1
0

Moving to Spark 2.1.0

This commit is contained in:
Prasanna Rajaperumal
2017-02-20 16:47:52 -08:00
parent be1dd9444f
commit 0e234ac0ef
6 changed files with 35 additions and 33 deletions

View File

@@ -38,6 +38,7 @@ import scala.Tuple2;
import java.io.IOException;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
/**
@@ -75,14 +76,14 @@ public class HoodieSnapshotCopier implements Serializable {
jsc.parallelize(partitions, partitions.size()).flatMap(new FlatMapFunction<String, Tuple2<String, String>>() {
@Override
public Iterable<Tuple2<String, String>> call(String partition) throws Exception {
public Iterator<Tuple2<String, String>> call(String partition) throws Exception {
// Only take latest version files <= latestCommit.
FileSystem fs = FSUtils.getFs();
List<Tuple2<String, String>> filePaths = new ArrayList<>();
for (FileStatus fileStatus : tableMetadata.getLatestVersionInPartition(fs, partition, latestCommit)) {
filePaths.add(new Tuple2<>(partition, fileStatus.getPath().toString()));
}
return filePaths;
return filePaths.iterator();
}
}).foreach(new VoidFunction<Tuple2<String, String>>() {
@Override