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

added tests for the normalization of the dois

This commit is contained in:
Miriam Baglioni 2021-06-30 12:57:11 +02:00
parent 1503ccbbb5
commit e487b5544c
1 changed files with 50 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/mag/MAGMappingTest.scala
View File

@ -4,7 +4,7 @@ import java.sql.Timestamp
import eu.dnetlib.dhp.schema.oaf.Publication
import org.apache.htrace.fasterxml.jackson.databind.SerializationFeature
import org.apache.spark.SparkConf
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.api.java.function.MapFunction
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
@ -62,6 +62,55 @@ class MAGMappingTest {
logger.debug(description)
}
@Test
def normalizeDoiTest():Unit = {
import org.json4s.jackson.Serialization.write
import org.json4s.DefaultFormats
implicit val formats = DefaultFormats
val conf = new SparkConf().setAppName("test").setMaster("local[2]")
val sc = new SparkContext(conf)
val spark = SparkSession.builder.config(sc.getConf).getOrCreate()
val path = getClass.getResource("magPapers.json").getPath
import org.apache.spark.sql.Encoders
val schema = Encoders.product[MagPapers].schema
import spark.implicits._
val magPapers :Dataset[MagPapers] = spark.read.option("multiline",true).schema(schema).json(path).as[MagPapers]
val ret :Dataset[MagPapers] = SparkProcessMAG.getDistinctResults(magPapers)
assertTrue(ret.count == 10)
ret.take(10).foreach(mp => assertTrue(mp.Doi.equals(mp.Doi.toLowerCase())))
spark.close()
}
@Test
def normalizeDoiTest2():Unit = {
import org.json4s.jackson.Serialization.write
import org.json4s.DefaultFormats
implicit val formats = DefaultFormats
val conf = new SparkConf().setAppName("test").setMaster("local[2]")
val sc = new SparkContext(conf)
val spark = SparkSession.builder.config(sc.getConf).getOrCreate()
val path = getClass.getResource("duplicatedMagPapers.json").getPath
import org.apache.spark.sql.Encoders
val schema = Encoders.product[MagPapers].schema
import spark.implicits._
val magPapers :Dataset[MagPapers] = spark.read.option("multiline",true).schema(schema).json(path).as[MagPapers]
val ret :Dataset[MagPapers] = SparkProcessMAG.getDistinctResults(magPapers)
assertTrue(ret.count == 8)
ret.take(8).foreach(mp => assertTrue(mp.Doi.equals(mp.Doi.toLowerCase())))
spark.close()
//ret.take(8).foreach(mp => println(write(mp)))
}
}