首页 > 代码库 > eclipse配置hadoop2.7.2开发环境

eclipse配置hadoop2.7.2开发环境

  先安装并启动hadoop,怎么弄见上文http://www.cnblogs.com/wuxun1997/p/6847950.html。这里说下怎么设置IDE来开发hadoop代码。首先要确保你本地装了eclipse,再下个eclipse的hadoop插件就完事了。下面细说一下:

  1、到http://download.csdn.net/detail/wuxun1997/9841487下载eclipse插件并丢到eclipse的pulgin目录下,重启eclipse,Project Explorer出现DFS Locations;

  2、点击Window->点Preferences->点Hadoop Map/Reduce->填D:\hadoop-2.7.2并OK;

  3、点击Window->点Show View->点MapReduce Tools下的Map/Reduce Locations->点右边角一个带+号的小象图标"New hadoop location"->eclipse已填好默认参数,但以下几个参数需要修改以下,参见上文中的两个配置文件core-site.xml和hdfs-site.xml:

  General->Map/Reduce(V2) Master->Port改为9001

  General->DSF Master->Port改为9000

  Advanced paramters->dfs.datanode.data.dir改为ffile:/hadoop/data/dfs/datanode

  Advanced paramters->dfs.namenode.name.dir改为file:/hadoop/data/dfs/namenode

  4、点击Finish后在DFS Locations右键点击左边三角图标,出现hdsf文件夹,可以直接在这里操作hdsf,右键点击文件图标选"Create new Dictionery"即可新增,再次右键点击文件夹图标选Reflesh出现新增的结果;此时在localhost:50070->Utilities->Browse the file system也可以看到新增的结果;

  5、新建hadoop项目:File->New->Project->Map/Reduce Project->next->输入自己取的项目名如hadoop再点Finish

  6、这里的代码演示最常见的分词例子,统计的是中文小说里的人名并降序排列。为了分词需要导入一个jar,在这里下载http://download.csdn.net/detail/wuxun1997/9841659。项目结构如下:

hadoop

   |--src

       |--com.wulinfeng.hadoop.wordsplit

                                                   |--WordSplit.java

       |--IKAnalyzer.cfg.xml

       |--myext.dic

       |--mystopword.dic

WordSplit.java

package com.wulinfeng.hadoop.wordsplit;

import java.io.IOException;
import java.io.StringReader;

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.io.WritableComparable;
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.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.map.InverseMapper;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;

public class WordSplit {
    
    /**
     * map实现分词
     * @author Administrator
     *
     */
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            StringReader input = new StringReader(value.toString());
            IKSegmenter ikSeg = new IKSegmenter(input, true); // 智能分词
            for (Lexeme lexeme = ikSeg.next(); lexeme != null; lexeme = ikSeg.next()) {
                this.word.set(lexeme.getLexemeText());
                context.write(this.word, one);
            }
        }
    }

    /**
     * reduce实现分词累计
     * @author Administrator
     *
     */
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

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

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String inputFile = "/input/people.txt"; // 输入文件
        Path outDir = new Path("/out"); // 输出目录
        Path tempDir = new Path("/tmp" + System.currentTimeMillis()); // 临时目录

        // 第一个任务:分词
        System.out.println("start task...");
        Job job = Job.getInstance(conf, "word split");
        job.setJarByClass(WordSplit.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(inputFile));
        FileOutputFormat.setOutputPath(job, tempDir);

        // 第一个任务结束,输出作为第二个任务的输入,开始排序任务
        job.setOutputFormatClass(SequenceFileOutputFormat.class);
        if (job.waitForCompletion(true)) {
            System.out.println("start sort...");
            Job sortJob = Job.getInstance(conf, "word sort");
            sortJob.setJarByClass(WordSplit.class);
            sortJob.setMapperClass(InverseMapper.class);
            sortJob.setInputFormatClass(SequenceFileInputFormat.class);

            // 反转map键值,计算词频并降序
            sortJob.setMapOutputKeyClass(IntWritable.class);
            sortJob.setMapOutputValueClass(Text.class);
            sortJob.setSortComparatorClass(IntWritableDecreasingComparator.class);
            sortJob.setNumReduceTasks(1);

            // 输出到out目录文件
            sortJob.setOutputKeyClass(IntWritable.class);
            sortJob.setOutputValueClass(Text.class);
            FileInputFormat.addInputPath(sortJob, tempDir);

            // 如果已经有out目录,先删再创建
            FileSystem fileSystem = outDir.getFileSystem(conf);
            if (fileSystem.exists(outDir)) {
                fileSystem.delete(outDir, true);
            }
            FileOutputFormat.setOutputPath(sortJob, outDir);

            if (sortJob.waitForCompletion(true)) {
                System.out.println("finish and quit....");
                // 删掉临时目录
                fileSystem = tempDir.getFileSystem(conf);
                if (fileSystem.exists(tempDir)) {
                    fileSystem.delete(tempDir, true);
                }
                System.exit(0);
            }
        }
    }

    /**
     * 实现降序
     * 
     * @author Administrator
     *
     */
    private static class IntWritableDecreasingComparator extends IntWritable.Comparator {
        public int compare(WritableComparable a, WritableComparable b) {
            return -super.compare(a, b);
        }

        public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {
            return -super.compare(b1, s1, l1, b2, s2, l2);
        }
    }
}

IKAnalyzer.cfg.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
<properties>
    <comment>IK Analyzer 扩展配置</comment>
    <!--用户可以在这里配置自己的扩展字典 -->
    <entry key="ext_dict">myext.dic</entry>
    <!--用户可以在这里配置自己的扩展停止词字典 -->
    <entry key="ext_stopwords">mystopword.dic</entry>
</properties>

myext.dic

高育良
祁同伟
陈海
陈岩石
侯亮平
高小琴
沙瑞金
李达康
蔡成功

mystopword.dic

你
我
他
是
的
了
啊
说
也
和
在
就

  这里直接在eclipse跑WordSplit类,右键选择Run as -> Run on hadoop。因为在类里写死了输入文件,所以需要在D盘建一个input目录,里面放个文件名叫people.txt的小说,是网上荡下来的热剧《人民的名义》,为了分词的需要把people.txt去Notepad++里打开,点编码->以UTF-8以无BOM格式编码。在myext.dic里输入一些不想拆分的人名,在mystopword.dic输入想要过滤掉的一些谓词和助词,跑完去D:\out里看part-r-00000文件即可知道谁是猪脚。

eclipse配置hadoop2.7.2开发环境