linux下基于eclipse的hadoop开发

太水了，要不是不会java和eclipse也不会浪费我这么多时间了，做个笔记。

1.安装eclipse。yum install eclipse,版本3.3.2。
2.下载MapReduce Tools for Eclipse插件。http://www.alphaworks.ibm.com/tech/mapreducetools。
3.查找eclipse安装路径，看插件放在哪里。打开eclipse,Help->About Fedora Eclipse->Configuration Details,，，安装路径：/usr/share/eclipse，下面有个plugins，插件放这里。
4.重启eclipse。
5.设置hadoop路径。Windows->Preferences->Hadoop Home Directory,填写hadoop路径。
6.建MapReduce项目。File->New->Project,选择MapReduce Project,,,,填写项目名，如wordcount
7.写代码。可以new file，也可以右键点击wordcount->import->general->FileSystem,,,导入文件到workspace/wordcount/src，，，主要是写Map，Reduce类，main函数。
WordCount：http://hadoop.apache.org/common/docs/r0.20.1/cn/mapred_tutorial，（WordCount v1.0）。
8.设置运行时参数。Run->Open Run Dialog,选中要运行的项目，->Arguments。
这里的路径是相对于workspace的，不是相对于hadoop安装路径的。shit。run。。。当然hadoop要start。

WordCount：
1. package org.myorg;
2.
3. import java.io.IOException;
4. import java.util.*;
5.
6. import org.apache.hadoop.fs.Path;
7. import org.apache.hadoop.conf.*;
8. import org.apache.hadoop.io.*;
9. import org.apache.hadoop.mapred.*;
10. import org.apache.hadoop.util.*;
11.
12. public class WordCount {
13.
14. public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
15. private final static IntWritable one = new IntWritable(1);
16. private Text word = new Text();
17.
18. public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
19. String line = value.toString();
20. StringTokenizer tokenizer = new StringTokenizer(line);
21. while (tokenizer.hasMoreTokens()) {
22. word.set(tokenizer.nextToken());
23. output.collect(word, one);
24. }
25. }
26. }
27.
28. public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
29. public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
30. int sum = 0;
31. while (values.hasNext()) {
32. sum += values.next().get();
33. }
34. output.collect(key, new IntWritable(sum));
35. }
36. }
37.
38. public static void main(String[] args) throws Exception {
39. JobConf conf = new JobConf(WordCount.class);
40. conf.setJobName("wordcount");
41.
42. conf.setOutputKeyClass(Text.class);
43. conf.setOutputValueClass(IntWritable.class);
44.
45. conf.setMapperClass(Map.class);
46. conf.setCombinerClass(Reduce.class);
47. conf.setReducerClass(Reduce.class);
48.
49. conf.setInputFormat(TextInputFormat.class);
50. conf.setOutputFormat(TextOutputFormat.class);
51.
52. FileInputFormat.setInputPaths(conf, new Path(args[0]));
53. FileOutputFormat.setOutputPath(conf, new Path(args[1]));
54.
55. JobClient.runJob(conf);
56. }
57. }

参考：
http://www.ibm.com/developerworks/cn/opensource/os-cn-hadoop2/

...
public class WordCount extends Configured implements Tool {
代码清单1
代码清单2
代码清单3
}