forked from D-Net/dnet-hadoop
[aggregator graph] using dedicated path to sync claims, adjusted paths with wildcards
This commit is contained in:
parent
5b8fd37314
commit
e28d395e87
|
@ -9,7 +9,6 @@ import java.util.Objects;
|
||||||
import java.util.Optional;
|
import java.util.Optional;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
import org.apache.hadoop.io.Text;
|
import org.apache.hadoop.io.Text;
|
||||||
|
@ -30,6 +29,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
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.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||||
|
|
|
@ -9,7 +9,6 @@ import java.util.Objects;
|
||||||
import java.util.Optional;
|
import java.util.Optional;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.hadoop.io.Text;
|
import org.apache.hadoop.io.Text;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
|
@ -24,6 +23,7 @@ import org.slf4j.LoggerFactory;
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
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.schema.oaf.Oaf;
|
||||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
||||||
|
|
|
@ -9,7 +9,6 @@ import java.util.Set;
|
||||||
import java.util.concurrent.atomic.AtomicInteger;
|
import java.util.concurrent.atomic.AtomicInteger;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
import org.apache.commons.logging.Log;
|
import org.apache.commons.logging.Log;
|
||||||
import org.apache.commons.logging.LogFactory;
|
import org.apache.commons.logging.LogFactory;
|
||||||
|
@ -17,14 +16,15 @@ import org.apache.hadoop.conf.Configuration;
|
||||||
import org.apache.hadoop.fs.Path;
|
import org.apache.hadoop.fs.Path;
|
||||||
import org.apache.hadoop.io.SequenceFile;
|
import org.apache.hadoop.io.SequenceFile;
|
||||||
import org.apache.hadoop.io.Text;
|
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.core.JsonProcessingException;
|
||||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||||
import org.apache.spark.api.java.JavaSparkContext;
|
|
||||||
import org.apache.spark.sql.SparkSession;
|
|
||||||
|
|
||||||
public class AbstractMigrationApplication implements Closeable {
|
public class AbstractMigrationApplication implements Closeable {
|
||||||
|
|
||||||
|
@ -104,10 +104,10 @@ public class AbstractMigrationApplication implements Closeable {
|
||||||
protected static List<String> listEntityPaths(final SparkSession spark, final String paths) {
|
protected static List<String> listEntityPaths(final SparkSession spark, final String paths) {
|
||||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||||
return Arrays
|
return Arrays
|
||||||
.stream(paths.split(","))
|
.stream(paths.split(","))
|
||||||
.filter(StringUtils::isNotBlank)
|
.filter(StringUtils::isNotBlank)
|
||||||
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()) || p.contains("/*"))
|
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()) || p.contains("/*"))
|
||||||
.collect(Collectors.toList());
|
.collect(Collectors.toList());
|
||||||
}
|
}
|
||||||
|
|
||||||
public ObjectMapper getObjectMapper() {
|
public ObjectMapper getObjectMapper() {
|
||||||
|
|
|
@ -456,7 +456,7 @@
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
</spark-opts>
|
</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>${workingDir}/invalid_records_claim</arg>
|
<arg>--invalidPath</arg><arg>${workingDir}/invalid_records_claim</arg>
|
||||||
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
|
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
|
@ -480,7 +480,7 @@
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
</spark-opts>
|
</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>${workingDir}/entities_claim</arg>
|
<arg>--targetPath</arg><arg>${workingDir}/entities_claim</arg>
|
||||||
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
|
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
|
||||||
<arg>--shouldHashId</arg><arg>${shouldHashId}</arg>
|
<arg>--shouldHashId</arg><arg>${shouldHashId}</arg>
|
||||||
|
|
Loading…
Reference in New Issue