1 创建Map/Reduce 工程
File->new->project->Map/Reduce
Project
2 创建类WordCount
File->new->class
3 设置输入输出参数
Run->Run Configuration, Arguments
在program arguments中写入输入输出参数,即输入输出文件路径:
hdfs://localhost:9000/user/leo/ hdfs://localhost:9000/user/out
4 run as java application
- import java.io.IOException;
- import java.util.StringTokenizer;
- import org.apache.hadoop.conf.Configuration;
- 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;
- 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);
- }
- }
- public static void main(String[] args) throws Exception {
- Configuration conf = new Configuration();
- String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
- if (otherArgs.length != 2) {
- System.err.println("Usage: wordcount ");
- System.exit(2);
- }
- Job job = new Job(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);
- FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
- FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
- System.exit(job.waitForCompletion(true) ? 0 : 1);
- }
- }
阅读(6016) | 评论(0) | 转发(1) |