介绍 package com.test;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
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.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.NLineInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;/* *
,* TextInputFormat处理的数据来自于一个InputSplit.InputSplit根据块大小划分。
,*由于每条记录有长有短,所以,每个地图任务处理的记录数都不一样
,* NLineInputFormat决定每个地图处理记录数是相同的
,*/public class WordCountNL extends Configured implements Tool {
,
,public static class Map extends Mapper, {
public 才能;void 地图(LongWritable 关键,Text 价值,Context 上下文),throws IOException, InterruptedException {
,,String line =, value.toString ();
,,
,,StringTokenizer st =, new StringTokenizer(线);
,,,(st.hasMoreElements ()), {
,,,context.write (new 文本(st.nextElement () .toString ()),, new IntWritable (1));
,,}
,,}
,}
,
,public static class Combiner extends Reducer<文本,IntWritable,,文本,IntWritable>, {
public 才能;void 减少(Text 关键,Iterable,价值观,Context 上下文),throws IOException, InterruptedException {
,,int count =, 0;
,,Iterator, {
public 才能;void 减少(Text 关键,Iterable,价值观,Context 上下文),throws IOException, InterruptedException {
,,int count =, 0;
,,Iterator
小编给大家分享一下NLineInputFormat的示例分析,希望大家阅读完这篇文章之后都有所收获、下面让我们一起去探讨吧!
看完了这篇文章,相信你对“NLineInputFormat的示例分析”有了一定的了解,如果想了解更多相关知识,欢迎关注行业资讯频道,感谢各位的阅读!
