[stats wf] indicators across stats dbs & updates in the org ids #248

Closed
dimitris.pierrakos wants to merge 1742 commits from beta into beta2master_sept_2022
4 changed files with 50 additions and 46 deletions
Showing only changes of commit 7aebedb43c - Show all commits

View File

@ -9,7 +9,6 @@ import java.io.Serializable;
import java.util.Optional; import java.util.Optional;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction; import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*; import org.apache.spark.sql.*;

View File

@ -83,9 +83,12 @@ public class SparkAtomicActionUsageJob implements Serializable {
private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName, private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName,
String attribute_name) { String attribute_name) {
spark spark
.sql(String.format( .sql(
String
.format(
"select %s as id, sum(downloads) as downloads, sum(views) as views " + "select %s as id, sum(downloads) as downloads, sum(views) as views " +
"from %s.%s group by %s", attribute_name, dbname, tableName, attribute_name)) "from %s.%s group by %s",
attribute_name, dbname, tableName, attribute_name))
.as(Encoders.bean(UsageStatsModel.class)) .as(Encoders.bean(UsageStatsModel.class))
.write() .write()
.mode(SaveMode.Overwrite) .mode(SaveMode.Overwrite)

View File

@ -1,7 +1,10 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities; package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import com.fasterxml.jackson.databind.ObjectMapper; import java.io.IOException;
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel; import java.nio.file.Files;
import java.nio.file.Path;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.FileSystem;
@ -17,9 +20,9 @@ import org.junit.jupiter.api.Test;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.io.IOException; import com.fasterxml.jackson.databind.ObjectMapper;
import java.nio.file.Files;
import java.nio.file.Path; import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
/** /**
* @author miriam.baglioni * @author miriam.baglioni
@ -63,13 +66,13 @@ public class GetFosTest {
FileUtils.deleteDirectory(workingDir.toFile()); FileUtils.deleteDirectory(workingDir.toFile());
spark.stop(); spark.stop();
} }
@Test @Test
void test3() throws Exception { void test3() throws Exception {
final String sourcePath = getClass() final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs.tsv") .getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs.tsv")
.getPath(); .getPath();
final String outputPath = workingDir.toString() + "/fos.json"; final String outputPath = workingDir.toString() + "/fos.json";
GetFOSSparkJob GetFOSSparkJob
.main( .main(

View File

@ -116,8 +116,7 @@ public class SolrConfigTest extends SolrTest {
System.out System.out
.println( .println(
doc.get("__indexrecordidentifier") + "\t" + doc.get("__indexrecordidentifier") + "\t" +
doc.get("__result") + "\t" doc.get("__result") + "\t");
);
} }
} }
} }