| 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 | * http://icu-project.org/userguide/boundaryAnalysis.html | 
|---|
| 103 | * and in the sample program icu/source/samples/break/break.cpp | 
|---|
| 104 | * | 
|---|
| 105 | */ | 
|---|
| 106 | class U_COMMON_API BreakIterator : public UObject { | 
|---|
| 107 | public: | 
|---|
| 108 | /** | 
|---|
| 109 | *  destructor | 
|---|
| 110 | *  @stable ICU 2.0 | 
|---|
| 111 | */ | 
|---|
| 112 | 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 | virtual UBool 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 | UBool 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 | 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 | virtual UClassID getDynamicClassID(void) const = 0; | 
|---|
| 150 |  | 
|---|
| 151 | /** | 
|---|
| 152 | * Return a CharacterIterator over the text being analyzed. | 
|---|
| 153 | * @stable ICU 2.0 | 
|---|
| 154 | */ | 
|---|
| 155 | virtual CharacterIterator& getText(void) const = 0; | 
|---|
| 156 |  | 
|---|
| 157 |  | 
|---|
| 158 | /** | 
|---|
| 159 | *  Get a UText for the text being analyzed. | 
|---|
| 160 | *  The returned UText is a shallow clone of the UText used internally | 
|---|
| 161 | *  by the break iterator implementation.  It can safely be used to | 
|---|
| 162 | *  access the text without impacting any break iterator operations, | 
|---|
| 163 | *  but the underlying text itself must not be altered. | 
|---|
| 164 | * | 
|---|
| 165 | * @param fillIn A UText to be filled in.  If NULL, a new UText will be | 
|---|
| 166 | *           allocated to hold the result. | 
|---|
| 167 | * @param status receives any error codes. | 
|---|
| 168 | * @return   The current UText for this break iterator.  If an input | 
|---|
| 169 | *           UText was provided, it will always be returned. | 
|---|
| 170 | * @stable ICU 3.4 | 
|---|
| 171 | */ | 
|---|
| 172 | virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0; | 
|---|
| 173 |  | 
|---|
| 174 | /** | 
|---|
| 175 | * Change the text over which this operates. The text boundary is | 
|---|
| 176 | * reset to the start. | 
|---|
| 177 | * | 
|---|
| 178 | * The BreakIterator will retain a reference to the supplied string. | 
|---|
| 179 | * The caller must not modify or delete the text while the BreakIterator | 
|---|
| 180 | * retains the reference. | 
|---|
| 181 | * | 
|---|
| 182 | * @param text The UnicodeString used to change the text. | 
|---|
| 183 | * @stable ICU 2.0 | 
|---|
| 184 | */ | 
|---|
| 185 | virtual void  setText(const UnicodeString &text) = 0; | 
|---|
| 186 |  | 
|---|
| 187 | /** | 
|---|
| 188 | * Reset the break iterator to operate over the text represented by | 
|---|
| 189 | * the UText.  The iterator position is reset to the start. | 
|---|
| 190 | * | 
|---|
| 191 | * This function makes a shallow clone of the supplied UText.  This means | 
|---|
| 192 | * that the caller is free to immediately close or otherwise reuse the | 
|---|
| 193 | * Utext that was passed as a parameter, but that the underlying text itself | 
|---|
| 194 | * must not be altered while being referenced by the break iterator. | 
|---|
| 195 | * | 
|---|
| 196 | * All index positions returned by break iterator functions are | 
|---|
| 197 | * native indices from the UText. For example, when breaking UTF-8 | 
|---|
| 198 | * encoded text, the break positions returned by next(), previous(), etc. | 
|---|
| 199 | * will be UTF-8 string indices, not UTF-16 positions. | 
|---|
| 200 | * | 
|---|
| 201 | * @param text The UText used to change the text. | 
|---|
| 202 | * @param status receives any error codes. | 
|---|
| 203 | * @stable ICU 3.4 | 
|---|
| 204 | */ | 
|---|
| 205 | virtual void  setText(UText *text, UErrorCode &status) = 0; | 
|---|
| 206 |  | 
|---|
| 207 | /** | 
|---|
| 208 | * Change the text over which this operates. The text boundary is | 
|---|
| 209 | * reset to the start. | 
|---|
| 210 | * Note that setText(UText *) provides similar functionality to this function, | 
|---|
| 211 | * and is more efficient. | 
|---|
| 212 | * @param it The CharacterIterator used to change the text. | 
|---|
| 213 | * @stable ICU 2.0 | 
|---|
| 214 | */ | 
|---|
| 215 | virtual void  adoptText(CharacterIterator* it) = 0; | 
|---|
| 216 |  | 
|---|
| 217 | enum { | 
|---|
| 218 | /** | 
|---|
| 219 | * DONE is returned by previous() and next() after all valid | 
|---|
| 220 | * boundaries have been returned. | 
|---|
| 221 | * @stable ICU 2.0 | 
|---|
| 222 | */ | 
|---|
| 223 | DONE = (int32_t)-1 | 
|---|
| 224 | }; | 
|---|
| 225 |  | 
|---|
| 226 | /** | 
|---|
| 227 | * Sets the current iteration position to the beginning of the text, position zero. | 
|---|
| 228 | * @return The offset of the beginning of the text, zero. | 
|---|
| 229 | * @stable ICU 2.0 | 
|---|
| 230 | */ | 
|---|
| 231 | virtual int32_t first(void) = 0; | 
|---|
| 232 |  | 
|---|
| 233 | /** | 
|---|
| 234 | * Set the iterator position to the index immediately BEYOND the last character in the text being scanned. | 
|---|
| 235 | * @return The index immediately BEYOND the last character in the text being scanned. | 
|---|
| 236 | * @stable ICU 2.0 | 
|---|
| 237 | */ | 
|---|
| 238 | virtual int32_t last(void) = 0; | 
|---|
| 239 |  | 
|---|
| 240 | /** | 
|---|
| 241 | * Set the iterator position to the boundary preceding the current boundary. | 
|---|
| 242 | * @return The character index of the previous text boundary or DONE if all | 
|---|
| 243 | * boundaries have been returned. | 
|---|
| 244 | * @stable ICU 2.0 | 
|---|
| 245 | */ | 
|---|
| 246 | virtual int32_t previous(void) = 0; | 
|---|
| 247 |  | 
|---|
| 248 | /** | 
|---|
| 249 | * Advance the iterator to the boundary following the current boundary. | 
|---|
| 250 | * @return The character index of the next text boundary or DONE if all | 
|---|
| 251 | * boundaries have been returned. | 
|---|
| 252 | * @stable ICU 2.0 | 
|---|
| 253 | */ | 
|---|
| 254 | virtual int32_t next(void) = 0; | 
|---|
| 255 |  | 
|---|
| 256 | /** | 
|---|
| 257 | * Return character index of the current iterator position within the text. | 
|---|
| 258 | * @return The boundary most recently returned. | 
|---|
| 259 | * @stable ICU 2.0 | 
|---|
| 260 | */ | 
|---|
| 261 | virtual int32_t current(void) const = 0; | 
|---|
| 262 |  | 
|---|
| 263 | /** | 
|---|
| 264 | * Advance the iterator to the first boundary following the specified offset. | 
|---|
| 265 | * The value returned is always greater than the offset or | 
|---|
| 266 | * the value BreakIterator.DONE | 
|---|
| 267 | * @param offset the offset to begin scanning. | 
|---|
| 268 | * @return The first boundary after the specified offset. | 
|---|
| 269 | * @stable ICU 2.0 | 
|---|
| 270 | */ | 
|---|
| 271 | virtual int32_t following(int32_t offset) = 0; | 
|---|
| 272 |  | 
|---|
| 273 | /** | 
|---|
| 274 | * Set the iterator position to the first boundary preceding the specified offset. | 
|---|
| 275 | * The value returned is always smaller than the offset or | 
|---|
| 276 | * the value BreakIterator.DONE | 
|---|
| 277 | * @param offset the offset to begin scanning. | 
|---|
| 278 | * @return The first boundary before the specified offset. | 
|---|
| 279 | * @stable ICU 2.0 | 
|---|
| 280 | */ | 
|---|
| 281 | virtual int32_t preceding(int32_t offset) = 0; | 
|---|
| 282 |  | 
|---|
| 283 | /** | 
|---|
| 284 | * Return true if the specified position is a boundary position. | 
|---|
| 285 | * As a side effect, the current position of the iterator is set | 
|---|
| 286 | * to the first boundary position at or following the specified offset. | 
|---|
| 287 | * @param offset the offset to check. | 
|---|
| 288 | * @return True if "offset" is a boundary position. | 
|---|
| 289 | * @stable ICU 2.0 | 
|---|
| 290 | */ | 
|---|
| 291 | virtual UBool isBoundary(int32_t offset) = 0; | 
|---|
| 292 |  | 
|---|
| 293 | /** | 
|---|
| 294 | * Set the iterator position to the nth boundary from the current boundary | 
|---|
| 295 | * @param n the number of boundaries to move by.  A value of 0 | 
|---|
| 296 | * does nothing.  Negative values move to previous boundaries | 
|---|
| 297 | * and positive values move to later boundaries. | 
|---|
| 298 | * @return The new iterator position, or | 
|---|
| 299 | * DONE if there are fewer than |n| boundaries in the specified direction. | 
|---|
| 300 | * @stable ICU 2.0 | 
|---|
| 301 | */ | 
|---|
| 302 | virtual int32_t next(int32_t n) = 0; | 
|---|
| 303 |  | 
|---|
| 304 | /** | 
|---|
| 305 | * For RuleBasedBreakIterators, return the status tag from the break rule | 
|---|
| 306 | * that determined the boundary at the current iteration position. | 
|---|
| 307 | * <p> | 
|---|
| 308 | * For break iterator types that do not support a rule status, | 
|---|
| 309 | * a default value of 0 is returned. | 
|---|
| 310 | * <p> | 
|---|
| 311 | * @return the status from the break rule that determined the boundary at | 
|---|
| 312 | *         the current iteration position. | 
|---|
| 313 | * @see RuleBaseBreakIterator::getRuleStatus() | 
|---|
| 314 | * @see UWordBreak | 
|---|
| 315 | * @stable ICU 52 | 
|---|
| 316 | */ | 
|---|
| 317 | virtual int32_t getRuleStatus() const; | 
|---|
| 318 |  | 
|---|
| 319 | /** | 
|---|
| 320 | * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s) | 
|---|
| 321 | * that determined the boundary at the current iteration position. | 
|---|
| 322 | * <p> | 
|---|
| 323 | * For break iterator types that do not support rule status, | 
|---|
| 324 | * no values are returned. | 
|---|
| 325 | * <p> | 
|---|
| 326 | * The returned status value(s) are stored into an array provided by the caller. | 
|---|
| 327 | * The values are stored in sorted (ascending) order. | 
|---|
| 328 | * If the capacity of the output array is insufficient to hold the data, | 
|---|
| 329 | *  the output will be truncated to the available length, and a | 
|---|
| 330 | *  U_BUFFER_OVERFLOW_ERROR will be signaled. | 
|---|
| 331 | * <p> | 
|---|
| 332 | * @see RuleBaseBreakIterator::getRuleStatusVec | 
|---|
| 333 | * | 
|---|
| 334 | * @param fillInVec an array to be filled in with the status values. | 
|---|
| 335 | * @param capacity  the length of the supplied vector.  A length of zero causes | 
|---|
| 336 | *                  the function to return the number of status values, in the | 
|---|
| 337 | *                  normal way, without attempting to store any values. | 
|---|
| 338 | * @param status    receives error codes. | 
|---|
| 339 | * @return          The number of rule status values from rules that determined | 
|---|
| 340 | *                  the boundary at the current iteration position. | 
|---|
| 341 | *                  In the event of a U_BUFFER_OVERFLOW_ERROR, the return value | 
|---|
| 342 | *                  is the total number of status values that were available, | 
|---|
| 343 | *                  not the reduced number that were actually returned. | 
|---|
| 344 | * @see getRuleStatus | 
|---|
| 345 | * @stable ICU 52 | 
|---|
| 346 | */ | 
|---|
| 347 | virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status); | 
|---|
| 348 |  | 
|---|
| 349 | /** | 
|---|
| 350 | * Create BreakIterator for word-breaks using the given locale. | 
|---|
| 351 | * Returns an instance of a BreakIterator implementing word breaks. | 
|---|
| 352 | * WordBreak is useful for word selection (ex. double click) | 
|---|
| 353 | * @param where the locale. | 
|---|
| 354 | * @param status the error code | 
|---|
| 355 | * @return A BreakIterator for word-breaks.  The UErrorCode& status | 
|---|
| 356 | * parameter is used to return status information to the user. | 
|---|
| 357 | * To check whether the construction succeeded or not, you should check | 
|---|
| 358 | * the value of U_SUCCESS(err).  If you wish more detailed information, you | 
|---|
| 359 | * can check for informational error results which still indicate success. | 
|---|
| 360 | * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For | 
|---|
| 361 | * example, 'de_CH' was requested, but nothing was found there, so 'de' was | 
|---|
| 362 | * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was | 
|---|
| 363 | * used; neither the requested locale nor any of its fall back locales | 
|---|
| 364 | * could be found. | 
|---|
| 365 | * The caller owns the returned object and is responsible for deleting it. | 
|---|
| 366 | * @stable ICU 2.0 | 
|---|
| 367 | */ | 
|---|
| 368 | static BreakIterator* U_EXPORT2 | 
|---|
| 369 | createWordInstance(const Locale& where, UErrorCode& status); | 
|---|
| 370 |  | 
|---|
| 371 | /** | 
|---|
| 372 | * Create BreakIterator for line-breaks using specified locale. | 
|---|
| 373 | * Returns an instance of a BreakIterator implementing line breaks. Line | 
|---|
| 374 | * breaks are logically possible line breaks, actual line breaks are | 
|---|
| 375 | * usually determined based on display width. | 
|---|
| 376 | * LineBreak is useful for word wrapping text. | 
|---|
| 377 | * @param where the locale. | 
|---|
| 378 | * @param status The error code. | 
|---|
| 379 | * @return A BreakIterator for line-breaks.  The UErrorCode& status | 
|---|
| 380 | * parameter is used to return status information to the user. | 
|---|
| 381 | * To check whether the construction succeeded or not, you should check | 
|---|
| 382 | * the value of U_SUCCESS(err).  If you wish more detailed information, you | 
|---|
| 383 | * can check for informational error results which still indicate success. | 
|---|
| 384 | * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For | 
|---|
| 385 | * example, 'de_CH' was requested, but nothing was found there, so 'de' was | 
|---|
| 386 | * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was | 
|---|
| 387 | * used; neither the requested locale nor any of its fall back locales | 
|---|
| 388 | * could be found. | 
|---|
| 389 | * The caller owns the returned object and is responsible for deleting it. | 
|---|
| 390 | * @stable ICU 2.0 | 
|---|
| 391 | */ | 
|---|
| 392 | static BreakIterator* U_EXPORT2 | 
|---|
| 393 | createLineInstance(const Locale& where, UErrorCode& status); | 
|---|
| 394 |  | 
|---|
| 395 | /** | 
|---|
| 396 | * Create BreakIterator for character-breaks using specified locale | 
|---|
| 397 | * Returns an instance of a BreakIterator implementing character breaks. | 
|---|
| 398 | * Character breaks are boundaries of combining character sequences. | 
|---|
| 399 | * @param where the locale. | 
|---|
| 400 | * @param status The error code. | 
|---|
| 401 | * @return A BreakIterator for character-breaks.  The UErrorCode& status | 
|---|
| 402 | * parameter is used to return status information to the user. | 
|---|
| 403 | * To check whether the construction succeeded or not, you should check | 
|---|
| 404 | * the value of U_SUCCESS(err).  If you wish more detailed information, you | 
|---|
| 405 | * can check for informational error results which still indicate success. | 
|---|
| 406 | * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For | 
|---|
| 407 | * example, 'de_CH' was requested, but nothing was found there, so 'de' was | 
|---|
| 408 | * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was | 
|---|
| 409 | * used; neither the requested locale nor any of its fall back locales | 
|---|
| 410 | * could be found. | 
|---|
| 411 | * The caller owns the returned object and is responsible for deleting it. | 
|---|
| 412 | * @stable ICU 2.0 | 
|---|
| 413 | */ | 
|---|
| 414 | static BreakIterator* U_EXPORT2 | 
|---|
| 415 | createCharacterInstance(const Locale& where, UErrorCode& status); | 
|---|
| 416 |  | 
|---|
| 417 | /** | 
|---|
| 418 | * Create BreakIterator for sentence-breaks using specified locale | 
|---|
| 419 | * Returns an instance of a BreakIterator implementing sentence breaks. | 
|---|
| 420 | * @param where the locale. | 
|---|
| 421 | * @param status The error code. | 
|---|
| 422 | * @return A BreakIterator for sentence-breaks.  The UErrorCode& status | 
|---|
| 423 | * parameter is used to return status information to the user. | 
|---|
| 424 | * To check whether the construction succeeded or not, you should check | 
|---|
| 425 | * the value of U_SUCCESS(err).  If you wish more detailed information, you | 
|---|
| 426 | * can check for informational error results which still indicate success. | 
|---|
| 427 | * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For | 
|---|
| 428 | * example, 'de_CH' was requested, but nothing was found there, so 'de' was | 
|---|
| 429 | * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was | 
|---|
| 430 | * used; neither the requested locale nor any of its fall back locales | 
|---|
| 431 | * could be found. | 
|---|
| 432 | * The caller owns the returned object and is responsible for deleting it. | 
|---|
| 433 | * @stable ICU 2.0 | 
|---|
| 434 | */ | 
|---|
| 435 | static BreakIterator* U_EXPORT2 | 
|---|
| 436 | createSentenceInstance(const Locale& where, UErrorCode& status); | 
|---|
| 437 |  | 
|---|
| 438 | #ifndef U_HIDE_DEPRECATED_API | 
|---|
| 439 | /** | 
|---|
| 440 | * Create BreakIterator for title-casing breaks using the specified locale | 
|---|
| 441 | * Returns an instance of a BreakIterator implementing title breaks. | 
|---|
| 442 | * The iterator returned locates title boundaries as described for | 
|---|
| 443 | * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, | 
|---|
| 444 | * please use a word boundary iterator. See {@link #createWordInstance }. | 
|---|
| 445 | * | 
|---|
| 446 | * @param where the locale. | 
|---|
| 447 | * @param status The error code. | 
|---|
| 448 | * @return A BreakIterator for title-breaks.  The UErrorCode& status | 
|---|
| 449 | * parameter is used to return status information to the user. | 
|---|
| 450 | * To check whether the construction succeeded or not, you should check | 
|---|
| 451 | * the value of U_SUCCESS(err).  If you wish more detailed information, you | 
|---|
| 452 | * can check for informational error results which still indicate success. | 
|---|
| 453 | * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For | 
|---|
| 454 | * example, 'de_CH' was requested, but nothing was found there, so 'de' was | 
|---|
| 455 | * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was | 
|---|
| 456 | * used; neither the requested locale nor any of its fall back locales | 
|---|
| 457 | * could be found. | 
|---|
| 458 | * The caller owns the returned object and is responsible for deleting it. | 
|---|
| 459 | * @deprecated ICU 64 Use createWordInstance instead. | 
|---|
| 460 | */ | 
|---|
| 461 | static BreakIterator* U_EXPORT2 | 
|---|
| 462 | createTitleInstance(const Locale& where, UErrorCode& status); | 
|---|
| 463 | #endif /* U_HIDE_DEPRECATED_API */ | 
|---|
| 464 |  | 
|---|
| 465 | /** | 
|---|
| 466 | * Get the set of Locales for which TextBoundaries are installed. | 
|---|
| 467 | * <p><b>Note:</b> this will not return locales added through the register | 
|---|
| 468 | * call. To see the registered locales too, use the getAvailableLocales | 
|---|
| 469 | * function that returns a StringEnumeration object </p> | 
|---|
| 470 | * @param count the output parameter of number of elements in the locale list | 
|---|
| 471 | * @return available locales | 
|---|
| 472 | * @stable ICU 2.0 | 
|---|
| 473 | */ | 
|---|
| 474 | static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); | 
|---|
| 475 |  | 
|---|
| 476 | /** | 
|---|
| 477 | * Get name of the object for the desired Locale, in the desired language. | 
|---|
| 478 | * @param objectLocale must be from getAvailableLocales. | 
|---|
| 479 | * @param displayLocale specifies the desired locale for output. | 
|---|
| 480 | * @param name the fill-in parameter of the return value | 
|---|
| 481 | * Uses best match. | 
|---|
| 482 | * @return user-displayable name | 
|---|
| 483 | * @stable ICU 2.0 | 
|---|
| 484 | */ | 
|---|
| 485 | static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, | 
|---|
| 486 | const Locale& displayLocale, | 
|---|
| 487 | UnicodeString& name); | 
|---|
| 488 |  | 
|---|
| 489 | /** | 
|---|
| 490 | * Get name of the object for the desired Locale, in the language of the | 
|---|
| 491 | * default locale. | 
|---|
| 492 | * @param objectLocale must be from getMatchingLocales | 
|---|
| 493 | * @param name the fill-in parameter of the return value | 
|---|
| 494 | * @return user-displayable name | 
|---|
| 495 | * @stable ICU 2.0 | 
|---|
| 496 | */ | 
|---|
| 497 | static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, | 
|---|
| 498 | UnicodeString& name); | 
|---|
| 499 |  | 
|---|
| 500 | #ifndef U_FORCE_HIDE_DEPRECATED_API | 
|---|
| 501 | /** | 
|---|
| 502 | * Deprecated functionality. Use clone() instead. | 
|---|
| 503 | * | 
|---|
| 504 | * Thread safe client-buffer-based cloning operation | 
|---|
| 505 | *    Do NOT call delete on a safeclone, since 'new' is not used to create it. | 
|---|
| 506 | * @param stackBuffer user allocated space for the new clone. If NULL new memory will be allocated. | 
|---|
| 507 | * If buffer is not large enough, new memory will be allocated. | 
|---|
| 508 | * @param BufferSize reference to size of allocated space. | 
|---|
| 509 | * If BufferSize == 0, a sufficient size for use in cloning will | 
|---|
| 510 | * be returned ('pre-flighting') | 
|---|
| 511 | * If BufferSize is not enough for a stack-based safe clone, | 
|---|
| 512 | * new memory will be allocated. | 
|---|
| 513 | * @param status to indicate whether the operation went on smoothly or there were errors | 
|---|
| 514 | *  An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were | 
|---|
| 515 | *  necessary. | 
|---|
| 516 | * @return pointer to the new clone | 
|---|
| 517 | * | 
|---|
| 518 | * @deprecated ICU 52. Use clone() instead. | 
|---|
| 519 | */ | 
|---|
| 520 | virtual BreakIterator *  createBufferClone(void *stackBuffer, | 
|---|
| 521 | int32_t &BufferSize, | 
|---|
| 522 | UErrorCode &status) = 0; | 
|---|
| 523 | #endif  // U_FORCE_HIDE_DEPRECATED_API | 
|---|
| 524 |  | 
|---|
| 525 | #ifndef U_HIDE_DEPRECATED_API | 
|---|
| 526 |  | 
|---|
| 527 | /** | 
|---|
| 528 | *   Determine whether the BreakIterator was created in user memory by | 
|---|
| 529 | *   createBufferClone(), and thus should not be deleted.  Such objects | 
|---|
| 530 | *   must be closed by an explicit call to the destructor (not delete). | 
|---|
| 531 | * @deprecated ICU 52. Always delete the BreakIterator. | 
|---|
| 532 | */ | 
|---|
| 533 | inline UBool isBufferClone(void); | 
|---|
| 534 |  | 
|---|
| 535 | #endif /* U_HIDE_DEPRECATED_API */ | 
|---|
| 536 |  | 
|---|
| 537 | #if !UCONFIG_NO_SERVICE | 
|---|
| 538 | /** | 
|---|
| 539 | * Register a new break iterator of the indicated kind, to use in the given locale. | 
|---|
| 540 | * The break iterator will be adopted.  Clones of the iterator will be returned | 
|---|
| 541 | * if a request for a break iterator of the given kind matches or falls back to | 
|---|
| 542 | * this locale. | 
|---|
| 543 | * Because ICU may choose to cache BreakIterators internally, this must | 
|---|
| 544 | * be called at application startup, prior to any calls to | 
|---|
| 545 | * BreakIterator::createXXXInstance to avoid undefined behavior. | 
|---|
| 546 | * @param toAdopt the BreakIterator instance to be adopted | 
|---|
| 547 | * @param locale the Locale for which this instance is to be registered | 
|---|
| 548 | * @param kind the type of iterator for which this instance is to be registered | 
|---|
| 549 | * @param status the in/out status code, no special meanings are assigned | 
|---|
| 550 | * @return a registry key that can be used to unregister this instance | 
|---|
| 551 | * @stable ICU 2.4 | 
|---|
| 552 | */ | 
|---|
| 553 | static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt, | 
|---|
| 554 | const Locale& locale, | 
|---|
| 555 | UBreakIteratorType kind, | 
|---|
| 556 | UErrorCode& status); | 
|---|
| 557 |  | 
|---|
| 558 | /** | 
|---|
| 559 | * Unregister a previously-registered BreakIterator using the key returned from the | 
|---|
| 560 | * register call.  Key becomes invalid after a successful call and should not be used again. | 
|---|
| 561 | * The BreakIterator corresponding to the key will be deleted. | 
|---|
| 562 | * Because ICU may choose to cache BreakIterators internally, this should | 
|---|
| 563 | * be called during application shutdown, after all calls to | 
|---|
| 564 | * BreakIterator::createXXXInstance to avoid undefined behavior. | 
|---|
| 565 | * @param key the registry key returned by a previous call to registerInstance | 
|---|
| 566 | * @param status the in/out status code, no special meanings are assigned | 
|---|
| 567 | * @return TRUE if the iterator for the key was successfully unregistered | 
|---|
| 568 | * @stable ICU 2.4 | 
|---|
| 569 | */ | 
|---|
| 570 | static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status); | 
|---|
| 571 |  | 
|---|
| 572 | /** | 
|---|
| 573 | * Return a StringEnumeration over the locales available at the time of the call, | 
|---|
| 574 | * including registered locales. | 
|---|
| 575 | * @return a StringEnumeration over the locales available at the time of the call | 
|---|
| 576 | * @stable ICU 2.4 | 
|---|
| 577 | */ | 
|---|
| 578 | static StringEnumeration* U_EXPORT2 getAvailableLocales(void); | 
|---|
| 579 | #endif | 
|---|
| 580 |  | 
|---|
| 581 | /** | 
|---|
| 582 | * Returns the locale for this break iterator. Two flavors are available: valid and | 
|---|
| 583 | * actual locale. | 
|---|
| 584 | * @stable ICU 2.8 | 
|---|
| 585 | */ | 
|---|
| 586 | Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; | 
|---|
| 587 |  | 
|---|
| 588 | #ifndef U_HIDE_INTERNAL_API | 
|---|
| 589 | /** Get the locale for this break iterator object. You can choose between valid and actual locale. | 
|---|
| 590 | *  @param type type of the locale we're looking for (valid or actual) | 
|---|
| 591 | *  @param status error code for the operation | 
|---|
| 592 | *  @return the locale | 
|---|
| 593 | *  @internal | 
|---|
| 594 | */ | 
|---|
| 595 | const char *getLocaleID(ULocDataLocaleType type, UErrorCode& status) const; | 
|---|
| 596 | #endif  /* U_HIDE_INTERNAL_API */ | 
|---|
| 597 |  | 
|---|
| 598 | /** | 
|---|
| 599 | *  Set the subject text string upon which the break iterator is operating | 
|---|
| 600 | *  without changing any other aspect of the matching state. | 
|---|
| 601 | *  The new and previous text strings must have the same content. | 
|---|
| 602 | * | 
|---|
| 603 | *  This function is intended for use in environments where ICU is operating on | 
|---|
| 604 | *  strings that may move around in memory.  It provides a mechanism for notifying | 
|---|
| 605 | *  ICU that the string has been relocated, and providing a new UText to access the | 
|---|
| 606 | *  string in its new position. | 
|---|
| 607 | * | 
|---|
| 608 | *  Note that the break iterator implementation never copies the underlying text | 
|---|
| 609 | *  of a string being processed, but always operates directly on the original text | 
|---|
| 610 | *  provided by the user. Refreshing simply drops the references to the old text | 
|---|
| 611 | *  and replaces them with references to the new. | 
|---|
| 612 | * | 
|---|
| 613 | *  Caution:  this function is normally used only by very specialized, | 
|---|
| 614 | *  system-level code.  One example use case is with garbage collection that moves | 
|---|
| 615 | *  the text in memory. | 
|---|
| 616 | * | 
|---|
| 617 | * @param input      The new (moved) text string. | 
|---|
| 618 | * @param status     Receives errors detected by this function. | 
|---|
| 619 | * @return           *this | 
|---|
| 620 | * | 
|---|
| 621 | * @stable ICU 49 | 
|---|
| 622 | */ | 
|---|
| 623 | virtual BreakIterator &refreshInputText(UText *input, UErrorCode &status) = 0; | 
|---|
| 624 |  | 
|---|
| 625 | private: | 
|---|
| 626 | static BreakIterator* buildInstance(const Locale& loc, const char *type, UErrorCode& status); | 
|---|
| 627 | static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status); | 
|---|
| 628 | static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status); | 
|---|
| 629 |  | 
|---|
| 630 | friend class ICUBreakIteratorFactory; | 
|---|
| 631 | friend class ICUBreakIteratorService; | 
|---|
| 632 |  | 
|---|
| 633 | protected: | 
|---|
| 634 | // Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API | 
|---|
| 635 | // or else the compiler will create a public ones. | 
|---|
| 636 | /** @internal */ | 
|---|
| 637 | BreakIterator(); | 
|---|
| 638 | /** @internal */ | 
|---|
| 639 | BreakIterator (const BreakIterator &other); | 
|---|
| 640 | #ifndef U_HIDE_INTERNAL_API | 
|---|
| 641 | /** @internal */ | 
|---|
| 642 | BreakIterator (const Locale& valid, const Locale &actual); | 
|---|
| 643 | /** @internal. Assignment Operator, used by RuleBasedBreakIterator. */ | 
|---|
| 644 | BreakIterator &operator = (const BreakIterator &other); | 
|---|
| 645 | #endif  /* U_HIDE_INTERNAL_API */ | 
|---|
| 646 |  | 
|---|
| 647 | private: | 
|---|
| 648 |  | 
|---|
| 649 | /** @internal (private) */ | 
|---|
| 650 | char actualLocale[ULOC_FULLNAME_CAPACITY]; | 
|---|
| 651 | char validLocale[ULOC_FULLNAME_CAPACITY]; | 
|---|
| 652 | }; | 
|---|
| 653 |  | 
|---|
| 654 | #ifndef U_HIDE_DEPRECATED_API | 
|---|
| 655 |  | 
|---|
| 656 | inline UBool BreakIterator::isBufferClone() | 
|---|
| 657 | { | 
|---|
| 658 | return FALSE; | 
|---|
| 659 | } | 
|---|
| 660 |  | 
|---|
| 661 | #endif /* U_HIDE_DEPRECATED_API */ | 
|---|
| 662 |  | 
|---|
| 663 | U_NAMESPACE_END | 
|---|
| 664 |  | 
|---|
| 665 | #endif /* #if !UCONFIG_NO_BREAK_ITERATION */ | 
|---|
| 666 |  | 
|---|
| 667 | #endif /* U_SHOW_CPLUSPLUS_API */ | 
|---|
| 668 |  | 
|---|
| 669 | #endif // BRKITER_H | 
|---|
| 670 | //eof | 
|---|
| 671 |  | 
|---|