Question

(Count the occurrences of words in a text file) Rewrite Listing 21.9 to read the text from a text file. The text file is passed as a command-line argument. Words are delimited by white space characters, punctuation marks (, ; . : ?), quotation marks (' "), and parentheses. Count the words in a case-sensitive fashion (e.g., consider Good and good to be the same word). The words must start with a letter. Display the output of words in alphabetical order, with each word preceded by the number of times it occurs.

Write it in Java language.

Thanks

Answer 1

// Java program to count the words in a text file delimited by white space characters, punctuation marks (, ; . : ?), quotation marks (' "), and parentheses
import java.io.File;
import java.io.FileNotFoundException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Scanner;

public class CountWords {

   // method to return the index of the keyWord in the list of words
   public static int indexOf(ArrayList<String> words, String keyWord)
   {
       // loop over the list of words
       for(int i=0;i<words.size();i++)
       {
           // case-insensitive comparison
           if(words.get(i).equalsIgnoreCase(keyWord))
               return i; // return i if ith word is keyWord
       }
      
       return -1; // keyWord not in list
   }
  
   // method to sort the words in alphabetical order and order the corresponding counts
   public static void sort(ArrayList<String> words, ArrayList<Integer> counts)
   {
       int min;
       for(int i=0;i<words.size()-1;i++)
       {
           min = i;
           for(int j=i+1;j<words.size();j++)
           {
               if(words.get(j).compareTo(words.get(min)) < 0)
                   min = j;
           }
          
           if(min != i)
           {
               String tempWord = words.get(i);
               words.set(i, words.get(min));
               words.set(min, tempWord);
              
               int tempCount = counts.get(i);
               counts.set(i, counts.get(min));
               counts.set(min, tempCount);
           }
       }
   }
  
   public static void main(String[] args) throws FileNotFoundException {

       // check if filename is passed
       if(args.length >= 1)
       {
           String filename = args[0]; // get the filename
           // open the file
           Scanner scan = new Scanner(new File(filename));
          
           String line;
           String lineWords[];
           int index;
           // create array list to contain the words and its corresponding counts
           ArrayList<String> words = new ArrayList<String>();
           ArrayList<Integer> counts = new ArrayList<Integer>();
          
           // read till the end of file
           while(scan.hasNextLine())
           {
               line = scan.nextLine(); // read a line
               // split the words on the mentioned delimiters
               lineWords = line.split("[,;.:?'\"() \t]");
               // loop over the words in the line
               for(int i=0;i<lineWords.length;i++)
               {
                   lineWords[i] = lineWords[i].trim(); // remove space if any from the word
                   // only consider those words that have length >=1 and starts with a letter
                   if(lineWords[i].length() > 0 && lineWords[i].matches("^[a-zA-Z].*"))
                   {
                       index = indexOf(words,lineWords[i]); // get the index of the word in the list
                       if(index == -1) // if word not present, add it to words and add count of 1 to counts
                       {
                           words.add(lineWords[i].toLowerCase());
                           counts.add(1);
                       }else // increment the count of the word in counts
                       {
                           counts.set(index, counts.get(index)+1);
                       }
                   }
               }
           }
          
           scan.close(); // close the file
           // sort the words in alphabetical order
           sort(words,counts);
          
           // display the words and their counts
           System.out.printf("%-20s%-10s","Word","Count");
           for(int i=0;i<words.size();i++)
           {
               System.out.printf("\n%-20s%-10d",words.get(i),counts.get(i));
           }
       }else
           System.out.println("Pass the filename as command line argument");
          

   }

}
//end of program

Output:

Input file:

Output: