[orcid propagation] skip empty directory

This commit is contained in:
Claudio Atzori 2022-12-20 10:28:22 +01:00
parent da85ca697d
commit 46972f8393
1 changed files with 10 additions and 4 deletions

View File

@ -5,6 +5,7 @@ import java.util.ArrayList;
import java.util.List;
import java.util.Optional;
import org.apache.hadoop.conf.Configuration;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
@ -228,10 +229,15 @@ public class PropagationConstant {
public static <R> Dataset<R> readPath(
SparkSession spark, String inputPath, Class<R> clazz) {
return spark
.read()
.textFile(inputPath)
.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
if (HdfsSupport.exists(inputPath, spark.sparkContext().hadoopConfiguration())) {
return spark
.read()
.textFile(inputPath)
.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
} else {
return spark.emptyDataset(Encoders.bean(clazz));
}
}
}