D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 11 Projects 2 Releases 2 Wiki Activity

update function to generete AS as sequence file

This commit is contained in:
Sandro La Bruzzo 2024-04-18 10:09:57 +02:00
parent ac8747582c
commit f9e940a2af
2 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/mag/MagUtility.scala
View File

@ -678,7 +678,7 @@ object MagUtility extends Serializable {
}
def generateOrganization(r: Row): String = {
def generateOrganization(r: Row): (String,String) = {
val o = new Organization
val affId = s"20|mag_________::${DHPUtils.md5(r.getAs[Long]("AffiliationId").toString)}"
@ -727,7 +727,7 @@ object MagUtility extends Serializable {
val a = new AtomicAction[Organization]()
a.setClazz(classOf[Organization])
a.setPayload(o)
mapper.writeValueAsString(a)
(a.getClazz.getName,mapper.writeValueAsString(a))
}
def generateAffiliationRelations(paperAffiliation: Row): List[Relation] = {

18
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/mag/SparkMagOrganizationAS.scala
View File

@ -3,6 +3,9 @@ package eu.dnetlib.dhp.collection.mag
import eu.dnetlib.dhp.application.AbstractScalaApplication
import eu.dnetlib.dhp.schema.action.AtomicAction
import eu.dnetlib.dhp.schema.oaf.Organization
import org.apache.hadoop.io.Text
import org.apache.hadoop.io.compress.{BZip2Codec, GzipCodec}
import org.apache.hadoop.mapred.SequenceFileOutputFormat
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
@ -24,9 +27,18 @@ class SparkMagOrganizationAS (propertyPath: String, args: Array[String], log: Lo
def generateAS(spark:SparkSession, magBasePath:String,outputPath:String ):Unit = {
import spark.implicits._
val organizations = MagUtility.loadMagEntity(spark,"Affiliations", magBasePath)
organizations.map(r => MagUtility.generateOrganization(r)).write.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.text(outputPath)
organizations
.map(r => MagUtility.generateOrganization(r))
.rdd
.map(s => (new Text(s._1), new Text(s._2)))
.filter(s => s!=null)
.saveAsHadoopFile(
outputPath,
classOf[Text],
classOf[Text],
classOf[SequenceFileOutputFormat[Text, Text]],
classOf[BZip2Codec]
)
}
}