forked from D-Net/dnet-hadoop
preparation step: creates the subset of the merges relations
This commit is contained in:
parent
276b95b7b3
commit
d6d6ebeae5
|
|
@ -0,0 +1,91 @@
|
||||||
|
package eu.dnetlib.dhp.blacklist;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
import com.google.gson.Gson;
|
||||||
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.apache.spark.SparkConf;
|
||||||
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
import org.apache.spark.sql.Dataset;
|
||||||
|
import org.apache.spark.sql.Encoders;
|
||||||
|
import org.apache.spark.sql.SaveMode;
|
||||||
|
import org.apache.spark.sql.SparkSession;
|
||||||
|
import org.slf4j.Logger;
|
||||||
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
import java.util.Arrays;
|
||||||
|
import java.util.List;
|
||||||
|
import java.util.Optional;
|
||||||
|
|
||||||
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
|
||||||
|
|
||||||
|
public class PrepareMergedRelationJob {
|
||||||
|
|
||||||
|
private static final Logger log = LoggerFactory.getLogger(PrepareMergedRelationJob.class);
|
||||||
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||||
|
|
||||||
|
public static void main(String[] args) throws Exception {
|
||||||
|
|
||||||
|
String jsonConfiguration = IOUtils
|
||||||
|
.toString(
|
||||||
|
PrepareMergedRelationJob.class
|
||||||
|
.getResourceAsStream(
|
||||||
|
"/eu/dnetlib/dhp/blacklist/input_preparerelation_parameters.json"));
|
||||||
|
|
||||||
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||||
|
|
||||||
|
parser.parseArgument(args);
|
||||||
|
|
||||||
|
Boolean isSparkSessionManaged = Optional
|
||||||
|
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||||
|
.map(Boolean::valueOf)
|
||||||
|
.orElse(Boolean.TRUE);
|
||||||
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||||
|
|
||||||
|
String inputPath = parser.get("sourcePath");
|
||||||
|
log.info("inputPath: {}", inputPath);
|
||||||
|
|
||||||
|
String outputPath = parser.get("outputPath");
|
||||||
|
log.info("outputPath: {} " , outputPath);
|
||||||
|
|
||||||
|
SparkConf conf = new SparkConf();
|
||||||
|
conf.set("hive.metastore.uris", parser.get("hive_metastore_uris"));
|
||||||
|
|
||||||
|
runWithSparkHiveSession(
|
||||||
|
conf,
|
||||||
|
isSparkSessionManaged,
|
||||||
|
spark -> {
|
||||||
|
// removeOutputDir(spark, potentialUpdatePath);
|
||||||
|
// removeOutputDir(spark, alreadyLinkedPath);
|
||||||
|
selectMergesRelations(
|
||||||
|
spark,
|
||||||
|
inputPath,
|
||||||
|
outputPath);
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
private static void selectMergesRelations(SparkSession spark, String inputPath, String outputPath) {
|
||||||
|
|
||||||
|
Dataset<Relation> relation = readRelations(spark, inputPath);
|
||||||
|
relation.createOrReplaceTempView("relation");
|
||||||
|
|
||||||
|
spark.sql("Select * from relation where relclass = 'merges' and datainfo.deletedbyinference = false")
|
||||||
|
.as(Encoders.bean(Relation.class))
|
||||||
|
.toJSON()
|
||||||
|
.write()
|
||||||
|
.mode(SaveMode.Overwrite)
|
||||||
|
.option("compression","gzip")
|
||||||
|
.text(outputPath);
|
||||||
|
}
|
||||||
|
|
||||||
|
public static org.apache.spark.sql.Dataset<Relation> readRelations(
|
||||||
|
SparkSession spark, String inputPath) {
|
||||||
|
return spark
|
||||||
|
.read()
|
||||||
|
.textFile(inputPath)
|
||||||
|
.map(
|
||||||
|
(MapFunction<String, Relation>) value -> OBJECT_MAPPER.readValue(value, Relation.class),
|
||||||
|
Encoders.bean(Relation.class));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,4 @@
|
||||||
|
package eu.dnetlib.dhp.blacklist;
|
||||||
|
|
||||||
|
public class RemoveBlacklistedRelationSparkJob {
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,26 @@
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"paramName": "p",
|
||||||
|
"paramLongName": "hdfsPath",
|
||||||
|
"paramDescription": "the path where storing the sequential file",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "s",
|
||||||
|
"paramLongName": "sourcePath",
|
||||||
|
"paramDescription": "the path to the graph used to remove the relations ",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "out",
|
||||||
|
"paramLongName": "outputPath",
|
||||||
|
"paramDescription": "the path where to store the temporary result ",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "issm",
|
||||||
|
"paramLongName": "isSparkSessionManaged",
|
||||||
|
"paramDescription": "true if the spark session is managed",
|
||||||
|
"paramRequired": false
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
@ -0,0 +1,32 @@
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"paramName": "p",
|
||||||
|
"paramLongName": "hdfsPath",
|
||||||
|
"paramDescription": "the path where storing the sequential file",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "nn",
|
||||||
|
"paramLongName": "hdfsNameNode",
|
||||||
|
"paramDescription": "the name node on hdfs",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "pgurl",
|
||||||
|
"paramLongName": "postgresUrl",
|
||||||
|
"paramDescription": "postgres url, example: jdbc:postgresql://localhost:5432/testdb",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "pguser",
|
||||||
|
"paramLongName": "postgresUser",
|
||||||
|
"paramDescription": "postgres user",
|
||||||
|
"paramRequired": false
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName": "pgpasswd",
|
||||||
|
"paramLongName": "postgresPassword",
|
||||||
|
"paramDescription": "postgres password",
|
||||||
|
"paramRequired": false
|
||||||
|
}
|
||||||
|
]
|
||||||
Loading…
Reference in New Issue