diff --git a/indexing-hadoop/src/main/java/io/druid/indexer/DetermineHashedPartitionsJob.java b/indexing-hadoop/src/main/java/io/druid/indexer/DetermineHashedPartitionsJob.java index c3abc93c84e..ee580ac23b7 100644 --- a/indexing-hadoop/src/main/java/io/druid/indexer/DetermineHashedPartitionsJob.java +++ b/indexing-hadoop/src/main/java/io/druid/indexer/DetermineHashedPartitionsJob.java @@ -49,6 +49,7 @@ import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Partitioner; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; +import org.apache.hadoop.mapreduce.lib.input.CombineTextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat; import org.joda.time.DateTime; @@ -91,7 +92,7 @@ public class DetermineHashedPartitionsJob implements Jobby ); JobHelper.injectSystemProperties(groupByJob); - groupByJob.setInputFormatClass(TextInputFormat.class); + groupByJob.setInputFormatClass(CombineTextInputFormat.class); groupByJob.setMapperClass(DetermineCardinalityMapper.class); groupByJob.setMapOutputKeyClass(LongWritable.class); groupByJob.setMapOutputValueClass(BytesWritable.class);