mapreduce練習11 倒排索引

1.輸入資料

gjh@gjh:~/date$ cat index1.txt 
MapReduce is sample gjh
gjh@gjh:~/date$ cat index2.txt 
MapReduce is powerful is sample
gjh@gjh:~/date$ cat index3.txt 
Hello MapReduce hello world gjh

2.輸出

3.程式碼

import java.io.IOException;
import java.net.URI;
import java.util.StringTokenizer;
 
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 
public class InversedIndex {
	
	/**
	 * 將輸入檔案拆分，
	 * 將關鍵字和關鍵字所在的檔名作為map的key輸出，
	 * 該組合的頻率作為value輸出
	 * */
	
	public static class InversedIndexMapper extends Mapper<Object, Text, Text, Text> {
		
		private Text outKey = new Text();
		private Text outVal = new Text();
		
		@Override
		public void map (Object key,Text value,Context context) {
			StringTokenizer tokens = new StringTokenizer(value.toString());
			FileSplit split = (FileSplit) context.getInputSplit();
			while(tokens.hasMoreTokens()) {
				String token = tokens.nextToken();
				try {
					outKey.set(token + ":" + split.getPath());
					outVal.set("1");
					context.write(outKey, outVal);
				} catch (IOException e) {
					e.printStackTrace();
				} catch (InterruptedException e) {
					e.printStackTrace();
				}
			}
		}
	}
	
	/**
	 * map的輸出進入到combiner階段，此時來自同一個檔案的相同關鍵字進行一次reduce處理，
	 * 將輸入的key拆分成關鍵字和檔名，然後關鍵字作為輸出key，
	 * 將檔名與詞頻拼接，作為輸出value，
	 * 這樣就形成了一個關鍵字，在某一檔案中出現的頻率的 key--value 對
	 * */
	public static class InversedIndexCombiner extends Reducer<Text, Text, Text, Text> {
		
		private Text outKey = new Text();
		private Text outVal = new Text();
		
		@Override
		public void reduce(Text key,Iterable<Text> values,Context context) {
			String[] keys = key.toString().split(":");
			int sum = 0;
			for(Text val : values) {
				sum += Integer.parseInt(val.toString());
			}
			try {
				outKey.set(keys[0]);
				int index = keys[keys.length-1].lastIndexOf('/');
				outVal.set(keys[keys.length-1].substring(index+1) + ":" + sum);
				context.write(outKey, outVal);
			} catch (IOException e) {
				e.printStackTrace();
			} catch (InterruptedException e) {
				e.printStackTrace();
			}
		}
		
	}
	
	/**
	 * 將combiner後的key value對進行reduce，
	 * 由於combiner之後，一個關鍵字可能對應了多個value，故需要將這些value進行合併輸出
	 * */
	
	public static class InversedIndexReducer extends Reducer<Text, Text, Text, Text> {
		
		@Override
		public void reduce (Text key,Iterable<Text> values,Context context) {
			StringBuffer sb = new StringBuffer();
			for(Text text : values) {
				sb.append(text.toString() + " ,");
			}
			try {
				context.write(key, new Text(sb.toString()));
			} catch (IOException e) {
				e.printStackTrace();
			} catch (InterruptedException e) {
				e.printStackTrace();
			}
		}
	}
	
	public static void main(String[] args) throws Exception, InterruptedException, ClassNotFoundException {
		// 1 獲取配置資訊，或者job物件例項
		String int_path = "hdfs://gjh:9000/1702240034/index";
		String out_path = "hdfs://gjh:9000/1702240034/output_index";
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(new URI(int_path), conf);
		if (fs.exists(new Path(out_path))) {
			fs.delete(new Path(out_path), true);
		}
		Job job = new Job(conf,"index inversed");
		
		job.setJarByClass(InversedIndex.class);
		job.setMapperClass(InversedIndexMapper.class);
		job.setCombinerClass(InversedIndexCombiner.class);
		job.setReducerClass(InversedIndexReducer.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
 
		job.setNumReduceTasks(3);
		
		FileInputFormat.addInputPath(job, new Path(int_path));
		FileOutputFormat.setOutputPath(job, new Path(out_path));
		
		System.exit(job.waitForCompletion(true)?0:1);
		
	}
 
}