integrated changes from branch dedupTest

dhp-workflows/dhp-dedup/pom.xml

@@ -65,6 +65,15 @@
             <groupId>com.arakelian</groupId>
             <artifactId>java-jq</artifactId>
         </dependency>
+        <dependency>
+            <groupId>dom4j</groupId>
+            <artifactId>dom4j</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>jaxen</groupId>
+            <artifactId>jaxen</artifactId>
+        </dependency>
+
 
         <dependency>
             <groupId>eu.dnetlib</groupId>
@@ -83,8 +92,6 @@
             <artifactId>jackson-core</artifactId>
         </dependency>
 
-
-
     </dependencies>
 
 

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkCreateConnectedComponent.java

@@ -1,79 +0,0 @@
-package eu.dnetlib.dedup;
-
-import com.google.common.collect.Iterables;
-import com.google.common.collect.Lists;
-import com.google.common.hash.HashFunction;
-import com.google.common.hash.Hashing;
-import eu.dnetlib.dedup.graph.ConnectedComponent;
-import eu.dnetlib.dedup.graph.GraphProcessor;
-import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.schema.oaf.Relation;
-import eu.dnetlib.pace.config.DedupConfig;
-import eu.dnetlib.pace.util.MapDocumentUtil;
-import org.apache.commons.io.IOUtils;
-import org.apache.spark.api.java.JavaPairRDD;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.FlatMapFunction;
-import org.apache.spark.api.java.function.PairFunction;
-import org.apache.spark.graphx.Edge;
-import org.apache.spark.rdd.RDD;
-import org.apache.spark.sql.Dataset;
-import org.apache.spark.sql.Encoders;
-import org.apache.spark.sql.SparkSession;
-import scala.Tuple2;
-
-import java.util.ArrayList;
-import java.util.List;
-
-public class SparkCreateConnectedComponent {
-
-    public static void main(String[] args) throws Exception {
-        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateConnectedComponent.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/dedup_parameters.json")));
-        parser.parseArgument(args);
-        final SparkSession spark = SparkSession
-                .builder()
-                .appName(SparkCreateConnectedComponent.class.getSimpleName())
-                .master(parser.get("master"))
-                .getOrCreate();
-
-        final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
-        final String inputPath = parser.get("sourcePath");
-        final String entity = parser.get("entity");
-        final String targetPath = parser.get("targetPath");
-//        final DedupConfig dedupConf = DedupConfig.load(IOUtils.toString(SparkCreateConnectedComponent.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/conf/org.curr.conf2.json")));
-        final DedupConfig dedupConf = DedupConfig.load(parser.get("dedupConf"));
-
-        final JavaPairRDD<Object, String> vertexes = sc.textFile(inputPath + "/" + entity)
-                .map(s -> MapDocumentUtil.getJPathString(dedupConf.getWf().getIdPath(), s))
-                .mapToPair((PairFunction<String, Object, String>)
-                        s -> new Tuple2<Object, String>(getHashcode(s), s)
-                );
-
-        final Dataset<Relation> similarityRelations = spark.read().load(DedupUtility.createSimRelPath(targetPath,entity)).as(Encoders.bean(Relation.class));
-        final RDD<Edge<String>> edgeRdd = similarityRelations.javaRDD().map(it -> new Edge<>(getHashcode(it.getSource()), getHashcode(it.getTarget()), it.getRelClass())).rdd();
-        final JavaRDD<ConnectedComponent> cc = GraphProcessor.findCCs(vertexes.rdd(), edgeRdd, dedupConf.getWf().getMaxIterations()).toJavaRDD();
-        final Dataset<Relation> mergeRelation = spark.createDataset(cc.filter(k->k.getDocIds().size()>1).flatMap((FlatMapFunction<ConnectedComponent, Relation>) c ->
-                c.getDocIds()
-                        .stream()
-                        .flatMap(id -> {
-                            List<Relation> tmp = new ArrayList<>();
-                            Relation r = new Relation();
-                            r.setSource(c.getCcId());
-                            r.setTarget(id);
-                            r.setRelClass("merges");
-                            tmp.add(r);
-                            r = new Relation();
-                            r.setTarget(c.getCcId());
-                            r.setSource(id);
-                            r.setRelClass("isMergedIn");
-                            tmp.add(r);
-                            return tmp.stream();
-                        }).iterator()).rdd(), Encoders.bean(Relation.class));
-        mergeRelation.write().mode("overwrite").save(DedupUtility.createMergeRelPath(targetPath,entity));
-    }
-
-    public  static long getHashcode(final String id) {
-        return Hashing.murmur3_128().hashString(id).asLong();
-    }
-}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkCreateDedupRecord.java

@@ -1,39 +0,0 @@
-package eu.dnetlib.dedup;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
-import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.schema.oaf.OafEntity;
-import eu.dnetlib.pace.config.DedupConfig;
-import org.apache.commons.io.IOUtils;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.sql.SparkSession;
-
-public class SparkCreateDedupRecord {
-
-    public static void main(String[] args) throws Exception {
-        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateDedupRecord.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/dedupRecord_parameters.json")));
-        parser.parseArgument(args);
-        final SparkSession spark = SparkSession
-                .builder()
-                .appName(SparkCreateDedupRecord.class.getSimpleName())
-                .master(parser.get("master"))
-                .getOrCreate();
-
-        final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
-        final String sourcePath = parser.get("sourcePath");
-        final String entity = parser.get("entity");
-        final String dedupPath = parser.get("dedupPath");
-//        final DedupConfig dedupConf = DedupConfig.load(IOUtils.toString(SparkCreateDedupRecord.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/conf/org.curr.conf2.json")));
-        final DedupConfig dedupConf = DedupConfig.load(parser.get("dedupConf"));
-
-        final JavaRDD<OafEntity> dedupRecord = DedupRecordFactory.createDedupRecord(sc, spark, DedupUtility.createMergeRelPath(dedupPath,entity), DedupUtility.createEntityPath(sourcePath,entity), OafEntityType.valueOf(entity), dedupConf);
-        dedupRecord.map(r-> {
-            ObjectMapper mapper = new ObjectMapper();
-            return mapper.writeValueAsString(r);
-        }).saveAsTextFile(dedupPath+"/"+entity+"_dedup_record_json");
-
-
-    }
-
-}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkCreateSimRels.java

@@ -1,73 +0,0 @@
-package eu.dnetlib.dedup;
-
-import com.google.common.hash.Hashing;
-import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.schema.oaf.Relation;
-import eu.dnetlib.pace.config.DedupConfig;
-import eu.dnetlib.pace.model.MapDocument;
-import eu.dnetlib.pace.util.MapDocumentUtil;
-import org.apache.commons.io.IOUtils;
-import org.apache.spark.api.java.JavaPairRDD;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.PairFunction;
-import org.apache.spark.sql.Encoders;
-import org.apache.spark.sql.SparkSession;
-import scala.Tuple2;
-
-import java.util.List;
-
-
-/**
- * This Spark class creates similarity relations between entities, saving result
- *
- * param request:
- *  sourcePath
- *  entityType
- *  target Path
- */
-public class SparkCreateSimRels {
-
-    public static void main(String[] args) throws Exception {
-        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateSimRels.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/dedup_parameters.json")));
-        parser.parseArgument(args);
-        final SparkSession spark = SparkSession
-                .builder()
-                .appName(SparkCreateSimRels.class.getSimpleName())
-                .master(parser.get("master"))
-                .getOrCreate();
-
-        final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
-        final String inputPath = parser.get("sourcePath");
-        final String entity = parser.get("entity");
-        final String targetPath = parser.get("targetPath");
-//        final DedupConfig dedupConf = DedupConfig.load(IOUtils.toString(SparkCreateSimRels.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/conf/org.curr.conf.json")));
-        final DedupConfig dedupConf = DedupConfig.load(parser.get("dedupConf"));
-
-        final long total = sc.textFile(inputPath + "/" + entity).count();
-
-        JavaPairRDD<String, MapDocument> mapDocument = sc.textFile(inputPath + "/" + entity)
-                .mapToPair(s->{
-                    MapDocument d = MapDocumentUtil.asMapDocumentWithJPath(dedupConf,s);
-                    return new Tuple2<>(d.getIdentifier(), d);});
-
-        //create blocks for deduplication
-        JavaPairRDD<String, List<MapDocument>> blocks = Deduper.createsortedBlocks(sc, mapDocument, dedupConf);
-//        JavaPairRDD<String, Iterable<MapDocument>> blocks = Deduper.createBlocks(sc, mapDocument, dedupConf);
-
-        //create relations by comparing only elements in the same group
-        final JavaPairRDD<String,String> dedupRels = Deduper.computeRelations2(sc, blocks, dedupConf);
-//        final JavaPairRDD<String,String> dedupRels = Deduper.computeRelations(sc, blocks, dedupConf);
-
-        final JavaRDD<Relation> isSimilarToRDD = dedupRels.map(simRel -> {
-            final Relation r = new Relation();
-            r.setSource(simRel._1());
-            r.setTarget(simRel._2());
-            r.setRelClass("isSimilarTo");
-            return r;
-        });
-
-        spark.createDataset(isSimilarToRDD.rdd(), Encoders.bean(Relation.class)).write().mode("overwrite").save( DedupUtility.createSimRelPath(targetPath,entity));
-
-    }
-}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/DatePicker.java

@@ -1,4 +1,4 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 import eu.dnetlib.dhp.schema.oaf.Field;
 import org.apache.commons.lang.StringUtils;

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/DedupRecordFactory.java

@@ -1,11 +1,9 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 import com.google.common.collect.Lists;
 import eu.dnetlib.dhp.schema.oaf.*;
 import eu.dnetlib.pace.config.DedupConfig;
 import eu.dnetlib.pace.util.MapDocumentUtil;
-import org.apache.commons.lang.NotImplementedException;
-import org.apache.commons.lang.StringUtils;
 import org.apache.spark.api.java.JavaPairRDD;
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
@@ -16,9 +14,6 @@ import org.codehaus.jackson.map.ObjectMapper;
 import scala.Tuple2;
 
 import java.util.Collection;
-import java.util.Random;
-
-import static java.util.stream.Collectors.toMap;
 
 public class DedupRecordFactory {
 

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/DedupUtility.java

@@ -1,35 +1,32 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 import com.google.common.collect.Sets;
 import com.wcohen.ss.JaroWinkler;
 import eu.dnetlib.dhp.schema.oaf.Author;
 import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
+import eu.dnetlib.dhp.utils.ISLookupClientFactory;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
 import eu.dnetlib.pace.clustering.BlacklistAwareClusteringCombiner;
 import eu.dnetlib.pace.config.DedupConfig;
 
 import eu.dnetlib.pace.model.MapDocument;
 import eu.dnetlib.pace.model.Person;
 import org.apache.commons.codec.binary.Hex;
-import org.apache.commons.io.IOUtils;
 import org.apache.commons.lang3.StringUtils;
-import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.FSDataInputStream;
-import org.apache.hadoop.fs.FileSystem;
-import org.apache.hadoop.fs.Path;
 import org.apache.spark.SparkContext;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.util.LongAccumulator;
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Element;
+import org.dom4j.io.SAXReader;
 import scala.Tuple2;
 
-import java.io.IOException;
+import java.io.StringReader;
-import java.io.StringWriter;
-import java.nio.charset.StandardCharsets;
 import java.security.MessageDigest;
 import java.text.Normalizer;
 import java.util.*;
 import java.util.stream.Collectors;
-import java.util.stream.Stream;
 
 public class DedupUtility {
     private static final Double THRESHOLD = 0.95;
@@ -54,38 +51,6 @@ public class DedupUtility {
         return accumulators;
     }
 
-    public static JavaRDD<String> loadDataFromHDFS(String path, JavaSparkContext context) {
-        return context.textFile(path);
-    }
-
-    public static void deleteIfExists(String path) throws IOException {
-        Configuration conf = new Configuration();
-        FileSystem fileSystem = FileSystem.get(conf);
-        if (fileSystem.exists(new Path(path))) {
-            fileSystem.delete(new Path(path), true);
-        }
-    }
-
-    public static DedupConfig loadConfigFromHDFS(String path) throws IOException {
-
-        Configuration conf = new Configuration();
-        FileSystem fileSystem = FileSystem.get(conf);
-        FSDataInputStream inputStream = new FSDataInputStream(fileSystem.open(new Path(path)));
-
-        return DedupConfig.load(IOUtils.toString(inputStream, StandardCharsets.UTF_8.name()));
-
-    }
-
-    static <T> String readFromClasspath(final String filename, final Class<T> clazz) {
-        final StringWriter sw = new StringWriter();
-        try {
-            IOUtils.copy(clazz.getResourceAsStream(filename), sw);
-            return sw.toString();
-        } catch (final IOException e) {
-            throw new RuntimeException("cannot load resource from classpath: " + filename);
-        }
-    }
-
     static Set<String> getGroupingKeys(DedupConfig conf, MapDocument doc) {
         return Sets.newHashSet(BlacklistAwareClusteringCombiner.filterAndCombine(doc, conf));
     }
@@ -146,16 +111,20 @@ public class DedupUtility {
         });
     }
 
+    public static String createDedupRecordPath(final String basePath, final String actionSetId, final String entityType) {
+        return String.format("%s/%s/%s_deduprecord", basePath, actionSetId, entityType);
+    }
+
     public static String createEntityPath(final String basePath, final String entityType) {
         return String.format("%s/%s", basePath, entityType);
     }
 
-    public static String createSimRelPath(final String basePath, final String entityType) {
+    public static String createSimRelPath(final String basePath, final String actionSetId,final String entityType) {
-        return String.format("%s/%s_simRel", basePath, entityType);
+        return String.format("%s/%s/%s_simrel", basePath, actionSetId, entityType);
     }
 
-    public static String createMergeRelPath(final String basePath, final String entityType) {
+    public static String createMergeRelPath(final String basePath, final String actionSetId, final String entityType) {
-        return String.format("%s/%s_mergeRel", basePath, entityType);
+        return String.format("%s/%s/%s_mergerel", basePath, actionSetId, entityType);
     }
 
     private static Double sim(Author a, Author b) {
@@ -216,4 +185,37 @@ public class DedupUtility {
             return false;
         return a.getPid().stream().anyMatch(p -> p != null && StringUtils.isNotBlank(p.getValue()));
     }
+
+    public static List<DedupConfig> getConfigurations(String isLookUpUrl, String orchestrator) throws ISLookUpException, DocumentException {
+        final ISLookUpService isLookUpService = ISLookupClientFactory.getLookUpService(isLookUpUrl);
+
+        final String xquery = String.format("/RESOURCE_PROFILE[.//DEDUPLICATION/ACTION_SET/@id = '%s']", orchestrator);
+
+        String orchestratorProfile = isLookUpService.getResourceProfileByQuery(xquery);
+
+        final Document doc = new SAXReader().read(new StringReader(orchestratorProfile));
+
+        final String actionSetId = doc.valueOf("//DEDUPLICATION/ACTION_SET/@id");
+        final List<DedupConfig> configurations = new ArrayList<>();
+
+        for (final Object o : doc.selectNodes("//SCAN_SEQUENCE/SCAN")) {
+            configurations.add(loadConfig(isLookUpService, actionSetId, o));
+        }
+
+        return configurations;
+
+    }
+
+    private static DedupConfig loadConfig(final ISLookUpService isLookUpService, final String actionSetId, final Object o)
+            throws ISLookUpException {
+        final Element s = (Element) o;
+        final String configProfileId = s.attributeValue("id");
+        final String conf =
+                isLookUpService.getResourceProfileByQuery(String.format(
+                        "for $x in /RESOURCE_PROFILE[.//RESOURCE_IDENTIFIER/@value = '%s'] return $x//DEDUPLICATION/text()",
+                        configProfileId));
+        final DedupConfig dedupConfig = DedupConfig.load(conf);
+        dedupConfig.getWf().setConfigurationId(actionSetId);
+        return dedupConfig;
+    }
 }

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/Deduper.java

@@ -1,7 +1,6 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 import eu.dnetlib.pace.config.DedupConfig;
-import eu.dnetlib.pace.model.Field;
 import eu.dnetlib.pace.model.MapDocument;
 import eu.dnetlib.pace.util.BlockProcessor;
 import eu.dnetlib.pace.util.MapDocumentUtil;

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/OafEntityType.java

@@ -1,4 +1,4 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 public enum OafEntityType {
 

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/SparkCreateConnectedComponent.java

@@ -0,0 +1,100 @@
+package eu.dnetlib.dhp.dedup;
+
+import com.google.common.hash.Hashing;
+import eu.dnetlib.dhp.dedup.graph.ConnectedComponent;
+import eu.dnetlib.dhp.dedup.graph.GraphProcessor;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+import eu.dnetlib.pace.config.DedupConfig;
+import eu.dnetlib.pace.util.MapDocumentUtil;
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.FlatMapFunction;
+import org.apache.spark.api.java.function.PairFunction;
+import org.apache.spark.graphx.Edge;
+import org.apache.spark.rdd.RDD;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SparkSession;
+import org.dom4j.DocumentException;
+import scala.Tuple2;
+
+import java.util.ArrayList;
+import java.util.List;
+
+public class SparkCreateConnectedComponent {
+
+    public static void main(String[] args) throws Exception {
+        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateConnectedComponent.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/createCC_parameters.json")));
+        parser.parseArgument(args);
+
+        new SparkCreateConnectedComponent().run(parser);
+    }
+
+    private void run(ArgumentApplicationParser parser) throws ISLookUpException, DocumentException {
+
+        final String graphBasePath = parser.get("graphBasePath");
+        final String workingPath = parser.get("workingPath");
+        final String isLookUpUrl = parser.get("isLookUpUrl");
+        final String actionSetId = parser.get("actionSetId");
+
+        try (SparkSession spark = getSparkSession(parser)) {
+
+            final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+            for (DedupConfig dedupConf: DedupUtility.getConfigurations(isLookUpUrl, actionSetId)) {
+
+                final String entity = dedupConf.getWf().getEntityType();
+                final String subEntity = dedupConf.getWf().getSubEntityValue();
+
+                final JavaPairRDD<Object, String> vertexes = sc.textFile(graphBasePath + "/" + subEntity)
+                        .map(s -> MapDocumentUtil.getJPathString(dedupConf.getWf().getIdPath(), s))
+                        .mapToPair((PairFunction<String, Object, String>)
+                                s -> new Tuple2<Object, String>(getHashcode(s), s)
+                        );
+
+                final Dataset<Relation> similarityRelations = spark.read().load(DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity)).as(Encoders.bean(Relation.class));
+                final RDD<Edge<String>> edgeRdd = similarityRelations.javaRDD().map(it -> new Edge<>(getHashcode(it.getSource()), getHashcode(it.getTarget()), it.getRelClass())).rdd();
+                final JavaRDD<ConnectedComponent> cc = GraphProcessor.findCCs(vertexes.rdd(), edgeRdd, dedupConf.getWf().getMaxIterations()).toJavaRDD();
+                final Dataset<Relation> mergeRelation = spark.createDataset(cc.filter(k -> k.getDocIds().size() > 1).flatMap((FlatMapFunction<ConnectedComponent, Relation>) c ->
+                        c.getDocIds()
+                                .stream()
+                                .flatMap(id -> {
+                                    List<Relation> tmp = new ArrayList<>();
+                                    Relation r = new Relation();
+                                    r.setSource(c.getCcId());
+                                    r.setTarget(id);
+                                    r.setRelClass("merges");
+                                    tmp.add(r);
+                                    r = new Relation();
+                                    r.setTarget(c.getCcId());
+                                    r.setSource(id);
+                                    r.setRelClass("isMergedIn");
+                                    tmp.add(r);
+                                    return tmp.stream();
+                                }).iterator()).rdd(), Encoders.bean(Relation.class));
+                mergeRelation.write().mode("overwrite").save(DedupUtility.createMergeRelPath(workingPath, actionSetId, entity));
+            }
+        }
+    }
+
+    public  static long getHashcode(final String id) {
+        return Hashing.murmur3_128().hashString(id).asLong();
+    }
+
+    private static SparkSession getSparkSession(ArgumentApplicationParser parser) {
+        SparkConf conf = new SparkConf();
+
+        return SparkSession
+                .builder()
+                .appName(SparkCreateSimRels.class.getSimpleName())
+                .master(parser.get("master"))
+                .config(conf)
+                .enableHiveSupport()
+                .getOrCreate();
+    }
+}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/SparkCreateDedupRecord.java

@@ -0,0 +1,62 @@
+package eu.dnetlib.dhp.dedup;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+import eu.dnetlib.pace.config.DedupConfig;
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SparkSession;
+import org.dom4j.DocumentException;
+
+public class SparkCreateDedupRecord {
+
+    public static void main(String[] args) throws Exception {
+        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateDedupRecord.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/createDedupRecord_parameters.json")));
+        parser.parseArgument(args);
+
+        new SparkCreateDedupRecord().run(parser);
+    }
+
+    private void run(ArgumentApplicationParser parser) throws ISLookUpException, DocumentException {
+
+        final String graphBasePath = parser.get("graphBasePath");
+        final String isLookUpUrl = parser.get("isLookUpUrl");
+        final String actionSetId = parser.get("actionSetId");
+        final String workingPath = parser.get("workingPath");
+
+        try (SparkSession spark = getSparkSession(parser)) {
+            final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+            for (DedupConfig dedupConf: DedupUtility.getConfigurations(isLookUpUrl, actionSetId)) {
+                String subEntity = dedupConf.getWf().getSubEntityValue();
+
+                final String mergeRelPath = DedupUtility.createMergeRelPath(workingPath, actionSetId, subEntity);
+                final String entityPath = DedupUtility.createEntityPath(graphBasePath, subEntity);
+                final OafEntityType entityType = OafEntityType.valueOf(subEntity);
+                final JavaRDD<OafEntity> dedupRecord =
+                        DedupRecordFactory.createDedupRecord(sc, spark, mergeRelPath, entityPath, entityType, dedupConf);
+                dedupRecord.map(r -> {
+                    ObjectMapper mapper = new ObjectMapper();
+                    return mapper.writeValueAsString(r);
+                }).saveAsTextFile(DedupUtility.createDedupRecordPath(workingPath, actionSetId, subEntity));
+            }
+        }
+    }
+
+    private static SparkSession getSparkSession(ArgumentApplicationParser parser) {
+        SparkConf conf = new SparkConf();
+
+        return SparkSession
+                .builder()
+                .appName(SparkCreateDedupRecord.class.getSimpleName())
+                .master(parser.get("master"))
+                .config(conf)
+                .enableHiveSupport()
+                .getOrCreate();
+    }
+}
+

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/SparkCreateSimRels.java

@@ -0,0 +1,134 @@
+package eu.dnetlib.dhp.dedup;
+
+import com.fasterxml.jackson.core.JsonProcessingException;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.action.AtomicAction;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+import eu.dnetlib.pace.config.DedupConfig;
+import eu.dnetlib.pace.model.MapDocument;
+import eu.dnetlib.pace.util.MapDocumentUtil;
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.compress.GzipCodec;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SparkSession;
+import org.dom4j.DocumentException;
+import scala.Tuple2;
+
+import java.io.Serializable;
+import java.util.List;
+
+public class SparkCreateSimRels implements Serializable {
+
+    private static final Log log = LogFactory.getLog(SparkCreateSimRels.class);
+
+    public static void main(String[] args) throws Exception {
+        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateSimRels.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/createSimRels_parameters.json")));
+        parser.parseArgument(args);
+
+        new SparkCreateSimRels().run(parser);
+    }
+
+    private void run(ArgumentApplicationParser parser) throws ISLookUpException, DocumentException {
+
+        //read oozie parameters
+        final String graphBasePath = parser.get("graphBasePath");
+        final String isLookUpUrl = parser.get("isLookUpUrl");
+        final String actionSetId = parser.get("actionSetId");
+        final String workingPath = parser.get("workingPath");
+
+        System.out.println(String.format("graphBasePath: '%s'", graphBasePath));
+        System.out.println(String.format("isLookUpUrl: '%s'", isLookUpUrl));
+        System.out.println(String.format("actionSetId: '%s'", actionSetId));
+        System.out.println(String.format("workingPath: '%s'", workingPath));
+
+        try (SparkSession spark = getSparkSession(parser)) {
+            final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+            //for each dedup configuration
+            for (DedupConfig dedupConf: DedupUtility.getConfigurations(isLookUpUrl, actionSetId)) {
+                final String entity = dedupConf.getWf().getEntityType();
+                final String subEntity = dedupConf.getWf().getSubEntityValue();
+
+                JavaPairRDD<String, MapDocument> mapDocument = sc.textFile(DedupUtility.createEntityPath(graphBasePath, subEntity))
+                        .mapToPair(s -> {
+                            MapDocument d = MapDocumentUtil.asMapDocumentWithJPath(dedupConf, s);
+                            return new Tuple2<>(d.getIdentifier(), d);
+                        });
+
+                //create blocks for deduplication
+                JavaPairRDD<String, List<MapDocument>> blocks = Deduper.createsortedBlocks(sc, mapDocument, dedupConf);
+
+                //create relations by comparing only elements in the same group
+                final JavaPairRDD<String, String> dedupRels = Deduper.computeRelations2(sc, blocks, dedupConf);
+
+                JavaRDD<Relation> relationsRDD = dedupRels.map(r -> createSimRel(r._1(), r._2(), entity));
+
+                //save the simrel in the workingdir
+                spark.createDataset(relationsRDD.rdd(), Encoders.bean(Relation.class))
+                        .write()
+                        .mode("overwrite")
+                        .save(DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity));
+            }
+        }
+    }
+
+    /**
+     * Utility method used to create an atomic action from a Relation object
+     * @param relation input relation
+     * @return A tuple2 with [id, json serialization of the atomic action]
+     * @throws JsonProcessingException
+     */
+    public Tuple2<Text, Text> createSequenceFileRow(Relation relation) throws JsonProcessingException {
+
+        ObjectMapper mapper = new ObjectMapper();
+
+        String id = relation.getSource() + "@" + relation.getRelClass() + "@" + relation.getTarget();
+        AtomicAction<Relation> aa = new AtomicAction<>(Relation.class, relation);
+
+        return new Tuple2<>(
+                new Text(id),
+                new Text(mapper.writeValueAsString(aa))
+        );
+    }
+
+    public Relation createSimRel(String source, String target, String entity){
+        final Relation r = new Relation();
+        r.setSource(source);
+        r.setTarget(target);
+
+        switch(entity){
+            case "result":
+                r.setRelClass("resultResult_dedupSimilarity_isSimilarTo");
+                break;
+            case "organization":
+                r.setRelClass("organizationOrganization_dedupSimilarity_isSimilarTo");
+                break;
+            default:
+                r.setRelClass("isSimilarTo");
+                break;
+        }
+        return r;
+    }
+
+    private static SparkSession getSparkSession(ArgumentApplicationParser parser) {
+        SparkConf conf = new SparkConf();
+
+        return SparkSession
+                .builder()
+                .appName(SparkCreateSimRels.class.getSimpleName())
+                .master(parser.get("master"))
+                .config(conf)
+                .getOrCreate();
+    }
+
+}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/SparkPropagateRelation.java

@@ -0,0 +1,169 @@
+package eu.dnetlib.dhp.dedup;
+
+import com.fasterxml.jackson.databind.DeserializationFeature;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.DataInfo;
+import eu.dnetlib.dhp.schema.oaf.Oaf;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+import eu.dnetlib.pace.util.MapDocumentUtil;
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.io.compress.GzipCodec;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.Optional;
+import org.apache.spark.api.java.function.Function;
+import org.apache.spark.api.java.function.PairFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+import scala.Tuple2;
+
+import java.io.IOException;
+
+public class SparkPropagateRelation {
+
+    enum FieldType {
+        SOURCE,
+        TARGET
+    }
+
+    final static String SOURCEJSONPATH = "$.source";
+    final static String TARGETJSONPATH = "$.target";
+
+    public static void main(String[] args) throws Exception {
+        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkPropagateRelation.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/propagateRelation_parameters.json")));
+        parser.parseArgument(args);
+
+        new SparkPropagateRelation().run(parser);
+    }
+
+    public void run(ArgumentApplicationParser parser) {
+
+        final String graphBasePath = parser.get("graphBasePath");
+        final String workingPath = parser.get("workingPath");
+        final String dedupGraphPath = parser.get("dedupGraphPath");
+
+        try (SparkSession spark = getSparkSession(parser)) {
+            final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+            final Dataset<Relation> mergeRels = spark.read().load(DedupUtility.createMergeRelPath(workingPath, "*", "*")).as(Encoders.bean(Relation.class));
+
+            final JavaPairRDD<String, String> mergedIds = mergeRels
+                    .where("relClass == 'merges'")
+                    .select(mergeRels.col("source"), mergeRels.col("target"))
+                    .distinct()
+                    .toJavaRDD()
+                    .mapToPair((PairFunction<Row, String, String>) r -> new Tuple2<>(r.getString(1), r.getString(0)));
+
+            JavaRDD<String> relations = sc.textFile(DedupUtility.createEntityPath(graphBasePath, "relation"));
+
+            JavaRDD<String> newRels = relations.mapToPair(
+                    (PairFunction<String, String, String>) s ->
+                            new Tuple2<>(MapDocumentUtil.getJPathString(SOURCEJSONPATH, s), s))
+                    .leftOuterJoin(mergedIds)
+                    .map((Function<Tuple2<String, Tuple2<String, Optional<String>>>, String>) v1 -> {
+                        if (v1._2()._2().isPresent()) {
+                            return replaceField(v1._2()._1(), v1._2()._2().get(), FieldType.SOURCE);
+                        }
+                        return v1._2()._1();
+                    })
+                    .mapToPair(
+                            (PairFunction<String, String, String>) s ->
+                                    new Tuple2<>(MapDocumentUtil.getJPathString(TARGETJSONPATH, s), s))
+                    .leftOuterJoin(mergedIds)
+                    .map((Function<Tuple2<String, Tuple2<String, Optional<String>>>, String>) v1 -> {
+                        if (v1._2()._2().isPresent()) {
+                            return replaceField(v1._2()._1(), v1._2()._2().get(), FieldType.TARGET);
+                        }
+                        return v1._2()._1();
+                    }).filter(SparkPropagateRelation::containsDedup)
+                    .repartition(500);
+
+            //update deleted by inference
+            relations = relations.mapToPair(
+                    (PairFunction<String, String, String>) s ->
+                            new Tuple2<>(MapDocumentUtil.getJPathString(SOURCEJSONPATH, s), s))
+                    .leftOuterJoin(mergedIds)
+                    .map((Function<Tuple2<String, Tuple2<String, Optional<String>>>, String>) v1 -> {
+                        if (v1._2()._2().isPresent()) {
+                            return updateDeletedByInference(v1._2()._1(), Relation.class);
+                        }
+                        return v1._2()._1();
+                    })
+                    .mapToPair(
+                            (PairFunction<String, String, String>) s ->
+                                    new Tuple2<>(MapDocumentUtil.getJPathString(TARGETJSONPATH, s), s))
+                    .leftOuterJoin(mergedIds)
+                    .map((Function<Tuple2<String, Tuple2<String, Optional<String>>>, String>) v1 -> {
+                        if (v1._2()._2().isPresent()) {
+                            return updateDeletedByInference(v1._2()._1(), Relation.class);
+                        }
+                        return v1._2()._1();
+                    })
+                    .repartition(500);
+
+            newRels.union(relations).repartition(1000)
+                    .saveAsTextFile(DedupUtility.createEntityPath(dedupGraphPath, "relation"), GzipCodec.class);
+        }
+    }
+
+    private static boolean containsDedup(final String json) {
+        final String source = MapDocumentUtil.getJPathString(SOURCEJSONPATH, json);
+        final String target = MapDocumentUtil.getJPathString(TARGETJSONPATH, json);
+
+        return source.toLowerCase().contains("dedup") || target.toLowerCase().contains("dedup");
+    }
+
+    private static String replaceField(final String json, final String id, final FieldType type) {
+        ObjectMapper mapper = new ObjectMapper();
+        mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
+        try {
+            Relation relation = mapper.readValue(json, Relation.class);
+            if (relation.getDataInfo() == null)
+                relation.setDataInfo(new DataInfo());
+            relation.getDataInfo().setDeletedbyinference(false);
+            switch (type) {
+                case SOURCE:
+                    relation.setSource(id);
+                    return mapper.writeValueAsString(relation);
+                case TARGET:
+                    relation.setTarget(id);
+                    return mapper.writeValueAsString(relation);
+                default:
+                    throw new IllegalArgumentException("");
+            }
+        } catch (IOException e) {
+            throw new RuntimeException("unable to deserialize json relation: " + json, e);
+        }
+    }
+
+    private static SparkSession getSparkSession(ArgumentApplicationParser parser) {
+        SparkConf conf = new SparkConf();
+
+        return SparkSession
+                .builder()
+                .appName(SparkPropagateRelation.class.getSimpleName())
+                .master(parser.get("master"))
+                .config(conf)
+                .enableHiveSupport()
+                .getOrCreate();
+    }
+
+    private static <T extends Oaf> String updateDeletedByInference(final String json, final Class<T> clazz) {
+        final ObjectMapper mapper = new ObjectMapper();
+        mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
+        try {
+            Oaf entity = mapper.readValue(json, clazz);
+            if (entity.getDataInfo()== null)
+                entity.setDataInfo(new DataInfo());
+            entity.getDataInfo().setDeletedbyinference(true);
+            return mapper.writeValueAsString(entity);
+        } catch (IOException e) {
+            throw new RuntimeException("Unable to convert json", e);
+        }
+    }
+}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/SparkReporter.java

@@ -1,4 +1,4 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 import eu.dnetlib.pace.util.Reporter;
 import org.apache.commons.logging.Log;

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/SparkUpdateEntity.java

@@ -0,0 +1,141 @@
+package eu.dnetlib.dhp.dedup;
+
+import com.fasterxml.jackson.databind.DeserializationFeature;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.*;
+import eu.dnetlib.pace.util.MapDocumentUtil;
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.*;
+import org.apache.hadoop.io.compress.GzipCodec;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.PairFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+import scala.Tuple2;
+
+import java.io.IOException;
+import java.io.Serializable;
+
+public class SparkUpdateEntity implements Serializable {
+
+    final String IDJSONPATH = "$.id";
+
+    public static void main(String[] args) throws Exception {
+        final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkUpdateEntity.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/updateEntity_parameters.json")));
+        parser.parseArgument(args);
+
+        new SparkUpdateEntity().run(parser);
+    }
+
+    public boolean mergeRelExists(String basePath, String entity) throws IOException {
+
+        boolean result = false;
+
+        FileSystem fileSystem = FileSystem.get(new Configuration());
+
+        FileStatus[] fileStatuses = fileSystem.listStatus(new Path(basePath));
+
+        for (FileStatus fs : fileStatuses) {
+            if (fs.isDirectory())
+                if (fileSystem.exists(new Path(DedupUtility.createMergeRelPath(basePath, fs.getPath().getName(), entity))))
+                    result = true;
+        }
+
+        return result;
+    }
+
+    public void run(ArgumentApplicationParser parser) throws IOException {
+
+        final String graphBasePath = parser.get("graphBasePath");
+        final String workingPath = parser.get("workingPath");
+        final String dedupGraphPath = parser.get("dedupGraphPath");
+
+        try (SparkSession spark = getSparkSession(parser)) {
+
+            final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+            //for each entity
+            for (OafEntityType entity: OafEntityType.values()) {
+
+                JavaRDD<String> sourceEntity = sc.textFile(DedupUtility.createEntityPath(graphBasePath, entity.toString()));
+
+                if (mergeRelExists(workingPath, entity.toString())) {
+
+                    final Dataset<Relation> rel = spark.read().load(DedupUtility.createMergeRelPath(workingPath, "*", entity.toString())).as(Encoders.bean(Relation.class));
+
+                    final JavaPairRDD<String, String> mergedIds = rel
+                            .where("relClass == 'merges'")
+                            .select(rel.col("target"))
+                            .distinct()
+                            .toJavaRDD()
+                            .mapToPair((PairFunction<Row, String, String>) r -> new Tuple2<>(r.getString(0), "d"));
+
+                    final JavaRDD<String> dedupEntity = sc.textFile(DedupUtility.createDedupRecordPath(workingPath, "*", entity.toString()));
+
+                    JavaPairRDD<String, String> entitiesWithId = sourceEntity.mapToPair((PairFunction<String, String, String>) s -> new Tuple2<>(MapDocumentUtil.getJPathString(IDJSONPATH, s), s));
+
+                    JavaRDD<String> map = entitiesWithId.leftOuterJoin(mergedIds).map(k -> k._2()._2().isPresent() ? updateDeletedByInference(k._2()._1(), getOafClass(entity)) : k._2()._1());
+                    sourceEntity = map.union(dedupEntity);
+
+                }
+
+                sourceEntity.saveAsTextFile(dedupGraphPath + "/" + entity, GzipCodec.class);
+
+            }
+        }
+    }
+
+    public Class<? extends Oaf> getOafClass(OafEntityType className) {
+        switch (className.toString()) {
+            case "publication":
+                return Publication.class;
+            case "dataset":
+                return eu.dnetlib.dhp.schema.oaf.Dataset.class;
+            case "datasource":
+                return Datasource.class;
+            case "software":
+                return Software.class;
+            case "organization":
+                return Organization.class;
+            case "otherresearchproduct":
+                return OtherResearchProduct.class;
+            case "project":
+                return Project.class;
+            default:
+                throw new IllegalArgumentException("Illegal type " + className);
+        }
+    }
+
+    private static <T extends Oaf> String updateDeletedByInference(final String json, final Class<T> clazz) {
+        final ObjectMapper mapper = new ObjectMapper();
+        mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
+        try {
+            Oaf entity = mapper.readValue(json, clazz);
+            if (entity.getDataInfo()== null)
+                entity.setDataInfo(new DataInfo());
+            entity.getDataInfo().setDeletedbyinference(true);
+            return mapper.writeValueAsString(entity);
+        } catch (IOException e) {
+            throw new RuntimeException("Unable to convert json", e);
+        }
+    }
+
+    private static SparkSession getSparkSession(ArgumentApplicationParser parser) {
+        SparkConf conf = new SparkConf();
+
+        return SparkSession
+                .builder()
+                .appName(SparkUpdateEntity.class.getSimpleName())
+                .master(parser.get("master"))
+                .config(conf)
+                .enableHiveSupport()
+                .getOrCreate();
+    }
+}

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/graph/ConnectedComponent.java

@@ -1,7 +1,7 @@
-package eu.dnetlib.dedup.graph;
+package eu.dnetlib.dhp.dedup.graph;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
-import eu.dnetlib.dedup.DedupUtility;
+import eu.dnetlib.dhp.dedup.DedupUtility;
 import eu.dnetlib.pace.util.PaceException;
 import org.apache.commons.lang.StringUtils;
 import org.codehaus.jackson.annotate.JsonIgnore;

dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dhp/dedup/graph/GraphProcessor.scala

@@ -1,4 +1,4 @@
-package eu.dnetlib.dedup.graph
+package eu.dnetlib.dhp.dedup.graph
 
 import org.apache.spark.graphx._
 import org.apache.spark.rdd.RDD

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/consistency/oozie_app/config-default.xml

@@ -15,12 +15,4 @@
         <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_db_name</name>
-        <value>openaire</value>
-    </property>
 </configuration>

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/consistency/oozie_app/workflow.xml

@@ -0,0 +1,105 @@
+<workflow-app name="Update Graph" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>graphBasePath</name>
+            <description>the raw graph base path</description>
+        </property>
+        <property>
+            <name>workingPath</name>
+            <description>path of the working directory</description>
+        </property>
+        <property>
+            <name>dedupGraphPath</name>
+            <description>path of the dedup graph</description>
+        </property>
+        <property>
+            <name>sparkDriverMemory</name>
+            <description>memory for driver process</description>
+        </property>
+        <property>
+            <name>sparkExecutorMemory</name>
+            <description>memory for individual executor</description>
+        </property>
+        <property>
+            <name>sparkExecutorCores</name>
+            <description>number of cores used by single executor</description>
+        </property>
+    </parameters>
+
+    <global>
+        <job-tracker>${jobTracker}</job-tracker>
+        <name-node>${nameNode}</name-node>
+        <configuration>
+            <property>
+                <name>mapreduce.job.queuename</name>
+                <value>${queueName}</value>
+            </property>
+            <property>
+                <name>oozie.launcher.mapred.job.queue.name</name>
+                <value>${oozieLauncherQueueName}</value>
+            </property>
+        </configuration>
+    </global>
+
+    <start to="UpdateEntity"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="UpdateEntity">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <prepare>
+                <delete path='${dedupGraphPath}'/>
+            </prepare>
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Update Entity</name>
+            <class>eu.dnetlib.dhp.dedup.SparkUpdateEntity</class>
+            <jar>dhp-dedup-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory ${sparkExecutorMemory}
+                --executor-cores ${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
+                --conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
+                --conf spark.sql.warehouse.dir="/user/hive/warehouse"
+            </spark-opts>
+            <arg>-mt</arg><arg>yarn</arg>
+            <arg>--i</arg><arg>${graphBasePath}</arg>
+            <arg>--w</arg><arg>${workingPath}</arg>
+            <arg>--o</arg><arg>${dedupGraphPath}</arg>
+        </spark>
+        <ok to="PropagateRelation"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="PropagateRelation">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <prepare>
+                <delete path='${dedupGraphPath}/relation'/>
+            </prepare>
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Update Relations</name>
+            <class>eu.dnetlib.dhp.dedup.SparkPropagateRelation</class>
+            <jar>dhp-dedup-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory ${sparkExecutorMemory}
+                --executor-cores ${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
+                --conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
+                --conf spark.sql.warehouse.dir="/user/hive/warehouse"
+            </spark-opts>
+            <arg>-mt</arg><arg>yarn</arg>
+            <arg>--i</arg><arg>${graphBasePath}</arg>
+            <arg>--o</arg><arg>${dedupGraphPath}</arg>
+            <arg>--w</arg><arg>${workingPath}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/createCC_parameters.json

@@ -0,0 +1,32 @@
+[
+  {
+    "paramName": "mt",
+    "paramLongName": "master",
+    "paramDescription": "should be local or yarn",
+    "paramRequired": true
+  },
+  {
+    "paramName": "asi",
+    "paramLongName": "actionSetId",
+    "paramDescription": "action set identifier (name of the orchestrator)",
+    "paramRequired": true
+  },
+  {
+    "paramName": "i",
+    "paramLongName": "graphBasePath",
+    "paramDescription": "the base path of the raw graph",
+    "paramRequired": true
+  },
+  {
+    "paramName": "la",
+    "paramLongName": "isLookUpUrl",
+    "paramDescription": "the url for the lookup service",
+    "paramRequired": true
+  },
+  {
+    "paramName": "w",
+    "paramLongName": "workingPath",
+    "paramDescription": "path for the working directory",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/createDedupRecord_parameters.json

@@ -0,0 +1,32 @@
+[
+  {
+    "paramName": "mt",
+    "paramLongName": "master",
+    "paramDescription": "should be local or yarn",
+    "paramRequired": true
+  },
+  {
+    "paramName": "i",
+    "paramLongName": "graphBasePath",
+    "paramDescription": "the base path of raw graph",
+    "paramRequired": true
+  },
+  {
+    "paramName": "w",
+    "paramLongName": "workingPath",
+    "paramDescription": "the working directory path",
+    "paramRequired": true
+  },
+  {
+    "paramName": "la",
+    "paramLongName": "isLookUpUrl",
+    "paramDescription": "the url of the lookup service",
+    "paramRequired": true
+  },
+  {
+    "paramName": "asi",
+    "paramLongName": "actionSetId",
+    "paramDescription": "the id of the actionset (orchestrator)",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/createSimRels_parameters.json

@@ -0,0 +1,32 @@
+[
+  {
+    "paramName": "mt",
+    "paramLongName": "master",
+    "paramDescription": "should be local or yarn",
+    "paramRequired": true
+  },
+  {
+    "paramName": "la",
+    "paramLongName": "isLookUpUrl",
+    "paramDescription": "address for the LookUp",
+    "paramRequired": true
+  },
+  {
+    "paramName": "asi",
+    "paramLongName": "actionSetId",
+    "paramDescription": "action set identifier (name of the orchestrator)",
+    "paramRequired": true
+  },
+  {
+    "paramName": "i",
+    "paramLongName": "graphBasePath",
+    "paramDescription": "the base path of the raw graph",
+    "paramRequired": true
+  },
+  {
+    "paramName": "w",
+    "paramLongName": "workingPath",
+    "paramDescription": "path of the working directory",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/dedup_parameters.json

@@ -1,33 +0,0 @@
-[
-  {
-    "paramName": "mt",
-    "paramLongName": "master",
-    "paramDescription": "should be local or yarn",
-    "paramRequired": true
-  },
-  {
-    "paramName": "s",
-    "paramLongName": "sourcePath",
-    "paramDescription": "the path of the sequential file to read",
-    "paramRequired": true
-  },
-  {
-    "paramName": "e",
-    "paramLongName": "entity",
-    "paramDescription": "the type of entity to be deduped",
-    "paramRequired": true
-  },
-  {
-    "paramName": "c",
-    "paramLongName": "dedupConf",
-    "paramDescription": "dedup configuration to be used",
-    "compressed": true,
-    "paramRequired": true
-  },
-  {
-    "paramName": "t",
-    "paramLongName": "targetPath",
-    "paramDescription": "target path to save dedup result",
-    "paramRequired": true
-  }
-]

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/oozie_app/workflow.xml

@@ -1,126 +0,0 @@
-<workflow-app name="Dedup Entities" xmlns="uri:oozie:workflow:0.5">
-    <parameters>
-        <property>
-            <name>sourcePath</name>
-            <description>the source path</description>
-        </property>
-        <property>
-            <name>entity</name>
-            <description>the entity that should be processed</description>
-        </property>
-        <property>
-            <name>dedupConf</name>
-            <description>the dedup Configuration</description>
-        </property>
-        <property>
-            <name>targetPath</name>
-            <description>the target path</description>
-        </property>
-        <property>
-            <name>sparkDriverMemory</name>
-            <description>memory for driver process</description>
-        </property>
-        <property>
-            <name>sparkExecutorMemory</name>
-            <description>memory for individual executor</description>
-        </property>
-        <property>
-            <name>sparkExecutorCores</name>
-            <description>number of cores used by single executor</description>
-        </property>
-    </parameters>
-
-    <start to="CreateSimRels"/>
-
-
-    <kill name="Kill">
-        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
-    </kill>
-
-<!--    <action name="DeleteTargetPath">-->
-<!--        <fs>-->
-<!--            <delete path='${targetPath}/${entity}_simrel'/>-->
-<!--            <delete path='${targetPath}/${entity}_mergeRels'/>-->
-<!--        </fs>-->
-<!--        <ok to="CreateSimRels"/>-->
-<!--        <error to="Kill"/>-->
-<!--    </action>-->
-
-    <action name="CreateSimRels">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <job-tracker>${jobTracker}</job-tracker>
-            <name-node>${nameNode}</name-node>
-            <master>yarn-cluster</master>
-            <mode>cluster</mode>
-            <name>Create Similarity Relations</name>
-            <class>eu.dnetlib.dedup.SparkCreateSimRels</class>
-            <jar>dhp-dedup-${projectVersion}.jar</jar>
-            <spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory} --conf
-                spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener" --conf
-                spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener" --conf
-                spark.sql.warehouse.dir="/user/hive/warehouse"
-            </spark-opts>
-            <arg>-mt</arg><arg>yarn-cluster</arg>
-            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
-            <arg>--targetPath</arg><arg>${targetPath}</arg>
-            <arg>--entity</arg><arg>${entity}</arg>
-            <arg>--dedupConf</arg><arg>${dedupConf}</arg>
-        </spark>
-        <ok to="CreateConnectedComponents"/>
-        <error to="Kill"/>
-    </action>
-
-
-    <action name="CreateConnectedComponents">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <job-tracker>${jobTracker}</job-tracker>
-            <name-node>${nameNode}</name-node>
-            <master>yarn-cluster</master>
-            <mode>cluster</mode>
-            <name>Create Connected Components</name>
-            <class>eu.dnetlib.dedup.SparkCreateConnectedComponent</class>
-            <jar>dhp-dedup-${projectVersion}.jar</jar>
-            <spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory} --conf
-                spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener" --conf
-                spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener" --conf
-                spark.sql.warehouse.dir="/user/hive/warehouse"
-            </spark-opts>
-            <arg>-mt</arg><arg>yarn-cluster</arg>
-            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
-            <arg>--targetPath</arg><arg>${targetPath}</arg>
-            <arg>--entity</arg><arg>${entity}</arg>
-            <arg>--dedupConf</arg><arg>${dedupConf}</arg>
-        </spark>
-        <ok to="CreateDedupRecord"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="CreateDedupRecord">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <job-tracker>${jobTracker}</job-tracker>
-            <name-node>${nameNode}</name-node>
-            <master>yarn-cluster</master>
-            <mode>cluster</mode>
-            <name>Create Dedup Record</name>
-            <class>eu.dnetlib.dedup.SparkCreateDedupRecord</class>
-            <jar>dhp-dedup-${projectVersion}.jar</jar>
-            <spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory} --conf
-                spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener" --conf
-                spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener" --conf
-                spark.sql.warehouse.dir="/user/hive/warehouse"
-            </spark-opts>
-            <arg>-mt</arg><arg>yarn-cluster</arg>
-            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
-            <arg>--dedupPath</arg><arg>${dedupPath}</arg>
-            <arg>--entity</arg><arg>${entity}</arg>
-            <arg>--dedupConf</arg><arg>${dedupConf}</arg>
-        </spark>
-        <ok to="End"/>
-        <error to="Kill"/>
-    </action>
-
-    <end name="End"/>
-</workflow-app>

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/propagateRelation_parameters.json

@@ -0,0 +1,26 @@
+[
+  {
+    "paramName": "mt",
+    "paramLongName": "master",
+    "paramDescription": "should be local or yarn",
+    "paramRequired": true
+  },
+  {
+    "paramName": "i",
+    "paramLongName": "graphBasePath",
+    "paramDescription": "the base path of raw graph",
+    "paramRequired": true
+  },
+  {
+    "paramName": "w",
+    "paramLongName": "workingPath",
+    "paramDescription": "the working directory path",
+    "paramRequired": true
+  },
+  {
+    "paramName": "o",
+    "paramLongName": "dedupGraphPath",
+    "paramDescription": "the path of the dedup graph",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/scan/oozie_app/config-default.xml

@@ -0,0 +1,18 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>yarnRM</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>hdfs://nameservice1</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>
+</configuration>

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/scan/oozie_app/workflow.xml

@@ -0,0 +1,138 @@
+<workflow-app name="Duplicate Scan" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>graphBasePath</name>
+            <description>the raw graph base path</description>
+        </property>
+        <property>
+            <name>isLookUpUrl</name>
+            <description>the address of the lookUp service</description>
+        </property>
+        <property>
+            <name>actionSetId</name>
+            <description>id of the actionSet</description>
+        </property>
+        <property>
+            <name>workingPath</name>
+            <description>path for the working directory</description>
+        </property>
+        <property>
+            <name>sparkDriverMemory</name>
+            <description>memory for driver process</description>
+        </property>
+        <property>
+            <name>sparkExecutorMemory</name>
+            <description>memory for individual executor</description>
+        </property>
+        <property>
+            <name>sparkExecutorCores</name>
+            <description>number of cores used by single executor</description>
+        </property>
+    </parameters>
+
+    <global>
+        <job-tracker>${jobTracker}</job-tracker>
+        <name-node>${nameNode}</name-node>
+        <configuration>
+            <property>
+                <name>mapreduce.job.queuename</name>
+                <value>${queueName}</value>
+            </property>
+            <property>
+                <name>oozie.launcher.mapred.job.queue.name</name>
+                <value>${oozieLauncherQueueName}</value>
+            </property>
+        </configuration>
+    </global>
+
+    <start to="CreateSimRel"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="CreateSimRel">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <prepare>
+                <delete path="${workingPath}/${actionSetId}/*_simrel"/>
+            </prepare>
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Create Similarity Relations</name>
+            <class>eu.dnetlib.dhp.dedup.SparkCreateSimRels</class>
+            <jar>dhp-dedup-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory ${sparkExecutorMemory}
+                --executor-cores ${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
+                --conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
+            </spark-opts>
+            <arg>-mt</arg><arg>yarn</arg>
+            <arg>--i</arg><arg>${graphBasePath}</arg>
+            <arg>--la</arg><arg>${isLookUpUrl}</arg>
+            <arg>--asi</arg><arg>${actionSetId}</arg>
+            <arg>--w</arg><arg>${workingPath}</arg>
+        </spark>
+        <ok to="CreateMergeRel"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="CreateMergeRel">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <prepare>
+                <delete path='${workingPath}/${actionSetId}/*_mergerel'/>
+            </prepare>
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Create Merge Relations</name>
+            <class>eu.dnetlib.dhp.dedup.SparkCreateConnectedComponent</class>
+            <jar>dhp-dedup-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory ${sparkExecutorMemory}
+                --executor-cores ${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
+                --conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
+                --conf spark.sql.warehouse.dir="/user/hive/warehouse"
+            </spark-opts>
+            <arg>-mt</arg><arg>yarn</arg>
+            <arg>--i</arg><arg>${graphBasePath}</arg>
+            <arg>--w</arg><arg>${workingPath}</arg>
+            <arg>--la</arg><arg>${isLookUpUrl}</arg>
+            <arg>--asi</arg><arg>${actionSetId}</arg>
+        </spark>
+        <ok to="CreateDedupRecord"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="CreateDedupRecord">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <prepare>
+                <delete path='${workingPath}/${actionSetId}/*_deduprecord'/>
+            </prepare>
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Create Dedup Record</name>
+            <class>eu.dnetlib.dhp.dedup.SparkCreateDedupRecord</class>
+            <jar>dhp-dedup-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory ${sparkExecutorMemory}
+                --executor-cores ${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
+                --conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
+                --conf spark.sql.warehouse.dir="/user/hive/warehouse"
+            </spark-opts>
+            <arg>-mt</arg><arg>yarn</arg>
+            <arg>--i</arg><arg>${graphBasePath}</arg>
+            <arg>--w</arg><arg>${workingPath}</arg>
+            <arg>--la</arg><arg>${isLookUpUrl}</arg>
+            <arg>--asi</arg><arg>${actionSetId}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/updateEntity_parameters.json

@@ -0,0 +1,26 @@
+[
+{
+  "paramName": "mt",
+  "paramLongName": "master",
+  "paramDescription": "should be local or yarn",
+  "paramRequired": true
+},
+{
+  "paramName": "i",
+  "paramLongName": "graphBasePath",
+  "paramDescription": "the base path of raw graph",
+  "paramRequired": true
+},
+{
+  "paramName": "w",
+  "paramLongName": "workingPath",
+  "paramDescription": "the working directory path",
+  "paramRequired": true
+},
+{
+    "paramName": "o",
+    "paramLongName": "dedupGraphPath",
+    "paramDescription": "the path of the dedup graph",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-dedup/src/test/java/eu/dnetlib/dedup/jpath/JsonPathTest.java

@@ -1,31 +0,0 @@
-package eu.dnetlib.dedup.jpath;
-
-import com.fasterxml.jackson.core.JsonProcessingException;
-import com.fasterxml.jackson.databind.ObjectMapper;
-import com.jayway.jsonpath.JsonPath;
-import org.apache.commons.io.IOUtils;
-import org.junit.Test;
-import java.util.List;
-import java.util.Map;
-
-public class JsonPathTest {
-
-    @Test
-    public void testJPath () throws  Exception {
-        final String json = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dedup/conf/sample.json"));
-        List<Map<String, Object>> pid = JsonPath.read(json, "$.pid[*]");
-//        System.out.println(json);
-
-        pid.forEach(it -> {
-            try {
-                System.out.println(new ObjectMapper().writeValueAsString(it));
-            } catch (JsonProcessingException e) {
-                e.printStackTrace();
-            }
-        });
-
-
-
-
-    }
-}

dhp-workflows/dhp-dedup/src/test/java/eu/dnetlib/dhp/dedup/MergeAuthorTest.java

@@ -1,4 +1,4 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
 import eu.dnetlib.dhp.schema.oaf.Publication;
 import org.apache.commons.io.IOUtils;

dhp-workflows/dhp-dedup/src/test/java/eu/dnetlib/dhp/dedup/SparkCreateDedupTest.java

@@ -1,19 +1,16 @@
-package eu.dnetlib.dedup;
+package eu.dnetlib.dhp.dedup;
 
-import com.fasterxml.jackson.databind.ObjectMapper;
 import com.google.common.hash.HashFunction;
 import com.google.common.hash.Hashing;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.schema.oaf.Publication;
-import org.apache.commons.io.FileUtils;
 import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.*;
 import org.junit.Before;
 import org.junit.Ignore;
 import org.junit.Test;
 
-import java.io.File;
 import java.io.IOException;
-import java.util.List;
 
 public class SparkCreateDedupTest {
 
@@ -22,19 +19,20 @@ public class SparkCreateDedupTest {
 
     @Before
     public void setUp() throws IOException {
-        configuration = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dedup/conf/org.curr.conf.json"));
+//        configuration = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dedup/conf/org.curr.conf.json"));
-
+        configuration = "";
     }
 
     @Test
     @Ignore
     public void createSimRelsTest() throws Exception {
-        SparkCreateSimRels.main(new String[] {
+        SparkCreateSimRels.main(new String[]{
                 "-mt", "local[*]",
-                "-s", "/Users/miconis/dumps",
+                "-i", "/Users/miconis/dumps",
-                "-e", entity,
+                "-o", "/tmp/dedup/rawset_test",
-                "-c", ArgumentApplicationParser.compressArgument(configuration),
+                "-asi", "dedup-similarity-result-levenstein",
-                "-t", "/tmp/dedup",
+                "-la", "lookupurl",
+                "-w", "workingPath"
         });
     }
 
@@ -42,7 +40,7 @@ public class SparkCreateDedupTest {
     @Ignore
     public void createCCTest() throws Exception {
 
-        SparkCreateConnectedComponent.main(new String[] {
+        SparkCreateConnectedComponent.main(new String[]{
                 "-mt", "local[*]",
                 "-s", "/Users/miconis/dumps",
                 "-e", entity,
@@ -54,7 +52,7 @@ public class SparkCreateDedupTest {
     @Test
     @Ignore
     public void dedupRecordTest() throws Exception {
-        SparkCreateDedupRecord.main(new String[] {
+        SparkCreateDedupRecord.main(new String[]{
                 "-mt", "local[*]",
                 "-s", "/Users/miconis/dumps",
                 "-e", entity,
@@ -64,23 +62,22 @@ public class SparkCreateDedupTest {
     }
 
     @Test
+    @Ignore
     public void printConfiguration() throws Exception {
         System.out.println(ArgumentApplicationParser.compressArgument(configuration));
     }
 
     @Test
+    @Ignore
     public void testHashCode() {
         final String s1 = "20|grid________::6031f94bef015a37783268ec1e75f17f";
         final String s2 = "20|nsf_________::b12be9edf414df8ee66b4c52a2d8da46";
 
         final HashFunction hashFunction = Hashing.murmur3_128();
 
-        System.out.println( s1.hashCode());
+        System.out.println(s1.hashCode());
         System.out.println(hashFunction.hashString(s1).asLong());
-        System.out.println( s2.hashCode());
+        System.out.println(s2.hashCode());
         System.out.println(hashFunction.hashString(s2).asLong());
-
     }
-
-
 }

dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dedup/conf/pub.curr.conf.json

@@ -1,280 +0,0 @@
-{
-  "wf" : {
-    "threshold" : "0.99",
-    "dedupRun" : "001",
-    "entityType" : "result",
-    "subEntityType" : "resulttype",
-    "subEntityValue" : "publication",
-    "orderField" : "title",
-    "queueMaxSize" : "2000",
-    "groupMaxSize" : "100",
-    "maxChildren" : "100",
-    "idPath": "$.id",
-    "slidingWindowSize" : "200",
-    "rootBuilder" : [ "result", "resultProject_outcome_isProducedBy", "resultResult_publicationDataset_isRelatedTo", "resultResult_similarity_isAmongTopNSimilarDocuments", "resultResult_similarity_hasAmongTopNSimilarDocuments", "resultOrganization_affiliation_isAffiliatedWith", "resultResult_part_hasPart", "resultResult_part_isPartOf", "resultResult_supplement_isSupplementTo", "resultResult_supplement_isSupplementedBy", "resultResult_version_isVersionOf" ],
-    "includeChildren" : "true"
-  },
-  "pace" : {
-    "clustering" : [
-      { "name" : "ngrampairs", "fields" : [ "title" ], "params" : { "max" : "1", "ngramLen" : "3"} },
-      { "name" : "suffixprefix", "fields" : [ "title" ], "params" : { "max" : "1", "len" : "3" } },
-      { "name" : "lowercase", "fields" : [ "doi" ], "params" : { } }
-    ],
-    "strictConditions" : [
-      { "name" : "pidMatch", "fields" : [ "pid" ] }
-    ],
-    "conditions" : [
-      { "name" : "titleVersionMatch", "fields" : [ "title" ] },
-      { "name" : "sizeMatch", "fields" : [ "authors" ] }
-    ],
-    "model" : [
-      { "name" : "doi", "algo" : "Null", "type" : "String", "weight" : "0.0", "ignoreMissing" : "true", "path" : "$.pid[?(@.qualifier.classid ==\"doi\")].value" },
-      { "name" : "pid", "algo" : "Null", "type" : "JSON", "weight" : "0.0", "ignoreMissing" : "true", "path" : "$.pid", "overrideMatch" : "true" },
-      { "name" : "title", "algo" : "LevensteinTitle", "type" : "String", "weight" : "1.0", "ignoreMissing" : "false", "path" : "$.title[?(@.qualifier.classid ==\"main title\")].value", "length" : 250, "size" : 5 },
-      { "name" : "authors", "algo" : "Null", "type" : "List", "weight" : "0.0", "ignoreMissing" : "true", "path" : "$.author[*].fullname", "size" : 200 },
-      { "name" : "resulttype", "algo" : "Null", "type" : "String", "weight" : "0.0", "ignoreMissing" : "false", "path" : "$.resulttype.classid" }
-    ],
-    "synonyms": {},
-    "blacklists" : {
-      "title" : [
-        "^Inside Front Cover$",
-        "(?i)^Poster presentations$",
-        "^THE ASSOCIATION AND THE GENERAL MEDICAL COUNCIL$",
-        "^Problems with perinatal pathology\\.?$",
-        "(?i)^Cases? of Puerperal Convulsions$",
-        "(?i)^Operative Gyna?ecology$",
-        "(?i)^Mind the gap\\!?\\:?$",
-        "^Chronic fatigue syndrome\\.?$",
-        "^Cartas? ao editor Letters? to the Editor$",
-        "^Note from the Editor$",
-        "^Anesthesia Abstract$",
-
-        "^Annual report$",
-        "(?i)^“?THE RADICAL PREVENTION OF VENEREAL DISEASE\\.?”?$",
-        "(?i)^Graph and Table of Infectious Diseases?$",
-        "^Presentation$",
-        "(?i)^Reviews and Information on Publications$",
-        "(?i)^PUBLIC HEALTH SERVICES?$",
-        "(?i)^COMBINED TEXT-?BOOK OF OBSTETRICS AND GYN(Æ|ae)COLOGY$",
-        "(?i)^Adrese autora$",
-        "(?i)^Systematic Part .*\\. Catalogus Fossilium Austriae, Band 2: Echinoidea neogenica$",
-        "(?i)^Acknowledgement to Referees$",
-        "(?i)^Behçet's disease\\.?$",
-        "(?i)^Isolation and identification of restriction endonuclease.*$",
-        "(?i)^CEREBROVASCULAR DISEASES?.?$",
-        "(?i)^Screening for abdominal aortic aneurysms?\\.?$",
-        "^Event management$",
-        "(?i)^Breakfast and Crohn's disease.*\\.?$",
-        "^Cálculo de concentraciones en disoluciones acuosas. Ejercicio interactivo\\..*\\.$",
-        "(?i)^Genetic and functional analyses of SHANK2 mutations suggest a multiple hit model of Autism spectrum disorders?\\.?$",
-        "^Gushi hakubutsugaku$",
-
-        "^Starobosanski nadpisi u Bosni i Hercegovini \\(.*\\)$",
-        "^Intestinal spirocha?etosis$",
-        "^Treatment of Rodent Ulcer$",
-        "(?i)^\\W*Cloud Computing\\W*$",
-        "^Compendio mathematico : en que se contienen todas las materias mas principales de las Ciencias que tratan de la cantidad$",
-        "^Free Communications, Poster Presentations: Session [A-F]$",
-
-        "^“The Historical Aspects? of Quackery\\.?”$",
-        "^A designated centre for people with disabilities operated by St John of God Community Services (Limited|Ltd), Louth$",
-        "^P(er|re)-Mile Premiums for Auto Insurance\\.?$",
-        "(?i)^Case Report$",
-        "^Boletín Informativo$",
-        "(?i)^Glioblastoma Multiforme$",
-        "(?i)^Nuevos táxones animales descritos en la península Ibérica y Macaronesia desde 1994 \\(.*\\)$",
-        "^Zaměstnanecké výhody$",
-        "(?i)^The Economics of Terrorism and Counter-Terrorism: A Survey \\(Part .*\\)$",
-        "(?i)^Carotid body tumours?\\.?$",
-        "(?i)^\\[Españoles en Francia : La condición Emigrante.*\\]$",
-        "^Avant-propos$",
-        "(?i)^St\\. Patrick's Cathedral, Dublin, County Dublin - Head(s)? and Capital(s)?$",
-        "(?i)^St\\. Patrick's Cathedral, Dublin, County Dublin - Bases?$",
-        "(?i)^PUBLIC HEALTH VERSUS THE STATE$",
-        "^Viñetas de Cortázar$",
-        "(?i)^Search for heavy neutrinos and W(\\[|_|\\(|_\\{|-)?R(\\]|\\)|\\})? bosons with right-handed couplings in a left-right symmetric model in pp collisions at.*TeV(\\.)?$",
-        "(?i)^Measurement of the pseudorapidity and centrality dependence of the transverse energy density in Pb(-?)Pb collisions at.*tev(\\.?)$",
-        "(?i)^Search for resonances decaying into top-quark pairs using fully hadronic decays in pp collisions with ATLAS at.*TeV$",
-        "(?i)^Search for neutral minimal supersymmetric standard model Higgs bosons decaying to tau pairs in pp collisions at.*tev$",
-
-        "(?i)^Relatório de Estágio (de|em) Angiologia e Cirurgia Vascular$",
-        "^Aus der AGMB$",
-
-        "^Znanstveno-stručni prilozi$",
-        "(?i)^Zhodnocení finanční situace podniku a návrhy na zlepšení$",
-        "(?i)^Evaluation of the Financial Situation in the Firm and Proposals to its Improvement$",
-        "(?i)^Hodnocení finanční situace podniku a návrhy na její zlepšení$",
-        "^Finanční analýza podniku$",
-        "^Financial analysis( of business)?$",
-        "(?i)^Textbook of Gyn(a)?(Æ)?(e)?cology$",
-        "^Jikken nihon shūshinsho$",
-        "(?i)^CORONER('|s)(s|') INQUESTS$",
-        "(?i)^(Μελέτη παραγόντων )?risk management( για ανάπτυξη και εφαρμογή ενός πληροφοριακού συστήματος| και ανάπτυξη συστήματος)?$",
-        "(?i)^Consultants' contract(s)?$",
-        "(?i)^Upute autorima$",
-        "(?i)^Bijdrage tot de Kennis van den Godsdienst der Dajaks van Lan(d|f)ak en Tajan$",
-        "^Joshi shin kokubun$",
-        "^Kōtō shōgaku dokuhon nōson'yō$",
-        "^Jinjō shōgaku shōka$",
-        "^Shōgaku shūjichō$",
-        "^Nihon joshi dokuhon$",
-        "^Joshi shin dokuhon$",
-        "^Chūtō kanbun dokuhon$",
-        "^Wabun dokuhon$",
-        "(?i)^(Analysis of economy selected village or town|Rozbor hospodaření vybrané obce či města)$",
-        "(?i)^cardiac rehabilitation$",
-        "(?i)^Analytical summary$",
-        "^Thesaurus resolutionum Sacrae Congregationis Concilii$",
-        "(?i)^Sumario analítico(\\s{1})?(Analitic summary)?$",
-        "^Prikazi i osvrti$",
-        "^Rodinný dům s provozovnou$",
-        "^Family house with an establishment$",
-        "^Shinsei chūtō shin kokugun$",
-        "^Pulmonary alveolar proteinosis(\\.?)$",
-        "^Shinshū kanbun$",
-        "^Viñeta(s?) de Rodríguez$",
-        "(?i)^RUBRIKA UREDNIKA$",
-        "^A Matching Model of the Academic Publication Market$",
-        "^Yōgaku kōyō$",
-
-        "^Internetový marketing$",
-        "^Internet marketing$",
-        "^Chūtō kokugo dokuhon$",
-        "^Kokugo dokuhon$",
-        "^Antibiotic Cover for Dental Extraction(s?)$",
-        "^Strategie podniku$",
-        "^Strategy of an Enterprise$",
-        "(?i)^respiratory disease(s?)(\\.?)$",
-        "^Award(s?) for Gallantry in Civil Defence$",
-        "^Podniková kultura$",
-        "^Corporate Culture$",
-        "^Severe hyponatraemia in hospital inpatient(s?)(\\.?)$",
-        "^Pracovní motivace$",
-        "^Work Motivation$",
-        "^Kaitei kōtō jogaku dokuhon$",
-        "^Konsolidovaná účetní závěrka$",
-        "^Consolidated Financial Statements$",
-        "(?i)^intracranial tumour(s?)$",
-        "^Climate Change Mitigation Options and Directed Technical Change: A Decentralized Equilibrium Analysis$",
-        "^\\[CERVECERIAS MAHOU(\\.|\\:) INTERIOR\\] \\[Material gráfico\\]$",
-        "^Housing Market Dynamics(\\:|\\.) On the Contribution of Income Shocks and Credit Constraint(s?)$",
-        "^\\[Funciones auxiliares de la música en Radio París,.*\\]$",
-        "^Úroveň motivačního procesu jako způsobu vedení lidí$",
-        "^The level of motivation process as a leadership$",
-        "^Pay-beds in N(\\.?)H(\\.?)S(\\.?) Hospitals$",
-        "(?i)^news and events$",
-        "(?i)^NOVOSTI I DOGAĐAJI$",
-        "^Sansū no gakushū$",
-        "^Posouzení informačního systému firmy a návrh změn$",
-        "^Information System Assessment and Proposal for ICT Modification$",
-        "^Stresové zatížení pracovníků ve vybrané profesi$",
-        "^Stress load in a specific job$",
-
-        "^Sunday: Poster Sessions, Pt.*$",
-        "^Monday: Poster Sessions, Pt.*$",
-        "^Wednesday: Poster Sessions, Pt.*",
-        "^Tuesday: Poster Sessions, Pt.*$",
-
-        "^Analýza reklamy$",
-        "^Analysis of advertising$",
-
-        "^Shōgaku shūshinsho$",
-        "^Shōgaku sansū$",
-        "^Shintei joshi kokubun$",
-        "^Taishō joshi kokubun dokuhon$",
-        "^Joshi kokubun$",
-
-        "^Účetní uzávěrka a účetní závěrka v ČR$",
-        "(?i)^The \"?Causes\"? of Cancer$",
-        "^Normas para la publicación de artículos$",
-        "^Editor('|s)(s|') [Rr]eply$",
-        "^Editor(’|s)(s|’) letter$",
-        "^Redaktoriaus žodis$",
-        "^DISCUSSION ON THE PRECEDING PAPER$",
-        "^Kōtō shōgaku shūshinsho jidōyō$",
-        "^Shōgaku nihon rekishi$",
-        "^(Theory of the flow of action currents in isolated myelinated nerve fibers).*$",
-        "^Préface$",
-        "^Occupational [Hh]ealth [Ss]ervices.$",
-        "^In Memoriam Professor Toshiyuki TAKESHIMA$",
-        "^Účetní závěrka ve vybraném podniku.*$",
-        "^Financial statements in selected company$",
-        "^Abdominal [Aa]ortic [Aa]neurysms.*$",
-        "^Pseudomyxoma peritonei$",
-        "^Kazalo autora$",
-
-        "(?i)^uvodna riječ$",
-        "^Motivace jako způsob vedení lidí$",
-        "^Motivation as a leadership$",
-        "^Polyfunkční dům$",
-        "^Multi\\-funkcional building$",
-        "^Podnikatelský plán$",
-        "(?i)^Podnikatelský záměr$",
-        "(?i)^Business Plan$",
-        "^Oceňování nemovitostí$",
-        "^Marketingová komunikace$",
-        "^Marketing communication$",
-        "^Sumario Analítico$",
-        "^Riječ uredništva$",
-        "^Savjetovanja i priredbe$",
-        "^Índice$",
-        "^(Starobosanski nadpisi).*$",
-        "^Vzdělávání pracovníků v organizaci$",
-        "^Staff training in organization$",
-        "^(Life Histories of North American Geometridae).*$",
-        "^Strategická analýza podniku$",
-        "^Strategic Analysis of an Enterprise$",
-        "^Sadržaj$",
-        "^Upute suradnicima$",
-        "^Rodinný dům$",
-        "(?i)^Fami(l)?ly house$",
-        "^Upute autorima$",
-        "^Strategic Analysis$",
-        "^Finanční analýza vybraného podniku$",
-        "^Finanční analýza$",
-        "^Riječ urednika$",
-        "(?i)^Content(s?)$",
-        "(?i)^Inhalt$",
-        "^Jinjō shōgaku shūshinsho jidōyō$",
-        "(?i)^Index$",
-        "^Chūgaku kokubun kyōkasho$",
-        "^Retrato de una mujer$",
-        "^Retrato de un hombre$",
-        "^Kōtō shōgaku dokuhon$",
-        "^Shotōka kokugo$",
-        "^Shōgaku dokuhon$",
-        "^Jinjō shōgaku kokugo dokuhon$",
-        "^Shinsei kokugo dokuhon$",
-        "^Teikoku dokuhon$",
-        "^Instructions to Authors$",
-        "^KİTAP TAHLİLİ$",
-        "^PRZEGLĄD PIŚMIENNICTWA$",
-        "(?i)^Presentación$",
-        "^İçindekiler$",
-        "(?i)^Tabl?e of contents$",
-        "^(CODICE DEL BEATO DE LOS REYES FERNANDO I Y SANCHA).*$",
-        "^(\\[MADRID\\. BIBL\\. NAC\\. N.*KING FERDINAND I.*FROM SAN ISIDORO DE LEON\\. FACUNDUS SCRIPSIT DATED.*\\]).*",
-        "^Editorial( Board)?$",
-        "(?i)^Editorial \\(English\\)$",
-        "^Editörden$",
-        "^(Corpus Oral Dialectal \\(COD\\)\\.).*$",
-        "^(Kiri Karl Morgensternile).*$",
-        "^(\\[Eksliibris Aleksandr).*\\]$",
-        "^(\\[Eksliibris Aleksandr).*$",
-        "^(Eksliibris Aleksandr).*$",
-        "^(Kiri A\\. de Vignolles).*$",
-        "^(2 kirja Karl Morgensternile).*$",
-        "^(Pirita kloostri idaosa arheoloogilised).*$",
-        "^(Kiri tundmatule).*$",
-        "^(Kiri Jenaer Allgemeine Literaturzeitung toimetusele).*$",
-        "^(Eksliibris Nikolai Birukovile).*$",
-        "^(Eksliibris Nikolai Issakovile).*$",
-        "^(WHP Cruise Summary Information of section).*$",
-        "^(Measurement of the top quark\\-pair production cross section with ATLAS in pp collisions at).*$",
-        "^(Measurement of the spin\\-dependent structure function).*",
-        "(?i)^.*authors['’′]? reply\\.?$",
-        "(?i)^.*authors['’′]? response\\.?$"
-      ]
-    }
-  }
-}

dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dhp/dedup/conf/org.curr.conf.json

@@ -3,6 +3,7 @@
     "threshold" : "0.99",
     "dedupRun" : "001",
     "entityType" : "organization",
+    "subEntityValue": "organization",
     "orderField" : "legalname",
     "queueMaxSize" : "2000",
     "groupMaxSize" : "50",
@@ -87,8 +88,8 @@
             }
           }
         ],
-        "threshold": 0.7,
+        "threshold": 0.1,
-        "aggregation": "W_MEAN",
+        "aggregation": "AVG",
         "positive": "layer4",
         "negative": "NO_MATCH",
         "undefined": "NO_MATCH",
@@ -106,7 +107,7 @@
             }
           }
         ],
-        "threshold": 0.9,
+        "threshold": 0.7,
         "aggregation": "AVG",
         "positive": "layer5",
         "negative": "NO_MATCH",
@@ -129,7 +130,9 @@
             "comparator": "jaroWinklerNormalizedName",
             "weight": 0.1,
             "countIfUndefined": "false",
-            "params": {}
+            "params": {
+              "windowSize": 4
+            }
           }
         ],
         "threshold": 0.9,
@@ -145,14 +148,14 @@
       { "name" : "legalshortname", "type" : "String", "path" : "$.legalshortname.value"},
       { "name" : "legalname", "type" : "String", "path" : "$.legalname.value" },
       { "name" : "websiteurl", "type" : "URL", "path" : "$.websiteurl.value" },
-      { "name" : "gridid", "type" : "String", "path" : "$.pid[?(@.qualifier.classid =='grid.ac')].value"},
+      { "name" : "gridid", "type" : "String", "path" : "$.pid[?(@.qualifier.classid =='grid')].value"},
       { "name" : "originalId", "type" : "String", "path" : "$.id" }
     ],
     "blacklists" : {
       "legalname" : []
     },
     "synonyms": {
-      "key::1": ["university","università","università studi","universitario","universitaria","université", "universite", "universitaire","universitaires","universidad","universitade","Universität","universitaet","Uniwersytet","университет","universiteit","πανεπιστήμιο","universitesi","universiteti", "universiti"],
+      "key::1": ["university","università", "universitas", "università studi","universitario","universitaria","université", "universite", "universitaire","universitaires","universidad","universitade","Universität","universitaet","Uniwersytet","университет","universiteit","πανεπιστήμιο","universitesi","universiteti", "universiti"],
       "key::2": ["studies","studi","études","estudios","estudos","Studien","studia","исследования","studies","σπουδές"],
       "key::3": ["advanced","superiore","supérieur","supérieure","supérieurs","supérieures","avancado","avancados","fortgeschrittene","fortgeschritten","zaawansowany","передовой","gevorderd","gevorderde","προχωρημένος","προχωρημένη","προχωρημένο","προχωρημένες","προχωρημένα","wyzsza"],
       "key::4": ["institute","istituto","institut","instituto","instituto","Institut","instytut","институт","instituut","ινστιτούτο"],

dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dhp/dedup/conf/pub.curr.conf.json

@@ -28,34 +28,10 @@
     "idPath": "$.id"
   },
   "pace": {
-    "clustering": [
+    "clustering" : [
-      {
+      { "name" : "ngrampairs", "fields" : [ "title" ], "params" : { "max" : "1", "ngramLen" : "3"} },
-        "name": "ngrampairs",
+      { "name" : "suffixprefix", "fields" : [ "title" ], "params" : { "max" : "1", "len" : "3" } },
-        "fields": [
+      { "name" : "lowercase", "fields" : [ "doi" ], "params" : { } }
-          "title"
-        ],
-        "params": {
-          "max": "1",
-          "ngramLen": "3"
-        }
-      },
-      {
-        "name": "suffixprefix",
-        "fields": [
-          "title"
-        ],
-        "params": {
-          "max": "1",
-          "len": "3"
-        }
-      },
-      {
-        "name": "lowercase",
-        "fields": [
-          "doi"
-        ],
-        "params": {}
-      }
     ],
     "decisionTree": {
       "start": {

dhp-workflows/dhp-graph-provision/job-override.properties

@@ -1,12 +1,14 @@
-sparkDriverMemory=10G
+sparkExecutorCoresForJoining=1
-sparkExecutorMemory=15G
+sparkDriverMemoryForJoining=10G
+sparkExecutorMemoryForJoining=15G
+sparkExecutorCoresForIndexing=64
+sparkDriverMemoryForIndexing=3G
+sparkExecutorMemoryForIndexing=2G
 #isLookupUrl=http://services.openaire.eu:8280/is/services/isLookUp
 isLookupUrl=http://beta.services.openaire.eu:8280/is/services/isLookUp?wsdl
 sourcePath=/tmp/db_openaireplus_services.export_dhp.2020.02.03
 outputPath=/tmp/openaire_provision
 format=TMF
 batchSize=2000
-sparkExecutorCoresForJoining=128
-sparkExecutorCoresForIndexing=64
 reuseRecords=false
 otherDsTypeId=scholarcomminfra, infospace, pubsrepository::mock, entityregistry, entityregistry::projects, entityregistry::repositories, websource

pom.xml

@@ -1,6 +1,6 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0"
-	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+		 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+		 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
 
 	<modelVersion>4.0.0</modelVersion>
 	<groupId>eu.dnetlib.dhp</groupId>
@@ -101,12 +101,12 @@
 			<dependency>
 				<groupId>org.apache.hadoop</groupId>
 				<artifactId>hadoop-common</artifactId>
-                <version>${dhp.hadoop.version}</version>
+				<version>${dhp.hadoop.version}</version>
-                <scope>provided</scope>
+				<scope>provided</scope>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>org.apache.hadoop</groupId>
+				<groupId>org.apache.hadoop</groupId>
-                <artifactId>hadoop-client</artifactId>
+				<artifactId>hadoop-client</artifactId>
 				<version>${dhp.hadoop.version}</version>
 				<scope>provided</scope>
 			</dependency>
@@ -174,11 +174,11 @@
 				<scope>provided</scope>
 			</dependency>
 
-            <dependency>
+			<dependency>
-                <groupId>net.sf.saxon</groupId>
+				<groupId>net.sf.saxon</groupId>
-                <artifactId>Saxon-HE</artifactId>
+				<artifactId>Saxon-HE</artifactId>
-                <version>9.9.1-6</version>
+				<version>9.9.1-6</version>
-            </dependency>
+			</dependency>
 
 			<dependency>
 				<groupId>dom4j</groupId>
@@ -199,56 +199,56 @@
 			</dependency>
 
 			<dependency>
-                <groupId>com.mycila.xmltool</groupId>
+				<groupId>com.mycila.xmltool</groupId>
-                <artifactId>xmltool</artifactId>
+				<artifactId>xmltool</artifactId>
-                <version>3.3</version>
+				<version>3.3</version>
-            </dependency>
+			</dependency>
 
-            <dependency>
+			<dependency>
-                <groupId>org.apache.solr</groupId>
+				<groupId>org.apache.solr</groupId>
-                <artifactId>solr-solrj</artifactId>
+				<artifactId>solr-solrj</artifactId>
-                <version>7.5.0</version>
+				<version>7.5.0</version>
-                <exclusions>
+				<exclusions>
-                    <exclusion>
+					<exclusion>
-                        <artifactId>*</artifactId>
+						<artifactId>*</artifactId>
-                        <groupId>*</groupId>
+						<groupId>*</groupId>
-                    </exclusion>
+					</exclusion>
-                </exclusions>
+				</exclusions>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>com.lucidworks.spark</groupId>
+				<groupId>com.lucidworks.spark</groupId>
-                <artifactId>spark-solr</artifactId>
+				<artifactId>spark-solr</artifactId>
-                <version>3.6.0</version>
+				<version>3.6.0</version>
-                <exclusions>
+				<exclusions>
-                    <exclusion>
+					<exclusion>
-                        <artifactId>*</artifactId>
+						<artifactId>*</artifactId>
-                        <groupId>*</groupId>
+						<groupId>*</groupId>
-                    </exclusion>
+					</exclusion>
-                </exclusions>
+				</exclusions>
-            </dependency>
+			</dependency>
 
-            <dependency>
+			<dependency>
-                <groupId>org.apache.httpcomponents</groupId>
+				<groupId>org.apache.httpcomponents</groupId>
-                <artifactId>httpclient</artifactId>
+				<artifactId>httpclient</artifactId>
-                <version>4.5.3</version>
+				<version>4.5.3</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>org.apache.httpcomponents</groupId>
+				<groupId>org.apache.httpcomponents</groupId>
-                <artifactId>httpmime</artifactId>
+				<artifactId>httpmime</artifactId>
-                <version>4.5.3</version>
+				<version>4.5.3</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>org.noggit</groupId>
+				<groupId>org.noggit</groupId>
-                <artifactId>noggit</artifactId>
+				<artifactId>noggit</artifactId>
-                <version>0.8</version>
+				<version>0.8</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>org.apache.zookeeper</groupId>
+				<groupId>org.apache.zookeeper</groupId>
-                <artifactId>zookeeper</artifactId>
+				<artifactId>zookeeper</artifactId>
-                <version>3.4.11</version>
+				<version>3.4.11</version>
-            </dependency>
+			</dependency>
 
-            <dependency>
+			<dependency>
 				<groupId>net.schmizz</groupId>
 				<artifactId>sshj</artifactId>
 				<version>0.10.0</version>
@@ -290,17 +290,17 @@
 				<artifactId>dnet-pace-core</artifactId>
 				<version>4.0.0</version>
 			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>eu.dnetlib</groupId>
+				<groupId>eu.dnetlib</groupId>
-                <artifactId>cnr-rmi-api</artifactId>
+				<artifactId>cnr-rmi-api</artifactId>
-                <version>[2.0.0,3.0.0)</version>
+				<version>[2.0.0,3.0.0)</version>
-            </dependency>
+			</dependency>
 
-            <dependency>
+			<dependency>
-                <groupId>org.apache.cxf</groupId>
+				<groupId>org.apache.cxf</groupId>
-                <artifactId>cxf-rt-transports-http</artifactId>
+				<artifactId>cxf-rt-transports-http</artifactId>
-                <version>3.1.5</version>
+				<version>3.1.5</version>
-            </dependency>
+			</dependency>
 			<dependency>
 				<groupId>javax.persistence</groupId>
 				<artifactId>javax.persistence-api</artifactId>
@@ -308,36 +308,36 @@
 				<scope>provided</scope>
 			</dependency>
 
-            <dependency>
+			<dependency>
-                <groupId>com.rabbitmq</groupId>
+				<groupId>com.rabbitmq</groupId>
-                <artifactId>amqp-client</artifactId>
+				<artifactId>amqp-client</artifactId>
-                <version>5.6.0</version>
+				<version>5.6.0</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>com.jayway.jsonpath</groupId>
+				<groupId>com.jayway.jsonpath</groupId>
-                <artifactId>json-path</artifactId>
+				<artifactId>json-path</artifactId>
-                <version>2.4.0</version>
+				<version>2.4.0</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>com.arakelian</groupId>
+				<groupId>com.arakelian</groupId>
-                <artifactId>java-jq</artifactId>
+				<artifactId>java-jq</artifactId>
-                <version>0.10.1</version>
+				<version>0.10.1</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>edu.cmu</groupId>
+				<groupId>edu.cmu</groupId>
-                <artifactId>secondstring</artifactId>
+				<artifactId>secondstring</artifactId>
-                <version>1.0.0</version>
+				<version>1.0.0</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>org.mongodb</groupId>
+				<groupId>org.mongodb</groupId>
-                <artifactId>mongo-java-driver</artifactId>
+				<artifactId>mongo-java-driver</artifactId>
-                <version>${mongodb.driver.version}</version>
+				<version>${mongodb.driver.version}</version>
-            </dependency>
+			</dependency>
-            <dependency>
+			<dependency>
-                <groupId>org.antlr</groupId>
+				<groupId>org.antlr</groupId>
-                <artifactId>stringtemplate</artifactId>
+				<artifactId>stringtemplate</artifactId>
-                <version>4.0</version>
+				<version>4.0</version>
-            </dependency>
+			</dependency>
 
 			<dependency>
 				<groupId>org.apache.oozie</groupId>
@@ -509,4 +509,3 @@
 		<mongodb.driver.version>3.4.2</mongodb.driver.version>
 	</properties>
 </project>
-