Storing files in HashTable

Question

I am trying to store the HTML to Text converted files into the hash table so as to retrieve them later. I am not understanding how to implement it. Please help me. How can I store the text files into the hash table?

package hashTable;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.math.BigInteger;
import java.util.Scanner;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;


public class HashMap {
  // Setting table size to a max of 32, value used to modulus for hash value.
  private final static int TABLE_SIZE = 32;

  HashEntry[] table;

  HashMap() {
        table = new HashEntry[TABLE_SIZE];
        for (int i = 0; i < TABLE_SIZE; i++)
              table[i] = null;
  }

  /* function to retrieve value from the table according to key */
  public int get(String key) {
        int hash = new BigInteger(toAscii(key)).mod(new BigInteger(((Integer)TABLE_SIZE).toString())).intValue();
        while (table[hash] != null && table[hash].getKey() != key)
              hash = (hash + 1) % TABLE_SIZE;
        if (table[hash] == null)
              return -1;
        else
              return table[hash].getValue();
  }

  /* function to add value to the table */
  public void put(String key, int value) {
        //creating hash code using key value given as a string
        int hash = new BigInteger(toAscii(key)).mod(new BigInteger(((Integer)TABLE_SIZE).toString())).intValue();
        while (table[hash] != null && table[hash].getKey() != key)
              hash = (hash + 1) % TABLE_SIZE;
        table[hash] = new HashEntry(key, value);
  }

  /* value to create the Hash code from he name entered, basically converting name to ASCII */
  public static String toAscii(String s){
      StringBuilder sb = new StringBuilder();
      long asciiInt;
      // loop through all values in the string, including blanks
      for (int i = 0; i < s.length(); i++){
          //getting Ascii value of character and adding it to the string.
          char c = s.charAt(i);
          asciiInt = (int)c; 
          sb.append(asciiInt);
      }
      return String.valueOf(sb);
     }
      public void HtmltoText(String fn){
      try{
         String uri="C:/Users/Bharadwaj/Downloads/W3C Web Pages";
         BufferedReader in = new BufferedReader(new FileReader(uri));
         String st=new String();
         String str;
         while((str=in.readLine())!=null){
             st += "\n" + str.replace("<br", "\n<br");
                         }        
         Document s=Jsoup.parse(st);
        // System.out.println(s1);
         String text=s.text();
        // System.out.println(filename.substring(0,filename.length()-4));   
         String txtpath="C:/Users/Bharadwaj/Downloads/W3C Web Pages/Text";
         System.out.println(text);
         String newname=txtpath+fn.substring(0,(fn.length()-4))+".txt";          
         BufferedWriter writerTxt = new BufferedWriter(new FileWriter(newname));
         writerTxt.write(text);
         writerTxt.close();                      
      }catch(Exception e){
          e.printStackTrace();
      }     
     }  

  public static void main(String[]args) throws IOException{
    HashMap entry = new HashMap();
    String uri="C:/Users/Bharadwaj/Downloads/W3C Web Pages";
    File fil=new File(uri);
    System.out.println(fil);
    entry.HtmltoText(uri);       
  }
}

Answer 1

This is not such a good idea to store many large files in a hashmap, but if you insist you could try the following:

1. Read each file line by line and store it in a string variable
2. Assign an automatically incremented integer value to each string variable
3. Insert the pairs of <Integer, String>'s into the hashmap.

Voila! Now you have a hashmap that contains all your files. of course exceptions might occur, for example when reading special characters like back-slash, etc...

Answer 2

Why not store the files on the filesytem and just put the path to the files in the map?