標籤:
1.把外掛程式hadoop-eclipse-plugin-2.6.2.jar拷貝到eclipse安裝目錄下的plugins中
2.重啟一下Eclipse
配製hadoop
3.進入map/reduce視圖模式
4.向hadoop分布式儲存系統中存入資料
5.串連hadoop
6.建立hadoop工程
7.建立類MyWordCount.java
package com.yc.hadoop;import java.io.IOException;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;public class MyWordCount { public static class MyWordCountMapper 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 { String[] words = value.toString().split("\\s"); for (String w : words) { word.set(w); context.write(word, one); } } } public static class MyWordCountReducer 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(); Job job = Job.getInstance(conf, "mywordcount"); job.setJarByClass(MyWordCount.class); job.setMapperClass(MyWordCountMapper.class); job.setCombinerClass(MyWordCountReducer.class); job.setReducerClass(MyWordCountReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
8.運行hadoop項目
window下eclipse配製hadoop外掛程式 (四)