData(dbname, spark, workingPath + "/datasourceDb", "datasource_stats", "repositor_id");
 				writeActionSet(spark, workingPath, outputPath);
 			});
 	}
 
-	public static void prepareResults(String db, SparkSession spark, String workingPath) {
+	private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName, String attribute_name) {
 		spark
-			.sql(
+				.sql(
-				"Select result_id, downloads, views " +
+						"Select " + attribute_name + " as id, sum(downloads) as downloads, sum(views) as views " +
-					"from " + db + ".usage_stats")
+								"from " + dbname + "." + tableName +
-			.as(Encoders.bean(UsageStatsModel.class))
+						"group by " + attribute_name)
-			.write()
+				.as(Encoders.bean(UsageStatsModel.class))
-			.mode(SaveMode.Overwrite)
+				.write()
-			.option("compression", "gzip")
+				.mode(SaveMode.Overwrite)
-			.json(workingPath);
+				.option("compression", "gzip")
+				.json(workingPath);
 	}
 
+
+
 	public static void writeActionSet(SparkSession spark, String inputPath, String outputPath) {
-		readPath(spark, inputPath, UsageStatsModel.class)
+		getFinalIndicatorsResult(spark, inputPath+ "/usageDb").
-			.groupByKey((MapFunction<UsageStatsModel, String>) us -> us.getResult_id(), Encoders.STRING())
+		toJavaRDD().
-			.mapGroups((MapGroupsFunction<String, UsageStatsModel, Result>) (k, it) -> {
+				map(p -> new AtomicAction(p.getClass(),p))
-				UsageStatsModel first = it.next();
+						.union(getFinalIndicatorsProject(spark, inputPath + "/projectDb")
-				it.forEachRemaining(us -> {
+								.toJavaRDD()
-					first.setDownloads(first.getDownloads() + us.getDownloads());
+								.map(p -> new AtomicAction(p.getClass(), p )))
-					first.setViews(first.getViews() + us.getViews());
+								.union(getFinalIndicatorsDatasource(spark, inputPath + "/datasourceDb")
-				});
+										.toJavaRDD()
-
+										.map(p -> new AtomicAction(p.getClass(), p)))
-				Result res = new Result();
-				res.setId("50|" + k);
-
-				res.setMeasures(getMeasure(first.getDownloads(), first.getViews()));
-				return res;
-			}, Encoders.bean(Result.class))
-			.toJavaRDD()
-			.map(p -> new AtomicAction(p.getClass(), p))
 			.mapToPair(
 				aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
 					new Text(OBJECT_MAPPER.writeValueAsString(aa))))
@@ -118,6 +112,41 @@ public class SparkAtomicActionUsageJob implements Serializable {
 
 	}
 
+	private static Dataset<Result> getFinalIndicatorsResult(SparkSession spark, String inputPath) {
+
+		return readPath(spark, inputPath, UsageStatsModel.class)
+				.map((MapFunction<UsageStatsModel, Result>) usm -> {
+					Result r = new Result();
+					r.setId("50|" + usm.getId());
+					r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
+					return r;
+				}, Encoders.bean(Result.class));
+	}
+
+	private static Dataset<Project> getFinalIndicatorsProject(SparkSession spark, String inputPath) {
+
+		return readPath(spark, inputPath, UsageStatsModel.class)
+				.map((MapFunction<UsageStatsModel, Project>) usm -> {
+					Project r = new Project();
+					r.setId("40|" + usm.getId());
+					r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
+					return r;
+				}, Encoders.bean(Project.class));
+	}
+
+	private static Dataset<Datasource> getFinalIndicatorsDatasource(SparkSession spark, String inputPath) {
+
+		return readPath(spark, inputPath, UsageStatsModel.class)
+				.map((MapFunction<UsageStatsModel, Datasource>) usm -> {
+					Datasource r = new Datasource();
+					r.setId("10|" + usm.getId());
+					r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
+					return r;
+				}, Encoders.bean(Datasource.class));
+	}
+
+
+
 	private static List<Measure> getMeasure(Long downloads, Long views) {
 		DataInfo dataInfo = OafMapperUtils
 			.dataInfo(

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/usagestats/UsageStatsModel.java

@@ -4,16 +4,16 @@ package eu.dnetlib.dhp.actionmanager.usagestats;
 import java.io.Serializable;
 
 public class UsageStatsModel implements Serializable {
-	private String result_id;
+	private String id;
 	private Long downloads;
 	private Long views;
 
-	public String getResult_id() {
+	public String getId() {
-		return result_id;
+		return id;
 	}
 
-	public void setResult_id(String result_id) {
+	public void setId(String id) {
-		this.result_id = result_id;
+		this.id = id;
 	}
 
 	public Long getDownloads() {

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/usagestats/oozie_app/workflow.xml

@@ -89,7 +89,7 @@
             <arg>--hive_metastore_uris</arg><arg>${hiveMetastoreUris}</arg>
             <arg>--outputPath</arg><arg>${outputPath}</arg>
             <arg>--usagestatsdb</arg><arg>${usagestatsdb}</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/usageDb</arg>
+            <arg>--workingPath</arg><arg>${workingDir}</arg>
         </spark>
         <ok to="End"/>
         <error to="Kill"/>

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/usagestats/SparkAtomicActionCountJobTest.java

@@ -8,6 +8,7 @@ import java.nio.file.Files;
 import java.nio.file.Path;
 import java.util.stream.Collectors;
 
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
 import org.apache.commons.io.FileUtils;
 import org.apache.hadoop.io.Text;
 import org.apache.spark.SparkConf;
@@ -68,24 +69,26 @@ public class SparkAtomicActionCountJobTest {
 	@Test
 	void testMatch() {
 		String usageScoresPath = getClass()
-			.getResource("/eu/dnetlib/dhp/actionmanager/usagestats/usagestatsdb")
+			.getResource("/eu/dnetlib/dhp/actionmanager/usagestats")
 			.getPath();
 
 		SparkAtomicActionUsageJob.writeActionSet(spark, usageScoresPath, workingDir.toString() + "/actionSet");
 
 		final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
 
-		JavaRDD<Result> tmp = sc
+		JavaRDD<AtomicAction> tmp = sc
 			.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
-			.map(usm -> OBJECT_MAPPER.readValue(usm._2.getBytes(), AtomicAction.class))
+			.map(usm -> OBJECT_MAPPER.readValue(usm._2.getBytes(), AtomicAction.class));
-			.map(aa -> (Result) aa.getPayload());
+			//.map(aa -> (Result) aa.getPayload());
 
-		Assertions.assertEquals(9, tmp.count());
+		Assertions.assertEquals(9,tmp.filter(aa -> ((OafEntity) aa.getPayload()).getId().startsWith("50|")).count());
+		Assertions.assertEquals(9,tmp.filter(aa -> ((OafEntity) aa.getPayload()).getId().startsWith("10|")).count());
+		Assertions.assertEquals(9,tmp.filter(aa -> ((OafEntity) aa.getPayload()).getId().startsWith("40|")).count());
 
-		tmp.foreach(r -> Assertions.assertEquals(2, r.getMeasures().size()));
+		tmp.foreach(r -> Assertions.assertEquals(2, ((OafEntity)r.getPayload()).getMeasures().size()));
 		tmp
 			.foreach(
-				r -> r
+				r -> ((OafEntity)r.getPayload())
 					.getMeasures()
 					.stream()
 					.forEach(
@@ -95,14 +98,14 @@ public class SparkAtomicActionCountJobTest {
 							.forEach(u -> Assertions.assertFalse(u.getDataInfo().getDeletedbyinference()))));
 		tmp
 			.foreach(
-				r -> r
+				r -> ((OafEntity)r.getPayload())
 					.getMeasures()
 					.stream()
 					.forEach(
 						m -> m.getUnit().stream().forEach(u -> Assertions.assertTrue(u.getDataInfo().getInferred()))));
 		tmp
 			.foreach(
-				r -> r
+				r -> ((OafEntity)r.getPayload())
 					.getMeasures()
 					.stream()
 					.forEach(
@@ -113,7 +116,7 @@ public class SparkAtomicActionCountJobTest {
 
 		tmp
 			.foreach(
-				r -> r
+				r -> ((OafEntity)r.getPayload())
 					.getMeasures()
 					.stream()
 					.forEach(
@@ -127,7 +130,7 @@ public class SparkAtomicActionCountJobTest {
 										u.getDataInfo().getProvenanceaction().getClassid()))));
 		tmp
 			.foreach(
-				r -> r
+				r -> ((OafEntity)r.getPayload())
 					.getMeasures()
 					.stream()
 					.forEach(
@@ -142,7 +145,7 @@ public class SparkAtomicActionCountJobTest {
 
 		tmp
 			.foreach(
-				r -> r
+				r -> ((OafEntity)r.getPayload())
 					.getMeasures()
 					.stream()
 					.forEach(
@@ -157,12 +160,13 @@ public class SparkAtomicActionCountJobTest {
 
 		Assertions
 			.assertEquals(
-				1, tmp.filter(r -> r.getId().equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6")).count());
+				1, tmp.filter(r -> ((OafEntity)r.getPayload()).getId().equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6")).count());
 
 		Assertions
 			.assertEquals(
 				"0",
 				tmp
+						.map(r -> ((OafEntity)r.getPayload()))
 					.filter(r -> r.getId().equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6"))
 					.collect()
 					.get(0)
@@ -178,7 +182,8 @@ public class SparkAtomicActionCountJobTest {
 			.assertEquals(
 				"5",
 				tmp
-					.filter(r -> r.getId().equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6"))
+		.map(r -> ((OafEntity)r.getPayload()))
+				.filter(r -> r.getId().equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6"))
 					.collect()
 					.get(0)
 					.getMeasures()
@@ -194,7 +199,8 @@ public class SparkAtomicActionCountJobTest {
 			.assertEquals(
 				"0",
 				tmp
-					.filter(r -> r.getId().equals("50|doi_________::17eda2ff77407538fbe5d3d719b9d1c0"))
+						.map(r -> ((OafEntity)r.getPayload()))
+						.filter(r -> r.getId().equals("50|doi_________::17eda2ff77407538fbe5d3d719b9d1c0"))
 					.collect()
 					.get(0)
 					.getMeasures()
@@ -209,7 +215,8 @@ public class SparkAtomicActionCountJobTest {
 			.assertEquals(
 				"1",
 				tmp
-					.filter(r -> r.getId().equals("50|doi_________::17eda2ff77407538fbe5d3d719b9d1c0"))
+						.map(r -> ((OafEntity)r.getPayload()))
+						.filter(r -> r.getId().equals("50|doi_________::17eda2ff77407538fbe5d3d719b9d1c0"))
 					.collect()
 					.get(0)
 					.getMeasures()
@@ -225,7 +232,8 @@ public class SparkAtomicActionCountJobTest {
 			.assertEquals(
 				"2",
 				tmp
-					.filter(r -> r.getId().equals("50|doi_________::3085e4c6e051378ca6157fe7f0430c1f"))
+						.map(r -> ((OafEntity)r.getPayload()))
+						.filter(r -> r.getId().equals("50|doi_________::3085e4c6e051378ca6157fe7f0430c1f"))
 					.collect()
 					.get(0)
 					.getMeasures()
@@ -240,7 +248,8 @@ public class SparkAtomicActionCountJobTest {
 			.assertEquals(
 				"6",
 				tmp
-					.filter(r -> r.getId().equals("50|doi_________::3085e4c6e051378ca6157fe7f0430c1f"))
+						.map(r -> ((OafEntity)r.getPayload()))
+						.filter(r -> r.getId().equals("50|doi_________::3085e4c6e051378ca6157fe7f0430c1f"))
 					.collect()
 					.get(0)
 					.getMeasures()
@@ -251,6 +260,206 @@ public class SparkAtomicActionCountJobTest {
 					.getUnit()
 					.get(0)
 					.getValue());
+
+
+		Assertions
+				.assertEquals(
+						"0",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("40|f1__________::53575dc69e9ace947e02d47ecd54a7a6"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("downloads"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+		Assertions
+				.assertEquals(
+						"5",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("40|f1__________::53575dc69e9ace947e02d47ecd54a7a6"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("views"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+
+		Assertions
+				.assertEquals(
+						"0",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("40|f11_________::17eda2ff77407538fbe5d3d719b9d1c0"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("downloads"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+		Assertions
+				.assertEquals(
+						"1",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("40|f11_________::17eda2ff77407538fbe5d3d719b9d1c0"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("views"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+
+		Assertions
+				.assertEquals(
+						"2",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("40|f12_________::3085e4c6e051378ca6157fe7f0430c1f"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("downloads"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+		Assertions
+				.assertEquals(
+						"6",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("40|f12_________::3085e4c6e051378ca6157fe7f0430c1f"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("views"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+
+
+		Assertions
+				.assertEquals(
+						"0",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("10|d1__________::53575dc69e9ace947e02d47ecd54a7a6"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("downloads"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+		Assertions
+				.assertEquals(
+						"5",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("10|d1__________::53575dc69e9ace947e02d47ecd54a7a6"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("views"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+
+		Assertions
+				.assertEquals(
+						"0",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("10|d11_________::17eda2ff77407538fbe5d3d719b9d1c0"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("downloads"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+		Assertions
+				.assertEquals(
+						"1",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("10|d11_________::17eda2ff77407538fbe5d3d719b9d1c0"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("views"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+
+		Assertions
+				.assertEquals(
+						"2",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("10|d12_________::3085e4c6e051378ca6157fe7f0430c1f"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("downloads"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
+		Assertions
+				.assertEquals(
+						"6",
+						tmp
+								.map(r -> ((OafEntity)r.getPayload()))
+								.filter(r -> r.getId().equals("10|d12_________::3085e4c6e051378ca6157fe7f0430c1f"))
+								.collect()
+								.get(0)
+								.getMeasures()
+								.stream()
+								.filter(m -> m.getId().equals("views"))
+								.collect(Collectors.toList())
+								.get(0)
+								.getUnit()
+								.get(0)
+								.getValue());
 	}
 
 }

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/datasourceDb

@@ -0,0 +1,9 @@
+{"id":"d1__________::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":5}
+{"id":"d11_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
+{"id":"d11_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
+{"id":"d11_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
+{"id":"d12_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":6}
+{"id":"d12_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
+{"id":"d12_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
+{"id":"d13_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":10}
+{"id":"d13_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/datasourceDb_old

@@ -0,0 +1,12 @@
+{"id":"d1__________::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":4}
+{"id":"d1__________::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":1}
+{"id":"d11_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
+{"id":"d11_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
+{"id":"d11_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
+{"id":"d12_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":3}
+{"id":"d12_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":0,"views":3}
+{"id":"d12_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
+{"id":"d12_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
+{"id":"d13_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":8}
+{"id":"d13_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":0,"views":2}
+{"id":"d13_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/projectDb

@@ -0,0 +1,9 @@
+{"id":"f1__________::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":5}
+{"id":"f11_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
+{"id":"f11_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
+{"id":"f11_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
+{"id":"f12_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":6}
+{"id":"f12_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
+{"id":"f12_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
+{"id":"f13_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":10}
+{"id":"f13_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/projectDb_old

@@ -0,0 +1,12 @@
+{"id":"f1__________::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":4}
+{"id":"f1__________::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":1}
+{"id":"f11_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
+{"id":"f11_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
+{"id":"f11_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
+{"id":"f12_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":3}
+{"id":"f12_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":0,"views":3}
+{"id":"f12_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
+{"id":"f12_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
+{"id":"f13_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":8}
+{"id":"f13_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":0,"views":2}
+{"id":"f13_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/usageDb

@@ -0,0 +1,9 @@
+{"id":"dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":5}
+{"id":"doi_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
+{"id":"doi_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
+{"id":"doi_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
+{"id":"doi_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":6}
+{"id":"doi_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
+{"id":"doi_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
+{"id":"doi_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":10}
+{"id":"doi_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/usageDb_old

@@ -0,0 +1,12 @@
+{"id":"dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":4}
+{"id":"dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":1}
+{"id":"doi_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
+{"id":"doi_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
+{"id":"doi_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
+{"id":"doi_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":3}
+{"id":"doi_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":0,"views":3}
+{"id":"doi_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
+{"id":"doi_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
+{"id":"doi_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":8}
+{"id":"doi_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":0,"views":2}
+{"id":"doi_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/usagestats/usagestatsdb

@@ -1,12 +0,0 @@
-{"result_id":"dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":4}
-{"result_id":"dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6","downloads":0,"views":1}
-{"result_id":"doi_________::17eda2ff77407538fbe5d3d719b9d1c0","downloads":0,"views":1}
-{"result_id":"doi_________::1d4dc08605fd0a2be1105d30c63bfea1","downloads":1,"views":3}
-{"result_id":"doi_________::2e3527822854ca9816f6dfea5bff61a8","downloads":1,"views":1}
-{"result_id":"doi_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":2,"views":3}
-{"result_id":"doi_________::3085e4c6e051378ca6157fe7f0430c1f","downloads":0,"views":3}
-{"result_id":"doi_________::33f710e6dd30cc5e67e35b371ddc33cf","downloads":0,"views":1}
-{"result_id":"doi_________::39738ebf10654732dd3a7af9f24655f8","downloads":1,"views":3}
-{"result_id":"doi_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":1,"views":8}
-{"result_id":"doi_________::3c3b65f07c1a06c7894397eda1d11bbf","downloads":0,"views":2}
-{"result_id":"doi_________::4938a71a884dd481d329657aa543b850","downloads":0,"views":3}

dhp-workflows/dhp-broker-events/src/main/java/eu/dnetlib/dhp/broker/oa/util/SubscriptionUtils.java

@@ -37,12 +37,24 @@ public class SubscriptionUtils {
 	}
 
 	public static boolean verifyDateRange(final long date, final String min, final String max) {
+
+		long from = 0;
+		long to = Long.MAX_VALUE;
+
 		try {
-			return date >= DateUtils.parseDate(min, "yyyy-MM-dd").getTime()
+			from = min != null ? DateUtils.parseDate(min, "yyyy-MM-dd").getTime() : 0;
-				&& date < DateUtils.parseDate(max, "yyyy-MM-dd").getTime() + ONE_DAY;
 		} catch (final ParseException e) {
-			return false;
+			from = 0;
 		}
+
+		try {
+			to = max != null ? DateUtils.parseDate(max, "yyyy-MM-dd").getTime() + ONE_DAY : Long.MAX_VALUE;
+		} catch (final ParseException e) {
+			to = Long.MAX_VALUE;
+		}
+
+		return date >= from && date < to;
+
 	}
 
 	public static boolean verifyExact(final String s1, final String s2) {

dhp-workflows/dhp-broker-events/src/test/java/eu/dnetlib/dhp/broker/oa/util/SubscriptionUtilsTest.java

@@ -41,6 +41,18 @@ public class SubscriptionUtilsTest {
 
 		assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", "2011-01-01"));
 		assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", "2021-01-01"));
+
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", "NULL"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", null));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "NULL", "2011-01-01"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, null, "2011-01-01"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "NULL", "NULL"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, null, null));
+
+		assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", null));
+		assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", "NULL"));
+		assertFalse(SubscriptionUtils.verifyDateRange(date, null, "2005-01-01"));
+		assertFalse(SubscriptionUtils.verifyDateRange(date, "NULL", "2005-01-01"));
 	}
 
 	@Test

dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala

@@ -370,10 +370,50 @@ case object Crossref2Oaf {
       case dataset: Dataset         => convertDataset(dataset)
     }
 
+    val doisReference: List[String] = for {
+      JObject(reference_json)          <- json \ "reference"
+      JField("DOI", JString(doi_json)) <- reference_json
+    } yield doi_json
+
+    if (doisReference != null && doisReference.nonEmpty) {
+      val citation_relations: List[Relation] = generateCitationRelations(doisReference, result)
+      resultList = resultList ::: citation_relations
+    }
     resultList = resultList ::: List(result)
     resultList
   }
 
+  private def createCiteRelation(source: Result, targetPid: String, targetPidType: String): List[Relation] = {
+
+    val targetId = IdentifierFactory.idFromPid("50", targetPidType, targetPid, true)
+
+    val from = new Relation
+    from.setSource(source.getId)
+    from.setTarget(targetId)
+    from.setRelType(ModelConstants.RESULT_RESULT)
+    from.setRelClass(ModelConstants.CITES)
+    from.setSubRelType(ModelConstants.CITATION)
+    from.setCollectedfrom(source.getCollectedfrom)
+    from.setDataInfo(source.getDataInfo)
+    from.setLastupdatetimestamp(source.getLastupdatetimestamp)
+
+    val to = new Relation
+    to.setTarget(source.getId)
+    to.setSource(targetId)
+    to.setRelType(ModelConstants.RESULT_RESULT)
+    to.setRelClass(ModelConstants.IS_CITED_BY)
+    to.setSubRelType(ModelConstants.CITATION)
+    to.setCollectedfrom(source.getCollectedfrom)
+    to.setDataInfo(source.getDataInfo)
+    to.setLastupdatetimestamp(source.getLastupdatetimestamp)
+
+    List(from, to)
+  }
+
+  def generateCitationRelations(dois: List[String], result: Result): List[Relation] = {
+    dois.flatMap(d => createCiteRelation(result, d, "doi"))
+  }
+
   def mappingFunderToRelations(
     funders: List[mappingFunder],
     sourceId: String,
@@ -446,6 +486,7 @@ case object Crossref2Oaf {
             case "10.13039/501100000781" =>
               generateSimpleRelationFromAward(funder, "corda_______", extractECAward)
               generateSimpleRelationFromAward(funder, "corda__h2020", extractECAward)
+              generateSimpleRelationFromAward(funder, "corda_____he", extractECAward)
             case "10.13039/100000001"    => generateSimpleRelationFromAward(funder, "nsf_________", a => a)
             case "10.13039/501100001665" => generateSimpleRelationFromAward(funder, "anr_________", a => a)
             case "10.13039/501100002341" => generateSimpleRelationFromAward(funder, "aka_________", a => a)
@@ -487,6 +528,34 @@ case object Crossref2Oaf {
               val targetId = getProjectId("wt__________", "1e5e62235d094afd01cd56e65112fc63")
               queue += generateRelation(sourceId, targetId, ModelConstants.IS_PRODUCED_BY)
               queue += generateRelation(targetId, sourceId, ModelConstants.PRODUCES)
+            //ASAP
+            case "10.13039/100018231" => generateSimpleRelationFromAward(funder, "asap________", a => a)
+            //CHIST-ERA
+            case "10.13039/501100001942" =>
+              val targetId = getProjectId("chistera____", "1e5e62235d094afd01cd56e65112fc63")
+              queue += generateRelation(sourceId, targetId, ModelConstants.IS_PRODUCED_BY)
+              queue += generateRelation(targetId, sourceId, ModelConstants.PRODUCES)
+            //HE
+            case "10.13039/100018693" | "10.13039/100018694" | "10.13039/100019188" | "10.13039/100019180" |
+                "10.13039/100018695" | "10.13039/100019185" | "10.13039/100019186" | "10.13039/100019187" =>
+              generateSimpleRelationFromAward(funder, "corda_____he", extractECAward)
+            //FCT
+            case "10.13039/501100001871" =>
+              generateSimpleRelationFromAward(funder, "fct_________", extractECAward)
+            //NHMRC
+            case "10.13039/501100000925" =>
+              generateSimpleRelationFromAward(funder, "mhmrc_______", extractECAward)
+            //NIH
+            case "10.13039/100000002" =>
+              generateSimpleRelationFromAward(funder, "nih_________", extractECAward)
+            //NWO
+            case "10.13039/501100003246" =>
+              generateSimpleRelationFromAward(funder, "nwo_________", extractECAward)
+            //UKRI
+            case "10.13039/100014013" | "10.13039/501100000267" | "10.13039/501100000268" | "10.13039/501100000269" |
+                "10.13039/501100000266" | "10.13039/501100006041" | "10.13039/501100000265" | "10.13039/501100000270" |
+                "10.13039/501100013589" | "10.13039/501100000271" =>
+              generateSimpleRelationFromAward(funder, "nwo_________", extractECAward)
 
             case _ => logger.debug("no match for " + funder.DOI.get)
 

dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala

@@ -1,9 +1,14 @@
 package eu.dnetlib.dhp.doiboost.crossref
 
+import eu.dnetlib.dhp.schema.common.ModelConstants
 import eu.dnetlib.dhp.schema.oaf._
 import eu.dnetlib.dhp.utils.DHPUtils
 import eu.dnetlib.doiboost.crossref.Crossref2Oaf
 import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
+import org.json4s
+import org.json4s.JsonAST.{JField, JObject, JString}
+import org.json4s.{DefaultFormats, JValue}
+import org.json4s.jackson.JsonMethods
 import org.junit.jupiter.api.Assertions._
 import org.junit.jupiter.api.Test
 import org.slf4j.{Logger, LoggerFactory}
@@ -109,6 +114,47 @@ class CrossrefMappingTest {
 
   }
 
+  private def parseJson(input: String): JValue = {
+    implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
+    lazy val json: json4s.JValue = JsonMethods.parse(input)
+
+    json
+  }
+
+  @Test
+  def testCitationRelations(): Unit = {
+    val json = Source
+      .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_embargo.json"))
+      .mkString
+
+    assertNotNull(json)
+    assertFalse(json.isEmpty)
+
+    val result: List[Oaf] = Crossref2Oaf.convert(json)
+
+    assertTrue(result.nonEmpty)
+
+    val j = parseJson(json)
+
+    val doisReference: List[String] = for {
+      JObject(reference_json)          <- j \ "reference"
+      JField("DOI", JString(doi_json)) <- reference_json
+    } yield doi_json
+
+    val relationList: List[Relation] = result
+      .filter(s => s.isInstanceOf[Relation])
+      .map(r => r.asInstanceOf[Relation])
+      .filter(r => r.getSubRelType.equalsIgnoreCase(ModelConstants.CITATION))
+
+    assertNotNull(relationList)
+    assertFalse(relationList.isEmpty)
+
+    assertEquals(doisReference.size * 2, relationList.size)
+
+    mapper.getSerializationConfig.enable(SerializationConfig.Feature.INDENT_OUTPUT)
+    relationList.foreach(p => println(mapper.writeValueAsString(p)))
+  }
+
   @Test
   def testEmptyTitle(): Unit = {
     val json = Source

dhp-workflows/dhp-monitor-update/pom.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <artifactId>dhp-workflows</artifactId>
+        <groupId>eu.dnetlib.dhp</groupId>
+        <version>1.2.4-SNAPSHOT</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <artifactId>dhp-monitor-update</artifactId>
+    <dependencies>
+        <dependency>
+            <groupId>org.apache.spark</groupId>
+            <artifactId>spark-core_2.11</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.spark</groupId>
+            <artifactId>spark-sql_2.11</artifactId>
+        </dependency>
+    </dependencies>
+	<build>
+		<plugins>
+			<plugin>
+				<groupId>pl.project13.maven</groupId>
+				<artifactId>git-commit-id-plugin</artifactId>
+                <version>2.1.11</version>
+				<configuration>
+					<failOnNoGitDirectory>false</failOnNoGitDirectory>
+				</configuration>
+			</plugin>
+		</plugins>
+	</build>
+</project>

dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/config-default.xml

@@ -0,0 +1,34 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>${jobTracker}</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>${nameNode}</value>
+    </property>
+    <property>
+        <name>oozie.use.system.libpath</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>oozie.action.sharelib.for.spark</name>
+        <value>spark2</value>
+    </property>
+    <property>
+        <name>hive_metastore_uris</name>
+        <value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
+    </property>
+    <property>
+        <name>hive_jdbc_url</name>
+        <value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000/;UseNativeQuery=1;?spark.executor.memory=19166291558;spark.yarn.executor.memoryOverhead=3225;spark.driver.memory=11596411699;spark.yarn.driver.memoryOverhead=1228</value>
+    </property>
+	<property>
+		<name>oozie.wf.workflow.notification.url</name>
+		<value>{serviceUrl}/v1/oozieNotification/jobUpdate?jobId=$jobId%26status=$status</value>
+	</property>
+    <property>
+        <name>stats_tool_api_url</name>
+        <value>${stats_tool_api_url}</value>
+    </property>
+</configuration>

dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/monitor.sh

@@ -0,0 +1,18 @@
+export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
+export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
+if ! [ -L $link_folder ]
+then
+    rm -Rf "$link_folder"
+    ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
+fi
+
+export SOURCE=$1
+export TARGET=$2
+export SCRIPT_PATH=$3
+
+echo "Getting file from " $3
+hdfs dfs -copyToLocal $3
+
+echo "Updating monitor database"
+cat createMonitorDB.sql | sed s/SOURCE/$1/g | sed s/TARGET/$2/g1 | impala-shell -f -
+echo "Impala shell finished"

dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/scripts/createMonitorDB.sql

@@ -0,0 +1,146 @@
+DROP TABLE IF EXISTS TARGET.result_new;
+
+create table TARGET.result_new as
+    select distinct * from (
+        select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in (
+--              'openorgs____::b8b8ca674452579f3f593d9f5e557483',  -- University College Cork
+--             'openorgs____::38d7097854736583dde879d12dacafca'	-- Brown University
+                'openorgs____::57784c9e047e826fefdb1ef816120d92' --Arts et Métiers ParisTech
+        ) )) foo;
+
+COMPUTE STATS TARGET.result_new;
+
+INSERT INTO TARGET.result select * from TARGET.result_new;
+COMPUTE STATS TARGET.result;
+
+INSERT INTO TARGET.result_citations select * from TARGET.result_citations orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_citations;
+
+INSERT INTO TARGET.result_references_oc select * from TARGET.result_references_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_references_oc;
+
+INSERT INTO TARGET.result_citations_oc select * from TARGET.result_citations_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_citations_oc;
+
+INSERT INTO TARGET.result_classifications select * from TARGET.result_classifications orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_classifications;
+
+INSERT INTO TARGET.result_apc select * from TARGET.result_apc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_apc;
+
+INSERT INTO TARGET.result_concepts select * from TARGET.result_concepts orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_concepts;
+
+INSERT INTO TARGET.result_datasources select * from TARGET.result_datasources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_datasources;
+
+INSERT INTO TARGET.result_fundercount select * from TARGET.result_fundercount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_fundercount;
+
+INSERT INTO TARGET.result_gold select * from TARGET.result_gold orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_gold;
+
+INSERT INTO TARGET.result_greenoa select * from TARGET.result_greenoa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_greenoa;
+
+INSERT INTO TARGET.result_languages select * from TARGET.result_languages orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_languages;
+
+INSERT INTO TARGET.result_licenses select * from TARGET.result_licenses orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_licenses;
+
+INSERT INTO TARGET.result_oids select * from TARGET.result_oids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_oids;
+
+INSERT INTO TARGET.result_organization select * from TARGET.result_organization orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_organization;
+
+INSERT INTO TARGET.result_peerreviewed select * from TARGET.result_peerreviewed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_peerreviewed;
+
+INSERT INTO TARGET.result_pids select * from TARGET.result_pids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_pids;
+
+INSERT INTO TARGET.result_projectcount select * from TARGET.result_projectcount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_projectcount;
+
+INSERT INTO TARGET.result_projects select * from TARGET.result_projects orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_projects;
+
+INSERT INTO TARGET.result_refereed select * from TARGET.result_refereed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_refereed;
+
+INSERT INTO TARGET.result_sources select * from TARGET.result_sources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_sources;
+
+INSERT INTO TARGET.result_topics select * from TARGET.result_topics orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_topics;
+
+INSERT INTO TARGET.result_fos select * from TARGET.result_fos orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.result_fos;
+
+create view TARGET.foo1 as select * from TARGET.result_result rr where rr.source in (select id from TARGET.result_new);
+create view TARGET.foo2 as select * from TARGET.result_result rr where rr.target in (select id from TARGET.result_new);
+INSERT INTO TARGET.result_result select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou;
+drop view TARGET.foo1;
+drop view TARGET.foo2;
+COMPUTE STATS TARGET.result_result;
+
+-- indicators
+-- Sprint 1 ----
+INSERT INTO TARGET.indi_pub_green_oa select * from TARGET.indi_pub_green_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_green_oa;
+INSERT INTO TARGET.indi_pub_grey_lit select * from TARGET.indi_pub_grey_lit orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_grey_lit;
+INSERT INTO TARGET.indi_pub_doi_from_crossref select * from TARGET.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_doi_from_crossref;
+-- Sprint 2 ----
+INSERT INTO TARGET.indi_result_has_cc_licence select * from TARGET.indi_result_has_cc_licence orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_result_has_cc_licence;
+INSERT INTO TARGET.indi_result_has_cc_licence_url select * from TARGET.indi_result_has_cc_licence_url orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_result_has_cc_licence_url;
+INSERT INTO TARGET.indi_pub_has_abstract select * from TARGET.indi_pub_has_abstract orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_has_abstract;
+INSERT INTO TARGET.indi_result_with_orcid select * from TARGET.indi_result_with_orcid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_result_with_orcid;
+---- Sprint 3 ----
+INSERT INTO TARGET.indi_funded_result_with_fundref select * from TARGET.indi_funded_result_with_fundref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_funded_result_with_fundref;
+---- Sprint 4 ----
+INSERT INTO TARGET.indi_pub_diamond select * from TARGET.indi_pub_diamond orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_diamond;
+INSERT INTO TARGET.indi_pub_in_transformative select * from TARGET.indi_pub_in_transformative orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_in_transformative;
+INSERT INTO TARGET.indi_pub_closed_other_open select * from TARGET.indi_pub_closed_other_open orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_closed_other_open;
+---- Sprint 5 ----
+INSERT INTO TARGET.indi_result_no_of_copies select * from TARGET.indi_result_no_of_copies orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_result_no_of_copies;
+---- Sprint 6 ----
+INSERT INTO TARGET.indi_pub_hybrid_oa_with_cc select * from TARGET.indi_pub_hybrid_oa_with_cc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_hybrid_oa_with_cc;
+INSERT INTO TARGET.indi_pub_downloads select * from TARGET.indi_pub_downloads orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
+COMPUTE STATS TARGET.indi_pub_downloads;
+INSERT INTO TARGET.indi_pub_downloads_datasource select * from TARGET.indi_pub_downloads_datasource orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
+COMPUTE STATS TARGET.indi_pub_downloads_datasource;
+INSERT INTO TARGET.indi_pub_downloads_year select * from TARGET.indi_pub_downloads_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
+COMPUTE STATS TARGET.indi_pub_downloads_year;
+INSERT INTO TARGET.indi_pub_downloads_datasource_year select * from TARGET.indi_pub_downloads_datasource_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
+COMPUTE STATS TARGET.indi_pub_downloads_datasource_year;
+---- Sprint 7 ----
+INSERT INTO TARGET.indi_pub_gold_oa select * from TARGET.indi_pub_gold_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_gold_oa;
+INSERT INTO TARGET.indi_pub_hybrid select * from TARGET.indi_pub_hybrid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_hybrid;
+
+INSERT INTO TARGET.indi_pub_has_preprint select * from TARGET.indi_pub_has_preprint orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_has_preprint;
+INSERT INTO TARGET.indi_pub_in_subscribed select * from TARGET.indi_pub_in_subscribed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_pub_in_subscribed;
+INSERT INTO TARGET.indi_result_with_pid select * from TARGET.indi_result_with_pid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
+COMPUTE STATS TARGET.indi_result_with_pid;
+--create table TARGET.indi_datasets_gold_oa stored as parquet as select * from SOURCE.indi_datasets_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
+--compute stats TARGET.indi_datasets_gold_oa;
+--create table TARGET.indi_software_gold_oa stored as parquet as select * from SOURCE.indi_software_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
+--compute stats TARGET.indi_software_gold_oa;
+DROP TABLE TARGET.result_new;

dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/workflow.xml

@@ -0,0 +1,77 @@
+<workflow-app name="Monitor DB" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>stats_db_name</name>
+            <description>the target stats database name</description>
+        </property>
+        <property>
+            <name>stats_db_shadow_name</name>
+            <description>the name of the shadow schema</description>
+        </property>
+        <property>
+            <name>monitor_db_name</name>
+            <description>the target monitor db name</description>
+        </property>
+        <property>
+            <name>monitor_db_shadow_name</name>
+            <description>the name of the shadow monitor db</description>
+        </property>
+        <property>
+            <name>stats_tool_api_url</name>
+            <description>The url of the API of the stats tool. Is used to trigger the cache update.</description>
+        </property>
+        <property>
+            <name>hive_metastore_uris</name>
+            <description>hive server metastore URIs</description>
+        </property>
+        <property>
+            <name>hive_jdbc_url</name>
+            <description>hive server jdbc url</description>
+        </property>
+        <property>
+            <name>hive_timeout</name>
+            <description>the time period, in seconds, after which Hive fails a transaction if a Hive client has not sent a hearbeat. The default value is 300 seconds.</description>
+        </property>
+        <property>
+            <name>context_api_url</name>
+            <description>the base url of the context api (https://services.openaire.eu/openaire)</description>
+        </property>
+    </parameters>
+
+    <global>
+        <job-tracker>${jobTracker}</job-tracker>
+        <name-node>${nameNode}</name-node>
+        <configuration>
+            <property>
+                <name>hive.metastore.uris</name>
+                <value>${hive_metastore_uris}</value>
+            </property>
+            <property>
+            	<name>hive.txn.timeout</name>
+            	<value>${hive_timeout}</value>
+            </property>
+        </configuration>
+    </global>
+
+    <start to="Step1-createMonitorDB"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="Step1-createMonitorDB">
+        <shell xmlns="uri:oozie:shell-action:0.1">
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <exec>monitor.sh</exec>
+            <argument>${stats_db_name}</argument>
+            <argument>${monitor_db_name}</argument>
+            <argument>${wf:appPath()}/scripts/createMonitorDB.sql</argument>
+            <file>monitor.sh</file>
+        </shell>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15_5.sql

@@ -30,11 +30,16 @@ from rcount
 group by rcount.pid;
 
 create view ${stats_db_name}.rndexpenditure as select * from stats_ext.rndexpediture;
+create view ${stats_db_name}.rndgdpexpenditure as select * from stats_ext.rndgdpexpenditure;
+create view ${stats_db_name}.doctoratestudents as select * from stats_ext.doctoratestudents;
+create view ${stats_db_name}.totalresearchers as select * from stats_ext.totalresearchers;
+create view ${stats_db_name}.totalresearchersft as select * from stats_ext.totalresearchersft;
+create view ${stats_db_name}.hrrst as select * from stats_ext.hrrst;
 
 create table ${stats_db_name}.result_instance stored as parquet as
 select distinct r.*
 from (
-         select substr(r.id, 4) as id, inst.accessright.classname as accessright, substr(inst.collectedfrom.key, 4) as collectedfrom,
+         select substr(r.id, 4) as id, inst.accessright.classname as accessright, inst.accessright.openaccessroute as accessright_uw, substr(inst.collectedfrom.key, 4) as collectedfrom,
                 substr(inst.hostedby.key, 4) as hostedby, inst.dateofacceptance.value as dateofacceptance, inst.license.value as license, p.qualifier.classname as pidtype, p.value as pid
          from ${openaire_db_name}.result r lateral view explode(r.instance) instances as inst lateral view explode(inst.pid) pids as p) r
 join ${stats_db_name}.result res on res.id=r.id;

dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql

@@ -10,6 +10,11 @@ create view if not exists TARGET.creation_date as select * from SOURCE.creation_
 create view if not exists TARGET.funder as select * from SOURCE.funder;
 create view if not exists TARGET.fundref as select * from SOURCE.fundref;
 create view if not exists TARGET.rndexpenditure as select * from SOURCE.rndexpediture;
+create view if not exists TARGET.rndgdpexpenditure as select * from SOURCE.rndgdpexpenditure;
+create view if not exists TARGET.doctoratestudents as select * from SOURCE.doctoratestudents;
+create view if not exists TARGET.totalresearchers as select * from SOURCE.totalresearchers;
+create view if not exists TARGET.totalresearchersft as select * from SOURCE.totalresearchersft;
+create view if not exists TARGET.hrrst as select * from SOURCE.hrrst;
 
 create table TARGET.result stored as parquet as
     select distinct * from (
@@ -50,8 +55,16 @@ create table TARGET.result stored as parquet as
              'openorgs____::1698a2eb1885ef8adb5a4a969e745ad3', -- École des Ponts ParisTech
              'openorgs____::e15adb13c4dadd49de4d35c39b5da93a',  -- Nanyang Technological University
              'openorgs____::4b34103bde246228fcd837f5f1bf4212',  -- Autonomous University of Barcelona
-             'openorgs____::72ec75fcfc4e0df1a76dc4c49007fceb'	-- McMaster University
+             'openorgs____::72ec75fcfc4e0df1a76dc4c49007fceb',	-- McMaster University
-        ) )) foo;
+             'openorgs____::51c7fc556e46381734a25a6fbc3fd398',	-- University of Modena and Reggio Emilia
+             'openorgs____::235d7f9ad18ecd7e6dc62ea4990cb9db',	-- Bilkent University
+             'openorgs____::31f2fa9e05b49d4cf40a19c3fed8eb06',	-- Saints Cyril and Methodius University of Skopje
+             'openorgs____::db7686f30f22cbe73a4fde872ce812a6', -- University of Milan
+             'openorgs____::b8b8ca674452579f3f593d9f5e557483',  -- University College Cork
+             'openorgs____::38d7097854736583dde879d12dacafca',	-- Brown University
+             'openorgs____::57784c9e047e826fefdb1ef816120d92',  --Arts et Métiers ParisTech
+             'openorgs____::2530baca8a15936ba2e3297f2bce2e7e'	-- University of Cape Town
+        )))  foo;
 compute stats TARGET.result;
 
 create table TARGET.result_citations stored as parquet as select * from SOURCE.result_citations orig where exists (select 1 from TARGET.result r where r.id=orig.id);

dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml

@@ -70,7 +70,40 @@
         </configuration>
     </global>
 
-    <start to="Step1"/>
+    <start to="resume_from"/>
+
+    <decision name="resume_from">
+        <switch>
+            <case to="Step1">${wf:conf('resumeFrom') eq 'Step1'}</case>
+            <case to="Step2">${wf:conf('resumeFrom') eq 'Step2'}</case>
+            <case to="Step3">${wf:conf('resumeFrom') eq 'Step3'}</case>
+            <case to="Step4">${wf:conf('resumeFrom') eq 'Step4'}</case>
+            <case to="Step5">${wf:conf('resumeFrom') eq 'Step5'}</case>
+            <case to="Step6">${wf:conf('resumeFrom') eq 'Step6'}</case>
+            <case to="Step7">${wf:conf('resumeFrom') eq 'Step7'}</case>
+            <case to="Step8">${wf:conf('resumeFrom') eq 'Step8'}</case>
+            <case to="Step9">${wf:conf('resumeFrom') eq 'Step9'}</case>
+            <case to="Step10">${wf:conf('resumeFrom') eq 'Step10'}</case>
+            <case to="Step11">${wf:conf('resumeFrom') eq 'Step11'}</case>
+            <case to="Step12">${wf:conf('resumeFrom') eq 'Step12'}</case>
+            <case to="Step13">${wf:conf('resumeFrom') eq 'Step13'}</case>
+            <case to="Step14">${wf:conf('resumeFrom') eq 'Step14'}</case>
+            <case to="Step15">${wf:conf('resumeFrom') eq 'Step15'}</case>
+            <case to="Step15_5">${wf:conf('resumeFrom') eq 'Step15_5'}</case>
+            <case to="Contexts">${wf:conf('resumeFrom') eq 'Contexts'}</case>
+            <case to="Step16-createIndicatorsTables">${wf:conf('resumeFrom') eq 'Step16-createIndicatorsTables'}</case>
+            <case to="Step16_1-definitions">${wf:conf('resumeFrom') eq 'Step16_1-definitions'}</case>
+            <case to="Step16_5">${wf:conf('resumeFrom') eq 'Step16_5'}</case>
+            <case to="Step19-finalize">${wf:conf('resumeFrom') eq 'Step19-finalize'}</case>
+            <case to="step20-createMonitorDB">${wf:conf('resumeFrom') eq 'step20-createMonitorDB'}</case>
+            <case to="step21-createObservatoryDB-pre">${wf:conf('resumeFrom') eq 'step21-createObservatoryDB-pre'}</case>
+            <case to="step21-createObservatoryDB">${wf:conf('resumeFrom') eq 'step21-createObservatoryDB'}</case>
+            <case to="step21-createObservatoryDB-post">${wf:conf('resumeFrom') eq 'step21-createObservatoryDB-post'}</case>
+            <case to="Step22">${wf:conf('resumeFrom') eq 'Step22'}</case>
+            <default to="Step1"/>
+        </switch>
+    </decision>
+
 
     <kill name="Kill">
         <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>

pom.xml

@@ -807,7 +807,7 @@
 		<mockito-core.version>3.3.3</mockito-core.version>
 		<mongodb.driver.version>3.4.2</mongodb.driver.version>
 		<vtd.version>[2.12,3.0)</vtd.version>
-		<dhp-schemas.version>[3.15.0]</dhp-schemas.version>
+		<dhp-schemas.version>[3.15.1-SNAPSHOT]</dhp-schemas.version>
 		<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
 		<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
 		<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>