倒排索引

倒排索引流程图：（有三个文件，里边有三句话，分别统计每个单词在每个文件中出现的次数）
倒排索引数据流动过程分析图：
代码实现：
 1 package com.zyx;
 2 
 3 import org.apache.commons.lang.StringUtils;
 4 import org.apache.hadoop.conf.Configuration;
 5 import org.apache.hadoop.fs.Path;
 6 import org.apache.hadoop.io.IntWritable;
 7 import org.apache.hadoop.io.LongWritable;
 8 import org.apache.hadoop.io.Text;
 9 import org.apache.hadoop.mapreduce.Job;
10 import org.apache.hadoop.mapreduce.Mapper;
11 import org.apache.hadoop.mapreduce.Reducer;
12 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
13 import org.apache.hadoop.mapreduce.lib.input.FileSplit;
14 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
15 import java.io.IOException;
16 public class App
17 {
18     public static class MyMap extends Mapper<LongWritable,Text,Text,IntWritable>{
19         @Override
20         protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
21             String line = value.toString();//按行读取文件
22             String[] fields = StringUtils.split(line," ");//按空格进行分片
23             FileSplit fileSplit = (FileSplit) context.getInputSplit();
24             String fileName = fileSplit.getPath().getName();//获取文件名
25             for(String field:fields)
26             {
27                 context.write(new Text(field+"-->" + fileName),new IntWritable(1));
28             }
29         }
30     }
31     public static class MyReduce extends Reducer<Text,IntWritable,Text,IntWritable>{
32         @Override
33         protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
34             int sum = 0;
35             for(IntWritable value:values)
36             {
37                 sum+=value.get();//统计每个key值对应的value值
38             }
39             context.write(key,new IntWritable(sum));
40         }
41     }
42     public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
43         Configuration conf = new Configuration();
44         conf.set("fs.defaultFS","hdfs://192.168.56.112:9000");
45         Job job  = Job.getInstance(conf);
46         job.setJarByClass(App.class);
47         job.setMapperClass(MyMap.class);
48         job.setMapOutputKeyClass(Text.class);
49         job.setMapOutputValueClass(IntWritable.class);
50         job.setReducerClass(MyReduce.class);
51         job.setMapOutputKeyClass(Text.class);
52         job.setMapOutputValueClass(IntWritable.class);
53         FileInputFormat.addInputPath(job,new Path("/idea/idea1/a.txt"));//读取HDFS上idea目录下的a.txt文件
54         FileInputFormat.addInputPath(job,new Path("/idea/idea1/b.txt"));
55         FileInputFormat.addInputPath(job,new Path("/idea/idea1/c.txt"));
56         FileOutputFormat.setOutputPath(job,new Path("/idea/idea2/out1.txt"));//将结果保存在idea目录下的out1目录下
57         job.waitForCompletion(true);
58     }
59 
60 }