przemyslaw.jacewicz
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

added kryo encoding for input files

This commit is contained in:
Miriam Baglioni 2021-06-18 09:42:07 +02:00
parent 3585e53da3
commit 6aca0d8ebb
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/SparkMapDumpIntoOAF.scala
View File

@ -4,9 +4,9 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf
import eu.dnetlib.dhp.schema.oaf.{Oaf, Publication, Relation, Dataset => OafDataset}
import org.apache.commons.io.IOUtils
import org.apache.hadoop.io.{IntWritable, Text}
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
@ -17,6 +17,7 @@ object SparkMapDumpIntoOAF {
def main(args: Array[String]): Unit = {
implicit val mrEncoder: Encoder[CrossrefDT] = Encoders.kryo[CrossrefDT]
val logger: Logger = LoggerFactory.getLogger(SparkMapDumpIntoOAF.getClass)
val conf: SparkConf = new SparkConf()
@ -35,7 +36,6 @@ object SparkMapDumpIntoOAF {
implicit val mapEncoderDatasets: Encoder[oaf.Dataset] = Encoders.kryo[OafDataset]
val targetPath = parser.get("targetPath")
import spark.implicits._
spark.read.load(parser.get("sourcePath")).as[CrossrefDT]
.flatMap(k => Crossref2Oaf.convert(k.json))