diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java index 883f5ca86..c47075272 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java @@ -109,12 +109,12 @@ public class PrepareResultCommunitySet { }); }); - if(cl.size() == 0) + if (cl.size() == 0) return null; rpl.setCommunityList(cl); return rpl; }, Encoders.bean(ResultProjectList.class)) - .filter(Objects::nonNull) + .filter(Objects::nonNull) .write() .mode(SaveMode.Overwrite) .option("compression", "gzip") diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java index daef6a317..90c30f812 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java @@ -62,10 +62,8 @@ public class SparkResultToCommunityFromProject implements Serializable { final String possibleupdatespath = parser.get("preparedInfoPath"); log.info("preparedInfoPath: {}", possibleupdatespath); - SparkConf conf = new SparkConf(); - runWithSparkSession( conf, isSparkSessionManaged, diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml index 7a5fd7434..d5d75fbc1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml @@ -92,7 +92,7 @@ --executor-cores=6 --executor-memory=5G - --spark.executor.memoryOverhead=3g + --conf spark.executor.memoryOverhead=3g --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} @@ -121,7 +121,7 @@ --executor-cores=6 --executor-memory=5G - --spark.executor.memoryOverhead=3g + --conf spark.executor.memoryOverhead=3g --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json index 8b6291e5d..9a50c79fa 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json @@ -5,12 +5,7 @@ "paramDescription": "the path of the sequencial file to read", "paramRequired": true }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, + { "paramName": "ssm", "paramLongName": "isSparkSessionManaged", diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml new file mode 100644 index 000000000..2744ea92b --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml new file mode 100644 index 000000000..21cc2d887 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml @@ -0,0 +1,144 @@ + + + + sourcePath + the source path + + + + outputPath + the output path + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + + + + + + + + + + + + + ${nameNode}/${sourcePath}/relation + ${nameNode}/${outputPath}/relation + + + + + + + + ${nameNode}/${sourcePath}/organization + ${nameNode}/${outputPath}/organization + + + + + + + + ${nameNode}/${sourcePath}/project + ${nameNode}/${outputPath}/project + + + + + + + + ${nameNode}/${sourcePath}/datasource + ${nameNode}/${outputPath}/datasource + + + + + + + + + + yarn + cluster + Prepare-Community-Result-Organization + eu.dnetlib.dhp.resulttocommunityfromproject.PrepareResultCommunitySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath}/relation + --outputPath${workingDir}/preparedInfo/resultCommunityList + --production${production} + + + + + + + + yarn + cluster + community2resultfromproject + eu.dnetlib.dhp.resulttocommunityfromproject.SparkResultToCommunityFromProject + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList + --sourcePath${sourcePath}/ + --outputPath${outputPath}/ + + + + + + + + + + \ No newline at end of file