MapReduce实战之倒排索引案例(多job串联)
原创
©著作权归作者所有:来自51CTO博客作者年轻即出发的原创作品,请联系作者获取转载授权,否则将追究法律责任
0)需求:有大量的文本(文档、网页),需要建立搜索索引
输出数据:
a:
atguigu pingping
atguigu ss
atguigu ss
b:
atguigu pingping
atguigu pingping
pingping ss
c:
atguigu ss
atguigu pingping
(1)第一次预期输出结果
atguigu--a.txt 3 atguigu--b.txt 2 atguigu--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 |
(2)第二次预期输出结果
atguigu 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 |
1)第一次处理
(1)第一次处理,编写OneIndexMapper
package com.atguigu.mapreduce.index; 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); } } } |
(2)第一次处理,编写OneIndexReducer
package com.atguigu.mapreduce.index; 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>{ @Override protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int count = 0; // 1 累加求和 for(IntWritable value: values){ count +=value.get(); } // 2 写出 context.write(key, new IntWritable(count)); } } |
(3)第一次处理,编写OneIndexDriver
package com.atguigu.mapreduce.index; 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 { 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); } } |
(4)查看第一次输出结果
atguigu--a.txt 3 atguigu--b.txt 2 atguigu--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 |
2)第二次处理
(1)第二次处理,编写TwoIndexMapper
package com.atguigu.mapreduce.index; 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); } } |
(2)第二次处理,编写TwoIndexReducer
package com.atguigu.mapreduce.index; 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> { @Override protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException { // atguigu a.txt 3 // atguigu b.txt 2 // atguigu c.txt 2 // atguigu 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"); } // 2 写出 context.write(key, new Text(sb.toString())); } } |
(3)第二次处理,编写TwoIndexDriver
package com.atguigu.mapreduce.index; 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 { 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); } } |
(4)第二次查看最终结果
atguigu 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 |