blob: 41663c81adb39c24921baa67f2bb8fb452e05347 (
about) (
plain) (
blame)
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
93
94
95
96
97
98
99
100
101
102
103
|
/*
* Copyright (C) 2010 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#ifndef LATINIME_CHAR_UTILS_H
#define LATINIME_CHAR_UTILS_H
#include <cctype>
#include "defines.h"
namespace latinime {
class CharUtils {
public:
static AK_FORCE_INLINE bool isAsciiUpper(int c) {
// Note: isupper(...) reports false positives for some Cyrillic characters, causing them to
// be incorrectly lower-cased using toAsciiLower(...) rather than latin_tolower(...).
return (c >= 'A' && c <= 'Z');
}
static AK_FORCE_INLINE int toAsciiLower(int c) {
return c - 'A' + 'a';
}
static AK_FORCE_INLINE bool isAscii(int c) {
return isascii(c) != 0;
}
static AK_FORCE_INLINE int toLowerCase(const int c) {
if (isAsciiUpper(c)) {
return toAsciiLower(c);
}
if (isAscii(c)) {
return c;
}
return static_cast<int>(latin_tolower(static_cast<unsigned short>(c)));
}
static AK_FORCE_INLINE int toBaseLowerCase(const int c) {
return toLowerCase(toBaseCodePoint(c));
}
static AK_FORCE_INLINE bool isIntentionalOmissionCodePoint(const int codePoint) {
// TODO: Do not hardcode here
return codePoint == KEYCODE_SINGLE_QUOTE || codePoint == KEYCODE_HYPHEN_MINUS;
}
static AK_FORCE_INLINE int getCodePointCount(const int arraySize, const int *const codePoints) {
int size = 0;
for (; size < arraySize; ++size) {
if (codePoints[size] == '\0') {
break;
}
}
return size;
}
static AK_FORCE_INLINE int toBaseCodePoint(int c) {
if (c < BASE_CHARS_SIZE) {
return static_cast<int>(BASE_CHARS[c]);
}
return c;
}
static AK_FORCE_INLINE int getSpaceCount(const int *const codePointBuffer, const int length) {
int spaceCount = 0;
for (int i = 0; i < length; ++i) {
if (codePointBuffer[i] == KEYCODE_SPACE) {
++spaceCount;
}
}
return spaceCount;
}
static unsigned short latin_tolower(const unsigned short c);
private:
DISALLOW_IMPLICIT_CONSTRUCTORS(CharUtils);
/**
* Table mapping most combined Latin, Greek, and Cyrillic characters
* to their base characters. If c is in range, BASE_CHARS[c] == c
* if c is not a combined character, or the base character if it
* is combined.
*/
static const int BASE_CHARS_SIZE = 0x0500;
static const unsigned short BASE_CHARS[BASE_CHARS_SIZE];
};
} // namespace latinime
#endif // LATINIME_CHAR_UTILS_H
|
