brkiter.h (29204B)
1 // © 2016 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 /* 4 ******************************************************************************** 5 * Copyright (C) 1997-2016, International Business Machines 6 * Corporation and others. All Rights Reserved. 7 ******************************************************************************** 8 * 9 * File brkiter.h 10 * 11 * Modification History: 12 * 13 * Date Name Description 14 * 02/18/97 aliu Added typedef for TextCount. Made DONE const. 15 * 05/07/97 aliu Fixed DLL declaration. 16 * 07/09/97 jfitz Renamed BreakIterator and interface synced with JDK 17 * 08/11/98 helena Sync-up JDK1.2. 18 * 01/13/2000 helena Added UErrorCode parameter to createXXXInstance methods. 19 ******************************************************************************** 20 */ 21 22 #ifndef BRKITER_H 23 #define BRKITER_H 24 25 #include "unicode/utypes.h" 26 27 /** 28 * \file 29 * \brief C++ API: Break Iterator. 30 */ 31 32 #include "unicode/utypes.h" 33 34 #if U_SHOW_CPLUSPLUS_API 35 36 #if UCONFIG_NO_BREAK_ITERATION 37 38 U_NAMESPACE_BEGIN 39 40 /* 41 * Allow the declaration of APIs with pointers to BreakIterator 42 * even when break iteration is removed from the build. 43 */ 44 class BreakIterator; 45 46 U_NAMESPACE_END 47 48 #else 49 50 #include "unicode/uobject.h" 51 #include "unicode/unistr.h" 52 #include "unicode/chariter.h" 53 #include "unicode/locid.h" 54 #include "unicode/ubrk.h" 55 #include "unicode/strenum.h" 56 #include "unicode/utext.h" 57 #include "unicode/umisc.h" 58 59 U_NAMESPACE_BEGIN 60 61 /** 62 * The BreakIterator class implements methods for finding the location 63 * of boundaries in text. BreakIterator is an abstract base class. 64 * Instances of BreakIterator maintain a current position and scan over 65 * text returning the index of characters where boundaries occur. 66 * <p> 67 * Line boundary analysis determines where a text string can be broken 68 * when line-wrapping. The mechanism correctly handles punctuation and 69 * hyphenated words. 70 * <p> 71 * Sentence boundary analysis allows selection with correct 72 * interpretation of periods within numbers and abbreviations, and 73 * trailing punctuation marks such as quotation marks and parentheses. 74 * <p> 75 * Word boundary analysis is used by search and replace functions, as 76 * well as within text editing applications that allow the user to 77 * select words with a double click. Word selection provides correct 78 * interpretation of punctuation marks within and following 79 * words. Characters that are not part of a word, such as symbols or 80 * punctuation marks, have word-breaks on both sides. 81 * <p> 82 * Character boundary analysis allows users to interact with 83 * characters as they expect to, for example, when moving the cursor 84 * through a text string. Character boundary analysis provides correct 85 * navigation of through character strings, regardless of how the 86 * character is stored. For example, an accented character might be 87 * stored as a base character and a diacritical mark. What users 88 * consider to be a character can differ between languages. 89 * <p> 90 * The text boundary positions are found according to the rules 91 * described in Unicode Standard Annex #29, Text Boundaries, and 92 * Unicode Standard Annex #14, Line Breaking Properties. These 93 * are available at http://www.unicode.org/reports/tr14/ and 94 * http://www.unicode.org/reports/tr29/. 95 * <p> 96 * In addition to the C++ API defined in this header file, a 97 * plain C API with equivalent functionality is defined in the 98 * file ubrk.h 99 * <p> 100 * Code snippets illustrating the use of the Break Iterator APIs 101 * are available in the ICU User Guide, 102 * https://unicode-org.github.io/icu/userguide/boundaryanalysis/ 103 * and in the sample program icu/source/samples/break/break.cpp 104 * 105 */ 106 class U_COMMON_API_CLASS BreakIterator : public UObject { 107 public: 108 /** 109 * destructor 110 * @stable ICU 2.0 111 */ 112 U_COMMON_API virtual ~BreakIterator(); 113 114 /** 115 * Return true if another object is semantically equal to this 116 * one. The other object should be an instance of the same subclass of 117 * BreakIterator. Objects of different subclasses are considered 118 * unequal. 119 * <P> 120 * Return true if this BreakIterator is at the same position in the 121 * same text, and is the same class and type (word, line, etc.) of 122 * BreakIterator, as the argument. Text is considered the same if 123 * it contains the same characters, it need not be the same 124 * object, and styles are not considered. 125 * @stable ICU 2.0 126 */ 127 U_COMMON_API virtual bool operator==(const BreakIterator&) const = 0; 128 129 /** 130 * Returns the complement of the result of operator== 131 * @param rhs The BreakIterator to be compared for inequality 132 * @return the complement of the result of operator== 133 * @stable ICU 2.0 134 */ 135 U_COMMON_API bool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); } 136 137 /** 138 * Return a polymorphic copy of this object. This is an abstract 139 * method which subclasses implement. 140 * @stable ICU 2.0 141 */ 142 U_COMMON_API virtual BreakIterator* clone() const = 0; 143 144 /** 145 * Return a polymorphic class ID for this object. Different subclasses 146 * will return distinct unequal values. 147 * @stable ICU 2.0 148 */ 149 U_COMMON_API virtual UClassID getDynamicClassID() const override = 0; 150 151 /** 152 * Return a CharacterIterator over the text being analyzed. 153 * @stable ICU 2.0 154 */ 155 U_COMMON_API virtual CharacterIterator& getText() const = 0; 156 157 /** 158 * Get a UText for the text being analyzed. 159 * The returned UText is a shallow clone of the UText used internally 160 * by the break iterator implementation. It can safely be used to 161 * access the text without impacting any break iterator operations, 162 * but the underlying text itself must not be altered. 163 * 164 * @param fillIn A UText to be filled in. If nullptr, a new UText will be 165 * allocated to hold the result. 166 * @param status receives any error codes. 167 * @return The current UText for this break iterator. If an input 168 * UText was provided, it will always be returned. 169 * @stable ICU 3.4 170 */ 171 U_COMMON_API virtual UText* getUText(UText* fillIn, UErrorCode& status) const = 0; 172 173 /** 174 * Change the text over which this operates. The text boundary is 175 * reset to the start. 176 * 177 * The BreakIterator will retain a reference to the supplied string. 178 * The caller must not modify or delete the text while the BreakIterator 179 * retains the reference. 180 * 181 * @param text The UnicodeString used to change the text. 182 * @stable ICU 2.0 183 */ 184 U_COMMON_API virtual void setText(const UnicodeString& text) = 0; 185 186 /** 187 * Reset the break iterator to operate over the text represented by 188 * the UText. The iterator position is reset to the start. 189 * 190 * This function makes a shallow clone of the supplied UText. This means 191 * that the caller is free to immediately close or otherwise reuse the 192 * Utext that was passed as a parameter, but that the underlying text itself 193 * must not be altered while being referenced by the break iterator. 194 * 195 * All index positions returned by break iterator functions are 196 * native indices from the UText. For example, when breaking UTF-8 197 * encoded text, the break positions returned by next(), previous(), etc. 198 * will be UTF-8 string indices, not UTF-16 positions. 199 * 200 * @param text The UText used to change the text. 201 * @param status receives any error codes. 202 * @stable ICU 3.4 203 */ 204 U_COMMON_API virtual void setText(UText* text, UErrorCode& status) = 0; 205 206 /** 207 * Change the text over which this operates. The text boundary is 208 * reset to the start. 209 * Note that setText(UText *) provides similar functionality to this function, 210 * and is more efficient. 211 * @param it The CharacterIterator used to change the text. 212 * @stable ICU 2.0 213 */ 214 U_COMMON_API virtual void adoptText(CharacterIterator* it) = 0; 215 216 enum { 217 /** 218 * DONE is returned by previous() and next() after all valid 219 * boundaries have been returned. 220 * @stable ICU 2.0 221 */ 222 DONE = static_cast<int32_t>(-1) 223 }; 224 225 /** 226 * Sets the current iteration position to the beginning of the text, position zero. 227 * @return The offset of the beginning of the text, zero. 228 * @stable ICU 2.0 229 */ 230 U_COMMON_API virtual int32_t first() = 0; 231 232 /** 233 * Set the iterator position to the index immediately BEYOND the last character in the text being scanned. 234 * @return The index immediately BEYOND the last character in the text being scanned. 235 * @stable ICU 2.0 236 */ 237 U_COMMON_API virtual int32_t last() = 0; 238 239 /** 240 * Set the iterator position to the boundary preceding the current boundary. 241 * @return The character index of the previous text boundary or DONE if all 242 * boundaries have been returned. 243 * @stable ICU 2.0 244 */ 245 U_COMMON_API virtual int32_t previous() = 0; 246 247 /** 248 * Advance the iterator to the boundary following the current boundary. 249 * @return The character index of the next text boundary or DONE if all 250 * boundaries have been returned. 251 * @stable ICU 2.0 252 */ 253 U_COMMON_API virtual int32_t next() = 0; 254 255 /** 256 * Return character index of the current iterator position within the text. 257 * @return The boundary most recently returned. 258 * @stable ICU 2.0 259 */ 260 U_COMMON_API virtual int32_t current() const = 0; 261 262 /** 263 * Advance the iterator to the first boundary following the specified offset. 264 * The value returned is always greater than the offset or 265 * the value BreakIterator.DONE 266 * @param offset the offset to begin scanning. 267 * @return The first boundary after the specified offset. 268 * @stable ICU 2.0 269 */ 270 U_COMMON_API virtual int32_t following(int32_t offset) = 0; 271 272 /** 273 * Set the iterator position to the first boundary preceding the specified offset. 274 * The value returned is always smaller than the offset or 275 * the value BreakIterator.DONE 276 * @param offset the offset to begin scanning. 277 * @return The first boundary before the specified offset. 278 * @stable ICU 2.0 279 */ 280 U_COMMON_API virtual int32_t preceding(int32_t offset) = 0; 281 282 /** 283 * Return true if the specified position is a boundary position. 284 * As a side effect, the current position of the iterator is set 285 * to the first boundary position at or following the specified offset. 286 * @param offset the offset to check. 287 * @return True if "offset" is a boundary position. 288 * @stable ICU 2.0 289 */ 290 U_COMMON_API virtual UBool isBoundary(int32_t offset) = 0; 291 292 /** 293 * Set the iterator position to the nth boundary from the current boundary 294 * @param n the number of boundaries to move by. A value of 0 295 * does nothing. Negative values move to previous boundaries 296 * and positive values move to later boundaries. 297 * @return The new iterator position, or 298 * DONE if there are fewer than |n| boundaries in the specified direction. 299 * @stable ICU 2.0 300 */ 301 U_COMMON_API virtual int32_t next(int32_t n) = 0; 302 303 /** 304 * For RuleBasedBreakIterators, return the status tag from the break rule 305 * that determined the boundary at the current iteration position. 306 * <p> 307 * For break iterator types that do not support a rule status, 308 * a default value of 0 is returned. 309 * <p> 310 * @return the status from the break rule that determined the boundary at 311 * the current iteration position. 312 * @see RuleBaseBreakIterator::getRuleStatus() 313 * @see UWordBreak 314 * @stable ICU 52 315 */ 316 U_COMMON_API virtual int32_t getRuleStatus() const; 317 318 /** 319 * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s) 320 * that determined the boundary at the current iteration position. 321 * <p> 322 * For break iterator types that do not support rule status, 323 * no values are returned. 324 * <p> 325 * The returned status value(s) are stored into an array provided by the caller. 326 * The values are stored in sorted (ascending) order. 327 * If the capacity of the output array is insufficient to hold the data, 328 * the output will be truncated to the available length, and a 329 * U_BUFFER_OVERFLOW_ERROR will be signaled. 330 * <p> 331 * @see RuleBaseBreakIterator::getRuleStatusVec 332 * 333 * @param fillInVec an array to be filled in with the status values. 334 * @param capacity the length of the supplied vector. A length of zero causes 335 * the function to return the number of status values, in the 336 * normal way, without attempting to store any values. 337 * @param status receives error codes. 338 * @return The number of rule status values from rules that determined 339 * the boundary at the current iteration position. 340 * In the event of a U_BUFFER_OVERFLOW_ERROR, the return value 341 * is the total number of status values that were available, 342 * not the reduced number that were actually returned. 343 * @see getRuleStatus 344 * @stable ICU 52 345 */ 346 U_COMMON_API virtual int32_t getRuleStatusVec(int32_t* fillInVec, 347 int32_t capacity, 348 UErrorCode& status); 349 350 /** 351 * Create BreakIterator for word-breaks using the given locale. 352 * Returns an instance of a BreakIterator implementing word breaks. 353 * WordBreak is useful for word selection (ex. double click) 354 * @param where the locale. 355 * @param status the error code 356 * @return A BreakIterator for word-breaks. The UErrorCode& status 357 * parameter is used to return status information to the user. 358 * To check whether the construction succeeded or not, you should check 359 * the value of U_SUCCESS(err). If you wish more detailed information, you 360 * can check for informational error results which still indicate success. 361 * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For 362 * example, 'de_CH' was requested, but nothing was found there, so 'de' was 363 * used. U_USING_DEFAULT_WARNING indicates that the default locale data was 364 * used; neither the requested locale nor any of its fall back locales 365 * could be found. 366 * The caller owns the returned object and is responsible for deleting it. 367 * @stable ICU 2.0 368 */ 369 U_COMMON_API static BreakIterator* U_EXPORT2 370 createWordInstance(const Locale& where, UErrorCode& status); 371 372 /** 373 * Create BreakIterator for line-breaks using specified locale. 374 * Returns an instance of a BreakIterator implementing line breaks. Line 375 * breaks are logically possible line breaks, actual line breaks are 376 * usually determined based on display width. 377 * LineBreak is useful for word wrapping text. 378 * @param where the locale. 379 * @param status The error code. 380 * @return A BreakIterator for line-breaks. The UErrorCode& status 381 * parameter is used to return status information to the user. 382 * To check whether the construction succeeded or not, you should check 383 * the value of U_SUCCESS(err). If you wish more detailed information, you 384 * can check for informational error results which still indicate success. 385 * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For 386 * example, 'de_CH' was requested, but nothing was found there, so 'de' was 387 * used. U_USING_DEFAULT_WARNING indicates that the default locale data was 388 * used; neither the requested locale nor any of its fall back locales 389 * could be found. 390 * The caller owns the returned object and is responsible for deleting it. 391 * @stable ICU 2.0 392 */ 393 U_COMMON_API static BreakIterator* U_EXPORT2 394 createLineInstance(const Locale& where, UErrorCode& status); 395 396 /** 397 * Create BreakIterator for character-breaks using specified locale 398 * Returns an instance of a BreakIterator implementing character breaks. 399 * Character breaks are boundaries of combining character sequences. 400 * @param where the locale. 401 * @param status The error code. 402 * @return A BreakIterator for character-breaks. The UErrorCode& status 403 * parameter is used to return status information to the user. 404 * To check whether the construction succeeded or not, you should check 405 * the value of U_SUCCESS(err). If you wish more detailed information, you 406 * can check for informational error results which still indicate success. 407 * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For 408 * example, 'de_CH' was requested, but nothing was found there, so 'de' was 409 * used. U_USING_DEFAULT_WARNING indicates that the default locale data was 410 * used; neither the requested locale nor any of its fall back locales 411 * could be found. 412 * The caller owns the returned object and is responsible for deleting it. 413 * @stable ICU 2.0 414 */ 415 U_COMMON_API static BreakIterator* U_EXPORT2 416 createCharacterInstance(const Locale& where, UErrorCode& status); 417 418 /** 419 * Create BreakIterator for sentence-breaks using specified locale 420 * Returns an instance of a BreakIterator implementing sentence breaks. 421 * @param where the locale. 422 * @param status The error code. 423 * @return A BreakIterator for sentence-breaks. The UErrorCode& status 424 * parameter is used to return status information to the user. 425 * To check whether the construction succeeded or not, you should check 426 * the value of U_SUCCESS(err). If you wish more detailed information, you 427 * can check for informational error results which still indicate success. 428 * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For 429 * example, 'de_CH' was requested, but nothing was found there, so 'de' was 430 * used. U_USING_DEFAULT_WARNING indicates that the default locale data was 431 * used; neither the requested locale nor any of its fall back locales 432 * could be found. 433 * The caller owns the returned object and is responsible for deleting it. 434 * @stable ICU 2.0 435 */ 436 U_COMMON_API static BreakIterator* U_EXPORT2 437 createSentenceInstance(const Locale& where, UErrorCode& status); 438 439 #ifndef U_HIDE_DEPRECATED_API 440 /** 441 * Create BreakIterator for title-casing breaks using the specified locale 442 * Returns an instance of a BreakIterator implementing title breaks. 443 * The iterator returned locates title boundaries as described for 444 * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, 445 * please use a word boundary iterator. See {@link #createWordInstance }. 446 * 447 * @param where the locale. 448 * @param status The error code. 449 * @return A BreakIterator for title-breaks. The UErrorCode& status 450 * parameter is used to return status information to the user. 451 * To check whether the construction succeeded or not, you should check 452 * the value of U_SUCCESS(err). If you wish more detailed information, you 453 * can check for informational error results which still indicate success. 454 * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For 455 * example, 'de_CH' was requested, but nothing was found there, so 'de' was 456 * used. U_USING_DEFAULT_WARNING indicates that the default locale data was 457 * used; neither the requested locale nor any of its fall back locales 458 * could be found. 459 * The caller owns the returned object and is responsible for deleting it. 460 * @deprecated ICU 64 Use createWordInstance instead. 461 */ 462 U_COMMON_API static BreakIterator* U_EXPORT2 463 createTitleInstance(const Locale& where, UErrorCode& status); 464 #endif /* U_HIDE_DEPRECATED_API */ 465 466 /** 467 * Get the set of Locales for which TextBoundaries are installed. 468 * <p><b>Note:</b> this will not return locales added through the register 469 * call. To see the registered locales too, use the getAvailableLocales 470 * function that returns a StringEnumeration object </p> 471 * @param count the output parameter of number of elements in the locale list 472 * @return available locales 473 * @stable ICU 2.0 474 */ 475 U_COMMON_API static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); 476 477 /** 478 * Get name of the object for the desired Locale, in the desired language. 479 * @param objectLocale must be from getAvailableLocales. 480 * @param displayLocale specifies the desired locale for output. 481 * @param name the fill-in parameter of the return value 482 * Uses best match. 483 * @return user-displayable name 484 * @stable ICU 2.0 485 */ 486 U_COMMON_API static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, 487 const Locale& displayLocale, 488 UnicodeString& name); 489 490 /** 491 * Get name of the object for the desired Locale, in the language of the 492 * default locale. 493 * @param objectLocale must be from getMatchingLocales 494 * @param name the fill-in parameter of the return value 495 * @return user-displayable name 496 * @stable ICU 2.0 497 */ 498 U_COMMON_API static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, 499 UnicodeString& name); 500 501 #ifndef U_FORCE_HIDE_DEPRECATED_API 502 /** 503 * Deprecated functionality. Use clone() instead. 504 * 505 * Thread safe client-buffer-based cloning operation 506 * Do NOT call delete on a safeclone, since 'new' is not used to create it. 507 * @param stackBuffer user allocated space for the new clone. If nullptr new memory will be allocated. 508 * If buffer is not large enough, new memory will be allocated. 509 * @param BufferSize reference to size of allocated space. 510 * If BufferSize == 0, a sufficient size for use in cloning will 511 * be returned ('pre-flighting') 512 * If BufferSize is not enough for a stack-based safe clone, 513 * new memory will be allocated. 514 * @param status to indicate whether the operation went on smoothly or there were errors 515 * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were 516 * necessary. 517 * @return pointer to the new clone 518 * 519 * @deprecated ICU 52. Use clone() instead. 520 */ 521 U_COMMON_API virtual BreakIterator* createBufferClone(void* stackBuffer, 522 int32_t& BufferSize, 523 UErrorCode& status) = 0; 524 #endif // U_FORCE_HIDE_DEPRECATED_API 525 526 #ifndef U_HIDE_DEPRECATED_API 527 528 /** 529 * Determine whether the BreakIterator was created in user memory by 530 * createBufferClone(), and thus should not be deleted. Such objects 531 * must be closed by an explicit call to the destructor (not delete). 532 * @deprecated ICU 52. Always delete the BreakIterator. 533 */ 534 U_COMMON_API inline UBool isBufferClone(); 535 536 #endif /* U_HIDE_DEPRECATED_API */ 537 538 #if !UCONFIG_NO_SERVICE 539 /** 540 * Register a new break iterator of the indicated kind, to use in the given locale. 541 * The break iterator will be adopted. Clones of the iterator will be returned 542 * if a request for a break iterator of the given kind matches or falls back to 543 * this locale. 544 * Because ICU may choose to cache BreakIterators internally, this must 545 * be called at application startup, prior to any calls to 546 * BreakIterator::createXXXInstance to avoid undefined behavior. 547 * @param toAdopt the BreakIterator instance to be adopted 548 * @param locale the Locale for which this instance is to be registered 549 * @param kind the type of iterator for which this instance is to be registered 550 * @param status the in/out status code, no special meanings are assigned 551 * @return a registry key that can be used to unregister this instance 552 * @stable ICU 2.4 553 */ 554 U_COMMON_API static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt, 555 const Locale& locale, 556 UBreakIteratorType kind, 557 UErrorCode& status); 558 559 /** 560 * Unregister a previously-registered BreakIterator using the key returned from the 561 * register call. Key becomes invalid after a successful call and should not be used again. 562 * The BreakIterator corresponding to the key will be deleted. 563 * Because ICU may choose to cache BreakIterators internally, this should 564 * be called during application shutdown, after all calls to 565 * BreakIterator::createXXXInstance to avoid undefined behavior. 566 * @param key the registry key returned by a previous call to registerInstance 567 * @param status the in/out status code, no special meanings are assigned 568 * @return true if the iterator for the key was successfully unregistered 569 * @stable ICU 2.4 570 */ 571 U_COMMON_API static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status); 572 573 /** 574 * Return a StringEnumeration over the locales available at the time of the call, 575 * including registered locales. 576 * @return a StringEnumeration over the locales available at the time of the call 577 * @stable ICU 2.4 578 */ 579 U_COMMON_API static StringEnumeration* U_EXPORT2 getAvailableLocales(); 580 #endif 581 582 /** 583 * Returns the locale for this break iterator. Two flavors are available: valid and 584 * actual locale. 585 * @stable ICU 2.8 586 */ 587 U_COMMON_API Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; 588 589 #ifndef U_HIDE_INTERNAL_API 590 /** Get the locale for this break iterator object. You can choose between valid and actual locale. 591 * @param type type of the locale we're looking for (valid or actual) 592 * @param status error code for the operation 593 * @return the locale 594 * @internal 595 */ 596 U_COMMON_API const char* getLocaleID(ULocDataLocaleType type, UErrorCode& status) const; 597 #endif /* U_HIDE_INTERNAL_API */ 598 599 /** 600 * Set the subject text string upon which the break iterator is operating 601 * without changing any other aspect of the matching state. 602 * The new and previous text strings must have the same content. 603 * 604 * This function is intended for use in environments where ICU is operating on 605 * strings that may move around in memory. It provides a mechanism for notifying 606 * ICU that the string has been relocated, and providing a new UText to access the 607 * string in its new position. 608 * 609 * Note that the break iterator implementation never copies the underlying text 610 * of a string being processed, but always operates directly on the original text 611 * provided by the user. Refreshing simply drops the references to the old text 612 * and replaces them with references to the new. 613 * 614 * Caution: this function is normally used only by very specialized, 615 * system-level code. One example use case is with garbage collection that moves 616 * the text in memory. 617 * 618 * @param input The new (moved) text string. 619 * @param status Receives errors detected by this function. 620 * @return *this 621 * 622 * @stable ICU 49 623 */ 624 U_COMMON_API virtual BreakIterator& refreshInputText(UText* input, UErrorCode& status) = 0; 625 626 private: 627 static BreakIterator* buildInstance(const Locale& loc, const char *type, UErrorCode& status); 628 static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status); 629 static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status); 630 631 friend class ICUBreakIteratorFactory; 632 friend class ICUBreakIteratorService; 633 634 protected: 635 // Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API 636 // or else the compiler will create a public ones. 637 /** @internal */ 638 U_COMMON_API BreakIterator(); 639 /** @internal */ 640 U_COMMON_API BreakIterator(const BreakIterator& other); 641 #ifndef U_HIDE_INTERNAL_API 642 /** @internal */ 643 U_COMMON_API BreakIterator(const Locale& valid, const Locale& actual); 644 /** @internal. Assignment Operator, used by RuleBasedBreakIterator. */ 645 U_COMMON_API BreakIterator& operator=(const BreakIterator& other); 646 #endif /* U_HIDE_INTERNAL_API */ 647 648 private: 649 650 Locale actualLocale; 651 Locale validLocale; 652 Locale requestLocale; 653 }; 654 655 #ifndef U_HIDE_DEPRECATED_API 656 657 inline UBool BreakIterator::isBufferClone() 658 { 659 return false; 660 } 661 662 #endif /* U_HIDE_DEPRECATED_API */ 663 664 U_NAMESPACE_END 665 666 #endif /* #if !UCONFIG_NO_BREAK_ITERATION */ 667 668 #endif /* U_SHOW_CPLUSPLUS_API */ 669 670 #endif // BRKITER_H 671 //eof