倒排索引案例(多job串联)
- 需求
有大量的文本(文档、网页),需要建立搜索索引
数据输入
a.txt
liujh pingping
liujh ss
liujh ss
b.txt
liujh pingping
liujh pingping
pingping ss
c.txt
liujh ss
liujh pingping
期望输出数据
liujh c.txt-->2 b.txt-->2 a.txt-->3
pingping c.txt-->1 b.txt-->3 a.txt-->1
ss c.txt-->1 b.txt-->1 a.txt-->2
- 需求分析
- 第一次处理
第一次处理,编写OneIndexMapper类
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
public class OneIndexMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
String name;
Text k = new Text();
IntWritable v = new IntWritable();
@Override
protected void setup(Context context)throws IOException, InterruptedException {
// 获取文件名称
FileSplit split = (FileSplit) context.getInputSplit();
name = split.getPath().getName();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取1行
String line = value.toString();
// 2 切割
String[] fields = line.split(" ");
for (String word : fields) {
// 3 拼接
k.set(word+"--"+name);
v.set(1);
// 4 写出
context.write(k, v);
}
}
}
第一次处理,编写OneIndexReducer类
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class OneIndexReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
IntWritable v = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
int sum = 0;
// 1 累加求和
for(IntWritable value: values){
sum +=value.get();
}
v.set(sum);
// 2 写出
context.write(key, v);
}
}
第一次处理,编写OneIndexDriver类
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class OneIndexDriver {
public static void main(String[] args) throws Exception {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] { "e:/input/inputoneindex", "e:/output5" };
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(OneIndexDriver.class);
job.setMapperClass(OneIndexMapper.class);
job.setReducerClass(OneIndexReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
查看第一次输出结果
liujh--a.txt 3
liujh--b.txt 2
liujh--c.txt 2
pingping--a.txt 1
pingping--b.txt 3
pingping--c.txt 1
ss--a.txt 2
ss--b.txt 1
ss--c.txt 1
- 第二次处理
第二次处理,编写TwoIndexMapper类
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class TwoIndexMapper extends Mapper<LongWritable, Text, Text, Text>{
Text k = new Text();
Text v = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取1行数据
String line = value.toString();
// 2用“--”切割
String[] fields = line.split("--");
k.set(fields[0]);
v.set(fields[1]);
// 3 输出数据
context.write(k, v);
}
}
第二次处理,编写TwoIndexReducer类
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class TwoIndexReducer extends Reducer<Text, Text, Text, Text> {
Text v = new Text();
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
// liujh a.txt 3
// liujh b.txt 2
// liujh c.txt 2
// liujh c.txt-->2 b.txt-->2 a.txt-->3
StringBuilder sb = new StringBuilder();
// 1 拼接
for (Text value : values) {
sb.append(value.toString().replace("\t", "-->") + "\t");
}
v.set(sb.toString());
// 2 写出
context.write(key, v);
}
}
第二次处理,编写TwoIndexDriver类
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TwoIndexDriver {
public static void main(String[] args) throws Exception {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] { "e:/input/inputtwoindex", "e:/output6" };
Configuration config = new Configuration();
Job job = Job.getInstance(config);
job.setJarByClass(TwoIndexDriver.class);
job.setMapperClass(TwoIndexMapper.class);
job.setReducerClass(TwoIndexReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean result = job.waitForCompletion(true);
System.exit(result?0:1);
}
}
第二次查看最终结果
liujh c.txt-->2 b.txt-->2 a.txt-->3
pingping c.txt-->1 b.txt-->3 a.txt-->1
ss c.txt-->1 b.txt-->1 a.txt-->2
简书:https://www.jianshu.com/u/0278602aea1d
CSDN:https://blog.csdn.net/u012387141