hadoop - hadoop倒排索引，无需重复文件名

我的输出是:

字文件
----- ------
wordx Doc2，Doc1，Doc1，Doc1，Doc1，Doc1，Doc1，Doc1

我想要的是:

字文件
----- ------
wordx Doc2，Doc1

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

    private final static Text word = new Text();
    private final static Text location = new Text();

    public void map(LongWritable key, Text val,
            OutputCollector<Text, Text> output, Reporter reporter)
            throws IOException {
        FileSplit fileSplit = (FileSplit) reporter.getInputSplit();
        String fileName = fileSplit.getPath().getName();
        location.set(fileName);

        String line = val.toString();
        StringTokenizer itr = new StringTokenizer(line.toLowerCase());
        while (itr.hasMoreTokens()) {
            word.set(itr.nextToken());
            output.collect(word, location);
        }
    }
}

public static class LineIndexReducer extends MapReduceBase
        implements Reducer<Text, Text, Text, Text> {

    public void reduce(Text key, Iterator<Text> values,
            OutputCollector<Text, Text> output, Reporter reporter)
            throws IOException {

        boolean first = true;
        StringBuilder toReturn = new StringBuilder();
        while (values.hasNext()) {
            if (!first) {
                toReturn.append(", ");
            }
            first = false;
            toReturn.append(values.next().toString());
        }

        output.collect(key, new Text(toReturn.toString()));
    }
}

为了获得最佳性能-我应该在哪里跳过重复文件名？ map ，减少还是两者兼而有之？
ps:我是编写MR任务的初学者，并且还试图用我的问题弄清楚编程逻辑。

最佳答案

您将只能在Reducer中删除重复项。为此，您可以使用Set，它不允许重复。

public void reduce(Text key, Iterator<Text> values,
        OutputCollector<Text, Text> output, Reporter reporter)
        throws IOException {

    // Text's equals() method should be overloaded to make this work
    Set<Text> outputValues = new HashSet<Text>();

    while (values.hasNext()) {
      // make a new Object because Hadoop may mess with original
      Text value = new Text(values.next());

      // takes care of removing duplicates
      outputValues.add(value);
    }

    boolean first = true;
    StringBuilder toReturn = new StringBuilder();
    Iterator<Text> outputIter = outputValues.iter();
    while (outputIter.hasNext()) {
        if (!first) {
            toReturn.append(", ");
        }
        first = false;
        toReturn.append(outputIter.next().toString());
    }

    output.collect(key, new Text(toReturn.toString()));
}

编辑:根据Chris的评论将值的副本添加到“设置”。