1 #ifndef __DALI_TOOLKIT_TEXT_ABSTRACTION_SCRIPT_H__
2 #define __DALI_TOOLKIT_TEXT_ABSTRACTION_SCRIPT_H__
5 * Copyright (c) 2015 Samsung Electronics Co., Ltd.
7 * Licensed under the Apache License, Version 2.0 (the "License");
8 * you may not use this file except in compliance with the License.
9 * You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
22 #include <dali/public-api/common/dali-common.h>
25 #include <dali/devel-api/text-abstraction/text-abstraction-definitions.h>
30 namespace TextAbstraction
34 * @brief Script is the writing system used by a language.
35 * Typically one script can be used to write different languages although one language could be written in different scrips.
39 COMMON, ///< Valid for all scripts. i.e white space or '\n'.
41 ASCII_DIGITS, ///< ASCII digits.
42 ASCII_PS, ///< ASCII punctuation and symbols.
44 C1_CONTROLS, ///< Controls of the C1 Controls and Latin-1 Supplement unicode block.
45 C1_PS, ///< Punctuation and symbols of the C1 Controls and Latin-1 Supplement unicode block.
46 C1_MATH, ///< Math symbols of the C1 Controls and Latin-1 Supplement unicode block.
48 SML_P, ///< Punctuation symbols of the Spacing Modifier Letters unicode block.
49 PHONETIC_U, ///< Uralic phonetic symbols of the Phonetic Extensions unicode block.
50 PHONETIC_SS, ///< Subscripts and superscripts of the Phonetic Extensions unicode block.
52 NUMERIC_SS, ///< Numeric subscripts and superscripts.
54 LETTER_LIKE, ///< Symbols of the Letterlike unicode block.
55 NUMBER_FORMS, ///< Number Forms unicode block.
56 FRACTIONS_NF, ///< Numeric fraction symbols of the Number Forms unicode block.
57 NON_LATIN_LED, ///< Non latin symbols within the Latin Extended D unicode block.
58 HWFW_S, ///< Non latin symbols within the Halfwidth and fullwidth unicode block.
60 CYRILLIC, ///< The Cyrillic script. Used by Russian, Bulgarian, Ukrainian, Macedonian, ...
61 GREEK, ///< The Greek script. Used by Greek.
62 LATIN, ///< The latin script. Used by many western languages and others around the world.
64 ARABIC, ///< The arabic script. Used by Arab and Urdu among others.
65 HEBREW, ///< The Hebrew script. Used by the Hebrew, Yiddish, Ladino, and Judeo-Arabic.
67 ARMENIAN, ///< The Armenian script. Used by Armenian.
68 GEORGIAN, ///< The Georgian script. Used by Georgian.
70 CJK, ///< The CJK script. Used by Chinese, Japanese, Korean and Vietnamese(old writing system).
71 HANGUL, ///< The Hangul jamo script. Used by Korean.
72 HIRAGANA, ///< The Hiragana script. Used by the Japanese.
73 KATAKANA, ///< The Katakana script. Used by the Japanese.
74 BOPOMOFO, ///< The Bopomofo script. Also called Zhuyin fuhao or Zhuyin. A phonetic notation used for the transcription of spoken Chinese.
76 BENGALI, ///< The Bengali script. Used by Bangla, Assamese, Bishnupriya Manipuri, Daphla, Garo, Hallam, Khasi, Mizo, Munda, Naga, Rian, and Santali.
77 BURMESE, ///< The Burmese script. Used by the Burmese (Myanmar) language.
78 DEVANAGARI, ///< The devanagari script. Used by Hindi, Marathi, Sindhi, Nepali and Sanskrit.
79 GUJARATI, ///< The Gujarati script. Used by Gujarati.
80 GURMUKHI, ///< The Gurmukhi script. Used by Punjabi.
81 KANNADA, ///< The Kannada script. Used by Kannada and Tulu.
82 MALAYALAM, ///< The Malayalam script. Used by Malayalam.
83 ORIYA, ///< The Oriya script. Used by Oriya (Odia), Khondi, and Santali.
84 SINHALA, ///< The Sinhala script. Used by Sinhala and Pali.
85 TAMIL, ///< The Tamil script. Used by Tamil, Badaga, and Saurashtra.
86 TELUGU, ///< The Telugu script. Used by Telugu, Gondi, and Lambadi.
88 LAO, ///< The Lao script. Used by the Lao language.
89 THAI, ///< The Thai script. Used by the Thai language
90 KHMER, ///< The Khmer script. Used by the Khmer language.
91 JAVANESE, ///< The Javanese script. Used by the Javanese language.
92 SUNDANESE, ///< The Sundanese script. Used by the Sundanese language.
94 GEEZ, ///< The Ge'ez script. Used by the Amharic, Tigrinya and other languages in Ethiopia and Eritrea.
95 OL_CHIKI, ///< The Ol Chiki script. Used by the Santali.
96 BAYBAYIN, ///< The Baybayin script. Used by the Tagalog, Bikol languages, Ilocano, Pangasinan, Visayan and other languages in Philippines.
97 MEITEI, ///< The Meitei script used for the Meitei language in Manipur, India.
99 EMOJI, ///< The Emoji which map to standardized Unicode characters.
101 SYMBOLS1, ///< Some symbols.
102 SYMBOLS2, ///< Some symbols.
103 SYMBOLS3, ///< Some symbols.
104 SYMBOLS4, ///< Some symbols.
105 SYMBOLS5, ///< Some symbols.
107 UNKNOWN ///< The script is unknown.
110 const char* const ScriptName[] =
112 "COMMON", ///< Valid for all scripts. i.e white space or '\n'.
114 "ASCII_DIGITS", ///< ASCII digits.
115 "ASCII_PS", ///< ASCII punctuation and symbols.
117 "C1_CONTROLS", ///< Controls of the C1 Controls and Latin-1 Supplement unicode block.
118 "C1_PS", ///< Punctuation and symbols of the C1 Controls and Latin-1 Supplement unicode block.
119 "C1_MATH", ///< Math symbols of the C1 Controls and Latin-1 Supplement unicode block.
121 "SML_P", ///< Punctuation symbols of the Spacing Modifier Letters unicode block.
122 "PHONETIC_U", ///< Uralic phonetic symbols of the Phonetic Extensions unicode block.
123 "PHONETIC_SS", ///< Subscripts and superscripts of the Phonetic Extensions unicode block.
125 "NUMERIC_SS", ///< Numeric subscripts and superscripts.
127 "LETTER_LIKE", ///< Symbols of the Letterlike unicode block.
128 "NUMBER_FORMS", ///< Number Forms unicode block.
129 "FRACTIONS_NF", ///< Numeric fraction symbols of the Number Forms unicode block.
130 "NON_LATIN_LED", ///< Non latin symbols within the Latin Extended D unicode block.
131 "HWFW_S", ///< Non latin symbols within the Halfwidth and fullwidth unicode block.
133 "CYRILLIC", ///< The Cyrillic script. Used by Russian, Bulgarian, Ukrainian, Macedonian, ...
134 "GREEK", ///< The Greek script. Used by Greek.
135 "LATIN", ///< The latin script. Used by many western languages and others around the world.
137 "ARABIC", ///< The arabic script. Used by Arab and Urdu among others.
138 "HEBREW", ///< The Hebrew script. Used by the Hebrew, Yiddish, Ladino, and Judeo-Arabic.
140 "ARMENIAN", ///< The Armenian script. Used by Armenian.
141 "GEORGIAN", ///< The Georgian script. Used by Georgian.
143 "CJK", ///< The CJK script. Used by Chinese, Japanese, Korean and Vietnamese(old writing system).
144 "HANGUL", ///< The Hangul jamo script. Used by Korean.
145 "HIRAGANA", ///< The Hiragana script. Used by the Japanese.
146 "KATAKANA", ///< The Katakana script. Used by the Japanese.
147 "BOPOMOFO", ///< The Bopomofo script. Also called Zhuyin fuhao or Zhuyin. A phonetic notation used for the transcription of spoken Chinese.
149 "BENGALI", ///< The Bengali script. Used by Bangla, Assamese, Bishnupriya Manipuri, Daphla, Garo, Hallam, Khasi, Mizo, Munda, Naga, Rian, and Santali.
150 "BURMESE", ///< The Burmese script. Used by the Burmese (Myanmar) language.
151 "DEVANAGARI", ///< The devanagari script. Used by Hindi, Marathi, Sindhi, Nepali and Sanskrit.
152 "GUJARATI", ///< The Gujarati script. Used by Gujarati.
153 "GURMUKHI", ///< The Gurmukhi script. Used by Punjabi.
154 "KANNADA", ///< The Kannada script. Used by Kannada and Tulu.
155 "MALAYALAM", ///< The Malayalam script. Used by Malayalam.
156 "ORIYA", ///< The Oriya script. Used by Oriya (Odia), Khondi, and Santali.
157 "SINHALA", ///< The Sinhala script. Used by Sinhala and Pali.
158 "TAMIL", ///< The Tamil script. Used by Tamil, Badaga, and Saurashtra.
159 "TELUGU", ///< The Telugu script. Used by Telugu, Gondi, and Lambadi.
161 "LAO", ///< The Lao script. Used by the Lao language.
162 "THAI", ///< The Thai script. Used by the Thai language
163 "KHMER", ///< The Khmer script. Used by the Khmer language.
164 "JAVANESE", ///< The Javanese script. Used by the Javanese language.
165 "SUNDANESE", ///< The Sundanese script. Used by the Sundanese language.
167 "GEEZ", ///< The Ge'ez script also known as Ethiopic. Used by the Amharic, Tigrinya and other languages in Ethiopia and Eritrea.
168 "OL_CHIKI", ///< The Ol Chiki script. Used by the Santali.
169 "BAYBAYIN", ///< The Baybayin script. Used by the Tagalog, Bikol languages, Ilocano, Pangasinan, Visayan and other languages in Philippines.
170 "MEITEI", ///< The Meitei script used for the Meitei language in Manipur, India.
172 "EMOJI", ///< The Emoji which map to standardized Unicode characters.
174 "SYMBOLS1", ///< Some symbols.
175 "SYMBOLS2", ///< Some symbols.
176 "SYMBOLS3", ///< Some symbols.
177 "SYMBOLS4", ///< Some symbols.
178 "SYMBOLS5", ///< Some symbols.
180 "UNKNOWN" ///< The script is unknown.
184 * @brief Whether the script is a right to left script.
186 * @param[in] script The script.
188 * @return @e true if the script is right to left.
190 DALI_IMPORT_API bool IsRightToLeftScript( Script script );
193 * @brief Retrieves a character's script.
195 * @param[in] character The character.
197 * @return The chraracter's script.
199 DALI_IMPORT_API Script GetCharacterScript( Character character );
202 * @brief Whether the character is a white space.
204 * @param[in] character The character.
206 * @return @e true if the character is a white space.
208 DALI_IMPORT_API bool IsWhiteSpace( Character character );
211 * @brief Whether the character is a new paragraph character.
213 * @param[in] character The character.
215 * @return @e true if the character is a new paragraph character.
217 DALI_IMPORT_API bool IsNewParagraph( Character character );
220 * @brief Whether the character is a zero width non joiner.
222 * @param[in] character The character.
224 * @return @e true if the character is a zero width non joiner.
226 DALI_IMPORT_API bool IsZeroWidthNonJoiner( Character character );
229 * @brief Whether the character is a zero width joiner.
231 * @param[in] character The character.
233 * @return @e true if the character is a zero width joiner.
235 DALI_IMPORT_API bool IsZeroWidthJoiner( Character character );
238 * @brief Whether the character is a zero width space.
240 * @param[in] character The character.
242 * @return @e true if the character is a zero width space.
244 DALI_IMPORT_API bool IsZeroWidthSpace( Character character );
247 * @brief Whether the character is a left to right mark.
249 * @param[in] character The character.
251 * @return @e true if the character is a left to right mark.
253 DALI_IMPORT_API bool IsLeftToRightMark( Character character );
256 * @brief Whether the character is a right to left mark.
258 * @param[in] character The character.
260 * @return @e true if the character is a right to left mark.
262 DALI_IMPORT_API bool IsRightToLeftMark( Character character );
265 * @brief Whether the character is a thin space.
267 * @param[in] character The character.
269 * @return @e true if the character is a thin space.
271 DALI_IMPORT_API bool IsThinSpace( Character character );
274 * @brief Whether the character is common within all scripts.
276 * @param[in] character The character.
278 * @return @e true if the character is common within all scripts.
280 DALI_IMPORT_API bool IsCommonScript( Character character );
283 * @brief Whether the script contains ligatures that must be 'broken' for selection or cursor position.
285 * i.e The latin script has the 'ff' or 'fi' ligatures that need to be broken to position the cursor
286 * between the two characters. Equally the arabic script has the 'ﻻ' ligature that needs to be broken.
288 * @param[in] script The script.
290 * @return @e true if the script has ligatures that must be 'broken'.
292 DALI_IMPORT_API bool HasLigatureMustBreak( Script script );
293 } // namespace TextAbstraction
297 #endif // __DALI_TOOLKIT_TEXT_ABSTRACTION_SCRIPT_H__