393. UTF-8 Validation

 Given an integer array data representing the data, return whether it is a valid UTF-8 encoding.

A character in UTF8 can be from 1 to 4 bytes long, subjected to the following rules:

1. For a 1-byte character, the first bit is a 0, followed by its Unicode code.
2. For an n-bytes character, the first n bits are all one's, the n + 1 bit is 0, followed by n - 1 bytes with the most significant 2 bits being 10.

This is how the UTF-8 encoding would work:

   Char. number range  |        UTF-8 octet sequence
      (hexadecimal)    |              (binary)
   --------------------+---------------------------------------------
   0000 0000-0000 007F | 0xxxxxxx
   0000 0080-0000 07FF | 110xxxxx 10xxxxxx
   0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx
   0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx

Note: The input is an array of integers. Only the least significant 8 bits of each integer is used to store the data. This means each integer represents only 1 byte of data.

 

Example 1:

Input: data = [197,130,1]
Output: true
Explanation: data represents the octet sequence: 11000101 10000010 00000001.
It is a valid utf-8 encoding for a 2-bytes character followed by a 1-byte character.

Example 2:

Input: data = [235,140,4]
Output: false
Explanation: data represented the octet sequence: 11101011 10001100 00000100.
The first 3 bits are all one's and the 4th bit is 0 means it is a 3-bytes character.
The next byte is a continuation byte which starts with 10 and that's correct.
But the second continuation byte does not start with 10, so it is invalid.

 

class Solution {

public:

    bool validUtf8(vector<int>& data) {

        if (data.size() == 0) {

            return false;

        }

        int i = 0;

        while (i < data.size()) {

            pair<bool, int> utf_code = getUtfByte(data[i]);

            if (utf_code.first == false) {

                return false;

            }

            if (utf_code.second == 0) {

                i++;

            } else {

                int it = 1;

                while (i + it < data.size() && it <= utf_code.second) {

                    if (!validate(data[i + it])) {

                        return false;

                    }

                    it++;

                }

                if (it <= utf_code.second) {

                    return false;

                }

                i = i + it;

            }

        }

        return true;

    }

    

    pair<bool, int> getUtfByte(int num) {

        int offset = (1 << 7);

        if ((num & offset) == 0) {

            return {true, 0};

        }

        offset >>= 1;

        if ((num & offset) == 0) {

            return {false, 0};

        }

        int count = 0;

        while (count < 3) {

            count++;

            offset >>= 1;

            if ((num & offset) == 0) {

                return {true, count};

            }

        }

        return {false, 0};

    }

    

    bool validate(int num) {

        int offset = (1 << 7);

        return ((num & offset) != 0);

    }

};