1 #ifndef _UNICODE_CHAR_H_
2 #define _UNICODE_CHAR_H_
3
4 #include <SupportDefs.h>
5
6 enum unicode_char_category
7 {
8 // Non-category for unassigned and non-character code points.
9 B_UNICODE_UNASSIGNED = 0,
10
11 B_UNICODE_GENERAL_OTHER_TYPES = 0, // Cn
12 B_UNICODE_UPPERCASE_LETTER = 1, // Lu
13 B_UNICODE_LOWERCASE_LETTER = 2, // Ll
14 B_UNICODE_TITLECASE_LETTER = 3, // Lt
15 B_UNICODE_MODIFIER_LETTER = 4, // Lm
16 B_UNICODE_OTHER_LETTER = 5, // Lo
17 B_UNICODE_NON_SPACING_MARK = 6, // Mn
18 B_UNICODE_ENCLOSING_MARK = 7, // Me
19 B_UNICODE_COMBINING_SPACING_MARK = 8, // Mc
20 B_UNICODE_DECIMAL_DIGIT_NUMBER = 9, // Nd
21 B_UNICODE_LETTER_NUMBER = 10, // Nl
22 B_UNICODE_OTHER_NUMBER = 11, // No
23 B_UNICODE_SPACE_SEPARATOR = 12, // Zs
24 B_UNICODE_LINE_SEPARATOR = 13, // Zl
25 B_UNICODE_PARAGRAPH_SEPARATOR = 14, // Zp
26 B_UNICODE_CONTROL_CHAR = 15, // Cc
27 B_UNICODE_FORMAT_CHAR = 16, // Cf
28 B_UNICODE_PRIVATE_USE_CHAR = 17, // Co
29 B_UNICODE_SURROGATE = 18, // Cs
30 B_UNICODE_DASH_PUNCTUATION = 19, // Pd
31 B_UNICODE_START_PUNCTUATION = 20, // Ps
32 B_UNICODE_END_PUNCTUATION = 21, // Pe
33 B_UNICODE_CONNECTOR_PUNCTUATION = 22, // Pc
34 B_UNICODE_OTHER_PUNCTUATION = 23, // Po
35 B_UNICODE_MATH_SYMBOL = 24, // Sm
36 B_UNICODE_CURRENCY_SYMBOL = 25, // Sc
37 B_UNICODE_MODIFIER_SYMBOL = 26, // Sk
38 B_UNICODE_OTHER_SYMBOL = 27, // So
39 B_UNICODE_INITIAL_PUNCTUATION = 28, // Pi
40 B_UNICODE_FINAL_PUNCTUATION = 29, // Pf
41
42 B_UNICODE_CATEGORY_COUNT
43 };
44
45
46 // This specifies the language directional property of a character set.
47
48 enum unicode_char_direction {
49 B_UNICODE_LEFT_TO_RIGHT = 0,
50 B_UNICODE_RIGHT_TO_LEFT = 1,
51 B_UNICODE_EUROPEAN_NUMBER = 2,
52 B_UNICODE_EUROPEAN_NUMBER_SEPARATOR = 3,
53 B_UNICODE_EUROPEAN_NUMBER_TERMINATOR = 4,
54 B_UNICODE_ARABIC_NUMBER = 5,
55 B_UNICODE_COMMON_NUMBER_SEPARATOR = 6,
56 B_UNICODE_BLOCK_SEPARATOR = 7,
57 B_UNICODE_SEGMENT_SEPARATOR = 8,
58 B_UNICODE_WHITE_SPACE_NEUTRAL = 9,
59 B_UNICODE_OTHER_NEUTRAL = 10,
60 B_UNICODE_LEFT_TO_RIGHT_EMBEDDING = 11,
61 B_UNICODE_LEFT_TO_RIGHT_OVERRIDE = 12,
62 B_UNICODE_RIGHT_TO_LEFT_ARABIC = 13,
63 B_UNICODE_RIGHT_TO_LEFT_EMBEDDING = 14,
64 B_UNICODE_RIGHT_TO_LEFT_OVERRIDE = 15,
65 B_UNICODE_POP_DIRECTIONAL_FORMAT = 16,
66 B_UNICODE_DIR_NON_SPACING_MARK = 17,
67 B_UNICODE_BOUNDARY_NEUTRAL = 18,
68
69 B_UNICODE_DIRECTION_COUNT
70 };
71
72
73 // Script range as defined in the Unicode standard.
74
75 enum unicode_char_script {
76 // New No_Block value in Unicode 4.
77 B_UNICODE_NO_BLOCK = 0, // [none] Special range
78 B_UNICODE_BASIC_LATIN = 1, // [0000]
79 B_UNICODE_LATIN_1_SUPPLEMENT = 2, // [0080]
80 B_UNICODE_LATIN_EXTENDED_A = 3, // [0100]
81 B_UNICODE_LATIN_EXTENDED_B = 4, // [0180]
82 B_UNICODE_IPA_EXTENSIONS = 5, // [0250]
83 B_UNICODE_SPACING_MODIFIER_LETTERS = 6, // [02B0]
84 B_UNICODE_COMBINING_DIACRITICAL_MARKS = 7, // [0300]
85 B_UNICODE_GREEK = 8, // [0370]
86 B_UNICODE_CYRILLIC = 9, // [0400]
87 B_UNICODE_ARMENIAN = 10, // [0530]
88 B_UNICODE_HEBREW = 11, // [0590]
89 B_UNICODE_ARABIC = 12, // [0600]
90 B_UNICODE_SYRIAC = 13, // [0700]
91 B_UNICODE_THAANA = 14, // [0780]
92 B_UNICODE_DEVANAGARI = 15, // [0900]
93 B_UNICODE_BENGALI = 16, // [0980]
94 B_UNICODE_GURMUKHI = 17, // [0A00]
95 B_UNICODE_GUJARATI = 18, // [0A80]
96 B_UNICODE_ORIYA = 19, // [0B00]
97 B_UNICODE_TAMIL = 20, // [0B80]
98 B_UNICODE_TELUGU = 21, // [0C00]
99 B_UNICODE_KANNADA = 22, // [0C80]
100 B_UNICODE_MALAYALAM = 23, // [0D00]
101 B_UNICODE_SINHALA = 24, // [0D80]
102 B_UNICODE_THAI = 25, // [0E00]
103 B_UNICODE_LAO = 26, // [0E80]
104 B_UNICODE_TIBETAN = 27, // [0F00]
105 B_UNICODE_MYANMAR = 28, // [1000]
106 B_UNICODE_GEORGIAN = 29, // [10A0]
107 B_UNICODE_HANGUL_JAMO = 30, // [1100]
108 B_UNICODE_ETHIOPIC = 31, // [1200]
109 B_UNICODE_CHEROKEE = 32, // [13A0]
110 B_UNICODE_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 33, // [1400]
111 B_UNICODE_OGHAM = 34, // [1680]
112 B_UNICODE_RUNIC = 35, // [16A0]
113 B_UNICODE_KHMER = 36, // [1780]
114 B_UNICODE_MONGOLIAN = 37, // [1800]
115 B_UNICODE_LATIN_EXTENDED_ADDITIONAL = 38, // [1E00]
116 B_UNICODE_GREEK_EXTENDED = 39, // [1F00]
117 B_UNICODE_GENERAL_PUNCTUATION = 40, // [2000]
118 B_UNICODE_SUPERSCRIPTS_AND_SUBSCRIPTS = 41, // [2070]
119 B_UNICODE_CURRENCY_SYMBOLS = 42, // [20A0]
120 B_UNICODE_COMBINING_MARKS_FOR_SYMBOLS = 43, // [20D0]
121 B_UNICODE_LETTERLIKE_SYMBOLS = 44, // [2100]
122 B_UNICODE_NUMBER_FORMS = 45, // [2150]
123 B_UNICODE_ARROWS = 46, // [2190]
124 B_UNICODE_MATHEMATICAL_OPERATORS = 47, // [2200]
125 B_UNICODE_MISCELLANEOUS_TECHNICAL = 48, // [2300]
126 B_UNICODE_CONTROL_PICTURES = 49, // [2400]
127 B_UNICODE_OPTICAL_CHARACTER_RECOGNITION = 50, // [2440]
128 B_UNICODE_ENCLOSED_ALPHANUMERICS = 51, // [2460]
129 B_UNICODE_BOX_DRAWING = 52, // [2500]
130 B_UNICODE_BLOCK_ELEMENTS = 53, // [2580]
131 B_UNICODE_GEOMETRIC_SHAPES = 54, // [25A0]
132 B_UNICODE_MISCELLANEOUS_SYMBOLS = 55, // [2600]
133 B_UNICODE_DINGBATS = 56, // [2700]
134 B_UNICODE_BRAILLE_PATTERNS = 57, // [2800]
135 B_UNICODE_CJK_RADICALS_SUPPLEMENT = 58, // [2E80]
136 B_UNICODE_KANGXI_RADICALS = 59, // [2F00]
137 B_UNICODE_IDEOGRAPHIC_DESCRIPTION_CHARACTERS = 60, // [2FF0]
138 B_UNICODE_CJK_SYMBOLS_AND_PUNCTUATION = 61, // [3000]
139 B_UNICODE_HIRAGANA = 62, // [3040]
140 B_UNICODE_KATAKANA = 63, // [30A0]
141 B_UNICODE_BOPOMOFO = 64, // [3100]
142 B_UNICODE_HANGUL_COMPATIBILITY_JAMO = 65, // [3130]
143 B_UNICODE_KANBUN = 66, // [3190]
144 B_UNICODE_BOPOMOFO_EXTENDED = 67, // [31A0]
145 B_UNICODE_ENCLOSED_CJK_LETTERS_AND_MONTHS = 68, // [3200]
146 B_UNICODE_CJK_COMPATIBILITY = 69, // [3300]
147 B_UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 70, // [3400]
148 B_UNICODE_CJK_UNIFIED_IDEOGRAPHS = 71, // [4E00]
149 B_UNICODE_YI_SYLLABLES = 72, // [A000]
150 B_UNICODE_YI_RADICALS = 73, // [A490]
151 B_UNICODE_HANGUL_SYLLABLES = 74, // [AC00]
152 B_UNICODE_HIGH_SURROGATES = 75, // [D800]
153 B_UNICODE_HIGH_PRIVATE_USE_SURROGATES = 76, // [DB80]
154 B_UNICODE_LOW_SURROGATES = 77, // [DC00]
155 B_UNICODE_PRIVATE_USE = 78,
156 B_UNICODE_PRIVATE_USE_AREA = B_UNICODE_PRIVATE_USE, // [E000]
157 B_UNICODE_CJK_COMPATIBILITY_IDEOGRAPHS = 79, // [F900]
158 B_UNICODE_ALPHABETIC_PRESENTATION_FORMS = 80, // [FB00]
159 B_UNICODE_ARABIC_PRESENTATION_FORMS_A = 81, // [FB50]
160 B_UNICODE_COMBINING_HALF_MARKS = 82, // [FE20]
161 B_UNICODE_CJK_COMPATIBILITY_FORMS = 83, // [FE30]
162 B_UNICODE_SMALL_FORM_VARIANTS = 84, // [FE50]
163 B_UNICODE_ARABIC_PRESENTATION_FORMS_B = 85, // [FE70]
164 B_UNICODE_SPECIALS = 86, // [FFF0]
165 B_UNICODE_HALFWIDTH_AND_FULLWIDTH_FORMS = 87, // [FF00]
166
167 // New blocks in Unicode 3.1
168 B_UNICODE_OLD_ITALIC = 88, // [10300]
169 B_UNICODE_GOTHIC = 89, // [10330]
170 B_UNICODE_DESERET = 90, // [10400]
171 B_UNICODE_BYZANTINE_MUSICAL_SYMBOLS = 91, // [1D000]
172 B_UNICODE_MUSICAL_SYMBOLS = 92, // [1D100]
173 B_UNICODE_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, // [1D400]
174 B_UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, // [20000]
175 B_UNICODE_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, // [2F800]
176 B_UNICODE_TAGS = 96, // [E0000]
177
178 // New blocks in Unicode
179 B_UNICODE_CYRILLIC_SUPPLEMENTARY = 97,
180 B_UNICODE_CYRILLIC_SUPPLEMENT = B_UNICODE_CYRILLIC_SUPPLEMENTARY, // [0500]
181 B_UNICODE_TAGALOG = 98, // [1700]
182 B_UNICODE_HANUNOO = 99, // [1720]
183 B_UNICODE_BUHID = 100, // [1740]
184 B_UNICODE_TAGBANWA = 101, // [1760]
185 B_UNICODE_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, // [27C0]
186 B_UNICODE_SUPPLEMENTAL_ARROWS_A = 103, // [27F0]
187 B_UNICODE_SUPPLEMENTAL_ARROWS_B = 104, // [2900]
188 B_UNICODE_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, // [2980]
189 B_UNICODE_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, // [2A00]
190 B_UNICODE_KATAKANA_PHONETIC_EXTENSIONS = 107, // [31F0]
191 B_UNICODE_VARIATION_SELECTORS = 108, // [FE00]
192 B_UNICODE_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, // [F0000]
193 B_UNICODE_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, // [100000]
194
195 // New blocks in Unicode 4
196 B_UNICODE_LIMBU = 111, // [1900]
197 B_UNICODE_TAI_LE = 112, // [1950]
198 B_UNICODE_KHMER_SYMBOLS = 113, // [19E0]
199 B_UNICODE_PHONETIC_EXTENSIONS = 114, // [1D00]
200 B_UNICODE_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, // [2B00]
201 B_UNICODE_YIJING_HEXAGRAM_SYMBOLS = 116, // [4DC0]
202 B_UNICODE_LINEAR_B_SYLLABARY = 117, // [10000]
203 B_UNICODE_LINEAR_B_IDEOGRAMS = 118, // [10080]
204 B_UNICODE_AEGEAN_NUMBERS = 119, // [10100]
205 B_UNICODE_UGARITIC = 120, // [10380]
206 B_UNICODE_SHAVIAN = 121, // [10450]
207 B_UNICODE_OSMANYA = 122, // [10480]
208 B_UNICODE_CYPRIOT_SYLLABARY = 123, // [10800]
209 B_UNICODE_TAI_XUAN_JING_SYMBOLS = 124, // [1D300]
210 B_UNICODE_VARIATION_SELECTORS_SUPPLEMENT = 125, // [E0100]
211
212 // New blocks in Unicode 4.1
213 B_UNICODE_ANCIENT_GREEK_MUSICAL_NOTATION = 126, // [1D200]
214 B_UNICODE_ANCIENT_GREEK_NUMBERS = 127, // [10140]
215 B_UNICODE_ARABIC_SUPPLEMENT = 128, // [0750]
216 B_UNICODE_BUGINESE = 129, // [1A00]
217 B_UNICODE_CJK_STROKES = 130, // [31C0]
218 B_UNICODE_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, // [1DC0]
219 B_UNICODE_COPTIC = 132, // [2C80]
220 B_UNICODE_ETHIOPIC_EXTENDED = 133, // [2D80]
221 B_UNICODE_ETHIOPIC_SUPPLEMENT = 134, // [1380]
222 B_UNICODE_GEORGIAN_SUPPLEMENT = 135, // [2D00]
223 B_UNICODE_GLAGOLITIC = 136, // [2C00]
224 B_UNICODE_KHAROSHTHI = 137, // [10A00]
225 B_UNICODE_MODIFIER_TONE_LETTERS = 138, // [A700]
226 B_UNICODE_NEW_TAI_LUE = 139, // [1980]
227 B_UNICODE_OLD_PERSIAN = 140, // [103A0]
228 B_UNICODE_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, // [1D80]
229 B_UNICODE_SUPPLEMENTAL_PUNCTUATION = 142, // [2E00]
230 B_UNICODE_SYLOTI_NAGRI = 143, // [A800]
231 B_UNICODE_TIFINAGH = 144, // [2D30]
232 B_UNICODE_VERTICAL_FORMS = 145, // [FE10]
233
234 // New blocks in Unicode 5.0
235 B_UNICODE_NKO = 146, // [07C0]
236 B_UNICODE_BALINESE = 147, // [1B00]
237 B_UNICODE_LATIN_EXTENDED_C = 148, // [2C60]
238 B_UNICODE_LATIN_EXTENDED_D = 149, // [A720]
239 B_UNICODE_PHAGS_PA = 150, // [A840]
240 B_UNICODE_PHOENICIAN = 151, // [10900]
241 B_UNICODE_CUNEIFORM = 152, // [12000]
242 B_UNICODE_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, // [12400]
243 B_UNICODE_COUNTING_ROD_NUMERALS = 154, // [1D360]
244
245 // New blocks in Unicode 5.1
246 B_UNICODE_SUNDANESE = 155, // [1B80]
247 B_UNICODE_LEPCHA = 156, // [1C00]
248 B_UNICODE_OL_CHIKI = 157, // [1C50]
249 B_UNICODE_CYRILLIC_EXTENDED_A = 158, // [2DE0]
250 B_UNICODE_VAI = 159, // [A500]
251 B_UNICODE_CYRILLIC_EXTENDED_B = 160, // [A640]
252 B_UNICODE_SAURASHTRA = 161, // [A880]
253 B_UNICODE_KAYAH_LI = 162, // [A900]
254 B_UNICODE_REJANG = 163, // [A930]
255 B_UNICODE_CHAM = 164, // [AA00]
256 B_UNICODE_ANCIENT_SYMBOLS = 165, // [10190]
257 B_UNICODE_PHAISTOS_DISC = 166, // [101D0]
258 B_UNICODE_LYCIAN = 167, // [10280]
259 B_UNICODE_CARIAN = 168, // [102A0]
260 B_UNICODE_LYDIAN = 169, // [10920]
261 B_UNICODE_MAHJONG_TILES = 170, // [1F000]
262 B_UNICODE_DOMINO_TILES = 171, // [1F030]
263
264 // New blocks in Unicode 5.2
265 B_UNICODE_SAMARITAN = 172, // [0800]
266 B_UNICODE_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, // [18B0]
267 B_UNICODE_TAI_THAM = 174, // [1A20]
268 B_UNICODE_VEDIC_EXTENSIONS = 175, // [1CD0]
269 B_UNICODE_LISU = 176, // [A4D0]
270 B_UNICODE_BAMUM = 177, // [A6A0]
271 B_UNICODE_COMMON_INDIC_NUMBER_FORMS = 178, // [A830]
272 B_UNICODE_DEVANAGARI_EXTENDED = 179, // [A8E0]
273 B_UNICODE_HANGUL_JAMO_EXTENDED_A = 180, // [A960]
274 B_UNICODE_JAVANESE = 181, // [A980]
275 B_UNICODE_MYANMAR_EXTENDED_A = 182, // [AA60]
276 B_UNICODE_TAI_VIET = 183, // [AA80]
277 B_UNICODE_MEETEI_MAYEK = 184, // [ABC0]
278 B_UNICODE_HANGUL_JAMO_EXTENDED_B = 185, // [D7B0]
279 B_UNICODE_IMPERIAL_ARAMAIC = 186, // [10840]
280 B_UNICODE_OLD_SOUTH_ARABIAN = 187, // [10A60]
281 B_UNICODE_AVESTAN = 188, // [10B00]
282 B_UNICODE_INSCRIPTIONAL_PARTHIAN = 189, // [10B40]
283 B_UNICODE_INSCRIPTIONAL_PAHLAVI = 190, // [10B60]
284 B_UNICODE_OLD_TURKIC = 191, // [10C00]
285 B_UNICODE_RUMI_NUMERAL_SYMBOLS = 192, // [10E60]
286 B_UNICODE_KAITHI = 193, // [11080]
287 B_UNICODE_EGYPTIAN_HIEROGLYPHS = 194, // [13000]
288 B_UNICODE_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, // [1F100]
289 B_UNICODE_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, // [1F200]
290 B_UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, // [2A700]
291
292 // New blocks in Unicode 6.0
293 B_UNICODE_MANDAIC = 198, // [0840]
294 B_UNICODE_BATAK = 199, // [1BC0]
295 B_UNICODE_ETHIOPIC_EXTENDED_A = 200, // [AB00]
296 B_UNICODE_BRAHMI = 201, // [11000]
297 B_UNICODE_BAMUM_SUPPLEMENT = 202, // [16800]
298 B_UNICODE_KANA_SUPPLEMENT = 203, // [1B000]
299 B_UNICODE_PLAYING_CARDS = 204, // [1F0A0]
300 B_UNICODE_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, // [1F300]
301 B_UNICODE_EMOTICONS = 206, // [1F600]
302 B_UNICODE_TRANSPORT_AND_MAP_SYMBOLS = 207, // [1F680]
303 B_UNICODE_ALCHEMICAL_SYMBOLS = 208, // [1F700]
304 B_UNICODE_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, // [2B740]
305
306 B_UNICODE_SCRIPT_COUNT = 210,
307 B_UNICODE_NO_SCRIPT = B_UNICODE_SCRIPT_COUNT,
308
309 B_UNICODE_INVALID_CODE = -1
310 };
311
312
313 // East Asian Width constants.
314
315 enum unicode_east_asian_width
316 {
317 B_UNICODE_EA_NEUTRAL, // [N]
318 B_UNICODE_EA_AMBIGUOUS, // [A]
319 B_UNICODE_EA_HALFWIDTH, // [H]
320 B_UNICODE_EA_FULLWIDTH, // [F]
321 B_UNICODE_EA_NARROW, // [Na]
322 B_UNICODE_EA_WIDE, // [W]
323 B_UNICODE_EA_COUNT
324 };
325
326
327 class BUnicodeChar {
328 public:
329 static bool IsAlpha(uint32 c);
330 static bool IsAlNum(uint32 c);
331 static bool IsDigit(uint32 c);
332 static bool IsHexDigit(uint32 c);
333 static bool IsUpper(uint32 c);
334 static bool IsLower(uint32 c);
335 static bool IsSpace(uint32 c);
336 static bool IsWhitespace(uint32 c);
337 static bool IsControl(uint32 c);
338 static bool IsPunctuation(uint32 c);
339 static bool IsPrintable(uint32 c);
340 static bool IsTitle(uint32 c);
341 static bool IsDefined(uint32 c);
342 static bool IsBase(uint32 c);
343
344 static int8 Type(uint32 c);
345
346 static uint32 ToLower(uint32 c);
347 static uint32 ToUpper(uint32 c);
348 static uint32 ToTitle(uint32 c);
349 static int32 DigitValue(uint32 c);
350 static unicode_east_asian_width EastAsianWidth(uint32 c);
351
352 static void ToUTF8(uint32 c, char** out);
353 static uint32 FromUTF8(const char** in);
354 static uint32 FromUTF8(const char* in);
355
356 static size_t UTF8StringLength(const char* string);
357 static size_t UTF8StringLength(const char* string, size_t maxLength);
358
359 private:
360 BUnicodeChar();
361 };
362
363
364 inline uint32
FromUTF8(const char * in)365 BUnicodeChar::FromUTF8(const char* in)
366 {
367 const char* string = in;
368 return FromUTF8(&string);
369 }
370
371
372 #endif // _UNICODE_CHAR_H_
373