Back to home page

EIC code displayed by LXR

 
 

    


Warning, file /include/unicode/brkiter.h was not indexed or was modified since last indexation (in which case cross-reference links may be missing, inaccurate or erroneous).

0001 // © 2016 and later: Unicode, Inc. and others.
0002 // License & terms of use: http://www.unicode.org/copyright.html
0003 /*
0004 ********************************************************************************
0005 *   Copyright (C) 1997-2016, International Business Machines
0006 *   Corporation and others.  All Rights Reserved.
0007 ********************************************************************************
0008 *
0009 * File brkiter.h
0010 *
0011 * Modification History:
0012 *
0013 *   Date        Name        Description
0014 *   02/18/97    aliu        Added typedef for TextCount.  Made DONE const.
0015 *   05/07/97    aliu        Fixed DLL declaration.
0016 *   07/09/97    jfitz       Renamed BreakIterator and interface synced with JDK
0017 *   08/11/98    helena      Sync-up JDK1.2.
0018 *   01/13/2000  helena      Added UErrorCode parameter to createXXXInstance methods.
0019 ********************************************************************************
0020 */
0021 
0022 #ifndef BRKITER_H
0023 #define BRKITER_H
0024 
0025 #include "unicode/utypes.h"
0026 
0027 /**
0028  * \file
0029  * \brief C++ API: Break Iterator.
0030  */
0031 
0032 #include "unicode/utypes.h"
0033 
0034 #if U_SHOW_CPLUSPLUS_API
0035 
0036 #if UCONFIG_NO_BREAK_ITERATION
0037 
0038 U_NAMESPACE_BEGIN
0039 
0040 /*
0041  * Allow the declaration of APIs with pointers to BreakIterator
0042  * even when break iteration is removed from the build.
0043  */
0044 class BreakIterator;
0045 
0046 U_NAMESPACE_END
0047 
0048 #else
0049 
0050 #include "unicode/uobject.h"
0051 #include "unicode/unistr.h"
0052 #include "unicode/chariter.h"
0053 #include "unicode/locid.h"
0054 #include "unicode/ubrk.h"
0055 #include "unicode/strenum.h"
0056 #include "unicode/utext.h"
0057 #include "unicode/umisc.h"
0058 
0059 U_NAMESPACE_BEGIN
0060 
0061 /**
0062  * The BreakIterator class implements methods for finding the location
0063  * of boundaries in text. BreakIterator is an abstract base class.
0064  * Instances of BreakIterator maintain a current position and scan over
0065  * text returning the index of characters where boundaries occur.
0066  * <p>
0067  * Line boundary analysis determines where a text string can be broken
0068  * when line-wrapping. The mechanism correctly handles punctuation and
0069  * hyphenated words.
0070  * <p>
0071  * Sentence boundary analysis allows selection with correct
0072  * interpretation of periods within numbers and abbreviations, and
0073  * trailing punctuation marks such as quotation marks and parentheses.
0074  * <p>
0075  * Word boundary analysis is used by search and replace functions, as
0076  * well as within text editing applications that allow the user to
0077  * select words with a double click. Word selection provides correct
0078  * interpretation of punctuation marks within and following
0079  * words. Characters that are not part of a word, such as symbols or
0080  * punctuation marks, have word-breaks on both sides.
0081  * <p>
0082  * Character boundary analysis allows users to interact with
0083  * characters as they expect to, for example, when moving the cursor
0084  * through a text string. Character boundary analysis provides correct
0085  * navigation of through character strings, regardless of how the
0086  * character is stored.  For example, an accented character might be
0087  * stored as a base character and a diacritical mark. What users
0088  * consider to be a character can differ between languages.
0089  * <p>
0090  * The text boundary positions are found according to the rules
0091  * described in Unicode Standard Annex #29, Text Boundaries, and
0092  * Unicode Standard Annex #14, Line Breaking Properties.  These
0093  * are available at http://www.unicode.org/reports/tr14/ and
0094  * http://www.unicode.org/reports/tr29/.
0095  * <p>
0096  * In addition to the C++ API defined in this header file, a
0097  * plain C API with equivalent functionality is defined in the
0098  * file ubrk.h
0099  * <p>
0100  * Code snippets illustrating the use of the Break Iterator APIs
0101  * are available in the ICU User Guide,
0102  * https://unicode-org.github.io/icu/userguide/boundaryanalysis/
0103  * and in the sample program icu/source/samples/break/break.cpp
0104  *
0105  */
0106 class U_COMMON_API BreakIterator : public UObject {
0107 public:
0108     /**
0109      *  destructor
0110      *  @stable ICU 2.0
0111      */
0112     virtual ~BreakIterator();
0113 
0114     /**
0115      * Return true if another object is semantically equal to this
0116      * one. The other object should be an instance of the same subclass of
0117      * BreakIterator. Objects of different subclasses are considered
0118      * unequal.
0119      * <P>
0120      * Return true if this BreakIterator is at the same position in the
0121      * same text, and is the same class and type (word, line, etc.) of
0122      * BreakIterator, as the argument.  Text is considered the same if
0123      * it contains the same characters, it need not be the same
0124      * object, and styles are not considered.
0125      * @stable ICU 2.0
0126      */
0127     virtual bool operator==(const BreakIterator&) const = 0;
0128 
0129     /**
0130      * Returns the complement of the result of operator==
0131      * @param rhs The BreakIterator to be compared for inequality
0132      * @return the complement of the result of operator==
0133      * @stable ICU 2.0
0134      */
0135     bool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); }
0136 
0137     /**
0138      * Return a polymorphic copy of this object.  This is an abstract
0139      * method which subclasses implement.
0140      * @stable ICU 2.0
0141      */
0142     virtual BreakIterator* clone() const = 0;
0143 
0144     /**
0145      * Return a polymorphic class ID for this object. Different subclasses
0146      * will return distinct unequal values.
0147      * @stable ICU 2.0
0148      */
0149     virtual UClassID getDynamicClassID(void) const override = 0;
0150 
0151     /**
0152      * Return a CharacterIterator over the text being analyzed.
0153      * @stable ICU 2.0
0154      */
0155     virtual CharacterIterator& getText(void) const = 0;
0156 
0157 
0158     /**
0159       *  Get a UText for the text being analyzed.
0160       *  The returned UText is a shallow clone of the UText used internally
0161       *  by the break iterator implementation.  It can safely be used to
0162       *  access the text without impacting any break iterator operations,
0163       *  but the underlying text itself must not be altered.
0164       *
0165       * @param fillIn A UText to be filled in.  If nullptr, a new UText will be
0166       *           allocated to hold the result.
0167       * @param status receives any error codes.
0168       * @return   The current UText for this break iterator.  If an input
0169       *           UText was provided, it will always be returned.
0170       * @stable ICU 3.4
0171       */
0172      virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0;
0173 
0174     /**
0175      * Change the text over which this operates. The text boundary is
0176      * reset to the start.
0177      *
0178      * The BreakIterator will retain a reference to the supplied string.
0179      * The caller must not modify or delete the text while the BreakIterator
0180      * retains the reference.
0181      *
0182      * @param text The UnicodeString used to change the text.
0183      * @stable ICU 2.0
0184      */
0185     virtual void  setText(const UnicodeString &text) = 0;
0186 
0187     /**
0188      * Reset the break iterator to operate over the text represented by
0189      * the UText.  The iterator position is reset to the start.
0190      *
0191      * This function makes a shallow clone of the supplied UText.  This means
0192      * that the caller is free to immediately close or otherwise reuse the
0193      * Utext that was passed as a parameter, but that the underlying text itself
0194      * must not be altered while being referenced by the break iterator.
0195      *
0196      * All index positions returned by break iterator functions are
0197      * native indices from the UText. For example, when breaking UTF-8
0198      * encoded text, the break positions returned by next(), previous(), etc.
0199      * will be UTF-8 string indices, not UTF-16 positions.
0200      *
0201      * @param text The UText used to change the text.
0202      * @param status receives any error codes.
0203      * @stable ICU 3.4
0204      */
0205     virtual void  setText(UText *text, UErrorCode &status) = 0;
0206 
0207     /**
0208      * Change the text over which this operates. The text boundary is
0209      * reset to the start.
0210      * Note that setText(UText *) provides similar functionality to this function,
0211      * and is more efficient.
0212      * @param it The CharacterIterator used to change the text.
0213      * @stable ICU 2.0
0214      */
0215     virtual void  adoptText(CharacterIterator* it) = 0;
0216 
0217     enum {
0218         /**
0219          * DONE is returned by previous() and next() after all valid
0220          * boundaries have been returned.
0221          * @stable ICU 2.0
0222          */
0223         DONE = (int32_t)-1
0224     };
0225 
0226     /**
0227      * Sets the current iteration position to the beginning of the text, position zero.
0228      * @return The offset of the beginning of the text, zero.
0229      * @stable ICU 2.0
0230      */
0231     virtual int32_t first(void) = 0;
0232 
0233     /**
0234      * Set the iterator position to the index immediately BEYOND the last character in the text being scanned.
0235      * @return The index immediately BEYOND the last character in the text being scanned.
0236      * @stable ICU 2.0
0237      */
0238     virtual int32_t last(void) = 0;
0239 
0240     /**
0241      * Set the iterator position to the boundary preceding the current boundary.
0242      * @return The character index of the previous text boundary or DONE if all
0243      * boundaries have been returned.
0244      * @stable ICU 2.0
0245      */
0246     virtual int32_t previous(void) = 0;
0247 
0248     /**
0249      * Advance the iterator to the boundary following the current boundary.
0250      * @return The character index of the next text boundary or DONE if all
0251      * boundaries have been returned.
0252      * @stable ICU 2.0
0253      */
0254     virtual int32_t next(void) = 0;
0255 
0256     /**
0257      * Return character index of the current iterator position within the text.
0258      * @return The boundary most recently returned.
0259      * @stable ICU 2.0
0260      */
0261     virtual int32_t current(void) const = 0;
0262 
0263     /**
0264      * Advance the iterator to the first boundary following the specified offset.
0265      * The value returned is always greater than the offset or
0266      * the value BreakIterator.DONE
0267      * @param offset the offset to begin scanning.
0268      * @return The first boundary after the specified offset.
0269      * @stable ICU 2.0
0270      */
0271     virtual int32_t following(int32_t offset) = 0;
0272 
0273     /**
0274      * Set the iterator position to the first boundary preceding the specified offset.
0275      * The value returned is always smaller than the offset or
0276      * the value BreakIterator.DONE
0277      * @param offset the offset to begin scanning.
0278      * @return The first boundary before the specified offset.
0279      * @stable ICU 2.0
0280      */
0281     virtual int32_t preceding(int32_t offset) = 0;
0282 
0283     /**
0284      * Return true if the specified position is a boundary position.
0285      * As a side effect, the current position of the iterator is set
0286      * to the first boundary position at or following the specified offset.
0287      * @param offset the offset to check.
0288      * @return True if "offset" is a boundary position.
0289      * @stable ICU 2.0
0290      */
0291     virtual UBool isBoundary(int32_t offset) = 0;
0292 
0293     /**
0294      * Set the iterator position to the nth boundary from the current boundary
0295      * @param n the number of boundaries to move by.  A value of 0
0296      * does nothing.  Negative values move to previous boundaries
0297      * and positive values move to later boundaries.
0298      * @return The new iterator position, or
0299      * DONE if there are fewer than |n| boundaries in the specified direction.
0300      * @stable ICU 2.0
0301      */
0302     virtual int32_t next(int32_t n) = 0;
0303 
0304    /**
0305      * For RuleBasedBreakIterators, return the status tag from the break rule
0306      * that determined the boundary at the current iteration position.
0307      * <p>
0308      * For break iterator types that do not support a rule status,
0309      * a default value of 0 is returned.
0310      * <p>
0311      * @return the status from the break rule that determined the boundary at
0312      *         the current iteration position.
0313      * @see RuleBaseBreakIterator::getRuleStatus()
0314      * @see UWordBreak
0315      * @stable ICU 52
0316      */
0317     virtual int32_t getRuleStatus() const;
0318 
0319    /**
0320     * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s)
0321     * that determined the boundary at the current iteration position.
0322     * <p>
0323     * For break iterator types that do not support rule status,
0324     * no values are returned.
0325     * <p>
0326     * The returned status value(s) are stored into an array provided by the caller.
0327     * The values are stored in sorted (ascending) order.
0328     * If the capacity of the output array is insufficient to hold the data,
0329     *  the output will be truncated to the available length, and a
0330     *  U_BUFFER_OVERFLOW_ERROR will be signaled.
0331     * <p>
0332     * @see RuleBaseBreakIterator::getRuleStatusVec
0333     *
0334     * @param fillInVec an array to be filled in with the status values.
0335     * @param capacity  the length of the supplied vector.  A length of zero causes
0336     *                  the function to return the number of status values, in the
0337     *                  normal way, without attempting to store any values.
0338     * @param status    receives error codes.
0339     * @return          The number of rule status values from rules that determined
0340     *                  the boundary at the current iteration position.
0341     *                  In the event of a U_BUFFER_OVERFLOW_ERROR, the return value
0342     *                  is the total number of status values that were available,
0343     *                  not the reduced number that were actually returned.
0344     * @see getRuleStatus
0345     * @stable ICU 52
0346     */
0347     virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status);
0348 
0349     /**
0350      * Create BreakIterator for word-breaks using the given locale.
0351      * Returns an instance of a BreakIterator implementing word breaks.
0352      * WordBreak is useful for word selection (ex. double click)
0353      * @param where the locale.
0354      * @param status the error code
0355      * @return A BreakIterator for word-breaks.  The UErrorCode& status
0356      * parameter is used to return status information to the user.
0357      * To check whether the construction succeeded or not, you should check
0358      * the value of U_SUCCESS(err).  If you wish more detailed information, you
0359      * can check for informational error results which still indicate success.
0360      * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
0361      * example, 'de_CH' was requested, but nothing was found there, so 'de' was
0362      * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
0363      * used; neither the requested locale nor any of its fall back locales
0364      * could be found.
0365      * The caller owns the returned object and is responsible for deleting it.
0366      * @stable ICU 2.0
0367      */
0368     static BreakIterator* U_EXPORT2
0369     createWordInstance(const Locale& where, UErrorCode& status);
0370 
0371     /**
0372      * Create BreakIterator for line-breaks using specified locale.
0373      * Returns an instance of a BreakIterator implementing line breaks. Line
0374      * breaks are logically possible line breaks, actual line breaks are
0375      * usually determined based on display width.
0376      * LineBreak is useful for word wrapping text.
0377      * @param where the locale.
0378      * @param status The error code.
0379      * @return A BreakIterator for line-breaks.  The UErrorCode& status
0380      * parameter is used to return status information to the user.
0381      * To check whether the construction succeeded or not, you should check
0382      * the value of U_SUCCESS(err).  If you wish more detailed information, you
0383      * can check for informational error results which still indicate success.
0384      * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
0385      * example, 'de_CH' was requested, but nothing was found there, so 'de' was
0386      * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
0387      * used; neither the requested locale nor any of its fall back locales
0388      * could be found.
0389      * The caller owns the returned object and is responsible for deleting it.
0390      * @stable ICU 2.0
0391      */
0392     static BreakIterator* U_EXPORT2
0393     createLineInstance(const Locale& where, UErrorCode& status);
0394 
0395     /**
0396      * Create BreakIterator for character-breaks using specified locale
0397      * Returns an instance of a BreakIterator implementing character breaks.
0398      * Character breaks are boundaries of combining character sequences.
0399      * @param where the locale.
0400      * @param status The error code.
0401      * @return A BreakIterator for character-breaks.  The UErrorCode& status
0402      * parameter is used to return status information to the user.
0403      * To check whether the construction succeeded or not, you should check
0404      * the value of U_SUCCESS(err).  If you wish more detailed information, you
0405      * can check for informational error results which still indicate success.
0406      * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
0407      * example, 'de_CH' was requested, but nothing was found there, so 'de' was
0408      * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
0409      * used; neither the requested locale nor any of its fall back locales
0410      * could be found.
0411      * The caller owns the returned object and is responsible for deleting it.
0412      * @stable ICU 2.0
0413      */
0414     static BreakIterator* U_EXPORT2
0415     createCharacterInstance(const Locale& where, UErrorCode& status);
0416 
0417     /**
0418      * Create BreakIterator for sentence-breaks using specified locale
0419      * Returns an instance of a BreakIterator implementing sentence breaks.
0420      * @param where the locale.
0421      * @param status The error code.
0422      * @return A BreakIterator for sentence-breaks.  The UErrorCode& status
0423      * parameter is used to return status information to the user.
0424      * To check whether the construction succeeded or not, you should check
0425      * the value of U_SUCCESS(err).  If you wish more detailed information, you
0426      * can check for informational error results which still indicate success.
0427      * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
0428      * example, 'de_CH' was requested, but nothing was found there, so 'de' was
0429      * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
0430      * used; neither the requested locale nor any of its fall back locales
0431      * could be found.
0432      * The caller owns the returned object and is responsible for deleting it.
0433      * @stable ICU 2.0
0434      */
0435     static BreakIterator* U_EXPORT2
0436     createSentenceInstance(const Locale& where, UErrorCode& status);
0437 
0438 #ifndef U_HIDE_DEPRECATED_API
0439     /**
0440      * Create BreakIterator for title-casing breaks using the specified locale
0441      * Returns an instance of a BreakIterator implementing title breaks.
0442      * The iterator returned locates title boundaries as described for
0443      * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
0444      * please use a word boundary iterator. See {@link #createWordInstance }.
0445      *
0446      * @param where the locale.
0447      * @param status The error code.
0448      * @return A BreakIterator for title-breaks.  The UErrorCode& status
0449      * parameter is used to return status information to the user.
0450      * To check whether the construction succeeded or not, you should check
0451      * the value of U_SUCCESS(err).  If you wish more detailed information, you
0452      * can check for informational error results which still indicate success.
0453      * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
0454      * example, 'de_CH' was requested, but nothing was found there, so 'de' was
0455      * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
0456      * used; neither the requested locale nor any of its fall back locales
0457      * could be found.
0458      * The caller owns the returned object and is responsible for deleting it.
0459      * @deprecated ICU 64 Use createWordInstance instead.
0460      */
0461     static BreakIterator* U_EXPORT2
0462     createTitleInstance(const Locale& where, UErrorCode& status);
0463 #endif /* U_HIDE_DEPRECATED_API */
0464 
0465     /**
0466      * Get the set of Locales for which TextBoundaries are installed.
0467      * <p><b>Note:</b> this will not return locales added through the register
0468      * call. To see the registered locales too, use the getAvailableLocales
0469      * function that returns a StringEnumeration object </p>
0470      * @param count the output parameter of number of elements in the locale list
0471      * @return available locales
0472      * @stable ICU 2.0
0473      */
0474     static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count);
0475 
0476     /**
0477      * Get name of the object for the desired Locale, in the desired language.
0478      * @param objectLocale must be from getAvailableLocales.
0479      * @param displayLocale specifies the desired locale for output.
0480      * @param name the fill-in parameter of the return value
0481      * Uses best match.
0482      * @return user-displayable name
0483      * @stable ICU 2.0
0484      */
0485     static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
0486                                          const Locale& displayLocale,
0487                                          UnicodeString& name);
0488 
0489     /**
0490      * Get name of the object for the desired Locale, in the language of the
0491      * default locale.
0492      * @param objectLocale must be from getMatchingLocales
0493      * @param name the fill-in parameter of the return value
0494      * @return user-displayable name
0495      * @stable ICU 2.0
0496      */
0497     static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
0498                                          UnicodeString& name);
0499 
0500 #ifndef U_FORCE_HIDE_DEPRECATED_API
0501     /**
0502      * Deprecated functionality. Use clone() instead.
0503      *
0504      * Thread safe client-buffer-based cloning operation
0505      *    Do NOT call delete on a safeclone, since 'new' is not used to create it.
0506      * @param stackBuffer user allocated space for the new clone. If nullptr new memory will be allocated.
0507      * If buffer is not large enough, new memory will be allocated.
0508      * @param BufferSize reference to size of allocated space.
0509      * If BufferSize == 0, a sufficient size for use in cloning will
0510      * be returned ('pre-flighting')
0511      * If BufferSize is not enough for a stack-based safe clone,
0512      * new memory will be allocated.
0513      * @param status to indicate whether the operation went on smoothly or there were errors
0514      *  An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were
0515      *  necessary.
0516      * @return pointer to the new clone
0517      *
0518      * @deprecated ICU 52. Use clone() instead.
0519      */
0520     virtual BreakIterator *  createBufferClone(void *stackBuffer,
0521                                                int32_t &BufferSize,
0522                                                UErrorCode &status) = 0;
0523 #endif  // U_FORCE_HIDE_DEPRECATED_API
0524 
0525 #ifndef U_HIDE_DEPRECATED_API
0526 
0527     /**
0528      *   Determine whether the BreakIterator was created in user memory by
0529      *   createBufferClone(), and thus should not be deleted.  Such objects
0530      *   must be closed by an explicit call to the destructor (not delete).
0531      * @deprecated ICU 52. Always delete the BreakIterator.
0532      */
0533     inline UBool isBufferClone(void);
0534 
0535 #endif /* U_HIDE_DEPRECATED_API */
0536 
0537 #if !UCONFIG_NO_SERVICE
0538     /**
0539      * Register a new break iterator of the indicated kind, to use in the given locale.
0540      * The break iterator will be adopted.  Clones of the iterator will be returned
0541      * if a request for a break iterator of the given kind matches or falls back to
0542      * this locale.
0543      * Because ICU may choose to cache BreakIterators internally, this must
0544      * be called at application startup, prior to any calls to
0545      * BreakIterator::createXXXInstance to avoid undefined behavior.
0546      * @param toAdopt the BreakIterator instance to be adopted
0547      * @param locale the Locale for which this instance is to be registered
0548      * @param kind the type of iterator for which this instance is to be registered
0549      * @param status the in/out status code, no special meanings are assigned
0550      * @return a registry key that can be used to unregister this instance
0551      * @stable ICU 2.4
0552      */
0553     static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt,
0554                                         const Locale& locale,
0555                                         UBreakIteratorType kind,
0556                                         UErrorCode& status);
0557 
0558     /**
0559      * Unregister a previously-registered BreakIterator using the key returned from the
0560      * register call.  Key becomes invalid after a successful call and should not be used again.
0561      * The BreakIterator corresponding to the key will be deleted.
0562      * Because ICU may choose to cache BreakIterators internally, this should
0563      * be called during application shutdown, after all calls to
0564      * BreakIterator::createXXXInstance to avoid undefined behavior.
0565      * @param key the registry key returned by a previous call to registerInstance
0566      * @param status the in/out status code, no special meanings are assigned
0567      * @return true if the iterator for the key was successfully unregistered
0568      * @stable ICU 2.4
0569      */
0570     static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status);
0571 
0572     /**
0573      * Return a StringEnumeration over the locales available at the time of the call,
0574      * including registered locales.
0575      * @return a StringEnumeration over the locales available at the time of the call
0576      * @stable ICU 2.4
0577      */
0578     static StringEnumeration* U_EXPORT2 getAvailableLocales(void);
0579 #endif
0580 
0581     /**
0582      * Returns the locale for this break iterator. Two flavors are available: valid and
0583      * actual locale.
0584      * @stable ICU 2.8
0585      */
0586     Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
0587 
0588 #ifndef U_HIDE_INTERNAL_API
0589     /** Get the locale for this break iterator object. You can choose between valid and actual locale.
0590      *  @param type type of the locale we're looking for (valid or actual)
0591      *  @param status error code for the operation
0592      *  @return the locale
0593      *  @internal
0594      */
0595     const char *getLocaleID(ULocDataLocaleType type, UErrorCode& status) const;
0596 #endif  /* U_HIDE_INTERNAL_API */
0597 
0598     /**
0599      *  Set the subject text string upon which the break iterator is operating
0600      *  without changing any other aspect of the matching state.
0601      *  The new and previous text strings must have the same content.
0602      *
0603      *  This function is intended for use in environments where ICU is operating on
0604      *  strings that may move around in memory.  It provides a mechanism for notifying
0605      *  ICU that the string has been relocated, and providing a new UText to access the
0606      *  string in its new position.
0607      *
0608      *  Note that the break iterator implementation never copies the underlying text
0609      *  of a string being processed, but always operates directly on the original text
0610      *  provided by the user. Refreshing simply drops the references to the old text
0611      *  and replaces them with references to the new.
0612      *
0613      *  Caution:  this function is normally used only by very specialized,
0614      *  system-level code.  One example use case is with garbage collection that moves
0615      *  the text in memory.
0616      *
0617      * @param input      The new (moved) text string.
0618      * @param status     Receives errors detected by this function.
0619      * @return           *this
0620      *
0621      * @stable ICU 49
0622      */
0623     virtual BreakIterator &refreshInputText(UText *input, UErrorCode &status) = 0;
0624 
0625  private:
0626     static BreakIterator* buildInstance(const Locale& loc, const char *type, UErrorCode& status);
0627     static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status);
0628     static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status);
0629 
0630     friend class ICUBreakIteratorFactory;
0631     friend class ICUBreakIteratorService;
0632 
0633 protected:
0634     // Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API
0635     // or else the compiler will create a public ones.
0636     /** @internal */
0637     BreakIterator();
0638     /** @internal */
0639     BreakIterator (const BreakIterator &other);
0640 #ifndef U_HIDE_INTERNAL_API
0641     /** @internal */
0642     BreakIterator (const Locale& valid, const Locale &actual);
0643     /** @internal. Assignment Operator, used by RuleBasedBreakIterator. */
0644     BreakIterator &operator = (const BreakIterator &other);
0645 #endif  /* U_HIDE_INTERNAL_API */
0646 
0647 private:
0648 
0649     /** @internal (private) */
0650     char actualLocale[ULOC_FULLNAME_CAPACITY];
0651     char validLocale[ULOC_FULLNAME_CAPACITY];
0652     char requestLocale[ULOC_FULLNAME_CAPACITY];
0653 };
0654 
0655 #ifndef U_HIDE_DEPRECATED_API
0656 
0657 inline UBool BreakIterator::isBufferClone()
0658 {
0659     return false;
0660 }
0661 
0662 #endif /* U_HIDE_DEPRECATED_API */
0663 
0664 U_NAMESPACE_END
0665 
0666 #endif /* #if !UCONFIG_NO_BREAK_ITERATION */
0667 
0668 #endif /* U_SHOW_CPLUSPLUS_API */
0669 
0670 #endif // BRKITER_H
0671 //eof