cannot found "KeyValueInputFormat" in Hadoop - hadoop

Question

I am newbie to Hadoop but have read the Yahoo tutorial on that and have already written a few mapReduce jobs. All my previous works used TextInputFormat but I now need to change that to KeyValueInputFormat. The problem is that KeyValueInputFormat.class cannot be found in hadoop 0.20.2?
I am attaching my code below (It is the word count example with only input format being changed)
package org.myorg;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;
public class WordCount {
public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}
public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(keyValueInputFormat.class); //The modified input format
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
}

Answer 1

There is KeyValueTextInputFormat in org.apache.hadoop.mapreduce.lib.input.
Some of the old tutorials are based on older versions of Hadoop API. I recommend that you go through some of the newer tutorials.
This is what I get when I do go to source on KeyValueTextInputFormat.
package org.apache.hadoop.mapreduce.lib.input;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
public class KeyValueTextInputFormat extends FileInputFormat<Text, Text> {
public KeyValueTextInputFormat() {
//compiled code
throw new RuntimeException("Compiled Code");
}
protected boolean isSplitable(JobContext context, Path file) {
//compiled code
throw new RuntimeException("Compiled Code");
}
public RecordReader<Text, Text> createRecordReader(InputSplit genericSplit, TaskAttemptContext context) throws IOException {
//compiled code
throw new RuntimeException("Compiled Code");
}
}