MapReduce之WordCount程序详解及常见错误汇总

1
2
3
4
5
6
7
8
log4j.rootLogger=DEBUG, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

1
2
HADOOP_HOME/sbin/start-dfs.sh
HADOOP_HOME/sbin/start-yarn.sh

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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
package hadoop.mr;

import java.io.IOException;
import java.net.URI;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount {

	public static class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
		private final static IntWritable ONE = new IntWritable(1);
		private Text word = new Text();
		 
		/**
		 * map程序，进行切割转换
		 */
		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
				throws IOException, InterruptedException {
			
			// 1.解析value为token，默认会按照空格进行分割
			StringTokenizer token = new StringTokenizer(value.toString());
			while(token.hasMoreTokens()){
				// 2.将分割后的字符放入Word
				word.set(token.nextToken());
				
				// 3.输出k-v格式	类似(hadoop,1)
				context.write(word, ONE);
			}
		}
	}
	
	public static class WCReduce extends Reducer<Text, IntWritable, Text, IntWritable>{
		private IntWritable result = new IntWritable();
		
		/**
		 * reduce程序，对map的结果进行合并
		 */
		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,
				Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
			
			// 1.计算总和
			int sum = 0;
			for (IntWritable intWritable : values) {
				sum += intWritable.get();
			}
			
			result.set(sum);
			// 2.输出结果
			context.write(key, result);
		}
	}
	
	private static String INPUT_PATH = "/user/hadoop/mapreduce/input/";
	private static String OUTPUT_PATH = "/user/hadoop/mapreduce/output/";
	private static String HDFS_URI = "hdfs://hadoop:9000";// 对应于core-site.xml中的FS.default
	
	public static void main(String[] args) {
		
		try {
			// 1.如果已经有output_path，则先进行删除
			deleteOutputFile(OUTPUT_PATH);
			
			// 2.创建job，设置基本属性
			Job job = Job.getInstance();
			job.setJarByClass(WordCount.class);
			job.setJobName("wordcount");
			
			// 3.设置Mapper、Reducer
			job.setMapperClass(WCMapper.class);
			job.setReducerClass(WCReduce.class);
			
			job.setOutputKeyClass(Text.class);
			job.setOutputValueClass(IntWritable.class);
			
			// 4.设置输入路径和输出路径
			FileInputFormat.addInputPath(job, new Path(INPUT_PATH));
			FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH));
			
			// 5.执行，执行完成后退出程序
			System.exit(job.waitForCompletion(true) ? 0 : 1);
		} catch (IOException e) {
			e.printStackTrace();
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	
	static void deleteOutputFile(String path) throws Exception{
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(new URI(HDFS_URI),conf,"hxw");
        if(fs.exists(new Path(path))){
            fs.delete(new Path(path),true);
        }
    }
}

1
org.apache.hadoop.security.AccessControlException: Permission denied: user=root, access=WRITE, inode="":nutch:supergroup:rwxr-xr-x

1
2
3
4
	<property>
		<name>dfs.permissions</name>
		<value>false</value>
	</property>

1
2
DEBUG [org.apache.hadoop.ipc.Client] - closing ipc connection to 0.0.0.0/0.0.0.0:8032: Connection refused: no further information
java.net.ConnectException: Connection refused: no further information

1
2
yarn.resourcemanager.hostname	0.0.0.0	The hostname of the RM.
yarn.resourcemanager.address	${yarn.resourcemanager.hostname}:8032

1
2
3
4
<property>
    <name>yarn.resourcemanager.hostname</name>
    <value>hadoop</value>
</property>

1
2
3
4
5
6
Exception message: /bin/bash: line 0: fg: no job control
Stack trace: ExitCodeException exitCode=1: /bin/bash: line 0: fg: no job control

	at org.apache.hadoop.util.Shell.runCommand(Shell.java:545)
	at org.apache.hadoop.util.Shell.run(Shell.java:456)
    ...

1
2
3
4
	<property>
		<name>mapreduce.app-submission.cross-platform</name>
		<value>true</value>
	</property>

1
2
3
4
Error: java.lang.RuntimeException: java.lang.ClassNotFoundException: Class hadoop.mr.WordCount$WCMapper not found
	at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2195)
	at org.apache.hadoop.mapreduce.task.JobContextImpl.getMapperClass(JobContextImpl.java:186)
...

1
2
3
4
<property>
    <name>mapred.jar</name>
    <value>C:/Users/lucky/Desktop/wc.jar</value>
</property>