D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 12 Projects 2 Releases 2 Wiki Activity

merge branch with master

This commit is contained in:
Miriam Baglioni 2021-04-23 12:11:15 +02:00
parent 04a0d1ba6e 72e5aa3b42
commit 1416a49b63
2 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkUpdateEntity.java
View File

@ -13,6 +13,7 @@ import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
@ -91,6 +92,7 @@ public class SparkUpdateEntity extends AbstractSparkAction {
final JavaPairRDD<String, String> mergedIds = rel
.where("relClass == 'merges'")
.where("source != target")
.select(rel.col("target"))
.distinct()
.toJavaRDD()

1
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/finalizedb.sh
View File

@ -10,6 +10,7 @@ export SOURCE=$1
export SHADOW=$2
echo "Updating shadow database"
impala-shell -q "invalidate metadata"
impala-shell -d ${SOURCE} -q "invalidate metadata"
impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/^\(.*\)/compute stats ${SOURCE}.\1;/" | impala-shell -c -f -
impala-shell -q "create database if not exists ${SHADOW}"