马士兵hadoop2.7.3_mapreduce笔记

java开发map_reduce程序
配置系统环境变量HADOOP_HOME，指向hadoop安装目录（如果你不想招惹不必要的麻烦，不要在目录中包含空格或者中文字符）
把HADOOP_HOME/bin加到PATH环境变量（非必要，只是为了方便）
如果是在windows下开发，需要添加windows的库文件
1. 把盘中共享的bin目录覆盖HADOOP_HOME/bin
2. 如果还是不行，把其中的hadoop.dll复制到c:windowssystem32目录下，可能需要重启机器
建立新项目，引入hadoop需要的jar文件
代码WordMapper：

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
 
 
public class WordMapper extends Mapper<LongWritable,Text, Text, IntWritable> {
 
    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");
        for(String word : words) {
            context.write(new Text(word), new IntWritable(1));
        }
    }
     
}

代码WordReducer：

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
 
public class WordReducer extends Reducer<Text, IntWritable, Text, LongWritable> {
 
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values,
            Reducer<Text, IntWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
        long count = 0;
        for(IntWritable v : values) {
            count += v.get();
        }
        context.write(key, new LongWritable(count));
    }
     
}

代码Test：

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 
 
public class Test {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
                         
        Job job = Job.getInstance(conf);
         
        job.setMapperClass(WordMapper.class);
        job.setReducerClass(WordReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
         
        FileInputFormat.setInputPaths(job, "c:/bigdata/hadoop/test/test.txt");
        FileOutputFormat.setOutputPath(job, new Path("c:/bigdata/hadoop/test/out/"));
         
        job.waitForCompletion(true);
    }
}

把hdfs中的文件拉到本地来运行

1

2

3

FileInputFormat.setInputPaths(job, "hdfs://master:9000/wcinput/");

FileOutputFormat.setOutputPath(job, new Path("hdfs://master:9000/wcoutput2/"));

注意这里是把hdfs文件拉到本地来运行，如果观察输出的话会观察到jobID带有local字样
同时这样的运行方式是不需要yarn的(自己停掉yarn服务做实验)

在远程服务器执行

conf.set("fs.defaultFS", "hdfs://master:9000/");
 
conf.set("mapreduce.job.jar", "target/wc.jar");
conf.set("mapreduce.framework.name", "yarn");
conf.set("yarn.resourcemanager.hostname", "master");
conf.set("mapreduce.app-submission.cross-platform", "true");

FileInputFormat.setInputPaths(job, "/wcinput/");
FileOutputFormat.setOutputPath(job, new Path("/wcoutput3/"));

如果遇到权限问题，配置执行时的虚拟机参数-DHADOOP_USER_NAME=root

也可以将hadoop的四个配置文件拿下来放到src根目录下，就不需要进行手工配置了，默认到classpath目录寻找
或者将配置文件放到别的地方，使用conf.addResource(.class.getClassLoader.getResourceAsStream)方式添加，不推荐使用绝对路径的方式

建立maven-hadoop项目：

<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>mashibing.com</groupid>
  <artifactid>maven</artifactid>
  <version>0.0.1-SNAPSHOT</version>
  <name>wc</name>
  <description>hello mp</description>
   
   
  <properties>
        <project.build.sourceencoding>UTF-8</project.build.sourceencoding>
        <hadoop.version>2.7.3</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <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>
    </dependencies>
   
   
</project>

配置log4j.properties，放到src/main/resources目录下

log4j.rootCategory=INFO, stdout
 
log4j.appender.stdout=org.apache.log4j.ConsoleAppender   
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout   
log4j.appender.stdout.layout.ConversionPattern=[QC] %p [%t] %C.%M(%L) | %m%n