Remove Strings with same characters in a String Array

Question

I'm facing a problem right now. In one of my program, I need to remove strings with same characters from an Array. For eg. suppose,

I have 3 Arrays like,

String[] name1 = {"amy", "jose", "jeremy", "alice", "patrick"};
String[] name2 = {"alan", "may", "jeremy", "helen", "alexi"};
String[] name3 = {"adel", "aron", "amy", "james", "yam"};

As you can see, there is a String amy in the name1 array. Also, I have strings like may, amy and yam in the next two arrays. What I need is that, I need a final array which does not contain these repeated Strings. I just need only one occurrence: I need to remove all permutations of a name in the final array. That is the final array should be:

String[] finalArray={"amy", "jose", "alice", "patrick","alan", "jeremy", "helen", "alexi","adel", "aron", "james"}

(The above array removed both yam, may, and only includes amy).

What i have tried so far, using HashSet, is as below

String[] name1 = {"Amy", "Jose", "Jeremy", "Alice", "Patrick"};
String[] name2 = {"Alan", "mAy", "Jeremy", "Helen", "Alexi"};
String[] name3 = {"Adel", "Aaron", "Amy", "James", "Alice"};
Set<String> letter = new HashSet<String>();
for (int i = 0; i < name1.length; i++) {
    letter.add(name1[i]);
}
for (int j = 0; j < name2.length; j++) {
    letter.add(name2[j]);
}
for (int k = 0; k < name3.length; k++) {
    letter.add(name3[k]);
}
System.out.println(letter.size() + " letters must be sent to: " + letter);

But, the problem with this code is that, it just removes multiple occurences of the same string. Is there any other alternative? Any help is very much appreciated.

Answer 1

You can sort the character array of the String (str.toCharArray ()) and create a new String from the sorted array to get a "canonical" representation of a String.

Then you can add these Strings to a Set, and check for each String whether the canonical representation is already in the Set.

Set<String> letter = new HashSet<String>();
for (int i = 0; i < name1.length; i++) {
    char[] chars = name1[i].toCharArray();
    Arrays.sort(chars);
    letter.add(new String(chars));
}
for (int j = 0; j < name2.length; j++) {
    char[] chars = name2[j].toCharArray();
    Arrays.sort(chars);
    letter.add(new String(chars));
}
for (int k = 0; k < name3.length; k++) {
    char[] chars = name3[k].toCharArray();
    Arrays.sort(chars);
    letter.add(new String(chars));
}

EDIT : I changed the Set<char[]> to Set<String>, since arrays don't override hashCode and equals, so HashSet<char[]> wouldn't work.

Answer 2

TreeSet allows us to give a comparator. See whether this helps. For keeping the count use a TreeMap.

package empty;

import java.util.Arrays;
import java.util.Comparator;
import java.util.Set;
import java.util.TreeMap;
import java.util.TreeSet;

public class RemoveDuplicateStrings {

    public static void main(String[] args) {
        String[] name1 = { "amy", "jose", "jeremy", "alice", "patrick" };
        String[] name2 = { "alan", "may", "jeremy", "helen", "alexi" };
        String[] name3 = { "adel", "aron", "amy", "james", "yam" };

        Comparator<String> comparator = new Comparator<String>() {
            @Override public int compare(String o1, String o2) {
                System.out.println("Compare(" + o1 + "," + o2 + ")");
                char[] a1 = o1.toCharArray();
                Arrays.sort(a1);
                char[] a2 = o2.toCharArray();
                Arrays.sort(a2);
                return new String(a1).compareTo(new String(a2));
            }
        };
        Set<String> set = new TreeSet<String>(comparator);

        for (String name : name1) {
            set.add(name);
        }
        for (String name : name2) {
            set.add(name);
        }
        for (String name : name3) {
            set.add(name);
        }

        String[] result = set.toArray(new String[set.size()]);
        System.out.println(Arrays.asList(result));

        // Using TreeMap to keep the count.

        TreeMap<String, Integer> map = new TreeMap<String, Integer>(comparator);

        addAll(name1, map);
        addAll(name2, map);
        addAll(name3, map);

        System.out.println(map);
    }

    private static void addAll(String[] names, TreeMap<String, Integer> map) {
        for (String name : names) {
            if (map.containsKey(name)) {
                int n = map.get(name);
                map.put(name, n + 1);
            } else
                map.put(name, 1);
        }
    }
}

Answer 3

In line with kdm:

import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

public class RemoveDuplicateString {

    private static boolean add(Set<String> keySet, String s){
        char[] sortCharacters = s.toCharArray();
        Arrays.sort(sortCharacters);
        return keySet.add(new String(sortCharacters));
    }

    private static void check(Set<String> keySet, String []names, List<String> result){
        for (String name : names) {
            if (add(keySet, name)){
                result.add(name);
            }
        }
    }

    public static void main(String[] args) {
        String[] name1 = {"amy", "jose", "jeremy", "alice", "patrick"};
        String[] name2 = {"alan", "may", "jeremy", "helen", "alexi"};
        String[] name3 = {"adel", "aron", "amy", "james", "yam"};
        Set<String> keySet = new HashSet<String>();
        List<String> result = new ArrayList<String>();
        check(keySet, name1, result);
        check(keySet, name2, result);
        check(keySet, name3, result);
        System.out.println(result);
    }
}