MapReduce一次讀取多個文件

MapReduce一次讀取多個文件

求出每一行數據所在的文件名

學習目標（獲取數據所在文件的名稱）

主要還是map中的改變
在map中通過context調用getInputSplit()這個方法，再將此對象強轉爲FileSplit就能通過getPath()方法的getName()方法獲取文件名了
上代碼：

package com.damo01;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

/**
 * @author 嗨皮騷
 * @version v 1.0
 * @date 2019/11/18
 */
public class MyMapper extends Mapper<LongWritable, Text,Text,Text> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
    
        //通過context調用getInputSplit()這個方法,因爲我們要讀取多個文件，所以要強轉爲FileSplit
        FileSplit fileSplit = (FileSplit) context.getInputSplit();
        //fileSplit調用getPath獲取路徑信息
        Path path = fileSplit.getPath();
        //通過路徑信息path獲取文件的名字
        String name = path.getName();


        context.write(new Text(name),value);
        //這樣我們就將文件的名字及其每一行的內容傳給reduce了
    }
}

後面的代碼和以前一樣，沒有什麼特別的操作

package com.damo01;

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

import java.io.IOException;

/**
 * @author 嗨皮騷
 * @version v 1.0
 * @date 2019/11/18
 */
public class MyReduce extends Reducer<Text,Text,Text,Text> {
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        //遍歷拿到的同一個key的數據，直接輸出便是
        for (Text value : values) {
            context.write(new Text(key.toString()),value);
        }
    }
}

Driver的代碼和以前一樣，沒有什麼特別的操作

ackage com.damo01;

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

/**
 * @author 嗨皮騷
 * @version v 1.0
 * @date 2019/11/18
 */
public class MyDriver extends Configured implements Tool {
    @Override
    public int run(String[] strings) throws Exception {
        //實例一個job對象參數（Configuration對象，隨便一個字符串的名字）
        Job job = Job.getInstance(new Configuration(), "demo01");
        //這一步是爲了獲取文件或目錄內的文件，我使用的是本地的地址
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("E:\\教學\\學習資料3\\11.18\\day24"));
        //這一步是爲了讓jar包在集羣中跑起來
        job.setJarByClass(MyDriver.class);
        //配置map類
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //配置reduce類
        job.setReducerClass(MyReduce.class);
        //配置輸出類型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        //這一步是輸出結果的目錄
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("E:\\教學\\學習資料3\\11.18\\day24\\結果"));

        //開啓job的運行，並打印信息，返回狀態碼
        return job.waitForCompletion(true)?0:1;
    }

    public static void main(String[] args) throws Exception {
        //運行MapReduce
        int run = ToolRunner.run(new MyDriver(), args);
        System.out.println(run==0?"成功":"失敗");
    }
}

Hadoop的pom依賴

 <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-common</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.7.4</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/junit/junit -->
        <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>
                    <!--    <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>