快速入門MapReduc① 實現WordCount

目錄

1.需要處理的數據

2.創建maven項目pom.xml

3.編寫map類

4.編寫Reduce類

5.編寫啓動類

6.執行的結果

---

1.需要處理的數據

hello word
word count
hello MapReduce

2.創建maven項目pom.xml

 <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-client</artifactId>
            <version>2.6.0-mr1-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-common</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </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>

3.編寫map類

package com.czxy.wordCount;

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

import java.io.IOException;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 將 Text類型轉換爲String 類型
        String s = value.toString();
        // 安裝空格切分
        String[] split = s.split(" ");
        // 循環遍歷輸出
        for (String s1 : split) {
            // 輸出 key=單詞 value =1
            context.write(new Text(s1), new LongWritable(1));
        }
    }
}

4.編寫Reduce類

package com.czxy.wordCount;

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

import java.io.IOException;

public class WordCountReduce extends Reducer<Text, LongWritable,Text,LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        // 定義一個變量用來記錄單詞出現的次數
        int sumCount=0;
        for (LongWritable value : values) {
            sumCount+=value.get();
        }
        // 結果數據
        context.write(key, new LongWritable(sumCount));
    }
}

5.編寫啓動類

package com.czxy.wordCount;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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;

public class WordCountDriver extends Configured implements Tool {


    @Override
    public int run(String[] args) throws Exception {
        // 獲取job
        Job job = Job.getInstance(new Configuration());
        //  設置支持jar執行
        job.setJarByClass(WordCountDriver.class);
        // 設置執行的napper
        job.setMapperClass(WordCountMapper.class);
        // 設置map輸出的key類型
        job.setMapOutputKeyClass(Text.class);
        // 設置map輸出value類型
        job.setMapOutputValueClass(LongWritable.class);
        // 設置執行的reduce
        job.setReducerClass(WordCountReduce.class);
        // 設置reduce輸出key的類型
        job.setOutputKeyClass(Text.class);
        // 設置reduce輸出value的類型
        job.setOutputValueClass(LongWritable.class);
        // 設置文件輸入
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("./data/wordCount/"));
        // 設置文件輸出
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job, new Path("./outPut/wordCount/"));
        // 設置啓動類
        boolean b = job.waitForCompletion(true);
        return b ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        // 調用啓動方法
        ToolRunner.run(new WordCountDriver(), args);
    }
}

6.執行的結果

MapReduce	1
count	1
hello	2
word	2