forked from chenyiAlone/LeetCode
-
Notifications
You must be signed in to change notification settings - Fork 0
/
UTF8Validation.java
75 lines (72 loc) · 2.67 KB
/
UTF8Validation.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
package medium;
/**
* ClassName: UTF8Validation.java
* Author: chenyiAlone
* Create Time: 2019/7/30 22:15
* Description: No.393 UTF-8 Validation
* 思路:
* 1. 位运算
* 2. unicode code < 128
*
*
* A character in UTF8 can be from 1 to 4 bytes long, subjected to the following rules:
*
* For 1-byte character, the first bit is a 0, followed by its unicode code.
* For n-bytes character, the first n-bits are all one's, the n+1 bit is 0, followed by n-1 bytes with 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
* 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.
*
*/
public class UTF8Validation {
private boolean error(int[] data, int index, int n) {
for (int j = 1; j <= n; j++) {
if (index + j >= data.length || (data[index + j] & 0x80) != 0x80)
return true;
}
return false;
}
public boolean validUtf8(int[] data) {
for (int i = 0; i < data.length; ) {
if (data[i] < 128) {
i += 1;
} else if ((data[i] & 0xe0) == 0xc0) {
if (error(data, i, 1)) return false;
i += 2;
} else if ((data[i] & 0xf0) == 0xe0) {
if (error(data, i, 2)) return false;
i += 3;
} else if ((data[i] & 0xf8) == 0xf0) {
if (error(data, i, 3)) return false;
i += 4;
} else
return false;
}
return true;
}
}