先安裝並啟動hadoop，怎麽弄見上文http://www.cnblogs.com/wuxun1997/p/6847950.html。這裏說下怎麽設置IDE來開發hadoop代碼。首先要確保你本地裝了eclipse，再下個eclipse的hadoop插件就完事了。下面細說一下：

　　1、到http://download.csdn.net/detail/wuxun1997/9841487下載eclipse插件並丟到eclipse的pulgin目錄下，重啟eclipse，Project Explorer出現DFS Locations；

　　2、點擊Window->點Preferences->點Hadoop Map/Reduce->填D:\hadoop-2.7.2並OK；

　　3、點擊Window->點Show View->點MapReduce Tools下的Map/Reduce Locations->點右邊角一個帶+號的小象圖標"New hadoop location"->eclipse已填好默認參數，但以下幾個參數需要修改以下，參見上文中的兩個配置文件core-site.xml和hdfs-site.xml：

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

　　General->DSF Master->Port改為9000

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

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

　　4、點擊Finish後在DFS Locations右鍵點擊左邊三角圖標，出現hdsf文件夾，可以直接在這裏操作hdsf，右鍵點擊文件圖標選"Create new Dictionery"即可新增，再次右鍵點擊文件夾圖標選Reflesh出現新增的結果；此時在localhost:50070->Utilities->Browse the file system也可以看到新增的結果；

　　5、新建hadoop項目：File->New->Project->Map/Reduce Project->next->輸入自己取的項目名如hadoop再點Finish

　　6、這裏的代碼演示最常見的分詞例子，統計的是中文小說裏的人名並降序排列。為了分詞需要導入一個jar，在這裏下載http://download.csdn.net/detail/wuxun1997/9841659。項目結構如下:

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實現分詞
     * @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); // 智能分詞
            for (Lexeme lexeme = ikSeg.next(); lexeme != null; lexeme = ikSeg.next()) {
                this.word.set(lexeme.getLexemeText());
                context.write(this.word, one);
            }
        }
    }

    /**
     * reduce實現分詞累計
     * @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"; // 輸入文件
        Path outDir = new Path("/out"); // 輸出目錄
        Path tempDir = new Path("/tmp" + System.currentTimeMillis()); // 臨時目錄

        // 第一個任務：分詞
        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);

        // 第一個任務結束，輸出作為第二個任務的輸入，開始排序任務
        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);

            // 反轉map鍵值，計算詞頻並降序
            sortJob.setMapOutputKeyClass(IntWritable.class);
            sortJob.setMapOutputValueClass(Text.class);
            sortJob.setSortComparatorClass(IntWritableDecreasingComparator.class);
            sortJob.setNumReduceTasks(1);

            // 輸出到out目錄文件
            sortJob.setOutputKeyClass(IntWritable.class);
            sortJob.setOutputValueClass(Text.class);
            FileInputFormat.addInputPath(sortJob, tempDir);

            // 如果已經有out目錄，先刪再創建
            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....");
                // 刪掉臨時目錄
                fileSystem = tempDir.getFileSystem(conf);
                if (fileSystem.exists(tempDir)) {
                    fileSystem.delete(tempDir, true);
                }
                System.exit(0);
            }
        }
    }

    /**
     * 實現降序
     * 
     * @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 擴展配置</comment>
    <!--用戶可以在這裏配置自己的擴展字典 -->
    <entry key="ext_dict">myext.dic</entry>
    <!--用戶可以在這裏配置自己的擴展停止詞字典 -->
    <entry key="ext_stopwords">mystopword.dic</entry>
</properties>

myext.dic

高育良
祁同偉
陳海
陳巖石
侯亮平
高小琴
沙瑞金
李達康
蔡成功

mystopword.dic

你
我
他
是
的
了
啊
說
也
和
在
就

　　這裏直接在eclipse跑WordSplit類，右鍵選擇Run as -> Run on hadoop。因為在類裏寫死了輸入文件，所以需要在D盤建一個input目錄，裏面放個文件名叫people.txt的小說，是網上蕩下來的熱劇《人民的名義》，為了分詞的需要把people.txt去Notepad++裏打開，點編碼->以UTF-8以無BOM格式編碼。在myext.dic裏輸入一些不想拆分的人名，在mystopword.dic輸入想要過濾掉的一些謂詞和助詞，跑完去D:\out裏看part-r-00000文件即可知道誰是豬腳。

eclipse配置hadoop2.7.2開發環境