Merge pull request '[aggregator graph] handle paths including wildcards' (#281) from aggregator_graph into beta

Reviewed-on: D-Net/dnet-hadoop#281

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/project/PrepareH2020ProgrammeTest.java

@@ -92,7 +92,7 @@ public class PrepareH2020ProgrammeTest {
 
 		Assertions.assertEquals(0, verificationDataset.filter("classification = ''").count());
 
-		//tmp.foreach(csvProgramme -> System.out.println(OBJECT_MAPPER.writeValueAsString(csvProgramme)));
+		// tmp.foreach(csvProgramme -> System.out.println(OBJECT_MAPPER.writeValueAsString(csvProgramme)));
 
 		Assertions
 			.assertEquals(

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/project/ReadProjectsTest.java

@@ -98,7 +98,7 @@ public class ReadProjectsTest {
 		Assertions.assertEquals("H2020-EU.1.3.", project.getLegalBasis());
 		Assertions.assertEquals("MSCA-IF-2019", project.getTopics());
 
-		//tmp.foreach(p -> System.out.println(OBJECT_MAPPER.writeValueAsString(p)));
+		// tmp.foreach(p -> System.out.println(OBJECT_MAPPER.writeValueAsString(p)));
 
 	}
 }

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/project/ReadTopicTest.java

@@ -93,7 +93,7 @@ public class ReadTopicTest {
 		Assertions.assertEquals("Individual Fellowships", topic.getTitle());
 		Assertions.assertEquals("MSCA-IF-2019", topic.getTopic());
 
-		//tmp.foreach(p -> System.out.println(OBJECT_MAPPER.writeValueAsString(p)));
+		// tmp.foreach(p -> System.out.println(OBJECT_MAPPER.writeValueAsString(p)));
 
 	}
 }

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

@@ -29,6 +29,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
+import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.*;
 import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
@@ -36,7 +37,7 @@ import eu.dnetlib.dhp.utils.ISLookupClientFactory;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
 import scala.Tuple2;
 
-public class GenerateEntitiesApplication {
+public class GenerateEntitiesApplication extends AbstractMigrationApplication {
 
 	private static final Logger log = LoggerFactory.getLogger(GenerateEntitiesApplication.class);
 
@@ -112,15 +113,12 @@ public class GenerateEntitiesApplication {
 		final boolean shouldHashId,
 		final Mode mode) {
 
-		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		final List<String> existingSourcePaths = listEntityPaths(spark, sourcePaths);
-		final List<String> existingSourcePaths = Arrays
-			.stream(sourcePaths.split(","))
-			.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
-			.collect(Collectors.toList());
 
 		log.info("Generate entities from files:");
 		existingSourcePaths.forEach(log::info);
 
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 		JavaRDD<Oaf> inputRdd = sc.emptyRDD();
 
 		for (final String sp : existingSourcePaths) {

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

@@ -23,12 +23,13 @@ import org.slf4j.LoggerFactory;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
+import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
 import eu.dnetlib.dhp.schema.oaf.Oaf;
 import eu.dnetlib.dhp.utils.ISLookupClientFactory;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
 import scala.Tuple2;
 
-public class VerifyRecordsApplication {
+public class VerifyRecordsApplication extends AbstractMigrationApplication {
 
 	private static final Logger log = LoggerFactory.getLogger(VerifyRecordsApplication.class);
 
@@ -69,15 +70,13 @@ public class VerifyRecordsApplication {
 	private static void validateRecords(SparkSession spark, String sourcePaths, String invalidPath,
 		VocabularyGroup vocs) {
 
-		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		final List<String> existingSourcePaths = listEntityPaths(spark, sourcePaths);
-		final List<String> existingSourcePaths = Arrays
-			.stream(sourcePaths.split(","))
-			.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
-			.collect(Collectors.toList());
 
 		log.info("Verify records in files:");
 		existingSourcePaths.forEach(log::info);
 
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+
 		for (final String sp : existingSourcePaths) {
 			RDD<String> invalidRecords = sc
 				.sequenceFile(sp, Text.class, Text.class)

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

@@ -3,19 +3,26 @@ package eu.dnetlib.dhp.oa.graph.raw.common;
 
 import java.io.Closeable;
 import java.io.IOException;
+import java.util.Arrays;
+import java.util.List;
 import java.util.Set;
 import java.util.concurrent.atomic.AtomicInteger;
+import java.util.stream.Collectors;
 
+import org.apache.commons.lang3.StringUtils;
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.io.SequenceFile;
 import org.apache.hadoop.io.Text;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SparkSession;
 
 import com.fasterxml.jackson.core.JsonProcessingException;
 import com.fasterxml.jackson.databind.ObjectMapper;
 
+import eu.dnetlib.dhp.common.HdfsSupport;
 import eu.dnetlib.dhp.schema.oaf.Oaf;
 import eu.dnetlib.dhp.utils.DHPUtils;
 
@@ -94,6 +101,15 @@ public class AbstractMigrationApplication implements Closeable {
 		}
 	}
 
+	protected static List<String> listEntityPaths(final SparkSession spark, final String paths) {
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		return Arrays
+			.stream(paths.split(","))
+			.filter(StringUtils::isNotBlank)
+			.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()) || p.contains("/*"))
+			.collect(Collectors.toList());
+	}
+
 	public ObjectMapper getObjectMapper() {
 		return objectMapper;
 	}

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml

@@ -215,7 +215,7 @@
     <action name="ImportODF_claims">
         <java>
             <main-class>eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication</main-class>
-            <arg>--hdfsPath</arg><arg>${contentPath}/mdstore</arg>
+            <arg>--hdfsPath</arg><arg>${contentPath}/odf_claims</arg>
             <arg>--mongoBaseUrl</arg><arg>${mongoURL}</arg>
             <arg>--mongoDb</arg><arg>${mongoDb}</arg>
             <arg>--mdFormat</arg><arg>ODF</arg>
@@ -238,7 +238,7 @@
     <action name="ImportOAF_claims">
         <java>
             <main-class>eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication</main-class>
-            <arg>--hdfsPath</arg><arg>${contentPath}/mdstore</arg>
+            <arg>--hdfsPath</arg><arg>${contentPath}/oaf_claims</arg>
             <arg>--mongoBaseUrl</arg><arg>${mongoURL}</arg>
             <arg>--mongoDb</arg><arg>${mongoDb}</arg>
             <arg>--mdFormat</arg><arg>OAF</arg>
@@ -456,7 +456,7 @@
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
             </spark-opts>
-            <arg>--sourcePaths</arg><arg>${contentPath}/db_claims,${contentPath}/oaf_claims,${contentPath}/odf_claims</arg>
+            <arg>--sourcePaths</arg><arg>${contentPath}/db_claims,${contentPath}/oaf_claims/*/*,${contentPath}/odf_claims/*/*</arg>
             <arg>--invalidPath</arg><arg>${workingDir}/invalid_records_claim</arg>
             <arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
         </spark>
@@ -480,7 +480,7 @@
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
             </spark-opts>
-            <arg>--sourcePaths</arg><arg>${contentPath}/db_claims,${contentPath}/oaf_claims,${contentPath}/odf_claims</arg>
+            <arg>--sourcePaths</arg><arg>${contentPath}/db_claims,${contentPath}/oaf_claims/*/*,${contentPath}/odf_claims/*/*</arg>
             <arg>--targetPath</arg><arg>${workingDir}/entities_claim</arg>
             <arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
             <arg>--shouldHashId</arg><arg>${shouldHashId}</arg>