Welcome to Subscribe On Youtube
393. UTF-8 Validation
Description
Given an integer array data
representing the data, return whether it is a valid UTF-8 encoding (i.e. it translates to a sequence of valid UTF-8 encoded characters).
A character in UTF8 can be from 1 to 4 bytes long, subjected to the following rules:
- For a 1-byte character, the first bit is a
0
, followed by its Unicode code. - For an n-bytes character, the first
n
bits are all one's, then + 1
bit is0
, followed byn - 1
bytes with the most significant2
bits being10
.
This is how the UTF-8 encoding would work:
Number of Bytes | UTF-8 Octet Sequence | (binary) --------------------+----------------------------------------- 1 | 0xxxxxxx 2 | 110xxxxx 10xxxxxx 3 | 1110xxxx 10xxxxxx 10xxxxxx 4 | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
x
denotes a bit in the binary form of a byte that may be either 0
or 1
.
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.
Constraints:
1 <= data.length <= 2 * 104
0 <= data[i] <= 255
Solutions
-
class Solution { public boolean validUtf8(int[] data) { int n = 0; for (int v : data) { if (n > 0) { if (v >> 6 != 0b10) { return false; } --n; } else if (v >> 7 == 0) { n = 0; } else if (v >> 5 == 0b110) { n = 1; } else if (v >> 4 == 0b1110) { n = 2; } else if (v >> 3 == 0b11110) { n = 3; } else { return false; } } return n == 0; } }
-
class Solution { public: bool validUtf8(vector<int>& data) { int n = 0; for (int& v : data) { if (n > 0) { if (v >> 6 != 0b10) return false; --n; } else if (v >> 7 == 0) n = 0; else if (v >> 5 == 0b110) n = 1; else if (v >> 4 == 0b1110) n = 2; else if (v >> 3 == 0b11110) n = 3; else return false; } return n == 0; } };
-
class Solution: def validUtf8(self, data: List[int]) -> bool: n = 0 for v in data: if n > 0: if v >> 6 != 0b10: return False n -= 1 elif v >> 7 == 0: n = 0 elif v >> 5 == 0b110: n = 1 elif v >> 4 == 0b1110: n = 2 elif v >> 3 == 0b11110: n = 3 else: return False return n == 0
-
func validUtf8(data []int) bool { n := 0 for _, v := range data { if n > 0 { if v>>6 != 0b10 { return false } n-- } else if v>>7 == 0 { n = 0 } else if v>>5 == 0b110 { n = 1 } else if v>>4 == 0b1110 { n = 2 } else if v>>3 == 0b11110 { n = 3 } else { return false } } return n == 0 }
-
function validUtf8(data: number[]): boolean { let cnt = 0; for (const v of data) { if (cnt > 0) { if (v >> 6 !== 0b10) { return false; } --cnt; } else if (v >> 7 === 0) { cnt = 0; } else if (v >> 5 === 0b110) { cnt = 1; } else if (v >> 4 === 0b1110) { cnt = 2; } else if (v >> 3 === 0b11110) { cnt = 3; } else { return false; } } return cnt === 0; }