Given an array of integers representing the data, return whether it is a valid utf-8 encoding.
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:
data = [197, 130, 1], which represents the octet sequence: 11000101 10000010 00000001.
Return true.
It is a valid utf-8 encoding for a 2-bytes character followed by a 1-byte character.
Example 2:
data = [235, 140, 4], which represented the octet sequence: 11101011 10001100 00000100.
Return false.
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.
Solution:
class Solution {
public boolean validUtf8(int[] data) {
if (data.length == 0) return true;
int[] binary = decimalToBinary(data[0]);
if (binary[0] == 0) {
return validUtf8(Arrays.copyOfRange(data, 1, data.length));
} else {
int bytes = 0;
while (bytes <= 3 && binary[bytes] == 1) {
bytes ++;
}
if (bytes < 2 || bytes > 4) {
return false;
}
return helper(Arrays.copyOfRange(data, 0, bytes)) && validUtf8(Arrays.copyOfRange(data, bytes, data.length));
}
}
private boolean helper(int[] data) {
int bytes = data.length;
for (int i = 0; i < bytes; i ++) {
int[] binary = decimalToBinary(data[i]);
if (i == 0) {
for (int j = 0; j < bytes; j ++) {
if (binary[j] != 1) {
return false;
}
}
if (binary[bytes] != 0) {
return false;
}
} else {
if (binary[0] != 1) return false;
if (binary[1] != 0) return false;
}
}
return true;
}
private int[] decimalToBinary(int number) {
int[] result = new int[8];
for (int i = 7; i >= 0; i --) {
if (number > 0) {
result[i] = (number & 1);
number >>= 1;
}
}
return result;
}
}