Mercurial > repos > rliterman > csp2

comparison CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/include/unicode/ubrk.h @ 69:33d812a61356

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 2e9511a184a1ca667c7be0c6321a36dc4e3d116d
author jpayne
date Tue, 18 Mar 2025 17:55:14 -0400
parents
children
comparison
equal deleted inserted replaced
67:0e9998148a16 69:33d812a61356
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 /**
272 * Open a new UBreakIterator for locating text boundaries using precompiled binary rules.
273 * Opening a UBreakIterator this way is substantially faster than using ubrk_openRules.
274 * Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not
275 * compatible across different major versions of ICU, nor across platforms of different
276 * endianness or different base character set family (ASCII vs EBCDIC).
277 * @param binaryRules A set of compiled binary rules specifying the text breaking
278 * conventions. Ownership of the storage containing the compiled
279 * rules remains with the caller of this function. The compiled
280 * rules must not be modified or deleted during the life of the
281 * break iterator.
282 * @param rulesLength The length of binaryRules in bytes; must be >= 0.
283 * @param text The text to be iterated over. May be null, in which case
284 * ubrk_setText() is used to specify the text to be iterated.
285 * @param textLength The number of characters in text, or -1 if null-terminated.
286 * @param status Pointer to UErrorCode to receive any errors.
287 * @return UBreakIterator for the specified rules.
288 * @see ubrk_getBinaryRules
289 * @stable ICU 59
290 */
291 U_STABLE UBreakIterator* U_EXPORT2
292 ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength,
293 const UChar * text, int32_t textLength,
294 UErrorCode * status);
295
296 /**
297 * Thread safe cloning operation
298 * @param bi iterator to be cloned
299 * @param stackBuffer <em>Deprecated functionality as of ICU 52, use NULL.</em><br>
300 * user allocated space for the new clone. If NULL new memory will be allocated.
301 * If buffer is not large enough, new memory will be allocated.
302 * Clients can use the U_BRK_SAFECLONE_BUFFERSIZE.
303 * @param pBufferSize <em>Deprecated functionality as of ICU 52, use NULL or 1.</em><br>
304 * pointer to size of allocated space.
305 * If *pBufferSize == 0, a sufficient size for use in cloning will
306 * be returned ('pre-flighting')
307 * If *pBufferSize is not enough for a stack-based safe clone,
308 * new memory will be allocated.
309 * @param status to indicate whether the operation went on smoothly or there were errors
310 * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary.
311 * @return pointer to the new clone
312 * @stable ICU 2.0
313 */
314 U_STABLE UBreakIterator * U_EXPORT2
315 ubrk_safeClone(
316 const UBreakIterator *bi,
317 void *stackBuffer,
318 int32_t *pBufferSize,
319 UErrorCode *status);
320
321 #ifndef U_HIDE_DEPRECATED_API
322
323 /**
324 * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone().
325 * @deprecated ICU 52. Do not rely on ubrk_safeClone() cloning into any provided buffer.
326 */
327 #define U_BRK_SAFECLONE_BUFFERSIZE 1
328
329 #endif /* U_HIDE_DEPRECATED_API */
330
331 /**
332 * Close a UBreakIterator.
333 * Once closed, a UBreakIterator may no longer be used.
334 * @param bi The break iterator to close.
335 * @stable ICU 2.0
336 */
337 U_STABLE void U_EXPORT2
338 ubrk_close(UBreakIterator *bi);
339
340 #if U_SHOW_CPLUSPLUS_API
341
342 U_NAMESPACE_BEGIN
343
344 /**
345 * \class LocalUBreakIteratorPointer
346 * "Smart pointer" class, closes a UBreakIterator via ubrk_close().
347 * For most methods see the LocalPointerBase base class.
348 *
349 * @see LocalPointerBase
350 * @see LocalPointer
351 * @stable ICU 4.4
352 */
353 U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close);
354
355 U_NAMESPACE_END
356
357 #endif
358
359 /**
360 * Sets an existing iterator to point to a new piece of text.
361 * The break iterator retains a pointer to the supplied text.
362 * The caller must not modify or delete the text while the BreakIterator
363 * retains the reference.
364 *
365 * @param bi The iterator to use
366 * @param text The text to be set
367 * @param textLength The length of the text
368 * @param status The error code
369 * @stable ICU 2.0
370 */
371 U_STABLE void U_EXPORT2
372 ubrk_setText(UBreakIterator* bi,
373 const UChar* text,
374 int32_t textLength,
375 UErrorCode* status);
376
377
378 /**
379 * Sets an existing iterator to point to a new piece of text.
380 *
381 * All index positions returned by break iterator functions are
382 * native indices from the UText. For example, when breaking UTF-8
383 * encoded text, the break positions returned by \ref ubrk_next, \ref ubrk_previous, etc.
384 * will be UTF-8 string indices, not UTF-16 positions.
385 *
386 * @param bi The iterator to use
387 * @param text The text to be set.
388 * This function makes a shallow clone of the supplied UText. This means
389 * that the caller is free to immediately close or otherwise reuse the
390 * UText that was passed as a parameter, but that the underlying text itself
391 * must not be altered while being referenced by the break iterator.
392 * @param status The error code
393 * @stable ICU 3.4
394 */
395 U_STABLE void U_EXPORT2
396 ubrk_setUText(UBreakIterator* bi,
397 UText* text,
398 UErrorCode* status);
399
400
401
402 /**
403 * Determine the most recently-returned text boundary.
404 *
405 * @param bi The break iterator to use.
406 * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous,
407 * \ref ubrk_first, or \ref ubrk_last.
408 * @stable ICU 2.0
409 */
410 U_STABLE int32_t U_EXPORT2
411 ubrk_current(const UBreakIterator *bi);
412
413 /**
414 * Advance the iterator to the boundary following the current boundary.
415 *
416 * @param bi The break iterator to use.
417 * @return The character index of the next text boundary, or UBRK_DONE
418 * if all text boundaries have been returned.
419 * @see ubrk_previous
420 * @stable ICU 2.0
421 */
422 U_STABLE int32_t U_EXPORT2
423 ubrk_next(UBreakIterator *bi);
424
425 /**
426 * Set the iterator position to the boundary preceding the current boundary.
427 *
428 * @param bi The break iterator to use.
429 * @return The character index of the preceding text boundary, or UBRK_DONE
430 * if all text boundaries have been returned.
431 * @see ubrk_next
432 * @stable ICU 2.0
433 */
434 U_STABLE int32_t U_EXPORT2
435 ubrk_previous(UBreakIterator *bi);
436
437 /**
438 * Set the iterator position to zero, the start of the text being scanned.
439 * @param bi The break iterator to use.
440 * @return The new iterator position (zero).
441 * @see ubrk_last
442 * @stable ICU 2.0
443 */
444 U_STABLE int32_t U_EXPORT2
445 ubrk_first(UBreakIterator *bi);
446
447 /**
448 * Set the iterator position to the index immediately <EM>beyond</EM> the last character in the text being scanned.
449 * This is not the same as the last character.
450 * @param bi The break iterator to use.
451 * @return The character offset immediately <EM>beyond</EM> the last character in the
452 * text being scanned.
453 * @see ubrk_first
454 * @stable ICU 2.0
455 */
456 U_STABLE int32_t U_EXPORT2
457 ubrk_last(UBreakIterator *bi);
458
459 /**
460 * Set the iterator position to the first boundary preceding the specified offset.
461 * The new position is always smaller than offset, or UBRK_DONE.
462 * @param bi The break iterator to use.
463 * @param offset The offset to begin scanning.
464 * @return The text boundary preceding offset, or UBRK_DONE.
465 * @see ubrk_following
466 * @stable ICU 2.0
467 */
468 U_STABLE int32_t U_EXPORT2
469 ubrk_preceding(UBreakIterator *bi,
470 int32_t offset);
471
472 /**
473 * Advance the iterator to the first boundary following the specified offset.
474 * The value returned is always greater than offset, or UBRK_DONE.
475 * @param bi The break iterator to use.
476 * @param offset The offset to begin scanning.
477 * @return The text boundary following offset, or UBRK_DONE.
478 * @see ubrk_preceding
479 * @stable ICU 2.0
480 */
481 U_STABLE int32_t U_EXPORT2
482 ubrk_following(UBreakIterator *bi,
483 int32_t offset);
484
485 /**
486 * Get a locale for which text breaking information is available.
487 * A UBreakIterator in a locale returned by this function will perform the correct
488 * text breaking for the locale.
489 * @param index The index of the desired locale.
490 * @return A locale for which number text breaking information is available, or 0 if none.
491 * @see ubrk_countAvailable
492 * @stable ICU 2.0
493 */
494 U_STABLE const char* U_EXPORT2
495 ubrk_getAvailable(int32_t index);
496
497 /**
498 * Determine how many locales have text breaking information available.
499 * This function is most useful as determining the loop ending condition for
500 * calls to \ref ubrk_getAvailable.
501 * @return The number of locales for which text breaking information is available.
502 * @see ubrk_getAvailable
503 * @stable ICU 2.0
504 */
505 U_STABLE int32_t U_EXPORT2
506 ubrk_countAvailable(void);
507
508
509 /**
510 * Returns true if the specified position is a boundary position. As a side
511 * effect, leaves the iterator pointing to the first boundary position at
512 * or after "offset".
513 * @param bi The break iterator to use.
514 * @param offset the offset to check.
515 * @return True if "offset" is a boundary position.
516 * @stable ICU 2.0
517 */
518 U_STABLE UBool U_EXPORT2
519 ubrk_isBoundary(UBreakIterator *bi, int32_t offset);
520
521 /**
522 * Return the status from the break rule that determined the most recently
523 * returned break position. The values appear in the rule source
524 * within brackets, {123}, for example. For rules that do not specify a
525 * status, a default value of 0 is returned.
526 * <p>
527 * For word break iterators, the possible values are defined in enum UWordBreak.
528 * @stable ICU 2.2
529 */
530 U_STABLE int32_t U_EXPORT2
531 ubrk_getRuleStatus(UBreakIterator *bi);
532
533 /**
534 * Get the statuses from the break rules that determined the most recently
535 * returned break position. The values appear in the rule source
536 * within brackets, {123}, for example. The default status value for rules
537 * that do not explicitly provide one is zero.
538 * <p>
539 * For word break iterators, the possible values are defined in enum UWordBreak.
540 * @param bi The break iterator to use
541 * @param fillInVec an array to be filled in with the status values.
542 * @param capacity the length of the supplied vector. A length of zero causes
543 * the function to return the number of status values, in the
544 * normal way, without attempting to store any values.
545 * @param status receives error codes.
546 * @return The number of rule status values from rules that determined
547 * the most recent boundary returned by the break iterator.
548 * @stable ICU 3.0
549 */
550 U_STABLE int32_t U_EXPORT2
551 ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status);
552
553 /**
554 * Return the locale of the break iterator. You can choose between the valid and
555 * the actual locale.
556 * @param bi break iterator
557 * @param type locale type (valid or actual)
558 * @param status error code
559 * @return locale string
560 * @stable ICU 2.8
561 */
562 U_STABLE const char* U_EXPORT2
563 ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status);
564
565 /**
566 * Set the subject text string upon which the break iterator is operating
567 * without changing any other aspect of the state.
568 * The new and previous text strings must have the same content.
569 *
570 * This function is intended for use in environments where ICU is operating on
571 * strings that may move around in memory. It provides a mechanism for notifying
572 * ICU that the string has been relocated, and providing a new UText to access the
573 * string in its new position.
574 *
575 * Note that the break iterator never copies the underlying text
576 * of a string being processed, but always operates directly on the original text
577 * provided by the user. Refreshing simply drops the references to the old text
578 * and replaces them with references to the new.
579 *
580 * Caution: this function is normally used only by very specialized
581 * system-level code. One example use case is with garbage collection
582 * that moves the text in memory.
583 *
584 * @param bi The break iterator.
585 * @param text The new (moved) text string.
586 * @param status Receives errors detected by this function.
587 *
588 * @stable ICU 49
589 */
590 U_STABLE void U_EXPORT2
591 ubrk_refreshUText(UBreakIterator *bi,
592 UText *text,
593 UErrorCode *status);
594
595
596 /**
597 * Get a compiled binary version of the rules specifying the behavior of a UBreakIterator.
598 * The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator
599 * more quickly than using ubrk_openRules. The compiled rules are not compatible across
600 * different major versions of ICU, nor across platforms of different endianness or
601 * different base character set family (ASCII vs EBCDIC). Supports preflighting (with
602 * binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to
603 * the binaryRules buffer. However, whether preflighting or not, if the actual length
604 * is greater than INT32_MAX, then the function returns 0 and sets *status to
605 * U_INDEX_OUTOFBOUNDS_ERROR.
606
607 * @param bi The break iterator to use.
608 * @param binaryRules Buffer to receive the compiled binary rules; set to NULL for
609 * preflighting.
610 * @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for
611 * preflighting. Must be >= 0.
612 * @param status Pointer to UErrorCode to receive any errors, such as
613 * U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or
614 * U_ILLEGAL_ARGUMENT_ERROR.
615 * @return The actual byte length of the binary rules, if <= INT32_MAX;
616 * otherwise 0. If not preflighting and this is larger than
617 * rulesCapacity, *status will be set to an error.
618 * @see ubrk_openBinaryRules
619 * @stable ICU 59
620 */
621 U_STABLE int32_t U_EXPORT2
622 ubrk_getBinaryRules(UBreakIterator *bi,
623 uint8_t * binaryRules, int32_t rulesCapacity,
624 UErrorCode * status);
625
626 #endif /* #if !UCONFIG_NO_BREAK_ITERATION */
627
628 #endif