Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 1 | // © 2016 and later: Unicode, Inc. and others. |
| 2 | // License & terms of use: http://www.unicode.org/copyright.html |
| 3 | /* |
| 4 | ****************************************************************************** |
| 5 | * Copyright (C) 1996-2015, International Business Machines Corporation and others. |
| 6 | * All Rights Reserved. |
| 7 | ****************************************************************************** |
| 8 | */ |
| 9 | |
| 10 | #ifndef UBRK_H |
| 11 | #define UBRK_H |
| 12 | |
| 13 | #include "unicode/utypes.h" |
| 14 | #include "unicode/uloc.h" |
| 15 | #include "unicode/utext.h" |
Victor Chang | eaf32ab | 2020-08-20 15:50:49 +0100 | [diff] [blame] | 16 | |
| 17 | #if U_SHOW_CPLUSPLUS_API |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 18 | #include "unicode/localpointer.h" |
Victor Chang | eaf32ab | 2020-08-20 15:50:49 +0100 | [diff] [blame] | 19 | #endif // U_SHOW_CPLUSPLUS_API |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 20 | |
| 21 | /** |
| 22 | * A text-break iterator. |
| 23 | * For usage in C programs. |
| 24 | */ |
| 25 | #ifndef UBRK_TYPEDEF_UBREAK_ITERATOR |
| 26 | # define UBRK_TYPEDEF_UBREAK_ITERATOR |
| 27 | /** |
| 28 | * Opaque type representing an ICU Break iterator object. |
| 29 | * @stable ICU 2.0 |
| 30 | */ |
| 31 | typedef struct UBreakIterator UBreakIterator; |
| 32 | #endif |
| 33 | |
| 34 | #if !UCONFIG_NO_BREAK_ITERATION |
| 35 | |
| 36 | #include "unicode/parseerr.h" |
| 37 | |
| 38 | /** |
| 39 | * \file |
| 40 | * \brief C API: BreakIterator |
| 41 | * |
| 42 | * <h2> BreakIterator C API </h2> |
| 43 | * |
| 44 | * The BreakIterator C API defines methods for finding the location |
| 45 | * of boundaries in text. Pointer to a UBreakIterator maintain a |
| 46 | * current position and scan over text returning the index of characters |
| 47 | * where boundaries occur. |
| 48 | * <p> |
| 49 | * Line boundary analysis determines where a text string can be broken |
| 50 | * when line-wrapping. The mechanism correctly handles punctuation and |
| 51 | * hyphenated words. |
| 52 | * <p> |
| 53 | * Note: The locale keyword "lb" can be used to modify line break |
| 54 | * behavior according to the CSS level 3 line-break options, see |
| 55 | * <http://dev.w3.org/csswg/css-text/#line-breaking>. For example: |
| 56 | * "ja@lb=strict", "zh@lb=loose". |
| 57 | * <p> |
| 58 | * Sentence boundary analysis allows selection with correct |
| 59 | * interpretation of periods within numbers and abbreviations, and |
| 60 | * trailing punctuation marks such as quotation marks and parentheses. |
| 61 | * <p> |
| 62 | * Note: The locale keyword "ss" can be used to enable use of |
| 63 | * segmentation suppression data (preventing breaks in English after |
| 64 | * abbreviations such as "Mr." or "Est.", for example), as follows: |
| 65 | * "en@ss=standard". |
| 66 | * <p> |
| 67 | * Word boundary analysis is used by search and replace functions, as |
| 68 | * well as within text editing applications that allow the user to |
| 69 | * select words with a double click. Word selection provides correct |
| 70 | * interpretation of punctuation marks within and following |
| 71 | * words. Characters that are not part of a word, such as symbols or |
| 72 | * punctuation marks, have word-breaks on both sides. |
| 73 | * <p> |
| 74 | * Character boundary analysis identifies the boundaries of |
| 75 | * "Extended Grapheme Clusters", which are groupings of codepoints |
| 76 | * that should be treated as character-like units for many text operations. |
| 77 | * Please see Unicode Standard Annex #29, Unicode Text Segmentation, |
| 78 | * http://www.unicode.org/reports/tr29/ for additional information |
| 79 | * on grapheme clusters and guidelines on their use. |
| 80 | * <p> |
| 81 | * Title boundary analysis locates all positions, |
| 82 | * typically starts of words, that should be set to Title Case |
| 83 | * when title casing the text. |
| 84 | * <p> |
| 85 | * The text boundary positions are found according to the rules |
| 86 | * described in Unicode Standard Annex #29, Text Boundaries, and |
| 87 | * Unicode Standard Annex #14, Line Breaking Properties. These |
| 88 | * are available at http://www.unicode.org/reports/tr14/ and |
| 89 | * http://www.unicode.org/reports/tr29/. |
| 90 | * <p> |
| 91 | * In addition to the plain C API defined in this header file, an |
| 92 | * object oriented C++ API with equivalent functionality is defined in the |
| 93 | * file brkiter.h. |
| 94 | * <p> |
| 95 | * Code snippets illustrating the use of the Break Iterator APIs |
| 96 | * are available in the ICU User Guide, |
| 97 | * http://icu-project.org/userguide/boundaryAnalysis.html |
| 98 | * and in the sample program icu/source/samples/break/break.cpp |
| 99 | */ |
| 100 | |
| 101 | /** The possible types of text boundaries. @stable ICU 2.0 */ |
| 102 | typedef enum UBreakIteratorType { |
| 103 | /** Character breaks @stable ICU 2.0 */ |
| 104 | UBRK_CHARACTER = 0, |
| 105 | /** Word breaks @stable ICU 2.0 */ |
| 106 | UBRK_WORD = 1, |
| 107 | /** Line breaks @stable ICU 2.0 */ |
| 108 | UBRK_LINE = 2, |
| 109 | /** Sentence breaks @stable ICU 2.0 */ |
| 110 | UBRK_SENTENCE = 3, |
| 111 | |
| 112 | #ifndef U_HIDE_DEPRECATED_API |
| 113 | /** |
| 114 | * Title Case breaks |
| 115 | * The iterator created using this type locates title boundaries as described for |
| 116 | * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, |
| 117 | * please use Word Boundary iterator. |
| 118 | * |
| 119 | * @deprecated ICU 2.8 Use the word break iterator for titlecasing for Unicode 4 and later. |
| 120 | */ |
| 121 | UBRK_TITLE = 4, |
| 122 | /** |
| 123 | * One more than the highest normal UBreakIteratorType value. |
| 124 | * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. |
| 125 | */ |
| 126 | UBRK_COUNT = 5 |
| 127 | #endif // U_HIDE_DEPRECATED_API |
| 128 | } UBreakIteratorType; |
| 129 | |
| 130 | /** Value indicating all text boundaries have been returned. |
| 131 | * @stable ICU 2.0 |
| 132 | */ |
| 133 | #define UBRK_DONE ((int32_t) -1) |
| 134 | |
| 135 | |
| 136 | /** |
| 137 | * Enum constants for the word break tags returned by |
| 138 | * getRuleStatus(). A range of values is defined for each category of |
| 139 | * word, to allow for further subdivisions of a category in future releases. |
| 140 | * Applications should check for tag values falling within the range, rather |
| 141 | * than for single individual values. |
| 142 | * |
| 143 | * The numeric values of all of these constants are stable (will not change). |
| 144 | * |
| 145 | * @stable ICU 2.2 |
| 146 | */ |
| 147 | typedef enum UWordBreak { |
| 148 | /** Tag value for "words" that do not fit into any of other categories. |
| 149 | * Includes spaces and most punctuation. */ |
| 150 | UBRK_WORD_NONE = 0, |
| 151 | /** Upper bound for tags for uncategorized words. */ |
| 152 | UBRK_WORD_NONE_LIMIT = 100, |
| 153 | /** Tag value for words that appear to be numbers, lower limit. */ |
| 154 | UBRK_WORD_NUMBER = 100, |
| 155 | /** Tag value for words that appear to be numbers, upper limit. */ |
| 156 | UBRK_WORD_NUMBER_LIMIT = 200, |
| 157 | /** Tag value for words that contain letters, excluding |
| 158 | * hiragana, katakana or ideographic characters, lower limit. */ |
| 159 | UBRK_WORD_LETTER = 200, |
| 160 | /** Tag value for words containing letters, upper limit */ |
| 161 | UBRK_WORD_LETTER_LIMIT = 300, |
| 162 | /** Tag value for words containing kana characters, lower limit */ |
| 163 | UBRK_WORD_KANA = 300, |
| 164 | /** Tag value for words containing kana characters, upper limit */ |
| 165 | UBRK_WORD_KANA_LIMIT = 400, |
| 166 | /** Tag value for words containing ideographic characters, lower limit */ |
| 167 | UBRK_WORD_IDEO = 400, |
| 168 | /** Tag value for words containing ideographic characters, upper limit */ |
| 169 | UBRK_WORD_IDEO_LIMIT = 500 |
| 170 | } UWordBreak; |
| 171 | |
| 172 | /** |
| 173 | * Enum constants for the line break tags returned by getRuleStatus(). |
| 174 | * A range of values is defined for each category of |
| 175 | * word, to allow for further subdivisions of a category in future releases. |
| 176 | * Applications should check for tag values falling within the range, rather |
| 177 | * than for single individual values. |
| 178 | * |
| 179 | * The numeric values of all of these constants are stable (will not change). |
| 180 | * |
| 181 | * @stable ICU 2.8 |
| 182 | */ |
| 183 | typedef enum ULineBreakTag { |
| 184 | /** Tag value for soft line breaks, positions at which a line break |
| 185 | * is acceptable but not required */ |
| 186 | UBRK_LINE_SOFT = 0, |
| 187 | /** Upper bound for soft line breaks. */ |
| 188 | UBRK_LINE_SOFT_LIMIT = 100, |
| 189 | /** Tag value for a hard, or mandatory line break */ |
| 190 | UBRK_LINE_HARD = 100, |
| 191 | /** Upper bound for hard line breaks. */ |
| 192 | UBRK_LINE_HARD_LIMIT = 200 |
| 193 | } ULineBreakTag; |
| 194 | |
| 195 | |
| 196 | |
| 197 | /** |
| 198 | * Enum constants for the sentence break tags returned by getRuleStatus(). |
| 199 | * A range of values is defined for each category of |
| 200 | * sentence, to allow for further subdivisions of a category in future releases. |
| 201 | * Applications should check for tag values falling within the range, rather |
| 202 | * than for single individual values. |
| 203 | * |
| 204 | * The numeric values of all of these constants are stable (will not change). |
| 205 | * |
| 206 | * @stable ICU 2.8 |
| 207 | */ |
| 208 | typedef enum USentenceBreakTag { |
| 209 | /** Tag value for for sentences ending with a sentence terminator |
| 210 | * ('.', '?', '!', etc.) character, possibly followed by a |
| 211 | * hard separator (CR, LF, PS, etc.) |
| 212 | */ |
| 213 | UBRK_SENTENCE_TERM = 0, |
| 214 | /** Upper bound for tags for sentences ended by sentence terminators. */ |
| 215 | UBRK_SENTENCE_TERM_LIMIT = 100, |
| 216 | /** Tag value for for sentences that do not contain an ending |
| 217 | * sentence terminator ('.', '?', '!', etc.) character, but |
| 218 | * are ended only by a hard separator (CR, LF, PS, etc.) or end of input. |
| 219 | */ |
| 220 | UBRK_SENTENCE_SEP = 100, |
| 221 | /** Upper bound for tags for sentences ended by a separator. */ |
| 222 | UBRK_SENTENCE_SEP_LIMIT = 200 |
| 223 | /** Tag value for a hard, or mandatory line break */ |
| 224 | } USentenceBreakTag; |
| 225 | |
| 226 | |
| 227 | /** |
| 228 | * Open a new UBreakIterator for locating text boundaries for a specified locale. |
| 229 | * A UBreakIterator may be used for detecting character, line, word, |
| 230 | * and sentence breaks in text. |
| 231 | * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD, |
| 232 | * UBRK_LINE, UBRK_SENTENCE |
| 233 | * @param locale The locale specifying the text-breaking conventions. Note that |
| 234 | * locale keys such as "lb" and "ss" may be used to modify text break behavior, |
| 235 | * see general discussion of BreakIterator C API. |
| 236 | * @param text The text to be iterated over. May be null, in which case ubrk_setText() is |
| 237 | * used to specify the text to be iterated. |
| 238 | * @param textLength The number of characters in text, or -1 if null-terminated. |
| 239 | * @param status A UErrorCode to receive any errors. |
| 240 | * @return A UBreakIterator for the specified locale. |
| 241 | * @see ubrk_openRules |
| 242 | * @stable ICU 2.0 |
| 243 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 244 | U_CAPI UBreakIterator* U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 245 | ubrk_open(UBreakIteratorType type, |
| 246 | const char *locale, |
| 247 | const UChar *text, |
| 248 | int32_t textLength, |
| 249 | UErrorCode *status); |
| 250 | |
| 251 | /** |
| 252 | * Open a new UBreakIterator for locating text boundaries using specified breaking rules. |
| 253 | * The rule syntax is ... (TBD) |
| 254 | * @param rules A set of rules specifying the text breaking conventions. |
| 255 | * @param rulesLength The number of characters in rules, or -1 if null-terminated. |
| 256 | * @param text The text to be iterated over. May be null, in which case ubrk_setText() is |
| 257 | * used to specify the text to be iterated. |
| 258 | * @param textLength The number of characters in text, or -1 if null-terminated. |
| 259 | * @param parseErr Receives position and context information for any syntax errors |
| 260 | * detected while parsing the rules. |
| 261 | * @param status A UErrorCode to receive any errors. |
| 262 | * @return A UBreakIterator for the specified rules. |
| 263 | * @see ubrk_open |
| 264 | * @stable ICU 2.2 |
| 265 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 266 | U_CAPI UBreakIterator* U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 267 | ubrk_openRules(const UChar *rules, |
| 268 | int32_t rulesLength, |
| 269 | const UChar *text, |
| 270 | int32_t textLength, |
| 271 | UParseError *parseErr, |
| 272 | UErrorCode *status); |
| 273 | |
| 274 | /** |
| 275 | * Open a new UBreakIterator for locating text boundaries using precompiled binary rules. |
| 276 | * Opening a UBreakIterator this way is substantially faster than using ubrk_openRules. |
| 277 | * Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not |
| 278 | * compatible across different major versions of ICU, nor across platforms of different |
| 279 | * endianness or different base character set family (ASCII vs EBCDIC). |
| 280 | * @param binaryRules A set of compiled binary rules specifying the text breaking |
| 281 | * conventions. Ownership of the storage containing the compiled |
| 282 | * rules remains with the caller of this function. The compiled |
| 283 | * rules must not be modified or deleted during the life of the |
| 284 | * break iterator. |
| 285 | * @param rulesLength The length of binaryRules in bytes; must be >= 0. |
| 286 | * @param text The text to be iterated over. May be null, in which case |
| 287 | * ubrk_setText() is used to specify the text to be iterated. |
| 288 | * @param textLength The number of characters in text, or -1 if null-terminated. |
| 289 | * @param status Pointer to UErrorCode to receive any errors. |
| 290 | * @return UBreakIterator for the specified rules. |
| 291 | * @see ubrk_getBinaryRules |
| 292 | * @stable ICU 59 |
| 293 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 294 | U_CAPI UBreakIterator* U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 295 | ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength, |
| 296 | const UChar * text, int32_t textLength, |
| 297 | UErrorCode * status); |
| 298 | |
Victor Chang | 16f37a6 | 2021-02-01 22:20:48 +0000 | [diff] [blame^] | 299 | #ifndef U_HIDE_DEPRECATED_API |
| 300 | |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 301 | /** |
| 302 | * Thread safe cloning operation |
| 303 | * @param bi iterator to be cloned |
| 304 | * @param stackBuffer <em>Deprecated functionality as of ICU 52, use NULL.</em><br> |
| 305 | * user allocated space for the new clone. If NULL new memory will be allocated. |
| 306 | * If buffer is not large enough, new memory will be allocated. |
| 307 | * Clients can use the U_BRK_SAFECLONE_BUFFERSIZE. |
| 308 | * @param pBufferSize <em>Deprecated functionality as of ICU 52, use NULL or 1.</em><br> |
| 309 | * pointer to size of allocated space. |
| 310 | * If *pBufferSize == 0, a sufficient size for use in cloning will |
| 311 | * be returned ('pre-flighting') |
| 312 | * If *pBufferSize is not enough for a stack-based safe clone, |
| 313 | * new memory will be allocated. |
| 314 | * @param status to indicate whether the operation went on smoothly or there were errors |
| 315 | * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary. |
| 316 | * @return pointer to the new clone |
Victor Chang | 16f37a6 | 2021-02-01 22:20:48 +0000 | [diff] [blame^] | 317 | * @deprecated ICU 69 Use ubrk_clone() instead. |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 318 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 319 | U_CAPI UBreakIterator * U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 320 | ubrk_safeClone( |
| 321 | const UBreakIterator *bi, |
| 322 | void *stackBuffer, |
| 323 | int32_t *pBufferSize, |
| 324 | UErrorCode *status); |
| 325 | |
Victor Chang | 16f37a6 | 2021-02-01 22:20:48 +0000 | [diff] [blame^] | 326 | #endif /* U_HIDE_DEPRECATED_API */ |
| 327 | |
| 328 | #ifndef U_HIDE_DRAFT_API |
| 329 | |
| 330 | /** |
| 331 | * Thread safe cloning operation. |
| 332 | * @param bi iterator to be cloned |
| 333 | * @param status to indicate whether the operation went on smoothly or there were errors |
| 334 | * @return pointer to the new clone |
| 335 | * @draft ICU 69 |
| 336 | */ |
| 337 | U_CAPI UBreakIterator * U_EXPORT2 |
| 338 | ubrk_clone(const UBreakIterator *bi, |
| 339 | UErrorCode *status); |
| 340 | |
| 341 | #endif // U_HIDE_DRAFT_API |
| 342 | |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 343 | #ifndef U_HIDE_DEPRECATED_API |
| 344 | |
| 345 | /** |
| 346 | * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone(). |
| 347 | * @deprecated ICU 52. Do not rely on ubrk_safeClone() cloning into any provided buffer. |
| 348 | */ |
| 349 | #define U_BRK_SAFECLONE_BUFFERSIZE 1 |
| 350 | |
| 351 | #endif /* U_HIDE_DEPRECATED_API */ |
| 352 | |
| 353 | /** |
| 354 | * Close a UBreakIterator. |
| 355 | * Once closed, a UBreakIterator may no longer be used. |
| 356 | * @param bi The break iterator to close. |
| 357 | * @stable ICU 2.0 |
| 358 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 359 | U_CAPI void U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 360 | ubrk_close(UBreakIterator *bi); |
| 361 | |
| 362 | #if U_SHOW_CPLUSPLUS_API |
| 363 | |
| 364 | U_NAMESPACE_BEGIN |
| 365 | |
| 366 | /** |
| 367 | * \class LocalUBreakIteratorPointer |
| 368 | * "Smart pointer" class, closes a UBreakIterator via ubrk_close(). |
| 369 | * For most methods see the LocalPointerBase base class. |
| 370 | * |
| 371 | * @see LocalPointerBase |
| 372 | * @see LocalPointer |
| 373 | * @stable ICU 4.4 |
| 374 | */ |
| 375 | U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close); |
| 376 | |
| 377 | U_NAMESPACE_END |
| 378 | |
| 379 | #endif |
| 380 | |
| 381 | /** |
| 382 | * Sets an existing iterator to point to a new piece of text. |
| 383 | * The break iterator retains a pointer to the supplied text. |
| 384 | * The caller must not modify or delete the text while the BreakIterator |
| 385 | * retains the reference. |
| 386 | * |
| 387 | * @param bi The iterator to use |
| 388 | * @param text The text to be set |
| 389 | * @param textLength The length of the text |
| 390 | * @param status The error code |
| 391 | * @stable ICU 2.0 |
| 392 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 393 | U_CAPI void U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 394 | ubrk_setText(UBreakIterator* bi, |
| 395 | const UChar* text, |
| 396 | int32_t textLength, |
| 397 | UErrorCode* status); |
| 398 | |
| 399 | |
| 400 | /** |
| 401 | * Sets an existing iterator to point to a new piece of text. |
| 402 | * |
| 403 | * All index positions returned by break iterator functions are |
| 404 | * native indices from the UText. For example, when breaking UTF-8 |
| 405 | * encoded text, the break positions returned by \ref ubrk_next, \ref ubrk_previous, etc. |
| 406 | * will be UTF-8 string indices, not UTF-16 positions. |
| 407 | * |
| 408 | * @param bi The iterator to use |
| 409 | * @param text The text to be set. |
| 410 | * This function makes a shallow clone of the supplied UText. This means |
| 411 | * that the caller is free to immediately close or otherwise reuse the |
| 412 | * UText that was passed as a parameter, but that the underlying text itself |
| 413 | * must not be altered while being referenced by the break iterator. |
| 414 | * @param status The error code |
| 415 | * @stable ICU 3.4 |
| 416 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 417 | U_CAPI void U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 418 | ubrk_setUText(UBreakIterator* bi, |
| 419 | UText* text, |
| 420 | UErrorCode* status); |
| 421 | |
| 422 | |
| 423 | |
| 424 | /** |
| 425 | * Determine the most recently-returned text boundary. |
| 426 | * |
| 427 | * @param bi The break iterator to use. |
| 428 | * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous, |
| 429 | * \ref ubrk_first, or \ref ubrk_last. |
| 430 | * @stable ICU 2.0 |
| 431 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 432 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 433 | ubrk_current(const UBreakIterator *bi); |
| 434 | |
| 435 | /** |
| 436 | * Advance the iterator to the boundary following the current boundary. |
| 437 | * |
| 438 | * @param bi The break iterator to use. |
| 439 | * @return The character index of the next text boundary, or UBRK_DONE |
| 440 | * if all text boundaries have been returned. |
| 441 | * @see ubrk_previous |
| 442 | * @stable ICU 2.0 |
| 443 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 444 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 445 | ubrk_next(UBreakIterator *bi); |
| 446 | |
| 447 | /** |
| 448 | * Set the iterator position to the boundary preceding the current boundary. |
| 449 | * |
| 450 | * @param bi The break iterator to use. |
| 451 | * @return The character index of the preceding text boundary, or UBRK_DONE |
| 452 | * if all text boundaries have been returned. |
| 453 | * @see ubrk_next |
| 454 | * @stable ICU 2.0 |
| 455 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 456 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 457 | ubrk_previous(UBreakIterator *bi); |
| 458 | |
| 459 | /** |
| 460 | * Set the iterator position to zero, the start of the text being scanned. |
| 461 | * @param bi The break iterator to use. |
| 462 | * @return The new iterator position (zero). |
| 463 | * @see ubrk_last |
| 464 | * @stable ICU 2.0 |
| 465 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 466 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 467 | ubrk_first(UBreakIterator *bi); |
| 468 | |
| 469 | /** |
| 470 | * Set the iterator position to the index immediately <EM>beyond</EM> the last character in the text being scanned. |
| 471 | * This is not the same as the last character. |
| 472 | * @param bi The break iterator to use. |
| 473 | * @return The character offset immediately <EM>beyond</EM> the last character in the |
| 474 | * text being scanned. |
| 475 | * @see ubrk_first |
| 476 | * @stable ICU 2.0 |
| 477 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 478 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 479 | ubrk_last(UBreakIterator *bi); |
| 480 | |
| 481 | /** |
| 482 | * Set the iterator position to the first boundary preceding the specified offset. |
| 483 | * The new position is always smaller than offset, or UBRK_DONE. |
| 484 | * @param bi The break iterator to use. |
| 485 | * @param offset The offset to begin scanning. |
| 486 | * @return The text boundary preceding offset, or UBRK_DONE. |
| 487 | * @see ubrk_following |
| 488 | * @stable ICU 2.0 |
| 489 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 490 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 491 | ubrk_preceding(UBreakIterator *bi, |
| 492 | int32_t offset); |
| 493 | |
| 494 | /** |
| 495 | * Advance the iterator to the first boundary following the specified offset. |
| 496 | * The value returned is always greater than offset, or UBRK_DONE. |
| 497 | * @param bi The break iterator to use. |
| 498 | * @param offset The offset to begin scanning. |
| 499 | * @return The text boundary following offset, or UBRK_DONE. |
| 500 | * @see ubrk_preceding |
| 501 | * @stable ICU 2.0 |
| 502 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 503 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 504 | ubrk_following(UBreakIterator *bi, |
| 505 | int32_t offset); |
| 506 | |
| 507 | /** |
| 508 | * Get a locale for which text breaking information is available. |
| 509 | * A UBreakIterator in a locale returned by this function will perform the correct |
| 510 | * text breaking for the locale. |
| 511 | * @param index The index of the desired locale. |
| 512 | * @return A locale for which number text breaking information is available, or 0 if none. |
| 513 | * @see ubrk_countAvailable |
| 514 | * @stable ICU 2.0 |
| 515 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 516 | U_CAPI const char* U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 517 | ubrk_getAvailable(int32_t index); |
| 518 | |
| 519 | /** |
| 520 | * Determine how many locales have text breaking information available. |
| 521 | * This function is most useful as determining the loop ending condition for |
| 522 | * calls to \ref ubrk_getAvailable. |
| 523 | * @return The number of locales for which text breaking information is available. |
| 524 | * @see ubrk_getAvailable |
| 525 | * @stable ICU 2.0 |
| 526 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 527 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 528 | ubrk_countAvailable(void); |
| 529 | |
| 530 | |
| 531 | /** |
| 532 | * Returns true if the specified position is a boundary position. As a side |
| 533 | * effect, leaves the iterator pointing to the first boundary position at |
| 534 | * or after "offset". |
| 535 | * @param bi The break iterator to use. |
| 536 | * @param offset the offset to check. |
| 537 | * @return True if "offset" is a boundary position. |
| 538 | * @stable ICU 2.0 |
| 539 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 540 | U_CAPI UBool U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 541 | ubrk_isBoundary(UBreakIterator *bi, int32_t offset); |
| 542 | |
| 543 | /** |
| 544 | * Return the status from the break rule that determined the most recently |
| 545 | * returned break position. The values appear in the rule source |
| 546 | * within brackets, {123}, for example. For rules that do not specify a |
| 547 | * status, a default value of 0 is returned. |
| 548 | * <p> |
| 549 | * For word break iterators, the possible values are defined in enum UWordBreak. |
| 550 | * @stable ICU 2.2 |
| 551 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 552 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 553 | ubrk_getRuleStatus(UBreakIterator *bi); |
| 554 | |
| 555 | /** |
| 556 | * Get the statuses from the break rules that determined the most recently |
| 557 | * returned break position. The values appear in the rule source |
| 558 | * within brackets, {123}, for example. The default status value for rules |
| 559 | * that do not explicitly provide one is zero. |
| 560 | * <p> |
| 561 | * For word break iterators, the possible values are defined in enum UWordBreak. |
| 562 | * @param bi The break iterator to use |
| 563 | * @param fillInVec an array to be filled in with the status values. |
| 564 | * @param capacity the length of the supplied vector. A length of zero causes |
| 565 | * the function to return the number of status values, in the |
| 566 | * normal way, without attempting to store any values. |
| 567 | * @param status receives error codes. |
| 568 | * @return The number of rule status values from rules that determined |
| 569 | * the most recent boundary returned by the break iterator. |
| 570 | * @stable ICU 3.0 |
| 571 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 572 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 573 | ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status); |
| 574 | |
| 575 | /** |
| 576 | * Return the locale of the break iterator. You can choose between the valid and |
| 577 | * the actual locale. |
| 578 | * @param bi break iterator |
| 579 | * @param type locale type (valid or actual) |
| 580 | * @param status error code |
| 581 | * @return locale string |
| 582 | * @stable ICU 2.8 |
| 583 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 584 | U_CAPI const char* U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 585 | ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status); |
| 586 | |
| 587 | /** |
| 588 | * Set the subject text string upon which the break iterator is operating |
| 589 | * without changing any other aspect of the state. |
| 590 | * The new and previous text strings must have the same content. |
| 591 | * |
| 592 | * This function is intended for use in environments where ICU is operating on |
| 593 | * strings that may move around in memory. It provides a mechanism for notifying |
| 594 | * ICU that the string has been relocated, and providing a new UText to access the |
| 595 | * string in its new position. |
| 596 | * |
| 597 | * Note that the break iterator never copies the underlying text |
| 598 | * of a string being processed, but always operates directly on the original text |
| 599 | * provided by the user. Refreshing simply drops the references to the old text |
| 600 | * and replaces them with references to the new. |
| 601 | * |
| 602 | * Caution: this function is normally used only by very specialized |
| 603 | * system-level code. One example use case is with garbage collection |
| 604 | * that moves the text in memory. |
| 605 | * |
| 606 | * @param bi The break iterator. |
| 607 | * @param text The new (moved) text string. |
| 608 | * @param status Receives errors detected by this function. |
| 609 | * |
| 610 | * @stable ICU 49 |
| 611 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 612 | U_CAPI void U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 613 | ubrk_refreshUText(UBreakIterator *bi, |
| 614 | UText *text, |
| 615 | UErrorCode *status); |
| 616 | |
| 617 | |
| 618 | /** |
| 619 | * Get a compiled binary version of the rules specifying the behavior of a UBreakIterator. |
| 620 | * The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator |
| 621 | * more quickly than using ubrk_openRules. The compiled rules are not compatible across |
| 622 | * different major versions of ICU, nor across platforms of different endianness or |
| 623 | * different base character set family (ASCII vs EBCDIC). Supports preflighting (with |
| 624 | * binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to |
| 625 | * the binaryRules buffer. However, whether preflighting or not, if the actual length |
| 626 | * is greater than INT32_MAX, then the function returns 0 and sets *status to |
| 627 | * U_INDEX_OUTOFBOUNDS_ERROR. |
| 628 | |
| 629 | * @param bi The break iterator to use. |
| 630 | * @param binaryRules Buffer to receive the compiled binary rules; set to NULL for |
| 631 | * preflighting. |
| 632 | * @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for |
| 633 | * preflighting. Must be >= 0. |
| 634 | * @param status Pointer to UErrorCode to receive any errors, such as |
| 635 | * U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or |
| 636 | * U_ILLEGAL_ARGUMENT_ERROR. |
| 637 | * @return The actual byte length of the binary rules, if <= INT32_MAX; |
| 638 | * otherwise 0. If not preflighting and this is larger than |
| 639 | * rulesCapacity, *status will be set to an error. |
| 640 | * @see ubrk_openBinaryRules |
| 641 | * @stable ICU 59 |
| 642 | */ |
Victor Chang | 0813948 | 2021-01-19 16:28:40 +0000 | [diff] [blame] | 643 | U_CAPI int32_t U_EXPORT2 |
Victor Chang | cacdd87 | 2018-10-24 03:31:13 +0100 | [diff] [blame] | 644 | ubrk_getBinaryRules(UBreakIterator *bi, |
| 645 | uint8_t * binaryRules, int32_t rulesCapacity, |
| 646 | UErrorCode * status); |
| 647 | |
| 648 | #endif /* #if !UCONFIG_NO_BREAK_ITERATION */ |
| 649 | |
| 650 | #endif |