Hadoop入门（十三）远程提交wordCout程序到hadoop集群

末蓝、 2023-06-03 09:55 6阅读 0赞

### 一、项目结构 ###

用到的文件有WordCount.java、core-site.xml、mapreduce-site.xml、yarn-site.xml、log4j.properties、pom.xml

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L21vYWt1bg_size_16_color_FFFFFF_t_70][]

### 二、项目源码 ###

（1）WordCount.java

package com.mk.mapreduce;
    
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.IntWritable;
    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;
    import java.util.StringTokenizer;
    
    public class WordCount {
    
        public static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    
            @Override
            protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
                 StringTokenizer tokenizer = new StringTokenizer(value.toString());
                 while (tokenizer.hasMoreTokens()){
                     context.write(new Text(tokenizer.nextToken()), new IntWritable(1));
                 }
    
            }
    
        }
    
        public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
            @Override
            protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
                int sum = 0;
                for (IntWritable v: values) {
                    sum += v.get();
                }
                context.write(key, new IntWritable(sum));
            }
        }
    
    
    
        public static void main(String[] args) throws Exception {
    
            final String uri = "hdfs://192.168.150.128:9000";
    
            Configuration conf = new Configuration();
            if(System.getProperty("os.name").toLowerCase().contains("win"))
                conf.set("mapreduce.app-submission.cross-platform","true");
    
            Job job = new Job(conf, "word count");
            String jar = ".\\out\\artifacts\\hadoop_test_jar\\hadoop-test.jar";
            job.setJar(jar);
            job.setJarByClass(WordCount.class);
            job.setMapperClass(MyMapper.class);
            job.setCombinerClass(MyReducer.class);
            job.setReducerClass(MyReducer.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
            FileInputFormat.addInputPath(job, new Path(uri + "/input"));
            FileOutputFormat.setOutputPath(job, new Path(uri + "/output"));
            System.exit(job.waitForCompletion(true) ? 0 : 1);
    
        }
    
    }

（2）core-site.xml

<configuration>
     <property>
       <name>fs.defaultFS</name>
       <value>hdfs://hadoop01:9000</value>       
     </property>
     <property>
         <name>hadoop.tmp.dir</name>
         <value>/home/mk/data/tmp</value>
     </property> 
    </configuration>

（3）mapreduce-site.xml

<?xml version="1.0"?>
    <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
    <configuration>
        <property>
          <name>mapreduce.framework.name</name>
          <value>yarn</value>
    </property>
    <property>
            <name>mapreduce.jobhistory.address</name>
            <value>hadoop01:10020</value>
    </property>
    <property>
            <name>mapreduce.jobhistory.webapp.address</name>
            <value>hadoop01:19888</value>
     </property>
     </configuration>

（4）yarn-site.xml

<configuration>
    	<property> 
    		<name>yarn.nodemanager.aux-services</name> 
    		<value>mapreduce_shuffle</value> 
    	</property> 
    	<property> 
    		<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name> 
    		<value>org.apache.hadoop.mapred.ShuffleHandler</value> 
    	</property> 
    	<property>
    		<name>yarn.resourcemanager.scheduler.address</name> 
    		<value>hadoop01:8030</value> 
    	</property> 
    	<property> 
    		<name>yarn.resourcemanager.resource-tracker.address</name> 
    		<value>hadoop01:8025</value> 
    	</property>
    	<property> 
    		<name>yarn.resourcemanager.address</name>
    		<value>hadoop01:8040</value>
    	</property> 
    </configuration>

（5）log4j.properties

log4j.rootLogger=INFO, stdout
    #log4j.logger.org.springframework=INFO
    #log4j.logger.org.apache.activemq=INFO
    #log4j.logger.org.apache.activemq.spring=WARN
    #log4j.logger.org.apache.activemq.store.journal=INFO
    #log4j.logger.org.activeio.journal=INFO
    
    
    log4j.appender.stdout=org.apache.log4j.ConsoleAppender
    log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
    log4j.appender.stdout.layout.ConversionPattern=%d{ABSOLUTE} | %-5.5p | %-16.16t | %-32.32c{1} | %-32.32C %4L | %m%n

（6）pom.xml

<?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>com.mk</groupId>
        <artifactId>hadoop-test</artifactId>
        <version>1.0-SNAPSHOT</version>
    
        <name>hadoop-test</name>
        <url>http://www.mk.com</url>
    
        <properties>
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
            <maven.compiler.source>1.7</maven.compiler.source>
            <maven.compiler.target>1.7</maven.compiler.target>
    
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
            <hadoop.version>2.6.0</hadoop.version>
        </properties>
    
        <dependencies>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-client</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-common</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
            <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
            </dependency>
            <dependency>
                <groupId>junit</groupId>
                <artifactId>junit</artifactId>
                <version>4.11</version>
                <scope>test</scope>
            </dependency>
    
        </dependencies>
    
        <build>
            <pluginManagement>
                <plugins>
                   <plugin>
                        <artifactId>maven-clean-plugin</artifactId>
                        <version>3.1.0</version>
                    </plugin>
                   <plugin>
                        <artifactId>maven-resources-plugin</artifactId>
                        <version>3.0.2</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-compiler-plugin</artifactId>
                        <version>3.8.0</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-surefire-plugin</artifactId>
                        <version>2.22.1</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-jar-plugin</artifactId>
                        <version>3.0.2</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-install-plugin</artifactId>
                        <version>2.5.2</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-deploy-plugin</artifactId>
                        <version>2.8.2</version>
                    </plugin>
                    
                    <plugin>
                        <artifactId>maven-site-plugin</artifactId>
                        <version>3.7.1</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-project-info-reports-plugin</artifactId>
                        <version>3.0.0</version>
                    </plugin>
                </plugins>
            </pluginManagement>
        </build>
    </project>

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L21vYWt1bg_size_16_color_FFFFFF_t_70]: /images/20230601/3485c19e14d84f408ef5865905fd04fc.png