2021-06-14 09:45:07 +02:00
|
|
|
|
|
|
|
package eu.dnetlib.doiboost.crossref;
|
|
|
|
|
|
|
|
import java.io.BufferedOutputStream;
|
|
|
|
import java.net.URI;
|
|
|
|
import java.util.zip.GZIPOutputStream;
|
|
|
|
|
|
|
|
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
|
|
|
|
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
|
|
|
|
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
|
|
|
|
import org.apache.commons.io.IOUtils;
|
|
|
|
import org.apache.hadoop.conf.Configuration;
|
|
|
|
import org.apache.hadoop.fs.FSDataInputStream;
|
|
|
|
import org.apache.hadoop.fs.FSDataOutputStream;
|
|
|
|
import org.apache.hadoop.fs.FileSystem;
|
|
|
|
import org.apache.hadoop.fs.Path;
|
|
|
|
import org.mortbay.log.Log;
|
|
|
|
|
|
|
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|
|
|
|
|
|
|
public class ExtractCrossrefRecords {
|
|
|
|
public static void main(String[] args) throws Exception {
|
2021-06-15 09:24:11 +02:00
|
|
|
|
2021-06-14 09:45:07 +02:00
|
|
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
|
|
|
IOUtils
|
|
|
|
.toString(
|
|
|
|
ExtractCrossrefRecords.class
|
|
|
|
.getResourceAsStream(
|
2021-08-20 11:12:31 +02:00
|
|
|
"/eu/dnetlib/dhp/doiboost/crossref_dump_reader/crossref_dump_reader.json")));
|
2021-06-14 09:45:07 +02:00
|
|
|
parser.parseArgument(args);
|
2021-06-15 09:24:11 +02:00
|
|
|
final String hdfsServerUri = parser.get("hdfsServerUri");
|
2021-08-05 10:54:03 +02:00
|
|
|
final String workingPath = hdfsServerUri.concat(parser.get("workingPath"));
|
2021-06-15 09:24:11 +02:00
|
|
|
final String outputPath = parser.get("outputPath");
|
|
|
|
final String crossrefFileNameTarGz = parser.get("crossrefFileNameTarGz");
|
2021-06-14 09:45:07 +02:00
|
|
|
|
2021-08-05 10:54:03 +02:00
|
|
|
Path hdfsreadpath = new Path(workingPath.concat("/").concat(crossrefFileNameTarGz));
|
2021-06-14 09:45:07 +02:00
|
|
|
Configuration conf = new Configuration();
|
2021-08-05 10:54:03 +02:00
|
|
|
conf.set("fs.defaultFS", workingPath);
|
2021-06-14 09:45:07 +02:00
|
|
|
conf.set("fs.hdfs.impl", org.apache.hadoop.hdfs.DistributedFileSystem.class.getName());
|
|
|
|
conf.set("fs.file.impl", org.apache.hadoop.fs.LocalFileSystem.class.getName());
|
2021-08-05 10:54:03 +02:00
|
|
|
FileSystem fs = FileSystem.get(URI.create(workingPath), conf);
|
2021-06-14 09:45:07 +02:00
|
|
|
FSDataInputStream crossrefFileStream = fs.open(hdfsreadpath);
|
|
|
|
try (TarArchiveInputStream tais = new TarArchiveInputStream(
|
|
|
|
new GzipCompressorInputStream(crossrefFileStream))) {
|
|
|
|
TarArchiveEntry entry = null;
|
|
|
|
while ((entry = tais.getNextTarEntry()) != null) {
|
2021-06-15 09:24:11 +02:00
|
|
|
if (!entry.isDirectory()) {
|
2021-06-14 09:45:07 +02:00
|
|
|
try (
|
|
|
|
FSDataOutputStream out = fs
|
2021-06-15 09:24:11 +02:00
|
|
|
.create(new Path(outputPath.concat(entry.getName()).concat(".gz")));
|
2021-06-14 09:45:07 +02:00
|
|
|
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
|
|
|
|
|
|
|
|
IOUtils.copy(tais, gzipOs);
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
Log.info("Crossref dump reading completed");
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|