public class PigInputFormatSpark extends PigInputFormat
PigInputFormat.RecordReaderFactory
log, PIG_INPUT_LIMITS, PIG_INPUT_SIGNATURES, PIG_INPUT_TARGETS, PIG_LOADS
Constructor and Description |
---|
PigInputFormatSpark() |
Modifier and Type | Method and Description |
---|---|
org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.Text,Tuple> |
createRecordReader(org.apache.hadoop.mapreduce.InputSplit split,
org.apache.hadoop.mapreduce.TaskAttemptContext context) |
java.util.List<org.apache.hadoop.mapreduce.InputSplit> |
getSplits(org.apache.hadoop.mapreduce.JobContext jobcontext)
This is where we have to wrap PigSplits into SparkPigSplits
|
getPigSplits
public org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.Text,Tuple> createRecordReader(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext context) throws java.io.IOException, java.lang.InterruptedException
createRecordReader
in class PigInputFormat
java.io.IOException
java.lang.InterruptedException
public java.util.List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext jobcontext) throws java.io.IOException, java.lang.InterruptedException
getSplits
in class PigInputFormat
jobcontext
- java.io.IOException
java.lang.InterruptedException
Copyright © 2007-2025 The Apache Software Foundation