xref: /aosp_15_r20/external/skia/modules/skunicode/src/SkUnicode_hardcoded.cpp (revision c8dee2aa9b3f27cf6c858bd81872bdeb2c07ed17)
1 /*
2  * Copyright 2023 Google Inc.
3  *
4  * Use of this source code is governed by a BSD-style license that can be
5  * found in the LICENSE file.
6  */
7 
8 #include "include/private/base/SkDebug.h"
9 #include "modules/skunicode/src/SkUnicode_hardcoded.h"
10 #include <algorithm>
11 #include <array>
12 #include <utility>
13 
isControl(SkUnichar utf8)14 bool SkUnicodeHardCodedCharProperties::isControl(SkUnichar utf8) {
15     return (utf8 < ' ') || (utf8 >= 0x7f && utf8 <= 0x9f) ||
16            (utf8 >= 0x200D && utf8 <= 0x200F) ||
17            (utf8 >= 0x202A && utf8 <= 0x202E);
18 }
19 
isWhitespace(SkUnichar unichar)20 bool SkUnicodeHardCodedCharProperties::isWhitespace(SkUnichar unichar) {
21     static constexpr std::array<SkUnichar, 21> whitespaces {
22             0x0009, // character tabulation
23             0x000A, // line feed
24             0x000B, // line tabulation
25             0x000C, // form feed
26             0x000D, // carriage return
27             0x0020, // space
28           //0x0085, // next line
29           //0x00A0, // no-break space
30             0x1680, // ogham space mark
31             0x2000, // en quad
32             0x2001, // em quad
33             0x2002, // en space
34             0x2003, // em space
35             0x2004, // three-per-em space
36             0x2005, // four-per-em space
37             0x2006, // six-per-em space
38           //0x2007, // figure space
39             0x2008, // punctuation space
40             0x2009, // thin space
41             0x200A, // hair space
42             0x2028, // line separator
43             0x2029, // paragraph separator
44           //0x202F, // narrow no-break space
45             0x205F, // medium mathematical space
46             0x3000};// ideographic space
47     return std::find(whitespaces.begin(), whitespaces.end(), unichar) != whitespaces.end();
48 }
49 
isSpace(SkUnichar unichar)50 bool SkUnicodeHardCodedCharProperties::isSpace(SkUnichar unichar) {
51     static constexpr std::array<SkUnichar, 25> spaces {
52             0x0009, // character tabulation
53             0x000A, // line feed
54             0x000B, // line tabulation
55             0x000C, // form feed
56             0x000D, // carriage return
57             0x0020, // space
58             0x0085, // next line
59             0x00A0, // no-break space
60             0x1680, // ogham space mark
61             0x2000, // en quad
62             0x2001, // em quad
63             0x2002, // en space
64             0x2003, // em space
65             0x2004, // three-per-em space
66             0x2005, // four-per-em space
67             0x2006, // six-per-em space
68             0x2007, // figure space
69             0x2008, // punctuation space
70             0x2009, // thin space
71             0x200A, // hair space
72             0x2028, // line separator
73             0x2029, // paragraph separator
74             0x202F, // narrow no-break space
75             0x205F, // medium mathematical space
76             0x3000}; // ideographic space
77     return std::find(spaces.begin(), spaces.end(), unichar) != spaces.end();
78 }
79 
isTabulation(SkUnichar utf8)80 bool SkUnicodeHardCodedCharProperties::isTabulation(SkUnichar utf8) {
81     return utf8 == '\t';
82 }
83 
isHardBreak(SkUnichar utf8)84 bool SkUnicodeHardCodedCharProperties::isHardBreak(SkUnichar utf8) {
85     return utf8 == '\n' || utf8 == u'\u2028';
86 }
87 
isEmoji(SkUnichar unichar)88 bool SkUnicodeHardCodedCharProperties::isEmoji(SkUnichar unichar) {
89     SkDEBUGFAIL("isEmoji Not implemented");
90     return false;
91 }
92 
isEmojiComponent(SkUnichar utf8)93 bool SkUnicodeHardCodedCharProperties::isEmojiComponent(SkUnichar utf8)  {
94     SkDEBUGFAIL("isEmojiComponent Not implemented");
95     return false;
96 }
97 
isEmojiModifier(SkUnichar utf8)98 bool SkUnicodeHardCodedCharProperties::isEmojiModifier(SkUnichar utf8)  {
99     SkDEBUGFAIL("isEmojiModifier Not implemented");
100     return false;
101 }
102 
isEmojiModifierBase(SkUnichar utf8)103 bool SkUnicodeHardCodedCharProperties::isEmojiModifierBase(SkUnichar utf8) {
104     SkDEBUGFAIL("isEmojiModifierBase Not implemented");
105     return false;
106 }
107 
isRegionalIndicator(SkUnichar unichar)108 bool SkUnicodeHardCodedCharProperties::isRegionalIndicator(SkUnichar unichar) {
109     SkDEBUGFAIL("isRegionalIndicator Not implemented");
110     return false;
111 }
112 
isIdeographic(SkUnichar unichar)113 bool SkUnicodeHardCodedCharProperties::isIdeographic(SkUnichar unichar) {
114     static constexpr std::array<std::pair<SkUnichar, SkUnichar>, 8> ranges {{
115           {4352,   4607}, // Hangul Jamo
116           {11904, 42191}, // CJK_Radicals
117           {43072, 43135}, // Phags_Pa
118           {44032, 55215}, // Hangul_Syllables
119           {63744, 64255}, // CJK_Compatibility_Ideographs
120           {65072, 65103}, // CJK_Compatibility_Forms
121           {65381, 65500}, // Katakana_Hangul_Halfwidth
122           {131072, 196607}// Supplementary_Ideographic_Plane
123     }};
124     for (auto range : ranges) {
125         if (range.first <= unichar && range.second > unichar) {
126             return true;
127         }
128     }
129     return false;
130 }
131