wiki:waue/2010/0115-WordCountV2

Word Count V2

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.filecache.DistributedCache;
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.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.StringUtils;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

//WordCountV2
//說明: 
//  用於字數統計,並且增加略過大小寫辨識、符號篩除等功能
//
//測試方法:
//  將此程式運作在hadoop 0.20 平台上,執行:
//  ---------------------------
//  hadoop jar WordCountV2.jar -Dwordcount.case.sensitive=false \
//    <input> <output> -skip patterns/patterns.txt
//  ---------------------------
//
//注意:
//1.  在hdfs 上來源檔案的路徑為 你所指定的 <input>
//  請注意必須先放資料到此hdfs上的資料夾內,且此資料夾內只能放檔案,不可再放資料夾
//2.  運算完後,程式將執行結果放在hdfs 的輸出路徑為 你所指定的 <output>
//3.    請建立一個資料夾 pattern 並在裡面放置pattern.txt,內容如下(一行一個,前置提示符號\)
//      \.
//      \,
//      \!

@SuppressWarnings("deprecation")
public class WordCountV2 extends Configured implements Tool {

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

    static enum Counters {
      INPUT_WORDS
    }

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

    private boolean caseSensitive = true;
    private Set<String> patternsToSkip = new HashSet<String>();

    private long numRecords = 0;
    private String inputFile;

    public void configure(JobConf job) {
      caseSensitive = job.getBoolean("wordcount.case.sensitive", true);
      inputFile = job.get("map.input.file");

      if (job.getBoolean("wordcount.skip.patterns", false)) {
        Path[] patternsFiles = new Path[0];
        try {
          patternsFiles = DistributedCache.getLocalCacheFiles(job);
        } catch (IOException ioe) {
          System.err
              .println("Caught exception while getting cached files: "
                  + StringUtils.stringifyException(ioe));
        }
        for (Path patternsFile : patternsFiles) {
          parseSkipFile(patternsFile);
        }
      }
    }

    private void parseSkipFile(Path patternsFile) {
      try {
        BufferedReader fis = new BufferedReader(new FileReader(
            patternsFile.toString()));
        String pattern = null;
        while ((pattern = fis.readLine()) != null) {
          patternsToSkip.add(pattern);
        }
      } catch (IOException ioe) {
        System.err
            .println("Caught exception while parsing the cached file '"
                + patternsFile
                + "' : "
                + StringUtils.stringifyException(ioe));
      }
    }

    public void map(LongWritable key, Text value,
        OutputCollector<Text, IntWritable> output, Reporter reporter)
        throws IOException {
      String line = (caseSensitive) ? value.toString() : value.toString()
          .toLowerCase();

      for (String pattern : patternsToSkip) {
        line = line.replaceAll(pattern, "");
      }

      StringTokenizer tokenizer = new StringTokenizer(line);
      while (tokenizer.hasMoreTokens()) {
        word.set(tokenizer.nextToken());
        output.collect(word, one);
        reporter.incrCounter(Counters.INPUT_WORDS, 1);
      }

      if ((++numRecords % 100) == 0) {
        reporter.setStatus("Finished processing " + numRecords
            + " records " + "from the input file: " + inputFile);
      }
    }
  }

  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));
    }
  }

  public int run(String[] args) throws Exception {

    JobConf conf = new JobConf(getConf(), WordCount.class);
    conf.setJobName("wordcount");
    String[] otherArgs = new GenericOptionsParser(conf, args)
        .getRemainingArgs();
    if (otherArgs.length < 2) {
      System.out.println("WordCountV2 [-Dwordcount.case.sensitive=<false|true>] \\ ");
      System.out.println("            <inDir> <outDir> [-skip Pattern_file]");
      return 0;
    }
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

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

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    List<String> other_args = new ArrayList<String>();
    for (int i = 0; i < args.length; ++i) {
      if ("-skip".equals(args[i])) {
        DistributedCache
            .addCacheFile(new Path(args[++i]).toUri(), conf);
        conf.setBoolean("wordcount.skip.patterns", true);
      } else {
        other_args.add(args[i]);
      }
    }

    FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
    CheckAndDelete.checkAndDelete(other_args.get(1), conf);
    JobClient.runJob(conf);
    return 0;
  }

  public static void main(String[] args) throws Exception {
//    String[] argv = { "-Dwordcount.case.sensitive=false", "input",
//        "output-wc2", "-skip", "patterns/patterns.txt" };
//    args = argv;

    int res = ToolRunner.run(new Configuration(), new WordCountV2(), args);
    System.exit(res);
  }
}

Last modified 15 years ago Last modified on Jan 19, 2010, 7:49:55 PM