WordCount On Hadoop怎么实现

这篇文章主要介绍“WordCount On Hadoop怎么实现”，在日常操作中，相信很多人在WordCount On Hadoop怎么实现问题上存在疑惑，小编查阅了各式资料，整理出简单好用的操作方法，希望对大家解答”WordCount On Hadoop怎么实现”的疑惑有所帮助！接下来，请跟着小编一起来学习吧！

官方例子：

WordCount2.java

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.StringTokenizer;

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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Counter;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.StringUtils;

public class WordCount2 {
    public static class TokenizerMapper extends
            Mapper<Object, Text, Text, IntWritable> {
        static enum CountersEnum {
            INPUT_WORDS
        }
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        private boolean caseSensitive;
        private Set<String> patternsToSkip = new HashSet<String>();
        private Configuration conf;
        private BufferedReader fis;
        @Override
        public void setup(Context context) throws IOException,
                InterruptedException {
            conf = context.getConfiguration();
            caseSensitive = conf.getBoolean("wordcount.case.sensitive", true);
            if (conf.getBoolean("wordcount.skip.patterns", false)) {//官方例子为true，若无配置文件将报错，改为false正常。参见：https://issues.apache.org/jira/browse/MAPREDUCE-6038
                URI[] patternsURIs = Job.getInstance(conf).getCacheFiles();
                for (URI patternsURI : patternsURIs) {
                    Path patternsPath = new Path(patternsURI.getPath());
                    String patternsFileName = patternsPath.getName().toString();
                    parseSkipFile(patternsFileName);
                }
            }
        }
        private void parseSkipFile(String fileName) {
            try {
                fis = new BufferedReader(new FileReader(fileName));
                String pattern = null;
                while ((pattern = fis.readLine()) != null) {
                    patternsToSkip.add(pattern);
                }
            } catch (IOException ioe) {
                System.err
                        .println("Caught exception while parsing the cached file '"
                                + StringUtils.stringifyException(ioe));
            }
        }
        @Override
        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = (caseSensitive) ? value.toString() : value.toString()
                    .toLowerCase();
            for (String pattern : patternsToSkip) {
                line = line.replaceAll(pattern, "");
            }
            StringTokenizer itr = new StringTokenizer(line);
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
                Counter counter = context.getCounter(
                        CountersEnum.class.getName(),
                        CountersEnum.INPUT_WORDS.toString());
                counter.increment(1);
            }
        }
    }
    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();
        GenericOptionsParser optionParser = new GenericOptionsParser(conf, args);
        String[] remainingArgs = optionParser.getRemainingArgs();
        if (!(remainingArgs.length != 2 || remainingArgs.length != 4)) {
            System.err
                    .println("Usage: wordcount <in> <out> [-skip skipPatternFile]");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount2.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        List<String> otherArgs = new ArrayList<String>();
        for (int i = 0; i < remainingArgs.length; ++i) {
            if ("-skip".equals(remainingArgs[i])) {
                job.addCacheFile(new Path(remainingArgs[++i]).toUri());
                job.getConfiguration().setBoolean("wordcount.skip.patterns",
                        true);
            } else {
                otherArgs.add(remainingArgs[i]);
            }
        }
        FileInputFormat.addInputPath(job, new Path(otherArgs.get(0)));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(1)));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

cd /data/program
javac -classpath /home/hadoop/hadoop-2.7.1/share/hadoop/common/hadoop-common-2.7.1.jar:/home/hadoop/hadoop-2.7.1/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.7.1.jar:/home/hadoop/hadoop-2.7.1/share/hadoop/common/lib/commons-cli-1.2.jar WordCount2.java
jar cf wc.jar WordCount*.class
cd /home/hadoop/hadoop-2.7.1/
bin/hadoop jar wc.jar WordCount2 /program/input /program/output

到此，关于“WordCount On Hadoop怎么实现”的学习就结束了，希望能够解决大家的疑惑。理论与实践的搭配能更好的帮助大家学习，快去试试吧！若想继续学习更多相关知识，请继续关注亿速云网站，小编会继续努力为大家带来更多实用的文章！