【甘道夫】官网MapReduce实例代码详细批注

引言

1.本文不描述MapReduce入门知识，这类知识网上很多，请自行查阅

2.本文的实例代码来自官网

http://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html

最后的WordCount v2.0，该代码相比源码中的org.apache.hadoop.examples.WordCount要复杂和完整，更适合作为MapReduce模板代码

3.本文的目的就是为开发MapReduce的同学提供一个详细注释了的模板，可以基于该模板做开发。

---

官网实例代码（略有改动）

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 {
    // 日志组名MapCounters，日志名INPUT_WORDS
    static enum MapCounters {
        INPUT_WORDS
    }
    static enum ReduceCounters {
        OUTPUT_WORDS
    }
    
    // static enum CountersEnum { INPUT_WORDS,OUTPUT_WORDS }
    // 日志组名CountersEnum，日志名INPUT_WORDS和OUTPUT_WORDS
    
    public static class TokenizerMapper extends
            Mapper
    
    
     
      {
        private final static IntWritable one = new IntWritable(1); // map输出的value
        private Text word = new Text(); // map输出的key
        private boolean caseSensitive; // 是否大小写敏感，从配置文件中读出赋值
        private Set
     
     
      
       patternsToSkip = new HashSet
      
      
       
       (); // 用来保存需过滤的关键词，从配置文件中读出赋值
        private Configuration conf;
        private BufferedReader fis; // 保存文件输入流
        /**
         * 整个setup就做了两件事： 1.读取配置文件中的wordcount.case.sensitive，赋值给caseSensitive变量
         * 2.读取配置文件中的wordcount.skip.patterns，如果为true，将CacheFiles的文件都加入过滤范围
         */
        @Override
        public void setup(Context context) throws IOException,
                InterruptedException {
            conf = context.getConfiguration();
            // getBoolean(String name, boolean defaultValue)
            // 获取name指定属性的值，如果属性没有指定，或者指定的值无效，就用defaultValue返回。
            // 属性可以在命令行中通过-Dpropretyname指定，例如 -Dwordcount.case.sensitive=true
            // 属性也可以在main函数中通过job.getConfiguration().setBoolean("wordcount.case.sensitive",
            // true)指定
            caseSensitive = conf.getBoolean("wordcount.case.sensitive", true); // 配置文件中的wordcount.case.sensitive功能是否打开
            // wordcount.skip.patterns属性的值取决于命令行参数是否有-skip，具体逻辑在main方法中
            if (conf.getBoolean("wordcount.skip.patterns", false)) { // 配置文件中的wordcount.skip.patterns功能是否打开
                URI[] patternsURIs = Job.getInstance(conf).getCacheFiles(); // getCacheFiles()方法可以取出缓存的本地化文件，本例中在main设置
                for (URI patternsURI : patternsURIs) { // 每一个patternsURI都代表一个文件
                    Path patternsPath = new Path(patternsURI.getPath());
                    String patternsFileName = patternsPath.getName().toString();
                    parseSkipFile(patternsFileName); // 将文件加入过滤范围，具体逻辑参见parseSkipFile(String
                                                        // fileName)
                }
            }
        }
        /**
         * 将指定文件的内容加入过滤范围
         * 
         * @param fileName
         */
        private void parseSkipFile(String fileName) {
            try {
                fis = new BufferedReader(new FileReader(fileName));
                String pattern = null;
                while ((pattern = fis.readLine()) != null) { // SkipFile的每一行都是一个需要过滤的pattern，例如\!
                    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 {
            // 这里的caseSensitive在setup()方法中赋值
            String line = (caseSensitive) ? value.toString() : value.toString()
                    .toLowerCase(); // 如果设置了大小写敏感，就保留原样，否则全转换成小写
            for (String pattern : patternsToSkip) { // 将数据中所有满足patternsToSkip的pattern都过滤掉
                line = line.replaceAll(pattern, "");
            }
            StringTokenizer itr = new StringTokenizer(line); // 将line以\t\n\r\f为分隔符进行分隔
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
                // getCounter(String groupName, String counterName)计数器
                // 枚举类型的名称即为组的名称，枚举类型的字段就是计数器名称
                Counter counter = context.getCounter(
                        MapCounters.class.getName(),
                        MapCounters.INPUT_WORDS.toString());
                counter.increment(1);
            }
        }
    }
    /**
     * Reducer没什么特别的升级特性
     * 
     * @author Administrator
     */
    public static class IntSumReducer extends
            Reducer
       
       
        
         {
        private IntWritable result = new IntWritable();
        public void reduce(Text key, Iterable
        
        
          values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); Counter counter = context.getCounter( ReduceCounters.class.getName(), ReduceCounters.OUTPUT_WORDS.toString()); counter.increment(1); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); GenericOptionsParser optionParser = new GenericOptionsParser(conf, args); /** * 命令行语法是：hadoop command [genericOptions] [application-specific * arguments] getRemainingArgs()取到的只是[application-specific arguments] * 比如：$ bin/hadoop jar wc.jar WordCount2 -Dwordcount.case.sensitive=true * /user/joe/wordcount/input /user/joe/wordcount/output -skip * /user/joe/wordcount/patterns.txt * getRemainingArgs()取到的是/user/joe/wordcount/input * /user/joe/wordcount/output -skip /user/joe/wordcount/patterns.txt */ String[] remainingArgs = optionParser.getRemainingArgs(); // remainingArgs.length == 2时，包括输入输出路径： ///user/joe/wordcount/input /user/joe/wordcount/output // remainingArgs.length == 4时，包括输入输出路径和跳过文件： ///user/joe/wordcount/input /user/joe/wordcount/output -skip /user/joe/wordcount/patterns.txt if (!(remainingArgs.length != 2 || remainingArgs.length != 4)) { System.err .println("Usage: wordcount 
          
          
            [-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 
           
             otherArgs = new ArrayList 
            
              (); // 除了 -skip 以外的其它参数 for (int i = 0; i < remainingArgs.length; ++i) { if ("-skip".equals(remainingArgs[i])) { job.addCacheFile(new Path(remainingArgs[++i]).toUri()); // 将 // -skip // 后面的参数，即skip模式文件的url，加入本地化缓存中 job.getConfiguration().setBoolean("wordcount.skip.patterns", true); // 这里设置的wordcount.skip.patterns属性，在mapper中使用 } else { otherArgs.add(remainingArgs[i]); // 将除了 -skip // 以外的其它参数加入otherArgs中 } } FileInputFormat.addInputPath(job, new Path(otherArgs.get(0))); // otherArgs的第一个参数是输入路径 FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(1))); // otherArgs的第二个参数是输出路径 System.exit(job.waitForCompletion(true) ? 0 : 1); } }