Edit Question - KnowledgeHub

Title Body

I have a simple hadoop application, which get one CSV file, then split the entry by ",", then count the first items. The following is my code. package com.bluedolphin; import java.io.IOException; import java.util.Iterator; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapred.OutputCollector; import org.apache.hadoop.mapred.Reporter; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; public class MyJob extends Configured implements Tool { private final static LongWritable one = new LongWritable(1); public static class MapClass extends Mapper<Object, Text, Text, LongWritable> { private Text word = new Text(); public void map(Object key, Text value, OutputCollector<Text, LongWritable> output, Reporter reporter) throws IOException, InterruptedException { String[] citation = value.toString().split(","); word.set(citation[0]); output.collect(word, one); } } public static class Reduce extends Reducer<Text, LongWritable, Text, LongWritable> { public void reduce( Text key, Iterator<LongWritable> values, OutputCollector<Text, LongWritable> output, Reporter reporter) throws IOException, InterruptedException { int sum = 0; while (values.has

Tags (comma-separated) Cancel