public class SparkUpdateEntity extends Object
| Modifier and Type | Field and Description |
|---|---|
protected static int |
NUM_CONNECTIONS |
protected static int |
NUM_PARTITIONS |
protected static com.fasterxml.jackson.databind.ObjectMapper |
OBJECT_MAPPER |
eu.dnetlib.dhp.application.ArgumentApplicationParser |
parser |
protected static String |
SP_SEPARATOR |
org.apache.spark.sql.SparkSession |
spark |
protected static String |
TYPE_VALUE_SEPARATOR |
| Constructor and Description |
|---|
SparkUpdateEntity(eu.dnetlib.dhp.application.ArgumentApplicationParser parser,
org.apache.spark.sql.SparkSession spark) |
| Modifier and Type | Method and Description |
|---|---|
List<eu.dnetlib.pace.config.DedupConfig> |
getConfigurations(eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService isLookUpService,
String orchestrator) |
protected static org.apache.spark.sql.SparkSession |
getSparkSession(org.apache.spark.SparkConf conf) |
protected boolean |
isOpenorgs(eu.dnetlib.dhp.schema.oaf.Relation rel) |
protected boolean |
isOpenorgsDedupRel(eu.dnetlib.dhp.schema.oaf.Relation rel) |
static void |
main(String[] args) |
boolean |
mergeRelExists(String basePath,
String entity) |
protected static Boolean |
parseECField(eu.dnetlib.dhp.schema.oaf.Field<String> field) |
protected static org.apache.spark.api.java.function.MapFunction<String,eu.dnetlib.dhp.schema.oaf.Relation> |
patchRelFn() |
protected static void |
removeOutputDir(org.apache.spark.sql.SparkSession spark,
String path) |
void |
run(eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService isLookUpService) |
protected static <T> void |
save(org.apache.spark.sql.Dataset<T> dataset,
String outPath,
org.apache.spark.sql.SaveMode mode) |
protected static <T> void |
saveParquet(org.apache.spark.sql.Dataset<T> dataset,
String outPath,
org.apache.spark.sql.SaveMode mode) |
protected static String |
structuredPropertyListToString(List<eu.dnetlib.dhp.schema.oaf.StructuredProperty> list) |
protected static final int NUM_PARTITIONS
protected static final int NUM_CONNECTIONS
protected static final String TYPE_VALUE_SEPARATOR
protected static final String SP_SEPARATOR
protected static final com.fasterxml.jackson.databind.ObjectMapper OBJECT_MAPPER
public final eu.dnetlib.dhp.application.ArgumentApplicationParser parser
public final org.apache.spark.sql.SparkSession spark
public SparkUpdateEntity(eu.dnetlib.dhp.application.ArgumentApplicationParser parser,
org.apache.spark.sql.SparkSession spark)
public void run(eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService isLookUpService)
throws IOException
IOExceptionpublic boolean mergeRelExists(String basePath, String entity) throws IOException
IOExceptionpublic List<eu.dnetlib.pace.config.DedupConfig> getConfigurations(eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService isLookUpService, String orchestrator) throws eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException, org.dom4j.DocumentException, IOException, SAXException
eu.dnetlib.enabling.is.lookup.rmi.ISLookUpExceptionorg.dom4j.DocumentExceptionIOExceptionSAXExceptionprotected static org.apache.spark.sql.SparkSession getSparkSession(org.apache.spark.SparkConf conf)
protected static <T> void save(org.apache.spark.sql.Dataset<T> dataset,
String outPath,
org.apache.spark.sql.SaveMode mode)
protected static <T> void saveParquet(org.apache.spark.sql.Dataset<T> dataset,
String outPath,
org.apache.spark.sql.SaveMode mode)
protected static void removeOutputDir(org.apache.spark.sql.SparkSession spark,
String path)
protected static String structuredPropertyListToString(List<eu.dnetlib.dhp.schema.oaf.StructuredProperty> list)
protected static org.apache.spark.api.java.function.MapFunction<String,eu.dnetlib.dhp.schema.oaf.Relation> patchRelFn()
protected boolean isOpenorgs(eu.dnetlib.dhp.schema.oaf.Relation rel)
protected boolean isOpenorgsDedupRel(eu.dnetlib.dhp.schema.oaf.Relation rel)
Copyright © 2022. All rights reserved.