Hadoop之——命令行运行时指定参数

转载请注明出处：http://blog.csdn.net/l1028386804/article/details/46056029

本文旨在提供一个Hadoop在运行的时候从命令行输入要统计的文件路径和统计结果的输出路径，不多说直接上代码

1、Mapper类的实现

        /**
 * KEYIN即k1表示行的偏移量
 * VALUEIN即v1表示行文本内容
 * KEYOUT即k2表示行中出现的单词
 * VALUEOUT即v2表示行中出现的单词的次数，固定值1
 */
static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException {
final String[] splited = v1.toString().split("\t");
for (String word : splited) {
context.write(new Text(word), new LongWritable(1));
}
};
}

2、Reducer类的实现

/**
 * KEYIN即k2表示行中出现的单词
 * VALUEIN即v2表示行中出现的单词的次数
 * KEYOUT即k3表示文本中出现的不同单词
 * VALUEOUT即v3表示文本中出现的不同单词的总次数
 *
 */
static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx) throws java.io.IOException ,InterruptedException {
long times = 0L;
for (LongWritable count : v2s) {
times += count.get();
}
ctx.write(k2, new LongWritable(times));
};
}

3、run方法的实现

       @Override
public int run(String[] args) throws Exception {
//接收命令行参数
INPUT_PATH = args[0];
OUT_PATH = args[1];
Configuration conf = new Configuration();
final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
final Path outPath = new Path(OUT_PATH);
//如果已经存在输出文件，则先删除已存在的输出文件
if(fileSystem.exists(outPath)){
fileSystem.delete(outPath, true);
}

final Job job = new Job(conf , WordCount.class.getSimpleName());
//*******打包运行必须执行的方法*******
job.setJarByClass(WordCount.class);

//1.1指定读取的文件位于哪里
FileInputFormat.setInputPaths(job, INPUT_PATH);
//指定如何对输入文件进行格式化，把输入文件每一行解析成键值对
job.setInputFormatClass(TextInputFormat.class);

//1.2 指定自定义的map类
job.setMapperClass(MyMapper.class);
//map输出的<k,v>类型。如果<k3,v3>的类型与<k2,v2>类型一致，下面两行代码可以省略
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

//1.3 分区
job.setPartitionerClass(HashPartitioner.class);
//有一个reduce任务运行
job.setNumReduceTasks(1);

//1.4 TODO 排序、分组

//1.5 TODO 规约

//2.2 指定自定义reduce类
job.setReducerClass(MyReducer.class);
//指定reduce的输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

//2.3 指定写出到哪里
FileOutputFormat.setOutputPath(job, outPath);
//指定输出文件的格式化类
job.setOutputFormatClass(TextOutputFormat.class);

//把job提交给JobTracker运行
job.waitForCompletion(true);
return 0;
}

 4、程序入口main

//程序入口Main方法
public static void main(String[] args) throws Exception {
      ToolRunner.run(new WordCount(), args);
}

5、完整程序代码

package com.lyz.hadoop.count;

import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
 * 利用Hadoop MapReduce统计文本中每个单词的数量
 * @author liuyazhuang
 */
public class WordCount extends Configured implements Tool{
//要统计的文件位置
static String INPUT_PATH = "";
//统计结果输出的位置
static String OUT_PATH = "";

@Override
public int run(String[] args) throws Exception {
//接收命令行参数
INPUT_PATH = args[0];
OUT_PATH = args[1];
Configuration conf = new Configuration();
final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
final Path outPath = new Path(OUT_PATH);
//如果已经存在输出文件，则先删除已存在的输出文件
if(fileSystem.exists(outPath)){
fileSystem.delete(outPath, true);
}

final Job job = new Job(conf , WordCount.class.getSimpleName());
//*******打包运行必须执行的方法*******
job.setJarByClass(WordCount.class);

//1.1指定读取的文件位于哪里
FileInputFormat.setInputPaths(job, INPUT_PATH);
//指定如何对输入文件进行格式化，把输入文件每一行解析成键值对
job.setInputFormatClass(TextInputFormat.class);

//1.2 指定自定义的map类
job.setMapperClass(MyMapper.class);
//map输出的<k,v>类型。如果<k3,v3>的类型与<k2,v2>类型一致，下面两行代码可以省略
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

//1.3 分区
job.setPartitionerClass(HashPartitioner.class);
//有一个reduce任务运行
job.setNumReduceTasks(1);

//1.4 TODO 排序、分组

//1.5 TODO 规约

//2.2 指定自定义reduce类
job.setReducerClass(MyReducer.class);
//指定reduce的输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

//2.3 指定写出到哪里
FileOutputFormat.setOutputPath(job, outPath);
//指定输出文件的格式化类
job.setOutputFormatClass(TextOutputFormat.class);

//把job提交给JobTracker运行
job.waitForCompletion(true);
return 0;
}
//程序入口Main方法
public static void main(String[] args) throws Exception {
ToolRunner.run(new WordCount(), args);
}

/**
 * KEYIN即k1表示行的偏移量
 * VALUEIN即v1表示行文本内容
 * KEYOUT即k2表示行中出现的单词
 * VALUEOUT即v2表示行中出现的单词的次数，固定值1
 */
static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException {
final String[] splited = v1.toString().split("\t");
for (String word : splited) {
context.write(new Text(word), new LongWritable(1));
}
};
}

/**
 * KEYIN即k2表示行中出现的单词
 * VALUEIN即v2表示行中出现的单词的次数
 * KEYOUT即k3表示文本中出现的不同单词
 * VALUEOUT即v3表示文本中出现的不同单词的总次数
 *
 */
static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx) throws java.io.IOException ,InterruptedException {
long times = 0L;
for (LongWritable count : v2s) {
times += count.get();
}
ctx.write(k2, new LongWritable(times));
};
}

}