sabeel
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

[OC] using the common pid cleaning function

This commit is contained in:
Claudio Atzori 2023-10-06 14:48:05 +02:00
parent 46034630cf
commit 84a58802ab
1 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java
View File

@ -7,6 +7,7 @@ import java.io.IOException;
import java.io.Serializable; import java.io.Serializable;
import java.util.*; import java.util.*;
import eu.dnetlib.dhp.schema.oaf.utils.*;
import org.apache.commons.cli.ParseException; import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Text;
@ -29,10 +30,6 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction; import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.schema.oaf.utils.PidType;
import eu.dnetlib.dhp.utils.DHPUtils; import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2; import scala.Tuple2;
@ -136,19 +133,19 @@ public class CreateActionSetSparkJob implements Serializable {
prefix = DOI_PREFIX; prefix = DOI_PREFIX;
citing = prefix citing = prefix
+ IdentifierFactory + IdentifierFactory
.md5(CleaningFunctions.normalizePidValue(PidType.doi.toString(), value.getCiting())); .md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting()));
cited = prefix cited = prefix
+ IdentifierFactory + IdentifierFactory
.md5(CleaningFunctions.normalizePidValue(PidType.doi.toString(), value.getCited())); .md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited()));
break; break;
case POCI: case POCI:
prefix = PMID_PREFIX; prefix = PMID_PREFIX;
citing = prefix citing = prefix
+ IdentifierFactory + IdentifierFactory
.md5(CleaningFunctions.normalizePidValue(PidType.pmid.toString(), value.getCiting())); .md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
cited = prefix cited = prefix
+ IdentifierFactory + IdentifierFactory
.md5(CleaningFunctions.normalizePidValue(PidType.pmid.toString(), value.getCited())); .md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCited()));
break; break;
default: default:
throw new IllegalStateException("Invalid prefix: " + p); throw new IllegalStateException("Invalid prefix: " + p);