MapReduce example 1-count the number of text words

Article Directory

Requirements: Count and output the total number of occurrences of each word in a given set of text files

Step 1. Data format preparation

Create a new file
```
cd /export/servers
vim wordcount.txt
```

Put the following content into it and save

hello,world,hadoop
hive,sqoop,flume,hello
kitty,tom,jerry,world
hadoop

Upload to HDFS

hdfs dfs -mkdir /wordcount/
hdfs dfs -put wordcount.txt /wordcount/

Step 2. Mapper

First of all, we must configure the pom.xml file

<!--最后要打包成jar包-->
<packaging>jar</packaging>

<dependencies>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>3.1.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>3.1.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>3.1.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-mapreduce-client-core</artifactId>
        <version>3.1.2</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.9</version>
    </dependency>
</dependencies>

<build>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <version>3.1</version>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
                <encoding>UTF-8</encoding>
                <!--    <verbal>true</verbal>-->
            </configuration>
        </plugin>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-shade-plugin</artifactId>
            <version>2.4.3</version>
            <executions>
                <execution>
                    <phase>package</phase>
                    <goals>
                        <goal>shade</goal>
                    </goals>
                    <configuration>
                        <minimizeJar>true</minimizeJar>
                    </configuration>
                </execution>
            </executions>
        </plugin>

    </plugins>
</build>

Create a package MapReduceDemo1

Then rewrite the mapper logic

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

import java.io.IOException;

/*
四个泛型：
KEYIN：K1的类型
VALUEIN：V1的类型
KEYOUT：K2的类型
VALUEOUT：V2的类型
 */
// hadoop中数据需要经常进行序列化，因此在Java中的数据结构较为臃肿
// 因此一般使用hadoop中的数据类型，如LongWritable, Text都是hadoop自带的数据类型
public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
    
    
    /*
    map是将K1，V1转为K2，V2
    K1          V1
    0           hello,world,hadoop
    12          hdfs,hive,hello
    ---------------------------------
    K2          V2
    hello       1
    world       1
    hadoop      1
    hdfs        1
    hive        1
    hello       1
     */
    @Override
    //protected void map(KEYIN key, VALUEIN value, Context context)
    protected void map(LongWritable key, Text value, Context context) throws InterruptedException, IOException {
    
    
        // 对每一行数据进行拆分
        // Text不能直接进行拆分
        String line = value.toString();
        String[] split = line.split(",");
        
        //遍历数组，得到K2和V2
        for (String word : split) {
    
    
            context.write(new Text(word),new LongWritable(1));
        }
    }
}

Step 3. Reducer

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, LongWritable,Text,LongWritable> {
    
    
    /*
    Reduce是将K2，V2转为K3，V3
    K2          V2
    hello       <1,1>
    world       <1>
    hadoop      <1>
    hdfs        <1>
    hive        <1>
    ---------------------------------
    K3          V3
    hello       2
    world       1
    hadoop      1
    hdfs        1
    hive        1
     */
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
    
    
        /*
        key:K3
        values:V3
        context:上下文对象
         */
        long count = 0;
        // 遍历集合
        for (LongWritable value : values) {
    
    
            count += value.get();
        }
        // 将K3和V3写入context
        context.write(key,new LongWritable(count));
    }
}

Step 4. Define the main class, describe the job and submit the job

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.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.net.URI;


public class main extends Configured implements Tool {
    
    
    //指定一个job任务
    @Override
    public int run(String[] args) throws Exception {
    
    
        // 创建job任务对象, 获取的是main中的Configuration
        Job job = Job.getInstance(super.getConf(), "wordCount");

        //打包到集群上面运行时候，必须要添加以下配置，指定程序的main函数
        job.setJarByClass(main.class);

        //第一步：读取输入文件解析成key，value对
        job.setInputFormatClass(TextInputFormat.class);
        //读取源文件
        //文件在hdfs上
        TextInputFormat.addInputPath(job, new Path("hdfs://hadoop1:8020/wordcount"));
        //文件在本地
//        TextInputFormat.addInputPath(job, new Path("file:///E:\\atest\\hello.txt"));

        //第二步：设置我们的mapper类
        job.setMapperClass(WordCountMapper.class);
        //设置我们map阶段完成之后的输出类型,即K2和V2的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //第三步，第四步，第五步，第六步采用默认方式，本案例不重新设置

        //第七步：设置我们的reduce类
        job.setReducerClass(WordCountReducer.class);
        //设置我们reduce阶段完成之后的输出类型，K3和V3的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //第八步：设置输出类以及输出路径
        job.setOutputFormatClass(TextOutputFormat.class);
        // 输出存到HDFS上
        Path path = new Path("hdfs://hadoop1:8020/wordcount_out");
        // 判断路径是否存在文件
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://hadoop1:8020"), new Configuration());
        boolean exists = fileSystem.exists(path);
        // 如果目标路径存在，删除之前的
        if(exists){
    
    
            fileSystem.delete(path,true);
        }
        TextOutputFormat.setOutputPath(job,path);
        // 输出存到本地
//        TextOutputFormat.setOutputPath(job,new Path("file:///E:\\atest\\output"));



        // 等待任务结束
        boolean b = job.waitForCompletion(true);

        return b?0:1;
    }

    /**
     * 程序main函数的入口类
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
    
    
        Configuration configuration = new Configuration();

        // 启动job任务，返回int，0表示失败
        int run = ToolRunner.run(configuration, new main(), args);
        System.exit(run);
    }
}

If there is log4j Warning, you can create a new log4j.properties under resorces

# Configure logging for testing: optionally with log file

#log4j.rootLogger=debug,appender
log4j.rootLogger=info,appender  
#log4j.rootLogger=error,appender

#\u8F93\u51FA\u5230\u63A7\u5236\u53F0
log4j.appender.appender=org.apache.log4j.ConsoleAppender  
#\u6837\u5F0F\u4E3ATTCCLayout
log4j.appender.appender.layout=org.apache.log4j.TTCCLayout

Run on the cluster

1. Package the program as a jar package

Insert picture description here

Packaged jar package

Insert picture description here

MapReduceDemo-1.0-SNAPSHOT.jar is to package all dependent packages together

Original-MapReduceDemo-1.0-SNAPSHOT.jar does not package the dependency package

2. Run the MapReduce program on the cluster

Upload jar package

cd /export/servers/
mkdir jar_test
rz -E

Run the program

hadoop jar jar包名主方法位置

hadoop jar MapReduceDemo-1.0-SNAPSHOT.jar MapReduceDemo1.main

Insert picture description here