dhp-graph-dump/dump/src/main/java/eu/dnetlib/dhp/oa/graph/dump/subset/ReadMasterDuplicateFromDB.java

98 lines
3.1 KiB
Java

package eu.dnetlib.dhp.oa.graph.dump.subset;
import java.io.BufferedWriter;
import java.io.Closeable;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.nio.charset.StandardCharsets;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.util.function.Function;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.mongodb.DBCursor;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.DbClient;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
public class ReadMasterDuplicateFromDB {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String QUERY = "SELECT id as master, duplicate FROM dsm_dedup_services; ";
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
ReadMasterDuplicateFromDB.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/dump/datasourcemaster_parameters.json")));
parser.parseArgument(args);
final String dbUrl = parser.get("postgresUrl");
final String dbUser = parser.get("postgresUser");
final String dbPassword = parser.get("postgresPassword");
final String hdfsPath = parser.get("hdfsPath");
final String hdfsNameNode = parser.get("hdfsNameNode");
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
FileSystem fileSystem = FileSystem.get(conf);
Path hdfsWritePath = new Path(hdfsPath);
FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath);
execute(dbUrl, dbUser, dbPassword, fsDataOutputStream);
}
private static void execute(String dbUrl, String dbUser, String dbPassword, FSDataOutputStream fos) {
try (DbClient dbClient = new DbClient(dbUrl, dbUser, dbPassword)) {
try (BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(fos, StandardCharsets.UTF_8))) {
dbClient.processResults(QUERY, rs -> writeMap(datasourceMasterMap(rs), writer));
}
} catch (IOException e) {
e.printStackTrace();
}
}
public static MasterDuplicate datasourceMasterMap(ResultSet rs) {
try {
MasterDuplicate dm = new MasterDuplicate();
String duplicate = rs.getString("duplicate");
dm.setDuplicate(OafMapperUtils.createOpenaireId(10, duplicate, true));
String master = rs.getString("master");
dm.setMaster(OafMapperUtils.createOpenaireId(10, master, true));
return dm;
} catch (final SQLException e) {
throw new RuntimeException(e);
}
}
protected static void writeMap(final MasterDuplicate dm, BufferedWriter writer) {
try {
writer.write(OBJECT_MAPPER.writeValueAsString(dm));
writer.newLine();
} catch (final IOException e) {
throw new RuntimeException(e);
}
}
}