org.apache.accumulo.examples.wikisearch.ingest
Class WikipediaInputFormat

java.lang.Object
  extended by org.apache.hadoop.mapreduce.InputFormat<K,V>
      extended by org.apache.hadoop.mapreduce.lib.input.FileInputFormat<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text>
          extended by org.apache.hadoop.mapreduce.lib.input.TextInputFormat
              extended by org.apache.accumulo.examples.wikisearch.ingest.WikipediaInputFormat

public class WikipediaInputFormat
extends org.apache.hadoop.mapreduce.lib.input.TextInputFormat


Nested Class Summary
static class WikipediaInputFormat.WikipediaInputSplit
           
 
Nested classes/interfaces inherited from class org.apache.hadoop.mapreduce.lib.input.FileInputFormat
org.apache.hadoop.mapreduce.lib.input.FileInputFormat.Counter
 
Constructor Summary
WikipediaInputFormat()
           
 
Method Summary
 org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> createRecordReader(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext context)
           
 List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext job)
           
 
Methods inherited from class org.apache.hadoop.mapreduce.lib.input.TextInputFormat
isSplitable
 
Methods inherited from class org.apache.hadoop.mapreduce.lib.input.FileInputFormat
addInputPath, addInputPaths, computeSplitSize, getBlockIndex, getFormatMinSplitSize, getInputPathFilter, getInputPaths, getMaxSplitSize, getMinSplitSize, listStatus, setInputPathFilter, setInputPaths, setInputPaths, setMaxInputSplitSize, setMinInputSplitSize
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

WikipediaInputFormat

public WikipediaInputFormat()
Method Detail

getSplits

public List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext job)
                                                       throws IOException
Overrides:
getSplits in class org.apache.hadoop.mapreduce.lib.input.FileInputFormat<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text>
Throws:
IOException

createRecordReader

public org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> createRecordReader(org.apache.hadoop.mapreduce.InputSplit split,
                                                                                                                                org.apache.hadoop.mapreduce.TaskAttemptContext context)
Overrides:
createRecordReader in class org.apache.hadoop.mapreduce.lib.input.TextInputFormat


Copyright © 2012 The Apache Software Foundation. All Rights Reserved.