idea+Windows+hadoop本地调试

1、下载hadoop-2.6.0.tar.gz包到本地

我解压后放入D:\hadoop-2.6.0-cdh5.9.3\

https://github.com/steveloughran/winutils.git

选择相应的版本

下载hadoop.dll、winutils.exe文件放入D:\hadoop-2.6.0-cdh5.9.3\hadoop-2.6.0\bin

配置环境变量

HADOOP_HOME=D:\hadoop-2.6.0-cdh5.9.3\hadoop-2.6.0

HADOOP_BIN_PATH=%HADOOP_HOME%\bin

HADOOP_PREFIX=D:\hadoop-2.6.0-cdh5.9.3\hadoop-2.6.0

PATH后增加;%HADOOP_HOME%\bin

基于官方WordCount 修改 增加了，如果输出目录存在就删除的逻辑和系统参数

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;
import org.apache.hadoop.util.GenericOptionsParser;

import java.io.IOException;
import java.util.Properties;
import java.util.StringTokenizer;

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);
        }
    }


    /**
     * 删除指定目录
     *
     * @param conf
     * @param dirPath
     * @throws IOException
     */
    private static void deleteDir(Configuration conf, String dirPath) throws IOException {
        FileSystem fs = FileSystem.get(conf);
        Path targetPath = new Path(dirPath);
        if (fs.exists(targetPath)) {
            boolean delResult = fs.delete(targetPath, true);
            if (delResult) {
                System.out.println(targetPath + " has been deleted sucessfullly.");
            } else {
                System.out.println(targetPath + " deletion failed.");
            }
        }

    }

    public static void main(String[] args) throws Exception {
        Properties props = System.getProperties(); //系统属性
        System.out.println("Java的运行环境版本：" + props.getProperty("java.version"));
        System.out.println("Java的运行环境供应商：" + props.getProperty("java.vendor"));
        System.out.println("Java供应商的URL：" + props.getProperty("java.vendor.url"));
        System.out.println("Java的安装路径：" + props.getProperty("java.home"));
        System.out.println("Java的虚拟机规范版本：" + props.getProperty("java.vm.specification.version"));
        System.out.println("Java的虚拟机规范供应商：" + props.getProperty("java.vm.specification.vendor"));
        System.out.println("Java的虚拟机规范名称：" + props.getProperty("java.vm.specification.name"));
        System.out.println("Java的虚拟机实现版本：" + props.getProperty("java.vm.version"));
        System.out.println("Java的虚拟机实现供应商：" + props.getProperty("java.vm.vendor"));
        System.out.println("Java的虚拟机实现名称：" + props.getProperty("java.vm.name"));
        System.out.println("Java运行时环境规范版本：" + props.getProperty("java.specification.version"));
        System.out.println("Java运行时环境规范供应商：" + props.getProperty("java.specification.vender"));
        System.out.println("Java运行时环境规范名称：" + props.getProperty("java.specification.name"));
        System.out.println("Java的类格式版本号：" + props.getProperty("java.class.version"));
        String jars = props.getProperty("java.class.path");
        String[] split = jars.split(";", -1);
        for (String jar : split) {
            System.out.println("Java的类路径jar: " + jar);
        }
        //System.out.println("Java的类路径：" + props.getProperty("java.class.path"));
        String paths = props.getProperty("java.library.path");
        String[] pathsSplit = paths.split(";", -1);
        for (String path : pathsSplit) {
            System.out.println("加载库时搜索的路径列表：" + path);
        }
        //System.out.println("加载库时搜索的路径列表：" + props.getProperty("java.library.path"));
        System.out.println("默认的临时文件路径：" + props.getProperty("java.io.tmpdir"));
        System.out.println("一个或多个扩展目录的路径：" + props.getProperty("java.ext.dirs"));
        System.out.println("操作系统的名称：" + props.getProperty("os.name"));
        System.out.println("操作系统的构架：" + props.getProperty("os.arch"));
        System.out.println("操作系统的版本：" + props.getProperty("os.version"));
        System.out.println("文件分隔符：" + props.getProperty("file.separator"));   //在 unix 系统中是＂／＂
        System.out.println("路径分隔符：" + props.getProperty("path.separator"));   //在 unix 系统中是＂:＂
        System.out.println("行分隔符：" + props.getProperty("line.separator"));   //在 unix 系统中是＂/n＂
        System.out.println("用户的账户名称：" + props.getProperty("user.name"));
        System.out.println("用户的主目录：" + props.getProperty("user.home"));
        System.out.println("用户的当前工作目录：" + props.getProperty("user.dir"));
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }

        //先删除output目录
        deleteDir(conf, otherArgs[otherArgs.length - 1]);

        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);
        for (int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job,
                new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

 pom依赖

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.6.0</version>
        </dependency>

添加本地依赖

 

集群信息

hdfs-site.xml

core-site.xml

放入resources 文件

 

给出输入输出参数运行即可

确保本地文件和maven依赖都被加载到