-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathUTF8Validation.py
More file actions
92 lines (71 loc) · 3.11 KB
/
Copy pathUTF8Validation.py
File metadata and controls
92 lines (71 loc) · 3.11 KB
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
"""
https://leetcode.com/problems/utf-8-validation/
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, 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:
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
"""
from typing import List
from Common.ObjectTestingUtils import run_functional_tests
# Runtime: 173 ms, faster than 60.23% of Python3 online submissions for UTF-8 Validation.
# Memory Usage: 14.2 MB, less than 70.76% of Python3 online submissions for UTF-8 Validation.
# https://leetcode.com/submissions/detail/337756183/
class Solution:
def validUtf8(self, data: List[int]) -> bool:
BIT7 = 1 << 7
BIT6 = 1 << 6
BIT5 = 1 << 5
BIT4 = 1 << 4
BIT3 = 1 << 3
MASK76 = BIT7 | BIT6
MASK765 = MASK76 | BIT5
MASK7654 = MASK765 | BIT4
MASK76543 = MASK7654 | BIT3
bytes_to_check = 0
for byte in data:
if bytes_to_check > 0:
if byte & MASK76 != BIT7:
return False
bytes_to_check -= 1
continue
if not (byte & BIT7):
continue
if byte & MASK765 == MASK76:
bytes_to_check = 1
elif byte & MASK7654 == MASK765:
bytes_to_check = 2
elif byte & MASK76543 == MASK7654:
bytes_to_check = 3
else:
return False
return 0 == bytes_to_check
tests = [
[[197,130,1], True],
[[235,140,4], False]
]
run_functional_tests(Solution().validUtf8, tests)