1. WordCount在Hadoop分布式集群中的实现

1
2
 第一行：word word

1
2
3
 word
 word

1
2
 < word, <1,1> >

1
2
输出：word，2

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
public class WordCount {

  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, IntWritable>{
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
      
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
  
  public static class IntSumReducer 
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
      System.err.println("Usage: wordcount <in> [<in>...] <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
import random
import string

f1 = open('1.txt', 'x')
for x in range(10000):
    string0 = str(''.join(random.sample(
        ['z', 'n', 'm', 'l', 'k', 'j', 'i', 'h', 'g', 'f', 'e', 'd', 'c', 'b', 'a'], 4)))
    f1.write(string0)
    if x % random.randint(1, 50) == 0:
        f1.write(' ')
        continue
    if x != 9999:
        f1.write('n')
f1.close()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
$ hadoop fs -put /home/hadoop1/data/input/1.txt hdfs://192.168.239.100:9000/input
#或者
$ hadoop fs -put /home/hadoop1/data/input/1.txt /input
#查看上传结果
$ hadoop fs -ls /input

#另：hdfs常用命令
hdfs dfs -copyFromLocal #local/data /hdfs/data：将本地文件上传到 hdfs 上（原路径只能是一个文件）
hdfs dfs -put /tmp/ /hdfs/ #和 copyFromLocal 区别是，put 原路径可以是文件夹等
hadoop fs -ls / #查看根目录文件
hadoop fs -ls /tmp/data #查看/tmp/data目录
hadoop fs -cat /tmp/a.txt #查看 a.txt，与 -text 一样
hadoop fs -mkdir dir #创建目录dir
hadoop fs -rmr dir：#删除目录dir

1
2
3
4
5
6
7
8
9
10
11
#执行自己打包的demo
$ hadoop jar WordCount_1-1.0-SNAPSHOT.jar com/hadoop1/wordcount.WdDriver /input/1.txt /out
#在此之后，自己写的代码都需要如此执行，该执行方式的说明：
#com/hadoop1/wordcount.WdDriver 对应的类是WdDriver，所在包:com.hadoop1.wordcount
$ hadoop jar <jar文件>  <注明主类> <hdfs输入文件>  <hdfs输出文件>

#执行官方源码中的WordCount
$ hadoop jar /opt/module/hadoop-2.7.7/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.7.jar wordcount /input/1.txt /out

#两种方式运行结果相同 注意在运行时，如果输出的文件夹已经存在，就会报错，在再次运行之前最好把相关的文件夹给删掉

1
2
3
$ hadoop fs -ls /out
$ hadoop fs -cat /out/part-r-00000