Java Regex 2 - Duplicate Words

  • + 1 comment

    With this code I got the same expected results except for a mysterious character at the end of the last test case. It is neither a whitespace or unprintable char. It makes no sense for me.

    import java.util.Scanner;
    import java.util.regex.Matcher;
    import java.util.regex.Pattern;
    
    public class DuplicateWords {
    
        public static void main(String[] args) {
    
            String regex = "\\b(\\w+)\\s+\\1\\b";
            Pattern p = Pattern.compile(regex, Pattern.CASE_INSENSITIVE);
    
            Scanner in = new Scanner(System.in);
            int numSentences = Integer.parseInt(in.nextLine());
            
            while (numSentences-- > 0) {
                String input = in.nextLine();
                Matcher m = p.matcher(input);
                
                // Check for subsequences of input that match the compiled pattern
                while (m.find()) {
                    input = input.replaceAll("(?i)"+regex,"$1");
                    //m = p.matcher(input);
                }
                
                // Prints the modified sentence.
                System.out.print(input+'\n');
            }
    			
            in.close();
        }
    }