diff options
author | Sandy Ryza <sandy@cloudera.com> | 2014-09-09 10:23:28 -0700 |
---|---|---|
committer | Reynold Xin <rxin@apache.org> | 2014-09-09 10:23:28 -0700 |
commit | 88547a09fcc25df132b401ecec4ebe1ef6778576 (patch) | |
tree | d43918cd86c090f34cc064c2532fd7d76eec32bb /core | |
parent | 1e03cf79f82b166b2e18dcbd181e074f0276a0a9 (diff) | |
download | spark-88547a09fcc25df132b401ecec4ebe1ef6778576.tar.gz spark-88547a09fcc25df132b401ecec4ebe1ef6778576.tar.bz2 spark-88547a09fcc25df132b401ecec4ebe1ef6778576.zip |
SPARK-3422. JavaAPISuite.getHadoopInputSplits isn't used anywhere.
Author: Sandy Ryza <sandy@cloudera.com>
Closes #2324 from sryza/sandy-spark-3422 and squashes the following commits:
6446175 [Sandy Ryza] SPARK-3422. JavaAPISuite.getHadoopInputSplits isn't used anywhere.
Diffstat (limited to 'core')
-rw-r--r-- | core/src/test/java/org/apache/spark/JavaAPISuite.java | 25 |
1 files changed, 0 insertions, 25 deletions
diff --git a/core/src/test/java/org/apache/spark/JavaAPISuite.java b/core/src/test/java/org/apache/spark/JavaAPISuite.java index be99dc501c..b8574dfb42 100644 --- a/core/src/test/java/org/apache/spark/JavaAPISuite.java +++ b/core/src/test/java/org/apache/spark/JavaAPISuite.java @@ -29,19 +29,14 @@ import com.google.common.collect.Iterables; import com.google.common.collect.Iterators; import com.google.common.collect.Lists; import com.google.common.collect.Maps; -import com.google.common.collect.Sets; import com.google.common.base.Optional; import com.google.common.base.Charsets; import com.google.common.io.Files; import org.apache.hadoop.io.IntWritable; -import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.compress.DefaultCodec; -import org.apache.hadoop.mapred.FileSplit; -import org.apache.hadoop.mapred.InputSplit; import org.apache.hadoop.mapred.SequenceFileInputFormat; import org.apache.hadoop.mapred.SequenceFileOutputFormat; -import org.apache.hadoop.mapred.TextInputFormat; import org.apache.hadoop.mapreduce.Job; import org.junit.After; import org.junit.Assert; @@ -49,7 +44,6 @@ import org.junit.Before; import org.junit.Test; import org.apache.spark.api.java.JavaDoubleRDD; -import org.apache.spark.api.java.JavaHadoopRDD; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; @@ -1313,23 +1307,4 @@ public class JavaAPISuite implements Serializable { SomeCustomClass[] collected = (SomeCustomClass[]) rdd.rdd().retag(SomeCustomClass.class).collect(); Assert.assertEquals(data.size(), collected.length); } - - public void getHadoopInputSplits() { - String outDir = new File(tempDir, "output").getAbsolutePath(); - sc.parallelize(Arrays.asList(1, 2, 3, 4, 5), 2).saveAsTextFile(outDir); - - JavaHadoopRDD<LongWritable, Text> hadoopRDD = (JavaHadoopRDD<LongWritable, Text>) - sc.hadoopFile(outDir, TextInputFormat.class, LongWritable.class, Text.class); - List<String> inputPaths = hadoopRDD.mapPartitionsWithInputSplit( - new Function2<InputSplit, Iterator<Tuple2<LongWritable, Text>>, Iterator<String>>() { - @Override - public Iterator<String> call(InputSplit split, Iterator<Tuple2<LongWritable, Text>> it) - throws Exception { - FileSplit fileSplit = (FileSplit) split; - return Lists.newArrayList(fileSplit.getPath().toUri().getPath()).iterator(); - } - }, true).collect(); - Assert.assertEquals(Sets.newHashSet(inputPaths), - Sets.newHashSet(outDir + "/part-00000", outDir + "/part-00001")); - } } |