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