|
| 1 | +/** |
| 2 | + * 393. UTF-8 Validation |
| 3 | + * https://leetcode.com/problems/utf-8-validation/ |
| 4 | + * Difficulty: Medium |
| 5 | + * |
| 6 | + * Given an integer array data representing the data, return whether it is a valid UTF-8 encoding |
| 7 | + * (i.e. it translates to a sequence of valid UTF-8 encoded characters). |
| 8 | + * |
| 9 | + * A character in UTF8 can be from 1 to 4 bytes long, subjected to the following rules: |
| 10 | + * 1. For a 1-byte character, the first bit is a 0, followed by its Unicode code. |
| 11 | + * 2. For an n-bytes character, the first n bits are all one's, the n + 1 bit is 0, followed by |
| 12 | + * n - 1 bytes with the most significant 2 bits being 10. |
| 13 | + * |
| 14 | + * This is how the UTF-8 encoding would work: |
| 15 | + * Number of Bytes | UTF-8 Octet Sequence |
| 16 | + * | (binary) |
| 17 | + * --------------------+----------------------------------------- |
| 18 | + * 1 | 0xxxxxxx |
| 19 | + * 2 | 110xxxxx 10xxxxxx |
| 20 | + * 3 | 1110xxxx 10xxxxxx 10xxxxxx |
| 21 | + * 4 | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx |
| 22 | + * |
| 23 | + * x denotes a bit in the binary form of a byte that may be either 0 or 1. |
| 24 | + * |
| 25 | + * Note: The input is an array of integers. Only the least significant 8 bits of each integer is |
| 26 | + * used to store the data. This means each integer represents only 1 byte of data. |
| 27 | + */ |
| 28 | + |
| 29 | +/** |
| 30 | + * @param {number[]} data |
| 31 | + * @return {boolean} |
| 32 | + */ |
| 33 | +var validUtf8 = function(data) { |
| 34 | + let result = 0; |
| 35 | + |
| 36 | + for (const n of data) { |
| 37 | + if (result === 0) { |
| 38 | + if (n >> 7 === 0) result = 0; |
| 39 | + else if (n >> 5 === 0b110) result = 1; |
| 40 | + else if (n >> 4 === 0b1110) result = 2; |
| 41 | + else if (n >> 3 === 0b11110) result = 3; |
| 42 | + else return false; |
| 43 | + } else { |
| 44 | + if (n >> 6 !== 0b10) return false; |
| 45 | + result--; |
| 46 | + } |
| 47 | + } |
| 48 | + |
| 49 | + return result === 0; |
| 50 | +}; |
0 commit comments