[java] 모든 문자가 고유한지 확인하기 위해 비트 벡터 사용을 설명하십시오.

나는이 모든 대답이 이것이 어떻게 작동하는지 설명한다고 생각하지만, 변수의 이름을 바꾸고 다른 변수를 추가하고 주석을 추가하여 더 잘 본 방법에 대한 정보를 제공하는 것처럼 느꼈습니다.

public static boolean isUniqueChars(String str) {

    /*
    checker is the bit array, it will have a 1 on the character index that
    has appeared before and a 0 if the character has not appeared, you
    can see this number initialized as 32 0 bits:
    00000000 00000000 00000000 00000000
     */
    int checker = 0;

    //loop through each String character
    for (int i = 0; i < str.length(); ++i) {
        /*
        a through z in ASCII are charactets numbered 97 through 122, 26 characters total
        with this, you get a number between 0 and 25 to represent each character index
        0 for 'a' and 25 for 'z'

        renamed 'val' as 'characterIndex' to be more descriptive
         */
        int characterIndex = str.charAt(i) - 'a'; //char 'a' would get 0 and char 'z' would get 26

        /*
        created a new variable to make things clearer 'singleBitOnPosition'

        It is used to calculate a number that represents the bit value of having that 
        character index as a 1 and the rest as a 0, this is achieved
        by getting the single digit 1 and shifting it to the left as many
        times as the character index requires
        e.g. character 'd'
        00000000 00000000 00000000 00000001
        Shift 3 spaces to the left (<<) because 'd' index is number 3
        1 shift: 00000000 00000000 00000000 00000010
        2 shift: 00000000 00000000 00000000 00000100
        3 shift: 00000000 00000000 00000000 00001000

        Therefore the number representing 'd' is
        00000000 00000000 00000000 00001000

         */
        int singleBitOnPosition = 1 << characterIndex;

        /*
        This peforms an AND between the checker, which is the bit array
        containing everything that has been found before and the number
        representing the bit that will be turned on for this particular
        character. e.g.
        if we have already seen 'a', 'b' and 'd', checker will have:
        checker = 00000000 00000000 00000000 00001011
        And if we see 'b' again:
        'b' = 00000000 00000000 00000000 00000010

        it will do the following:
        00000000 00000000 00000000 00001011
        & (AND)
        00000000 00000000 00000000 00000010
        -----------------------------------
        00000000 00000000 00000000 00000010

        Since this number is different than '0' it means that the character
        was seen before, because on that character index we already have a 
        1 bit value
         */
        if ((checker & singleBitOnPosition) > 0) {
            return false;
        }

        /* 
        Remember that 
        checker |= singleBitOnPosition is the same as  
        checker = checker | singleBitOnPosition
        Sometimes it is easier to see it expanded like that.

        What this achieves is that it builds the checker to have the new 
        value it hasnt seen, by doing an OR between checker and the value 
        representing this character index as a 1. e.g.
        If the character is 'f' and the checker has seen 'g' and 'a', the 
        following will happen

        'f' = 00000000 00000000 00000000 00100000
        checker(seen 'a' and 'g' so far) = 00000000 00000000 00000000 01000001

        00000000 00000000 00000000 00100000
        | (OR)
        00000000 00000000 00000000 01000001
        -----------------------------------
        00000000 00000000 00000000 01100001

        Therefore getting a new checker as 00000000 00000000 00000000 01100001

         */
        checker |= singleBitOnPosition;
    }
    return true;
}

답변

In ASCII, val = str.charAt(i) - 'a' = 116 - 97 = 19
What about 1 << val ?
1          == 00000000000000000000000000000001
1 << 19    == 00000000000010000000000000000000
checker |= (1 << val) means checker = checker | (1 << val)
so checker = 00000000000000000000000000000000 | 00000000000010000000000000000000
checker == 524288 (00000000000010000000000000000000)

val = 101 - 97 = 4
1          == 00000000000000000000000000000001
1 << 4     == 00000000000000000000000000010000
checker |= (1 << val) 
so checker = 00000000000010000000000000000000 | 00000000000000000000000000010000
checker == 524304 (00000000000010000000000000010000)

(checker & (1 << val)) > 0

int val = str.charAt(i) - 'a'; 

public static boolean isUniqueStringUsingBitVectorClass(String s) {

    final int ASCII_CHARACTER_SET_SIZE = 256;

    final BitSet tracker = new BitSet(ASCII_CHARACTER_SET_SIZE);

    // if more than  256 ASCII characters then there can't be unique characters
    if(s.length() > 256) {
        return false;
    }

    //this will be used to keep the location of each character in String
    final BitSet charBitLocation = new BitSet(ASCII_CHARACTER_SET_SIZE);

    for(int i = 0; i < s.length(); i++) {

        int charVal = s.charAt(i);
        charBitLocation.set(charVal); //set the char location in BitSet

        //check if tracker has already bit set with the bit present in charBitLocation
        if(tracker.intersects(charBitLocation)) {
            return false;
        }

        //set the tracker with new bit from charBitLocation
        tracker.or(charBitLocation);

        charBitLocation.clear(); //clear charBitLocation to store bit for character in the next iteration of the loop

    }

    return true;

}

function checkIfUniqueChars (str) {

    var checker = 0; // 32 or 64 bit integer variable 

    for (var i = 0; i< str.length; i++) {
        var index = str[i].charCodeAt(0) - 96;
        var bitRepresentationOfIndex = 1 << index;

        if ( (checker & bitRepresentationOfIndex) > 1) {
            console.log(str, false);
            return false;
        } else {
            checker = (checker | bitRepresentationOfIndex);
        }
    }
    console.log(str, true);
    return true;
}

checkIfUniqueChars("abcdefghi");  // true
checkIfUniqueChars("aabcdefghi"); // false
checkIfUniqueChars("abbcdefghi"); // false
checkIfUniqueChars("abcdefghii"); // false
checkIfUniqueChars("abcdefghii"); // false

// checker is intialized to 32-bit-Int(0)
// therefore, checker is
checker= 00000000000000000000000000000000

str[0] is 'a'
str[i].charCodeAt(0) - 96 = 1

checker 'AND' 32-bit-Int(1) = 00000000000000000000000000000000
Boolean(0) == false

// So, we go for the '`OR`' operation.

checker = checker OR 32-bit-Int(1)
checker = 00000000000000000000000000000001

str[1] is 'a'
str[i].charCodeAt(0) - 96 = 1

checker= 00000000000000000000000000000001
a      = 00000000000000000000000000000001

checker 'AND' 32-bit-Int(1) = 00000000000000000000000000000001
Boolean(1) == true
// We've our duplicate now