MapReduce一次读取多个文件
程序员文章站
2024-02-03 17:31:04
...
MoreFileMap
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;
public class MoreFileMap extends Mapper<LongWritable, Text,Text,Text> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//获取 所属文件名称
FileSplit fs = (FileSplit) context.getInputSplit();
String name = fs.getPath().getName();
context.write(new Text(name),value);
}
}
MoreFileReduce
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class MoreFileReduce extends Reducer<Text,Text,Text,Text> {
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
for (Text value : values) {
context.write(key,value);
}
}
}
MoreFileDriver
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.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 MoreFileDriver extends Configured implements Tool {
@Override
public int run(String[] args) throws Exception {
Configuration con = new Configuration();
FileSystem fs = FileSystem.get(con);
Job job = Job.getInstance(new Configuration(), "MoreFileDriver");
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.addInputPath(job,new Path("C:\\Users\\真情\\Desktop\\demo01"));
job.setMapperClass(MoreFileMap.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setReducerClass(MoreFileReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setOutputFormatClass(TextOutputFormat.class);
boolean exists = fs.exists(new Path("C:\\Users\\真情\\Desktop\\demo01\\OutPut"));
if (exists){
fs.delete(new Path("C:\\Users\\真情\\Desktop\\demo01\\OutPut"));
}
TextOutputFormat.setOutputPath(job,new Path("C:\\Users\\真情\\Desktop\\demo01\\OutPut"));
return job.waitForCompletion(true)?0:1;
}
public static void main(String[] args) throws Exception {
ToolRunner.run(new MoreFileDriver(),args);
}
}
效果图
两个文件
生成一个大的文件
POM文件
<?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>cn.itcast</groupId>
<artifactId>mapreduce</artifactId>
<version>1.0-SNAPSHOT</version>
<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>
</project>
上一篇: 求解数组中任意两个元素的和最接近某一个数