Hadoop MapReduce WordCount v2.0结合个人理解进行注释

这里没有进行具体的讲解，只是在代码中添加了一些根据个人理解的注释，方便以后复习，后面可以会继续完善。
具体说明以及使用方法请参考官方文档：http://hadoop.apache.org/docs/r3.0.0-alpha1/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html#Job_Input

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 WordCount3 {

    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);

            /*
             * 官方源码是"conf.getBoolean("wordcount.skip.patterns", true)"
             * 这里我改成了"conf.getBoolean("wordcount.skip.patterns", false)"
             */
            if (conf.getBoolean("wordcount.skip.patterns", false)) {
                URI[] patternsURIs = Job.getInstance(conf).getCacheFiles();
                for (URI patternsURI : patternsURIs) {
                    Path patternsPath = new Path(patternsURI.getPath());
                    String patternsFileName = patternsPath.getName().toString();
                    parseSkipFile(patternsFileName);
                }
            }
        }

        /**
         * 读取本地文件，并将内容（字符）保存到patternsToSkip成员变量中去。
         * 
         * @param fileName
         *            : the file which save the chars to ignore.
         */
        private void parseSkipFile(String fileName) {
            try {
                fis = new BufferedReader(new FileReader(fileName));
                /*
                 * 此方法是在本地上找文件而无法在hdfs上面读取文件，否则我们需要替换此方法，
                 * 又或许我们通过-files命令指定本地的文件，然后就不用手动put到hdfs上面了。
                 */

                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();
            // 原来是要代码来实现大小写忽略！
            for (String pattern : patternsToSkip) {
                line = line.replaceAll(pattern, "");
                // 替换所有的要求被忽略的字符为空字符
            }
            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);
        // 这会把args中的Generic Options加入到Configuration中

        String[] remainingArgs = optionParser.getRemainingArgs();
        // 返回不属于Generic Options的参数项

        if (!(remainingArgs.length != 2 || remainingArgs.length != 4)) {
            // 这里可能有错，因为表达式的结果肯定为真.
            System.err.println("Usage: wordcount <in> <out> [-skip skipPatternFile]");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount3.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) {
            // 可能会有多个-skip选项，即多个文件包含忽略字符
            if ("-skip".equals(remainingArgs[i])) {
                job.addCacheFile(new Path(remainingArgs[++i]).toUri());
                // 添加到CacheFile，不作为Map-Reduce的输入文件。

                job.getConfiguration().setBoolean("wordcount.skip.patterns", true);
                // 设置一个新的属性到Configuration，到时候Map-Reduce处理的时候就可以获取相应的属性，属性名自己取。

            } 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);
    }
}