diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java index 006d3af76..73b4b77cb 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java @@ -42,6 +42,9 @@ public class Constants { public static final String NULL = "NULL"; public static final String NA = "N/A"; + public static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b"; + public static final String WEB_CRAWL_NAME = "Web Crawl"; + public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private Constants() { diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/webcrawl/CreateActionSetFromWebEntries.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/webcrawl/CreateActionSetFromWebEntries.java index 27970f2c3..f2a73889f 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/webcrawl/CreateActionSetFromWebEntries.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/webcrawl/CreateActionSetFromWebEntries.java @@ -21,6 +21,7 @@ import org.slf4j.LoggerFactory; import com.fasterxml.jackson.databind.ObjectMapper; +import eu.dnetlib.dhp.actionmanager.Constants; import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.schema.action.AtomicAction; import eu.dnetlib.dhp.schema.common.ModelConstants; @@ -29,6 +30,7 @@ import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory; import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils; import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner; import eu.dnetlib.dhp.schema.oaf.utils.PidType; +import io.netty.util.Constant; import scala.Tuple2; /** @@ -44,8 +46,7 @@ public class CreateActionSetFromWebEntries implements Serializable { private static final String PMID_PREFIX = "50|pmid________::"; private static final String PMCID_PREFIX = "50|pmc_________::"; - private static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b"; - private static final String WEB_CRAWL_NAME = "Web Crawl"; + public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); public static void main(String[] args) throws Exception { @@ -104,8 +105,7 @@ public class CreateActionSetFromWebEntries implements Serializable { final String ror = ROR_PREFIX + IdentifierFactory.md5(PidCleaner.normalizePidValue("ROR", row.getAs("ror"))); ret.addAll(createAffiliationRelationPairDOI(row.getAs("doi"), ror)); - ret.addAll(createAffiliationRelationPairPMID(row.getAs("pmid"), ror)); - ret.addAll(createAffiliationRelationPairPMCID(row.getAs("pmcid"), ror)); + return ret .iterator(); @@ -139,8 +139,9 @@ public class CreateActionSetFromWebEntries implements Serializable { "institution", functions .explode( functions.col("institutions"))) + .selectExpr( - "id", "doi", "ids.pmcid as pmcid", "ids.pmid as pmid", "institution.ror as ror", + "id", "doi", "institution.ror as ror", "institution.country_code as country_code", "publication_year") .distinct(); @@ -214,7 +215,7 @@ public class CreateActionSetFromWebEntries implements Serializable { ModelConstants.IS_AUTHOR_INSTITUTION_OF, Arrays .asList( - OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)), + OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)), OafMapperUtils .dataInfo( false, null, false, false, @@ -233,7 +234,7 @@ public class CreateActionSetFromWebEntries implements Serializable { ModelConstants.HAS_AUTHOR_INSTITUTION, Arrays .asList( - OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)), + OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)), OafMapperUtils .dataInfo( false, null, false, false,