倒排索引實現

簡介：參考文章：

輸入輸出：

輸入：

a.txt:

hadoop hello world

hello test

test hadoop

b.txt:

test world

hello world test

hadoop

輸出：

hadoop hdfs://h2/apps/ca/yanh/data/invertedIndex/a.txt-->2       hdfs://h2/apps/ca/yanh/data/invertedIndex/b.txt-->1 
hello hdfs://h2/apps/ca/yanh/data/invertedIndex/b.txt-->1           hdfs://h2/apps/ca/yanh/data/invertedIndex/a.txt-->2 
test hdfs://h2/apps/ca/yanh/data/invertedIndex/a.txt-->2             hdfs://h2/apps/ca/yanh/data/invertedIndex/b.txt-->2 
world hdfs://h2/apps/ca/yanh/data/invertedIndex/b.txt-->2          hdfs://h2/apps/ca/yanh/data/invertedIndex/a.txt-->1

實現代碼：

<span style="font-size:12px;">import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

import java.io.IOException;

/**
 * Created by 浩 on 2015/4/20.
 */
public class InvertedIndex {

    public static void main(String[] args)throws IOException,InterruptedException, ClassNotFoundException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(InvertedIndex.class);

        job.setMapperClass(InvertedMapper.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));

        job.setCombinerClass(InvertedCombiner.class);

        job.setReducerClass(InvertedReducer.class);
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        System.exit(job.waitForCompletion(true)? 0: 1);
    }
}

class InvertedMapper extends Mapper<LongWritable, Text, Text, Text> {
    private Text k = new Text();
    private Text v = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");
        FileSplit inputSplit = (FileSplit) context.getInputSplit();
        Path path = inputSplit.getPath();

        for (String word: words) {
            k.set(word + "-->" + path.toString());
            v.set("1");
            context.write(k, v);
        }
    }
}

class InvertedCombiner extends Reducer<Text, Text, Text, Text> {
    private Text k = new Text();
    private Text v = new Text();

    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        String[] fields = key.toString().split("-->");
        int sum = 0;
        for(Text val: values) {
            sum += Integer.parseInt(val.toString());
        }

        k.set(fields[0]);
        v.set(fields[1] + "-->" + sum);

        context.write(k, v);
    }
}

class InvertedReducer extends Reducer<Text, Text, Text, Text> {
    private Text k = new Text();
    private Text v = new Text();

    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context)throws IOException, InterruptedException {

        String str = "";
        for(Text val: values) {
            str += val.toString() + "\t";
        }

        k.set(key);
        v.set(str);
        context.write(k, v);
    }
}
</span>