大数据入门--hadoop（二）--window开发环境与编程入门

得到hadoop的window环境下的编译包
配置windows下hadoop环境变量（注意HADOOP_HOME不要有空格、中文）
验证环境配置是否成功

hadoop version

准备开发环境

建立maven工程
导入maven依赖

<dependencies>
	<dependency>
		<groupId>junit</groupId>
		<artifactId>junit</artifactId>
		<version>RELEASE</version>
	</dependency>
	<dependency>
		<groupId>org.apache.logging.log4j</groupId>
		<artifactId>log4j-core</artifactId>
		<version>2.8.2</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-common</artifactId>
		<version>2.7.2</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-client</artifactId>
		<version>2.7.2</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-hdfs</artifactId>
		<version>2.7.2</version>
	</dependency>
	<dependency>
		<groupId>jdk.tools</groupId>
		<artifactId>jdk.tools</artifactId>
		<version>1.8</version>
		<scope>system</scope>
		<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
	</dependency>
</dependencies>

配置日志 log4j.properties

log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

案例：单词统计

首先一个MR程序包含三部分

• Mapper
• Reducer
• Driver

Mapper.java

package com.xbz.study.bigdata.hadoop.mr.wc;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * 单词统计 mapper
 */
public class WcMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    private IntWritable one = new IntWritable(1);
    private Text word = new Text();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");
        for (String w : words) {
            word.set(w);
            context.write(word , one);
        }
    }
}

Reducer.java

package com.xbz.study.bigdata.hadoop.mr.wc;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;

public class WcReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    private IntWritable totalCount = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        Iterator<IntWritable> iterator = values.iterator();
        while(iterator.hasNext()){
            IntWritable next = iterator.next();
            sum += next.get();
        }
        totalCount.set(sum);
        context.write(key,totalCount);
    }
}

Driver.java

package com.xbz.study.bigdata.hadoop.mr.wc;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WcDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1. 创建一个Job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2. 设置类路径
        job.setJarByClass(WcDriver.class);

        //3. 设置Mapper和Reducer
        job.setMapperClass(WcMapper.class);
        job.setReducerClass(WcReducer.class);

        //4. 设置Mapper和Reducer的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //5. 设置输入输出数据
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //6. 提交job
        boolean b = job.waitForCompletion(true);
        System.out.println(b?0:1);
    }
}

值得注意的是：FileXXXFormat出自org.apache.hadoop.mapreduce.lib.input包

案例：统计手机号码上行、下行流量

主要演示hadoop里的序列化：主要通过实现org.apache.hadoop.io.Writable接口实现
输入文件格式如下

18701100188 10 120
13901124552 20 2345
13901124551 30 300
18701100188 11 220
13901124552 20 20
13901124551 10 500

package com.xbz.study.bigdata.hadoop.mr.flow;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class FlowBean implements Writable {
    private long upFlow;
    private long downFlow;
    private long sumFlow;


    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        //注意读取顺序
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }
    @Override
    public String toString() {
        return upFlow + " " + downFlow + " " + sumFlow;
    }
    //...省略setter和getter
}

Mapper.java

package com.xbz.study.bigdata.hadoop.mr.flow;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class FlowMapper extends Mapper<LongWritable, Text,Text,FlowBean> {
    private Text phone = new Text();
    private FlowBean flowBean = new FlowBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split(" ");
        phone.set(split[0]);
        Long upFlow = Long.valueOf(split[1]);
        Long downFlow = Long.valueOf(split[2]);
        flowBean.setUpFlow(upFlow);
        flowBean.setDownFlow(downFlow);
        flowBean.setSumFlow(upFlow + downFlow);
        context.write(phone,flowBean);
    }
}

package com.xbz.study.bigdata.hadoop.mr.flow;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.concurrent.atomic.AtomicLong;

public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
    private FlowBean result = new FlowBean();
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        AtomicLong sumUp = new AtomicLong();
        AtomicLong sumDown = new AtomicLong();
        AtomicLong totalSum = new AtomicLong();
        values.forEach((i)->{
            sumUp.addAndGet(i.getUpFlow());
            sumDown.addAndGet(i.getDownFlow());
            totalSum.addAndGet(i.getSumFlow());
        });
        result.setUpFlow(sumUp.get());
        result.setDownFlow(sumDown.get());
        result.setSumFlow(totalSum.get());
        context.write(key,result);
    }
}