1
0
Fork 0

step of data preparation before actual country propagation will take palce

This commit is contained in:
Miriam Baglioni 2020-04-11 16:36:03 +02:00
parent 6897c920a2
commit a2d833d5dd
1 changed files with 27 additions and 24 deletions

View File

@ -5,6 +5,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Dataset; import org.apache.spark.sql.Dataset;
@ -14,14 +15,14 @@ import org.apache.spark.sql.SaveMode;
import java.util.Arrays; import java.util.Arrays;
import java.util.List; import java.util.List;
import java.util.Optional;
import static eu.dnetlib.dhp.PropagationConstant.createOutputDirs;
import static eu.dnetlib.dhp.PropagationConstant.getConstraintList;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import static eu.dnetlib.dhp.PropagationConstant.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
/** /**
* For the association of the country to the datasource * For the association of the country to the datasource
* The association is computed only for datasource of specific type or having whitelisted ids * The association is computed only for datasource of specific type or having whitelisted ids
@ -30,48 +31,50 @@ import org.slf4j.LoggerFactory;
*/ */
public class PrepareDatasourceCountryAssociation { public class PrepareDatasourceCountryAssociation {
private static final Logger log = LoggerFactory.getLogger(PrepareDatasourceCountryAssociation.class);
private static final Logger log = LoggerFactory.getLogger(PrepareDatasourceCountryAssociation.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(String[] args) throws Exception { public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils.toString(PrepareDatasourceCountryAssociation.class String jsonConfiguration = IOUtils.toString(PrepareDatasourceCountryAssociation.class
.getResourceAsStream("/eu/dnetlib/dhp/countrypropagation/input_prepare_dc_assoc.json")); .getResourceAsStream("/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser( final ArgumentApplicationParser parser = new ArgumentApplicationParser(
jsonConfiguration); jsonConfiguration);
parser.parseArgument(args); parser.parseArgument(args);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String inputPath = parser.get("sourcePath"); String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath); log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}: ", outputPath);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
conf.set("hive.metastore.uris", parser.get("hive_metastore_uris")); conf.set("hive.metastore.uris", parser.get("hive_metastore_uris"));
final SparkSession spark = SparkSession
.builder()
.appName(SparkCountryPropagationJob.class.getSimpleName())
.master(parser.get("master"))
.config(conf)
.enableHiveSupport()
.getOrCreate();
final String outputPath = "/tmp/provision/propagation/countrytoresultfrominstitutionalrepositories"; runWithSparkHiveSession(conf, isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
createOutputDirs(outputPath, FileSystem.get(spark.sparkContext().hadoopConfiguration()));
prepareDatasourceCountryAssociation(spark, prepareDatasourceCountryAssociation(spark,
Arrays.asList(parser.get("whitelist").split(";")), Arrays.asList(parser.get("whitelist").split(";")),
Arrays.asList(parser.get("allowedtypes").split(";")), Arrays.asList(parser.get("allowedtypes").split(";")),
inputPath, inputPath,
outputPath); outputPath);
});
} }
private static void prepareDatasourceCountryAssociation(SparkSession spark, private static void prepareDatasourceCountryAssociation(SparkSession spark,
List<String> whitelist, List<String> whitelist,
List<String> allowedtypes, List<String> allowedtypes,
@ -97,7 +100,7 @@ public class PrepareDatasourceCountryAssociation {
relation.createOrReplaceTempView("relation"); relation.createOrReplaceTempView("relation");
organization.createOrReplaceTempView("organization"); organization.createOrReplaceTempView("organization");
String query = "SELECT source ds, named_struct('classid', country.classid, 'classname', country.classname) country " + String query = "SELECT source dataSourceId, named_struct('classid', country.classid, 'classname', country.classname) country " +
"FROM ( SELECT id " + "FROM ( SELECT id " +
" FROM datasource " + " FROM datasource " +
" WHERE (datainfo.deletedbyinference = false " + whitelisted + ") " + " WHERE (datainfo.deletedbyinference = false " + whitelisted + ") " +
@ -115,9 +118,9 @@ public class PrepareDatasourceCountryAssociation {
spark.sql(query) spark.sql(query)
.as(Encoders.bean(DatasourceCountry.class)) .as(Encoders.bean(DatasourceCountry.class))
.write() .toJavaRDD()
.mode(SaveMode.Overwrite) .map(c -> OBJECT_MAPPER.writeValueAsString(c))
.parquet(outputPath + "/prepared_datasource_country"); .saveAsTextFile(outputPath, GzipCodec.class);
} }