使用idea在windows上连接远程hadoop开发

Posted 2020-12-31 SUIB

一.前置环境准备

1.下载一份hadoop本地解压，配置HADOOP_HOME的环境变量   

idea运行时会读这个环境变量然后找到他里面的bin文件，其实不需要启动 只要有bin这个目录就行,不然会报错 找不到HADOOP_HOME这个环境变量

2.bin里面缺少了winutils.exe和hadoop.dll 需要额外下载

https://github.com/steveloughran/winutils

也可以不下载hadoop直接下载这个bin把环境变量配置成这个bin的上一级目录

3.将hadoop.dll 复制到C:\\Windows\\System32中 否则 会报 Exception in thread "main"java.lang.UnsatisfiedLinkError:org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z

 

二.构建项目

　　1.导入jar

<dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>3.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>3.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>3.1.0</version>
        </dependency>

　　2.拷贝源码中WordCount.java  位置在 hadoop-3.1.0-src\\hadoop-mapreduce-project\\hadoop-mapreduce-client\\hadoop-mapreduce-client-jobclient\\src\\test\\java\\org\\apache\\hadoop\\mapred目录中  我这个稍有改动

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * This is an example Hadoop Map/Reduce application.
 * It reads the text input files, breaks each line into words
 * and counts them. The output is a locally sorted list of words and the 
 * count of how often they occurred.
 *
 * To run: bin/hadoop jar build/hadoop-examples.jar wordcount
 *            [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i> <i>out-dir</i> 
 */
public class WordCount extends Configured implements Tool {
  
  /**
   * Counts the words in each line.
   * For each line of input, break the line into words and emit them as
   * (<b>word</b>, <b>1</b>).
   */
  public static class MapClass extends MapReduceBase
    implements Mapper<LongWritable, Text, Text, IntWritable> {
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
    
    public void map(LongWritable key, Text value, 
                    OutputCollector<Text, IntWritable> output, 
                    Reporter reporter) throws IOException {
      String line = value.toString();
      StringTokenizer itr = new StringTokenizer(line," \\t\\n\\r\\f,.:;?![]\'");
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken().toLowerCase());
        output.collect(word, one);
      }
    }
  }
  
  /**
   * A reducer class that just emits the sum of the input values.
   */
  public static class Reduce extends MapReduceBase
    implements Reducer<Text, IntWritable, Text, IntWritable> {
    
    public void reduce(Text key, Iterator<IntWritable> values,
                       OutputCollector<Text, IntWritable> output, 
                       Reporter reporter) throws IOException {
      int sum = 0;
      while (values.hasNext()) {
        sum += values.next().get();
      }
      if(sum>4){
        output.collect(key, new IntWritable(sum));
      }
    }
  }
  
  static int printUsage() {
    System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
    ToolRunner.printGenericCommandUsage(System.out);
    return -1;
  }
  
  /**
   * The main driver for word count map/reduce program.
   * Invoke this method to submit the map/reduce job.
   * @throws IOException When there is communication problems with the 
   *                     job tracker.
   */
  public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), WordCount.class);
    conf.setJobName("wordcount");
 
    // the keys are words (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are counts (ints)
    conf.setOutputValueClass(IntWritable.class);
    
    conf.setMapperClass(MapClass.class);        
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);
    
    List<String> other_args = new ArrayList<String>();
    for(int i=0; i < args.length; ++i) {
      try {
        if ("-m".equals(args[i])) {
          conf.setNumMapTasks(Integer.parseInt(args[++i]));
        } else if ("-r".equals(args[i])) {
          conf.setNumReduceTasks(Integer.parseInt(args[++i]));
        } else {
          other_args.add(args[i]);
        }
      } catch (NumberFormatException except) {
        System.out.println("ERROR: Integer expected instead of " + args[i]);
        return printUsage();
      } catch (ArrayIndexOutOfBoundsException except) {
        System.out.println("ERROR: Required parameter missing from " +
                           args[i-1]);
        return printUsage();
      }
    }
    // Make sure there are exactly 2 parameters left.
    if (other_args.size() != 2) {
      System.out.println("ERROR: Wrong number of parameters: " +
                         other_args.size() + " instead of 2.");
      return printUsage();
    }
    FileInputFormat.setInputPaths(conf, other_args.get(0));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
        
    JobClient.runJob(conf);
    return 0;
  }
  
  
  public static void main(String[] args) throws Exception {
    int res = ToolRunner.run(new Configuration(), new WordCount(), new String[]{"D:\\\\my.txt","D:\\\\out"});
    System.exit(res);
  }

}

 

运行可能会报权限不足的问题 ，编辑服务器etc/hadoop/hdfs-site.xml  将 dfs.permissions修改为false 重启即可

<property>
    <name>dfs.permissions</name>
    <value>false</value>
</property>

好啦 现在运行 

 

控制台没有任何报错  去D盘看看

D盘已经生成了out文件夹 打开out 发现里面有四个文件 比服务器本地执行多了两个.crc文件  我们先看看part-00000

已经出来统计结果了 。idea本地调用远程hadoop服务成功！  eclipse应该也差不多 ，之前百度大多是eclipse的教程，而且好像还要有什么插件，但是今天就弄了几个文件就好了，不知道是不是hadoop3对windows方面做了升级。

 

刚刚也打开了crc文件里面是乱码 

百度了一下说是hadoop数据校验文件 

大家有兴趣可以看看这篇博客 了解crc文件更多知识  （我是只看了前面 是不是太没耐心了  。。。）

https://www.cnblogs.com/gpcuster/archive/2011/01/26/1945363.html

 

还在一个人摸爬滚打学习hadoop  大家有兴趣可以一起交流