import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;

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.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.mapreduce.Counter;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.StringUtils;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount2for020 extends Configured implements Tool {
  // 問題一： configuration 所設定的參數值沒有傳遞到map裡
  // 問題二： inputFile 也沒用到
  // 問題三：由於configuration 的問題，以致 DistributedCache 也無法取得正確的LocalCacheFiles
  public static class Map extends
      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 setup(Context context) {
      System.err.println("yes yes yes !!! setup work");

      Configuration conf = context.getConfiguration();

      caseSensitive = conf.getBoolean("wordcount.case.sensitive", false);

      // inputFile = conf.get("map.input.file","");
      // inputFile = "/user/waue/patterns";
      // 此處 inputFile 之後就在也沒用到，因此在這裡處理一下

      boolean wsp = conf.getBoolean("wordcount.skip.patterns", true);

      System.err.println("caseSensitive = " + caseSensitive);
      System.err.println("wordcount.skip.patterns = " + wsp);

      if (wsp) {
        Path[] patternsFiles = new Path[0];

        try {
          patternsFiles = DistributedCache.getLocalCacheFiles(conf);

        } catch (IOException ioe) {
          System.err
              .println("Caught exception while getting cached files: "
                  + StringUtils.stringifyException(ioe));
        }
        for (Path patternsFile : patternsFiles) {
          parseSkipFile(patternsFile);
          System.err.println("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, Context context)
        throws IOException, InterruptedException {
      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());
        context.write(word, one);
        Counter count = context.getCounter(Counters.INPUT_WORDS);
        count.increment(1);
      }

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

  public static class Reduce extends
      Reducer<Text, IntWritable, Text, IntWritable> {
    /* on V0.20, we should use Iterable to replace Iterator */
    // public void reduce(Text key, Iterator<IntWritable> values,

    public void reduce(Text key, Iterable<IntWritable> values,
        Context context) throws IOException, InterruptedException {
      int sum = 0;
      /* these three line only be used on V0.19 nor V0.20 */
      // while (values.hasNext()) {
      // sum += values.next().get();
      // }

      for (IntWritable val : values) {
        sum += val.get();
      }
      context.write(key, new IntWritable(sum));
    }
  }

  public int run(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf);
    job.setJarByClass(WordCount2for020.class);
    job.setJobName("wordcount");

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

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

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(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);

        System.err.println("cache file = " + args[i]);

        conf.setBoolean("wordcount.skip.patterns", true);
        System.err.println("wordcount.skip.patterns = true");
      } else {
        other_args.add(args[i]);
      }
    }
    // conf.set("mapred.job.tracker", "local");
    // conf.set("fs.default.name", "file:///");

    FileInputFormat.setInputPaths(job, new Path(other_args.get(0)));
    FileOutputFormat.setOutputPath(job, new Path(other_args.get(1)));

    job.waitForCompletion(true);

    return 0;
  }

  public static void main(String[] args) throws Exception {
    String[] argv = { "-Dwordcount.case.sensitive=false",
        "/user/waue/text_input", "/user/waue/output-v020", "-skip",
        "/user/waue/patterns/patterns.txt" };
    args = argv;
    int res = ToolRunner.run(new Configuration(), new WordCount2for020(),
        args);
    System.exit(res);
  }
}

問題

• -skip 參數、以及 case.sensitive 的參數無用

問題研判

  // 問題一： configuration 所設定的參數值沒有傳遞到map裡
  // 問題二： inputFile 也沒用到
  // 問題三：由於configuration 的問題，以致 DistributedCache 也無法取得正確的LocalCacheFiles

10/04/19 16:02:58 WARN conf.Configuration: DEPRECATED: hadoop-site.xml found in the classpath. Usage of hadoop-site.xml is deprecated. Instead use core-site.xml, mapred-site.xml and hdfs-site.xml to override properties of core-default.xml, mapred-default.xml and hdfs-default.xml respectively
cache file = /user/waue/patterns/patterns.txt
wordcount.skip.patterns = true
10/04/19 16:02:59 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
10/04/19 16:02:59 INFO input.FileInputFormat: Total input paths to process : 4
10/04/19 16:02:59 INFO mapred.JobClient: Running job: job_201004190849_0011
10/04/19 16:03:00 INFO mapred.JobClient:  map 0% reduce 0%
10/04/19 16:03:10 INFO mapred.JobClient: Task Id : attempt_201004190849_0011_m_000000_0, Status : FAILED
java.lang.NullPointerException
	at WordCount2for020$Map.setup(WordCount2for020.java:79)
	at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142)
	at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:583)
	at org.apache.hadoop.mapred.MapTask.run(MapTask.java:305)
	at org.apache.hadoop.mapred.Child.main(Child.java:170)