欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

hadoop平台运行WordCount程序

程序员文章站 2022-06-14 15:31:58
...

1. 经典的WordCound程序(WordCount.java)

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool {

    public static class MapClass extends MapReduceBase implements
            Mapper<LongWritable, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = value.toString();
            StringTokenizer itr = new StringTokenizer(line);
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                output.collect(word, one);
            }
        }
    }

    /**
     * A reducer class that just emits the sum of the input values.
     */
    public static class Reduce extends MapReduceBase implements
            Reducer<Text, IntWritable, Text, IntWritable> {

        public void reduce(Text key, Iterator<IntWritable> values,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }

    static int printUsage() {
        System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    /**
     * The main driver for word count map/reduce program. Invoke this method to
     * submit the map/reduce job.
     *
     * @throws IOException
     *             When there is communication problems with the job tracker.
     */
    public int run(String[] args) throws Exception {
        JobConf conf = new JobConf(getConf(), WordCount.class);
        conf.setJobName("wordcount");

        // the keys are words (strings)
        conf.setOutputKeyClass(Text.class);
        // the values are counts (ints)
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(MapClass.class);
        conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        List<String> other_args = new ArrayList<String>();
        for (int i = 0; i < args.length; ++i) {
            try {
                if ("-m".equals(args[i])) {
                    conf.setNumMapTasks(Integer.parseInt(args[++i]));
                } else if ("-r".equals(args[i])) {
                    conf.setNumReduceTasks(Integer.parseInt(args[++i]));
                } else {
                    other_args.add(args[i]);
                }
            } catch (NumberFormatException except) {
                System.out.println("ERROR: Integer expected instead of "
                        + args[i]);
                return printUsage();
            } catch (ArrayIndexOutOfBoundsException except) {
                System.out.println("ERROR: Required parameter missing from "
                        + args[i - 1]);
                return printUsage();
            }
        }

        // Make sure there are exactly 2 parameters left.
        if (other_args.size() != 2) {
            System.out.println("ERROR: Wrong number of parameters: "
                    + other_args.size() + " instead of 2.");
            return printUsage();
        }
        FileInputFormat.setInputPaths(conf, other_args.get(0));
        FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

        JobClient.runJob(conf);
        return 0;
    }

    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new WordCount(), args);
        System.exit(res);
    }

}



2. 保证hadoop集群是配置好了的,单机的也好。新建一个目录,比如 /home/admin/WordCount编译WordCount.java程序。

javac -classpath /home/admin/hadoop/hadoop-0.19.1-core.jar WordCount.java -d /home/admin/WordCount

3. 编译完后在/home/admin/WordCount目录会发现三个class文件 WordCount.class,WordCount$Map.class,WordCount$Reduce.class。
  cd 进入 /home/admin/WordCount目录,然后执行:

jar cvf WordCount.jar*.class

  就会生成 WordCount.jar 文件。

  4. 构造一些输入数据
  input1.txt和input2.txt的文件里面是一些单词。如下:

[[email protected] WordCount]$ cat input1.txt
Hello, i love china
are you ok
?
[[email protected] WordCount]$ cat input2.txt
hello, i love word
You are ok

  在hadoop上新建目录,和put程序运行所需要的输入文件:

hadoop fs-mkdir/tmp/input
hadoop fs
-mkdir/tmp/output
hadoop fs
-put input1.txt/tmp/input/
hadoop fs
-put input2.txt/tmp/input/

  5. 运行程序,会显示job运行时的一些信息。

hadoop平台运行WordCount程序
[[email protected] WordCount]$ hadoop jar WordCount.jar WordCount/tmp/input/tmp/output
10/09/1622:49:43WARN mapred.JobClient: Use GenericOptionsParserforparsing the arguments. Applications should implement Toolforthe same.
10/09/1622:49:43INFO mapred.FileInputFormat: Total input paths to process :2
10/09/1622:49:43INFO mapred.JobClient: Running job: job_201008171228_76165
10/09/1622:49:44INFO mapred.JobClient: map0%reduce0%
10/09/1622:49:47INFO mapred.JobClient: map100%reduce0%
10/09/1622:49:54INFO mapred.JobClient: map100%reduce100%
10/09/1622:49:55INFO mapred.JobClient: Job complete: job_201008171228_76165
10/09/1622:49:55INFO mapred.JobClient: Counters:16
10/09/1622:49:55INFO mapred.JobClient: File Systems
10/09/1622:49:55INFO mapred.JobClient: HDFS bytes read=62
10/09/1622:49:55INFO mapred.JobClient: HDFS bytes written=73
10/09/1622:49:55INFO mapred.JobClient: Local bytes read=152
10/09/1622:49:55INFO mapred.JobClient: Local bytes written=366
10/09/1622:49:55INFO mapred.JobClient: Job Counters
10/09/1622:49:55INFO mapred.JobClient: Launched reduce tasks=1
10/09/1622:49:55INFO mapred.JobClient: Rack-local map tasks=2
10/09/1622:49:55INFO mapred.JobClient: Launched map tasks=2
10/09/1622:49:55INFO mapred.JobClient: Map-Reduce Framework
10/09/1622:49:55INFO mapred.JobClient: Reduce input groups=11
10/09/1622:49:55INFO mapred.JobClient: Combine output records=14
10/09/1622:49:55INFO mapred.JobClient: Map input records=4
10/09/1622:49:55INFO mapred.JobClient: Reduce output records=11
10/09/1622:49:55INFO mapred.JobClient: Map output bytes=118
10/09/1622:49:55INFO mapred.JobClient: Map input bytes=62
10/09/1622:49:55INFO mapred.JobClient: Combine input records=14
10/09/1622:49:55INFO mapred.JobClient: Map output records=14
10/09/1622:49:55INFO mapred.JobClient: Reduce input records=14
hadoop平台运行WordCount程序

  6. 查看运行结果

hadoop平台运行WordCount程序
[[email protected] WordCount]$ hadoop fs-ls/tmp/output/
Found
2items
drwxr
-x----admin admin02010-09-1622:43/tmp/output/_logs
-rw-r-----1admin admin1022010-09-1622:44/tmp/output/part-00000
[[email protected] WordCount]$ hadoop fs
-cat/tmp/output/part-00000
Hello,
1
You
1
are
2
china
1
hello,
1
i
2
love
2
ok
1
ok
?1
word
1
you
1
hadoop平台运行WordCount程序

其中可能出现的问题

1:java.io.FileNotFoundException

这个异常是因为目录创建上有问题,于是重新检查了下目录,发现自己弄成/opt/hadoop/tmp/inout。而是/tmp/input

2:org.apache.hadoop.mapred.FileAlreadyExistsException

这个异常主要是因为上一个导致的,因为hadoop 由于进行的是耗费资源的计算,生产的结果默认是不能被覆盖的,因此中间结果输出目录一定不能存在,否则出现这个错误。

于是就执行命令删除output文件 /opt/hadoop/bin/hadoop fs -rmr /tmp/output


3:ERROR namenode.NameNode: java.io.IOException: Cannot create directory /usr/local/hadoop-datastore/hadoop-hadoop/dfs/name/current

是因为hadoop-database 文件夹没有获取权限