MapReduce分布式框架-WordCount案例实战

combiner - 本地统计，减少传输

partitioner - 分发规则自定义

jobhistory - 记录完整的mapreduce运行信息 - log

 

package wordcount;

import org.apache.hadoop.conf.Configuration;
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.output.FileOutputFormat;

import java.io.IOException;

public class WordCountApp{

    /** Map : 读取输入文件 - 分裂文本
     *  mapper<行号， 一行一行文本数据， 单个单词， 计数1 >
     *  map 输出是 reduce 输入
     */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{

        LongWritable one = new LongWritable(1);
        /**
         * map 方法, 自动继承
         * @param key - 是偏移量 - 行号
         * @param value - 每一行字符串
         * @param context
         * @throws IOException
         * @throws InterruptedException
         */
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // 接收到每一行数据
            String line = value.toString();
            // 按照指定的方式正则分割
            String[] wordList = line.split(" ");
            // 循环打标记1
            for (String word : wordList) {
                context.write(new Text(word), one);
            }


        }

    }

    /**
     * Text,
     * LongWritable,
     * Text,
     * LongWritable
     */
    public static class MyReducer extends Reducer<Text, LongWritable,Text, LongWritable>{

        /**
         *
         * @param key - map输出的主键值，一个一个单词
         * @param values - 是个
         * @param context
         * @throws IOException
         * @throws InterruptedException
         */
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
            // super.reduce(key, values, context);
            // 循环统计 单词的个数
            long sum = 0;
            for (LongWritable value : values) {
                // value.get(); 自动转化 longwrite类型
                sum += value.get();
            }
            // 统计结果输出
            context.write(key, new LongWritable(sum));

        }
    }


    /**
     * Driver 封装了mapreduce的所有信息
     * @param args
     */
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1. 创建configuration
        Configuration configuration = new Configuration();

        // 删除已经存在的输出目录
        Path ouputPath = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(configuration);
        if (fileSystem.exists(ouputPath)){
            fileSystem.delete(ouputPath, true);
            System.out.println("删除已经存在的wordcount输出目录");
        }

        // 2. 创建JOB
        Job job = Job.getInstance(configuration);
        // 3. 设置JOB的处理主类
        job.setJarByClass(WordCountApp.class);
        // 4. 设置作业处理的输入路径 - 控制台输入
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        // 5. 设置map相关的参数
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        // 6. 设置reduce相关的参数
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        // 7. 设置作业处理输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 8. 退出
        System.exit(job.waitForCompletion(true) ? 0 : 1 );


    }

}


// 编译 mvn clean package -DskipTests

 

 

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>youngpeng</groupId>
    <artifactId>wordcount</artifactId>
    <version>4.0</version>

    <properties>
        <hadoop.version>2.6.0</hadoop.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

    </dependencies>

    <build>

        <plugins>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>


            <plugin>
                <!-- JAR Maven 管理-->
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <configuration>
                    <archive>
                        <manifest>
                            <!-- 配置主程序 java -jar 默认Class -->
                            <addClasspath>true</addClasspath>
                            <classpathPrefix>lib/</classpathPrefix>
                            <!-- 指定 mainclass，该配置将最终体现在jar包manifest文件中 -->
                            <mainClass>wordcount.WordCountApp</mainClass>
                        </manifest>
                    </archive>
                </configuration>
            </plugin>

            <!-- maven 打包集成插件 -->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <descriptorRefs>
                        <!-- 将依赖一起打包到 JAR -->
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                            <!-- 配置主程序 java -jar 默认Class -->
                            <addClasspath>true</addClasspath>
                            <classpathPrefix>lib/</classpathPrefix>
                            <!-- 指定 mainclass，该配置将最终体现在jar包manifest文件中 -->
                            <mainClass>wordcount.WordCountApp</mainClass>
                        </manifest>
                    </archive>
                </configuration>
            </plugin>


        </plugins>
    </build>



</project>

 

        // 删除已经存在的输出目录
        Path ouputPath = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(configuration);
        if (fileSystem.exists(ouputPath)){
            fileSystem.delete(ouputPath, true);
            System.out.println("删除已经存在的wordcount输出目录");
        }

mvn clean package

# 讲一个坑， 就是打包把依赖打进去的问题， 添加插件 - 变更打包命令