问在不破坏文件格式的情况下，通过键提取tfidf向量

EN

org.apache.mahout.common.Pair;
org.apache.mahout.common.iterator.sequencefile.SequenceFileIterable;
org.apache.mahout.math.VectorWritable;  

org.apache.hadoop.io.SequenceFile;
org.apache.hadoop.io.Text;
com.google.common.io.Closeables;

// load up the 500 desired keys with some function
Vector<Text>desiredKeys = getDesiredKeys();
//create a new SequenceFile writer for the 500 Desired Vectors 
SequenceFile.Writer writer =
        SequenceFile.createWriter(fs, conf, output500filePath ,
                                  Text.class,
                                  VectorWritable.class);         
try {
  // create an iterator over the tfidfVector sequence file 
  SequenceFileIterable<Text, VectorWritable>seqFileIterable =
          new SequenceFileIterable<Text, VectorWritable>(
              tfidfVectorPath, true, conf)

  // loop over tfidf sequence file and write out only Pairs with keys
  // contained in the desiredKeys Vector to the output500file 
  for (Pair<Text, VectorWritable> pair : seqFileIterable) {
      if(desiredKeys.contains(pair.getFirst())){
            writer.append(pair.getFirst(),pair.getSecond());
      }
  }
}finally {
  Closeables.close(writer, false);
}