windows10下使用idea远程调试hadoop集群

在windows10环境下，使用idea搭建maven项目链接Linux上的hadoop集群。

注意事项： 

         保证hadoop集群的用户与Windows的用户一致，不然后报错，错误信息我忘了，反正很麻烦

1. 下载hadoop-2.6.0.tar.gz，解压到本地文件夹：D:\configureSoftWare\hadoop-2.6.0

2. 配置hadoop环境变量： %HADOOP_HOME% = D:\configureSoftWare\hadoop-2.6.0

3. 将winutils.exe文件拷贝到%HADOOP_HOME%/bin 目录下

4. hadoop.dll文件拷贝到C:\Windows\System32目录下

     winutils.lb和hadoop.dll的下载地址：http://pan.baidu.com/s/1hrNXq3y

5. 新建一个maven项目，这个比较简单，网上很多创建maven工程的文章，创建好以后项目结构如下：

6. 如图，将hadoop-2.6.0/etc/hadoop文件夹下的core-site.xml和log4j.properties文件拷贝到resources文件夹下

        在core-site.xml中添加配置：

<configuration>
  <property>
               <name>fs.defaultFS</name>
               <value>hdfs://192.168.0.26:9000</value>
  </property>
<property>
               <name>hadoop.proxyuser.hadoop.hosts</name>
               <value>*</value>
</property>
<property>
               <name>hadoop.proxyuser.hadoop.groups</name>
               <value>*</value>
</property>
</configuration>

fs.defaultFS处换为hadoop集群的namenode的IP地址。

7. 要想使用hadoop，害得添加依赖包。修改pom.xml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>com.fun</groupId>
    <artifactId>hadoop</artifactId>
    <version>1.0-SNAPSHOT</version>

    <repositories>
        <repository>
            <id>apache</id>
            <url>http://maven.apache.org</url>
        </repository>
    </repositories>

    <dependencies>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs-client</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>commons-cli</groupId>
            <artifactId>commons-cli</artifactId>
            <version>1.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.6.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/com.alibaba/fastjson -->
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.33</version>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <artifactId>maven-dependency-plugin</artifactId>
                <configuration>
                    <excludeTransitive>false</excludeTransitive>
                    <stripVersion>true</stripVersion>
                    <outputDirectory>./lib</outputDirectory>
                </configuration>

            </plugin>
        </plugins>
    </build>
</project>

8. 到此为止，所有环境已搭建好，我们来试一试，使用最经典的Wordcount测试一下

package MR;

/**
 * Created by hadoop on 2017/5/25.
 */
/**
 * Created by jinshilin on 16/12/7.
 */
import java.io.IOException;
import java.net.URI;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;

public class WordCount {

    public static class TokenizerMapper
            extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context
        ) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer
            extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values,
                           Context context
        ) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();

//        Path input = new Path("hdfs://192.168.0.26:9000/people");
        Path input = new Path(URI.create("hdfs://192.168.0.26:9000/people"));
        Path output = new Path(URI.create("hdfs://192.168.0.26:9000/output"));
        Job job = Job.getInstance(conf, "word count");

        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, input);
        FileOutputFormat.setOutputPath(job, output);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

10 . 运行程序：

在HDFS上查看结果：

11 . 大功告成！！