Untitled

Fast loading of elements into array/list with fixed index without duplicates
import java.io.*;
import java.util.ArrayList;
import static java.lang.Math.log;


class DocumentRepresentation
{
  private String dirPath;
  private ArrayList<String> fileNameVector;
  private ArrayList<String> termVector;
  private ArrayList<Integer[]> tf; /* store it in natural 2d array */
  private Integer df[]; /* do normal 1d array */
  private Double idf[]; /* do normal 1d array */
  private Double tfIdf[][]; /* do normal 2d array */

  DocumentRepresentation (String dirPath)
  {
    this.dirPath = dirPath;
    fileNameVector = new ArrayList<String> ();
    termVector = new ArrayList<String> ();
    tf = new ArrayList<Integer[]> ();
  }

  /* Later sepatere the internal works */
  public int start ()
  {
    /* Load the files, and populate the fileNameVector string */
    File fileDir = new File (dirPath);
    int fileCount = 0;
    int index;

    if (fileDir.isDirectory () == false)
    {
      return -1;
    }

    File fileList[] = fileDir.listFiles ();

    for (int i=0; i<fileList.length; i++)
    {
      if (fileList[i].isFile () == true)
      {
        fileNameVector.add (fileList[i].getName ());
        //      System.out.print ("File Name " + (i + 1) + ": " + fileList[i].getName () + "n");
      }
    }

    fileCount = fileNameVector.size ();
    for (int i=0;i<fileNameVector.size (); i++)
    {
      System.out.print ("Name " + (i+1) + ": " + fileNameVector.get (i) + "n");
    }

    /* Bind the files with a buffered reader */
    BufferedReader fileReaderVector[] = new BufferedReader [fileCount];
    for (int i=0; i<fileCount; i++)
    {
      try
      {
        fileReaderVector[i] = new BufferedReader (new FileReader (fileList[i]));
      }
      /* Not handled */
      catch (FileNotFoundException e)
      {
        System.out.println (e);
      }
    }

    /* Scan the term frequencies in the tf 2d array */
    for (int i=0; i<fileCount; i++)
    {
      String line;

      try
      {
            /*** THIS IS THE PLACE OF MY QUESTION **/
        while ((line = fileReaderVector[i].readLine ()) != null)
        {
          String words[] = line.split ("[\W]");

          for (int j=0;j<words.length;j++)
          {
            if ((index = termVector.indexOf (words[j])) != -1)
            {
              tf.get (index)[i]++;
              /* increase the tf count */
            }
            else
            {
              termVector.add (words[j]);
              Integer temp[] = new Integer [fileCount];

              for (int k=0; k<fileCount; k++)
              {
                temp[k] = new Integer (0);
              }
              temp[i] = 1;
              tf.add (temp);
              index = termVector.indexOf (words[j]);
            }

            System.out.println (words[j]);
          }
        }
      }
      /* Not handled */
      catch (IOException e)
      {
        System.out.println (e);
      }
    }

    return 0;
  }
}

class DocumentRepresentationTest
{
  public static void main (String args[])
  {
    DocumentRepresentation docSet = new DocumentRepresentation (args[0]);
    docSet.start ();
    System.out.print ("n");
  }
}

LinkedHashMap<Item,Integer> map = new LinkedHashMap<Item,Integer>();

Integer index = map.get(item);
if (index != null) {
  // already in the map; use `index'
} else {
  // not in the map
}

if (!map.containsKey(item)) {
  map.put(item, map.size());
}

for (Entry<Item,Integer> e : map.entrySet()) {
  Item item = e.getKey();
  int index = e.getValue();
  ...
}