Hadoop1.x代码求海量数据最大值

 1 /**
 2   * 数据格式文件为：
 3   * 4
 4   * 7
 5   * 5
 6   * 即每个数字占一行
 7   */
 8 import java.io.IOException;
 9 import java.net.URI;
10 
11 import org.apache.hadoop.conf.Configuration;
12 import org.apache.hadoop.fs.FileSystem;
13 import org.apache.hadoop.fs.Path;
14 import org.apache.hadoop.io.LongWritable;
15 import org.apache.hadoop.io.NullWritable;
16 import org.apache.hadoop.io.Text;
17 import org.apache.hadoop.mapreduce.Job;
18 import org.apache.hadoop.mapreduce.Mapper;
19 import org.apache.hadoop.mapreduce.Reducer;
20 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
21 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
22 
23 
24 public class TopKApp {
25     
26     static final String INPUT = "hdfs://192.168.56.100:9000/input";
27     static final String OUT = "hdfs://192.168.56.100:9000/out";
28     
29     static final Path INPUT_PATH = new Path(INPUT);
30     static final Path OUT_PATH = new Path(OUT);
31     
32     public static void main(String[] args) throws Exception{
33 
34         Configuration conf = new Configuration();
35         FileSystem fileSystem = FileSystem.get(new URI(OUT),conf);
36         if(fileSystem.exists(OUT_PATH)){
37             fileSystem.delete(OUT_PATH, true);
38         }
39         /**
40          * Map Reduce 天龙八步
41          */
42         Job job = new Job(conf,TopKApp.class.getSimpleName());
43         FileInputFormat.setInputPaths(job, INPUT_PATH);
44         job.setMapperClass(MyMapper.class);
45         job.setReducerClass(MyReducer.class);
46         job.setOutputKeyClass(LongWritable.class);
47         job.setOutputValueClass(NullWritable.class);
48         FileOutputFormat.setOutputPath(job, OUT_PATH);
49         job.waitForCompletion(true);
50     }
51     
52     static class MyMapper extends Mapper<LongWritable,Text,LongWritable,NullWritable>{
53         @Override
54         protected void map(
55                 LongWritable key,
56                 Text value,
57                 Mapper<LongWritable, Text, LongWritable, NullWritable>.Context context)
58                 throws IOException, InterruptedException {
59             context.write(new LongWritable(Long.parseLong(value.toString())), NullWritable.get());
60         }
61             
62     }
63     
64     
65     static class MyReducer extends Reducer<LongWritable,NullWritable,LongWritable,NullWritable>{
66         long max = Long.MIN_VALUE;
67         @Override
68         protected void reduce(
69                 LongWritable k2,
70                 Iterable<NullWritable> v2s,
71                 Reducer<LongWritable, NullWritable, LongWritable, NullWritable>.Context context)
72                 throws IOException, InterruptedException {
73             
74             long num = k2.get();
75             if(num > max){
76                 max = num;
77             }
78         }
79         
80         @Override
81         protected void cleanup(
82                 Reducer<LongWritable, NullWritable, LongWritable, NullWritable>.Context context)
83                 throws IOException, InterruptedException {
84             context.write(new LongWritable(max), NullWritable.get());
85         }
86     }
87

相关阅读:
scala :: , +:, :+ , ::: , ++ 的区别
 Scala 函数式编程思想
 Scala 关键字
 HDFS 的内存存储是什么？
LRU
高并发情况限流
 Java中List集合去除重复数据的方法
 MySQL支持的跨库事务
 死磕ConcurrentHashMap 1.8源码解析
 一致性Hash算法
原文地址：https://www.cnblogs.com/litaiqing/p/4538508.html