Gecko [ dallasfobana2023.variationbd.com ]

Name	Size	Permission
alphaindex.h	26.54 KB	-rw-r--r--
appendable.h	8.54 KB	-rw-r--r--
basictz.h	9.99 KB	-rw-r--r--
brkiter.h	27.83 KB	-rw-r--r--
bytestream.h	10.75 KB	-rw-r--r--
bytestrie.h	20.8 KB	-rw-r--r--
bytestriebuilder.h	7.48 KB	-rw-r--r--
calendar.h	107.68 KB	-rw-r--r--
caniter.h	7.53 KB	-rw-r--r--
casemap.h	25.42 KB	-rw-r--r--
char16ptr.h	7.22 KB	-rw-r--r--
chariter.h	23.79 KB	-rw-r--r--
choicfmt.h	23.99 KB	-rw-r--r--
coleitr.h	13.77 KB	-rw-r--r--
coll.h	56.28 KB	-rw-r--r--
compactdecimalformat.h	6.88 KB	-rw-r--r--
curramt.h	3.67 KB	-rw-r--r--
currpinf.h	7.3 KB	-rw-r--r--
currunit.h	4.02 KB	-rw-r--r--
datefmt.h	40.7 KB	-rw-r--r--
dbbi.h	1.19 KB	-rw-r--r--
dcfmtsym.h	20.93 KB	-rw-r--r--
decimfmt.h	87.46 KB	-rw-r--r--
displayoptions.h	7.08 KB	-rw-r--r--
docmain.h	7.46 KB	-rw-r--r--
dtfmtsym.h	38.21 KB	-rw-r--r--
dtintrv.h	3.84 KB	-rw-r--r--
dtitvfmt.h	48.87 KB	-rw-r--r--
dtitvinf.h	18.63 KB	-rw-r--r--
dtptngen.h	28.05 KB	-rw-r--r--
dtrule.h	8.66 KB	-rw-r--r--
edits.h	20.73 KB	-rw-r--r--
enumset.h	2.08 KB	-rw-r--r--
errorcode.h	4.84 KB	-rw-r--r--
fieldpos.h	8.69 KB	-rw-r--r--
filteredbrk.h	5.37 KB	-rw-r--r--
fmtable.h	24.36 KB	-rw-r--r--
format.h	12.5 KB	-rw-r--r--
formattednumber.h	6.28 KB	-rw-r--r--
formattedvalue.h	9.75 KB	-rw-r--r--
fpositer.h	3.03 KB	-rw-r--r--
gender.h	3.35 KB	-rw-r--r--
gregocal.h	30.3 KB	-rw-r--r--
icudataver.h	1.02 KB	-rw-r--r--
icuplug.h	12.1 KB	-rw-r--r--
idna.h	12.71 KB	-rw-r--r--
listformatter.h	8.59 KB	-rw-r--r--
localebuilder.h	11.08 KB	-rw-r--r--
localematcher.h	26.86 KB	-rw-r--r--
localpointer.h	19.55 KB	-rw-r--r--
locdspnm.h	7.12 KB	-rw-r--r--
locid.h	48.31 KB	-rw-r--r--
measfmt.h	11.41 KB	-rw-r--r--
measunit.h	108.23 KB	-rw-r--r--
measure.h	4.68 KB	-rw-r--r--
messageformat2.h	18.13 KB	-rw-r--r--
messageformat2_arguments.h	4.3 KB	-rw-r--r--
messageformat2_data_model.h	123 KB	-rw-r--r--
messageformat2_data_model_name...	784 B	-rw-r--r--
messageformat2_formattable.h	38.29 KB	-rw-r--r--
messageformat2_function_regist...	18 KB	-rw-r--r--
messagepattern.h	33.72 KB	-rw-r--r--
msgfmt.h	44.2 KB	-rw-r--r--
normalizer2.h	34.73 KB	-rw-r--r--
normlzr.h	30.79 KB	-rw-r--r--
nounit.h	2.24 KB	-rw-r--r--
numberformatter.h	90.74 KB	-rw-r--r--
numberrangeformatter.h	26.05 KB	-rw-r--r--
numfmt.h	50.16 KB	-rw-r--r--
numsys.h	7.22 KB	-rw-r--r--
parseerr.h	3.08 KB	-rw-r--r--
parsepos.h	5.56 KB	-rw-r--r--
platform.h	26.66 KB	-rw-r--r--
plurfmt.h	25.07 KB	-rw-r--r--
plurrule.h	20.63 KB	-rw-r--r--
ptypes.h	2.16 KB	-rw-r--r--
putil.h	6.32 KB	-rw-r--r--
rbbi.h	32.04 KB	-rw-r--r--
rbnf.h	50.53 KB	-rw-r--r--
rbtz.h	15.75 KB	-rw-r--r--
regex.h	84.45 KB	-rw-r--r--
region.h	9.2 KB	-rw-r--r--
reldatefmt.h	22.36 KB	-rw-r--r--
rep.h	9.38 KB	-rw-r--r--
resbund.h	18.03 KB	-rw-r--r--
schriter.h	6.09 KB	-rw-r--r--
scientificnumberformatter.h	6.44 KB	-rw-r--r--
search.h	22.21 KB	-rw-r--r--
selfmt.h	14.35 KB	-rw-r--r--
simpleformatter.h	12.58 KB	-rw-r--r--
simplenumberformatter.h	9.18 KB	-rw-r--r--
simpletz.h	45.62 KB	-rw-r--r--
smpdtfmt.h	57.06 KB	-rw-r--r--
sortkey.h	11.12 KB	-rw-r--r--
std_string.h	1.05 KB	-rw-r--r--
strenum.h	9.96 KB	-rw-r--r--
stringoptions.h	5.79 KB	-rw-r--r--
stringpiece.h	10.02 KB	-rw-r--r--
stringtriebuilder.h	15.5 KB	-rw-r--r--
stsearch.h	21.43 KB	-rw-r--r--
symtable.h	4.28 KB	-rw-r--r--
tblcoll.h	36.93 KB	-rw-r--r--
timezone.h	45.64 KB	-rw-r--r--
tmunit.h	3.4 KB	-rw-r--r--
tmutamt.h	4.9 KB	-rw-r--r--
tmutfmt.h	7.42 KB	-rw-r--r--
translit.h	65.8 KB	-rw-r--r--
tzfmt.h	42.95 KB	-rw-r--r--
tznames.h	16.85 KB	-rw-r--r--
tzrule.h	34.81 KB	-rw-r--r--
tztrans.h	6.11 KB	-rw-r--r--
ubidi.h	89.61 KB	-rw-r--r--
ubiditransform.h	12.71 KB	-rw-r--r--
ubrk.h	24.43 KB	-rw-r--r--
ucal.h	64.01 KB	-rw-r--r--
ucasemap.h	15.21 KB	-rw-r--r--
ucat.h	5.35 KB	-rw-r--r--
uchar.h	150.13 KB	-rw-r--r--
ucharstrie.h	22.56 KB	-rw-r--r--
ucharstriebuilder.h	7.48 KB	-rw-r--r--
uchriter.h	13.24 KB	-rw-r--r--
uclean.h	11.21 KB	-rw-r--r--
ucnv.h	83.34 KB	-rw-r--r--
ucnv_cb.h	6.58 KB	-rw-r--r--
ucnv_err.h	20.98 KB	-rw-r--r--
ucnvsel.h	6.24 KB	-rw-r--r--
ucol.h	62.7 KB	-rw-r--r--
ucoleitr.h	9.82 KB	-rw-r--r--
uconfig.h	12.56 KB	-rw-r--r--
ucpmap.h	5.54 KB	-rw-r--r--
ucptrie.h	22.51 KB	-rw-r--r--
ucsdet.h	14.69 KB	-rw-r--r--
ucurr.h	16.72 KB	-rw-r--r--
udat.h	62.36 KB	-rw-r--r--
udata.h	15.63 KB	-rw-r--r--
udateintervalformat.h	11.93 KB	-rw-r--r--
udatpg.h	30.13 KB	-rw-r--r--
udisplaycontext.h	5.94 KB	-rw-r--r--
udisplayoptions.h	8.86 KB	-rw-r--r--
uenum.h	7.79 KB	-rw-r--r--
ufieldpositer.h	4.41 KB	-rw-r--r--
uformattable.h	10.97 KB	-rw-r--r--
uformattednumber.h	8.09 KB	-rw-r--r--
uformattedvalue.h	12.25 KB	-rw-r--r--
ugender.h	2.06 KB	-rw-r--r--
uidna.h	33.43 KB	-rw-r--r--
uiter.h	22.75 KB	-rw-r--r--
uldnames.h	10.48 KB	-rw-r--r--
ulistformatter.h	10.78 KB	-rw-r--r--
uloc.h	55.38 KB	-rw-r--r--
ulocale.h	6.35 KB	-rw-r--r--
ulocbuilder.h	16.73 KB	-rw-r--r--
ulocdata.h	11.3 KB	-rw-r--r--
umachine.h	14.59 KB	-rw-r--r--
umisc.h	1.34 KB	-rw-r--r--
umsg.h	24.25 KB	-rw-r--r--
umutablecptrie.h	8.3 KB	-rw-r--r--
unifilt.h	4 KB	-rw-r--r--
unifunct.h	4.05 KB	-rw-r--r--
unimatch.h	6.1 KB	-rw-r--r--
unirepl.h	3.38 KB	-rw-r--r--
uniset.h	66.82 KB	-rw-r--r--
unistr.h	171.33 KB	-rw-r--r--
unorm.h	20.55 KB	-rw-r--r--
unorm2.h	25.71 KB	-rw-r--r--
unum.h	55.16 KB	-rw-r--r--
unumberformatter.h	19.68 KB	-rw-r--r--
unumberoptions.h	5.23 KB	-rw-r--r--
unumberrangeformatter.h	15.35 KB	-rw-r--r--
unumsys.h	7.26 KB	-rw-r--r--
uobject.h	10.66 KB	-rw-r--r--
upluralrules.h	8.79 KB	-rw-r--r--
uregex.h	71.99 KB	-rw-r--r--
uregion.h	9.81 KB	-rw-r--r--
ureldatefmt.h	16.98 KB	-rw-r--r--
urename.h	141.31 KB	-rw-r--r--
urep.h	5.38 KB	-rw-r--r--
ures.h	36.65 KB	-rw-r--r--
uscript.h	27.89 KB	-rw-r--r--
usearch.h	39.21 KB	-rw-r--r--
uset.h	45.56 KB	-rw-r--r--
usetiter.h	9.63 KB	-rw-r--r--
ushape.h	18 KB	-rw-r--r--
usimplenumberformatter.h	7.63 KB	-rw-r--r--
uspoof.h	80.32 KB	-rw-r--r--
usprep.h	8.19 KB	-rw-r--r--
ustdio.h	38.56 KB	-rw-r--r--
ustream.h	1.89 KB	-rw-r--r--
ustring.h	72.13 KB	-rw-r--r--
ustringtrie.h	3.15 KB	-rw-r--r--
utext.h	58.1 KB	-rw-r--r--
utf.h	7.87 KB	-rw-r--r--
utf16.h	23.35 KB	-rw-r--r--
utf32.h	763 B	-rw-r--r--
utf8.h	30.83 KB	-rw-r--r--
utf_old.h	45.8 KB	-rw-r--r--
utmscale.h	13.78 KB	-rw-r--r--
utrace.h	17.18 KB	-rw-r--r--
utrans.h	25.54 KB	-rw-r--r--
utypes.h	33.71 KB	-rw-r--r--
uvernum.h	6.33 KB	-rw-r--r--
uversion.h	5.99 KB	-rw-r--r--
vtzone.h	20.68 KB	-rw-r--r--

Code Editor : brkiter.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
********************************************************************************
*   Copyright (C) 1997-2016, International Business Machines
*   Corporation and others.  All Rights Reserved.
********************************************************************************
*
* File brkiter.h
*
* Modification History:
*
*   Date        Name        Description
*   02/18/97    aliu        Added typedef for TextCount.  Made DONE const.
*   05/07/97    aliu        Fixed DLL declaration.
*   07/09/97    jfitz       Renamed BreakIterator and interface synced with JDK
*   08/11/98    helena      Sync-up JDK1.2.
*   01/13/2000  helena      Added UErrorCode parameter to createXXXInstance methods.
********************************************************************************
*/

#ifndef BRKITER_H
#define BRKITER_H

#include "unicode/utypes.h"

/**
 * \file
 * \brief C++ API: Break Iterator.
 */

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

#if UCONFIG_NO_BREAK_ITERATION

U_NAMESPACE_BEGIN

/*
 * Allow the declaration of APIs with pointers to BreakIterator
 * even when break iteration is removed from the build.
 */
class BreakIterator;

U_NAMESPACE_END

#else

#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/chariter.h"
#include "unicode/locid.h"
#include "unicode/ubrk.h"
#include "unicode/strenum.h"
#include "unicode/utext.h"
#include "unicode/umisc.h"

U_NAMESPACE_BEGIN

/**
 * The BreakIterator class implements methods for finding the location
 * of boundaries in text. BreakIterator is an abstract base class.
 * Instances of BreakIterator maintain a current position and scan over
 * text returning the index of characters where boundaries occur.
 * 
 * Line boundary analysis determines where a text string can be broken
 * when line-wrapping. The mechanism correctly handles punctuation and
 * hyphenated words.
 * 
 * Sentence boundary analysis allows selection with correct
 * interpretation of periods within numbers and abbreviations, and
 * trailing punctuation marks such as quotation marks and parentheses.
 * 
 * Word boundary analysis is used by search and replace functions, as
 * well as within text editing applications that allow the user to
 * select words with a double click. Word selection provides correct
 * interpretation of punctuation marks within and following
 * words. Characters that are not part of a word, such as symbols or
 * punctuation marks, have word-breaks on both sides.
 * 
 * Character boundary analysis allows users to interact with
 * characters as they expect to, for example, when moving the cursor
 * through a text string. Character boundary analysis provides correct
 * navigation of through character strings, regardless of how the
 * character is stored. For example, an accented character might be
 * stored as a base character and a diacritical mark. What users
 * consider to be a character can differ between languages.
 * 
 * The text boundary positions are found according to the rules
 * described in Unicode Standard Annex #29, Text Boundaries, and
 * Unicode Standard Annex #14, Line Breaking Properties. These
 * are available at http://www.unicode.org/reports/tr14/ and
 * http://www.unicode.org/reports/tr29/.
 * 
 * In addition to the C++ API defined in this header file, a
 * plain C API with equivalent functionality is defined in the
 * file ubrk.h
 * 
 * Code snippets illustrating the use of the Break Iterator APIs
 * are available in the ICU User Guide,
 * https://unicode-org.github.io/icu/userguide/boundaryanalysis/
 * and in the sample program icu/source/samples/break/break.cpp
 *
 */
class U_COMMON_API BreakIterator : public UObject {
public:
 /**
 * destructor
 * @stable ICU 2.0
 */
 virtual ~BreakIterator();

/**
 * Return true if another object is semantically equal to this
 * one. The other object should be an instance of the same subclass of
 * BreakIterator. Objects of different subclasses are considered
 * unequal.
 * 
 * Return true if this BreakIterator is at the same position in the
 * same text, and is the same class and type (word, line, etc.) of
 * BreakIterator, as the argument. Text is considered the same if
 * it contains the same characters, it need not be the same
 * object, and styles are not considered.
 * @stable ICU 2.0
 */
 virtual bool operator==(const BreakIterator&) const = 0;

/**
     * Returns the complement of the result of operator==
     * @param rhs The BreakIterator to be compared for inequality
     * @return the complement of the result of operator==
     * @stable ICU 2.0
     */
    bool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); }

/**
     * Return a polymorphic copy of this object.  This is an abstract
     * method which subclasses implement.
     * @stable ICU 2.0
     */
    virtual BreakIterator* clone() const = 0;

/**
     * Return a polymorphic class ID for this object. Different subclasses
     * will return distinct unequal values.
     * @stable ICU 2.0
     */
    virtual UClassID getDynamicClassID() const override = 0;

/**
     * Return a CharacterIterator over the text being analyzed.
     * @stable ICU 2.0
     */
    virtual CharacterIterator& getText() const = 0;

/**
      *  Get a UText for the text being analyzed.
      *  The returned UText is a shallow clone of the UText used internally
      *  by the break iterator implementation.  It can safely be used to
      *  access the text without impacting any break iterator operations,
      *  but the underlying text itself must not be altered.
      *
      * @param fillIn A UText to be filled in.  If nullptr, a new UText will be
      *           allocated to hold the result.
      * @param status receives any error codes.
      * @return   The current UText for this break iterator.  If an input
      *           UText was provided, it will always be returned.
      * @stable ICU 3.4
      */
     virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0;

/**
     * Change the text over which this operates. The text boundary is
     * reset to the start.
     *
     * The BreakIterator will retain a reference to the supplied string.
     * The caller must not modify or delete the text while the BreakIterator
     * retains the reference.
     *
     * @param text The UnicodeString used to change the text.
     * @stable ICU 2.0
     */
    virtual void  setText(const UnicodeString &text) = 0;

/**
     * Reset the break iterator to operate over the text represented by
     * the UText.  The iterator position is reset to the start.
     *
     * This function makes a shallow clone of the supplied UText.  This means
     * that the caller is free to immediately close or otherwise reuse the
     * Utext that was passed as a parameter, but that the underlying text itself
     * must not be altered while being referenced by the break iterator.
     *
     * All index positions returned by break iterator functions are
     * native indices from the UText. For example, when breaking UTF-8
     * encoded text, the break positions returned by next(), previous(), etc.
     * will be UTF-8 string indices, not UTF-16 positions.
     *
     * @param text The UText used to change the text.
     * @param status receives any error codes.
     * @stable ICU 3.4
     */
    virtual void  setText(UText *text, UErrorCode &status) = 0;

/**
     * Change the text over which this operates. The text boundary is
     * reset to the start.
     * Note that setText(UText *) provides similar functionality to this function,
     * and is more efficient.
     * @param it The CharacterIterator used to change the text.
     * @stable ICU 2.0
     */
    virtual void  adoptText(CharacterIterator* it) = 0;

enum {
        /**
         * DONE is returned by previous() and next() after all valid
         * boundaries have been returned.
         * @stable ICU 2.0
         */
        DONE = (int32_t)-1
    };

/**
     * Sets the current iteration position to the beginning of the text, position zero.
     * @return The offset of the beginning of the text, zero.
     * @stable ICU 2.0
     */
    virtual int32_t first() = 0;

/**
     * Set the iterator position to the index immediately BEYOND the last character in the text being scanned.
     * @return The index immediately BEYOND the last character in the text being scanned.
     * @stable ICU 2.0
     */
    virtual int32_t last() = 0;

/**
     * Set the iterator position to the boundary preceding the current boundary.
     * @return The character index of the previous text boundary or DONE if all
     * boundaries have been returned.
     * @stable ICU 2.0
     */
    virtual int32_t previous() = 0;

/**
     * Advance the iterator to the boundary following the current boundary.
     * @return The character index of the next text boundary or DONE if all
     * boundaries have been returned.
     * @stable ICU 2.0
     */
    virtual int32_t next() = 0;

/**
     * Return character index of the current iterator position within the text.
     * @return The boundary most recently returned.
     * @stable ICU 2.0
     */
    virtual int32_t current() const = 0;

/**
     * Advance the iterator to the first boundary following the specified offset.
     * The value returned is always greater than the offset or
     * the value BreakIterator.DONE
     * @param offset the offset to begin scanning.
     * @return The first boundary after the specified offset.
     * @stable ICU 2.0
     */
    virtual int32_t following(int32_t offset) = 0;

/**
     * Set the iterator position to the first boundary preceding the specified offset.
     * The value returned is always smaller than the offset or
     * the value BreakIterator.DONE
     * @param offset the offset to begin scanning.
     * @return The first boundary before the specified offset.
     * @stable ICU 2.0
     */
    virtual int32_t preceding(int32_t offset) = 0;

/**
     * Return true if the specified position is a boundary position.
     * As a side effect, the current position of the iterator is set
     * to the first boundary position at or following the specified offset.
     * @param offset the offset to check.
     * @return True if "offset" is a boundary position.
     * @stable ICU 2.0
     */
    virtual UBool isBoundary(int32_t offset) = 0;

/**
     * Set the iterator position to the nth boundary from the current boundary
     * @param n the number of boundaries to move by.  A value of 0
     * does nothing.  Negative values move to previous boundaries
     * and positive values move to later boundaries.
     * @return The new iterator position, or
     * DONE if there are fewer than |n| boundaries in the specified direction.
     * @stable ICU 2.0
     */
    virtual int32_t next(int32_t n) = 0;

/**
 * For RuleBasedBreakIterators, return the status tag from the break rule
 * that determined the boundary at the current iteration position.
 * 
 * For break iterator types that do not support a rule status,
 * a default value of 0 is returned.
 * 
 * @return the status from the break rule that determined the boundary at
 * the current iteration position.
 * @see RuleBaseBreakIterator::getRuleStatus()
 * @see UWordBreak
 * @stable ICU 52
 */
 virtual int32_t getRuleStatus() const;

/**
 * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s)
 * that determined the boundary at the current iteration position.
 * 
 * For break iterator types that do not support rule status,
 * no values are returned.
 * 
 * The returned status value(s) are stored into an array provided by the caller.
 * The values are stored in sorted (ascending) order.
 * If the capacity of the output array is insufficient to hold the data,
 * the output will be truncated to the available length, and a
 * U_BUFFER_OVERFLOW_ERROR will be signaled.
 * 
 * @see RuleBaseBreakIterator::getRuleStatusVec
 *
 * @param fillInVec an array to be filled in with the status values.
 * @param capacity the length of the supplied vector. A length of zero causes
 * the function to return the number of status values, in the
 * normal way, without attempting to store any values.
 * @param status receives error codes.
 * @return The number of rule status values from rules that determined
 * the boundary at the current iteration position.
 * In the event of a U_BUFFER_OVERFLOW_ERROR, the return value
 * is the total number of status values that were available,
 * not the reduced number that were actually returned.
 * @see getRuleStatus
 * @stable ICU 52
 */
 virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status);

/**
     * Create BreakIterator for word-breaks using the given locale.
     * Returns an instance of a BreakIterator implementing word breaks.
     * WordBreak is useful for word selection (ex. double click)
     * @param where the locale.
     * @param status the error code
     * @return A BreakIterator for word-breaks.  The UErrorCode& status
     * parameter is used to return status information to the user.
     * To check whether the construction succeeded or not, you should check
     * the value of U_SUCCESS(err).  If you wish more detailed information, you
     * can check for informational error results which still indicate success.
     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
     * used; neither the requested locale nor any of its fall back locales
     * could be found.
     * The caller owns the returned object and is responsible for deleting it.
     * @stable ICU 2.0
     */
    static BreakIterator* U_EXPORT2
    createWordInstance(const Locale& where, UErrorCode& status);

/**
     * Create BreakIterator for line-breaks using specified locale.
     * Returns an instance of a BreakIterator implementing line breaks. Line
     * breaks are logically possible line breaks, actual line breaks are
     * usually determined based on display width.
     * LineBreak is useful for word wrapping text.
     * @param where the locale.
     * @param status The error code.
     * @return A BreakIterator for line-breaks.  The UErrorCode& status
     * parameter is used to return status information to the user.
     * To check whether the construction succeeded or not, you should check
     * the value of U_SUCCESS(err).  If you wish more detailed information, you
     * can check for informational error results which still indicate success.
     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
     * used; neither the requested locale nor any of its fall back locales
     * could be found.
     * The caller owns the returned object and is responsible for deleting it.
     * @stable ICU 2.0
     */
    static BreakIterator* U_EXPORT2
    createLineInstance(const Locale& where, UErrorCode& status);

/**
     * Create BreakIterator for character-breaks using specified locale
     * Returns an instance of a BreakIterator implementing character breaks.
     * Character breaks are boundaries of combining character sequences.
     * @param where the locale.
     * @param status The error code.
     * @return A BreakIterator for character-breaks.  The UErrorCode& status
     * parameter is used to return status information to the user.
     * To check whether the construction succeeded or not, you should check
     * the value of U_SUCCESS(err).  If you wish more detailed information, you
     * can check for informational error results which still indicate success.
     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
     * used; neither the requested locale nor any of its fall back locales
     * could be found.
     * The caller owns the returned object and is responsible for deleting it.
     * @stable ICU 2.0
     */
    static BreakIterator* U_EXPORT2
    createCharacterInstance(const Locale& where, UErrorCode& status);

/**
     * Create BreakIterator for sentence-breaks using specified locale
     * Returns an instance of a BreakIterator implementing sentence breaks.
     * @param where the locale.
     * @param status The error code.
     * @return A BreakIterator for sentence-breaks.  The UErrorCode& status
     * parameter is used to return status information to the user.
     * To check whether the construction succeeded or not, you should check
     * the value of U_SUCCESS(err).  If you wish more detailed information, you
     * can check for informational error results which still indicate success.
     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
     * used; neither the requested locale nor any of its fall back locales
     * could be found.
     * The caller owns the returned object and is responsible for deleting it.
     * @stable ICU 2.0
     */
    static BreakIterator* U_EXPORT2
    createSentenceInstance(const Locale& where, UErrorCode& status);

#ifndef U_HIDE_DEPRECATED_API
    /**
     * Create BreakIterator for title-casing breaks using the specified locale
     * Returns an instance of a BreakIterator implementing title breaks.
     * The iterator returned locates title boundaries as described for
     * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
     * please use a word boundary iterator. See {@link #createWordInstance }.
     *
     * @param where the locale.
     * @param status The error code.
     * @return A BreakIterator for title-breaks.  The UErrorCode& status
     * parameter is used to return status information to the user.
     * To check whether the construction succeeded or not, you should check
     * the value of U_SUCCESS(err).  If you wish more detailed information, you
     * can check for informational error results which still indicate success.
     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
     * used; neither the requested locale nor any of its fall back locales
     * could be found.
     * The caller owns the returned object and is responsible for deleting it.
     * @deprecated ICU 64 Use createWordInstance instead.
     */
    static BreakIterator* U_EXPORT2
    createTitleInstance(const Locale& where, UErrorCode& status);
#endif /* U_HIDE_DEPRECATED_API */

/**
 * Get the set of Locales for which TextBoundaries are installed.
 * Note: this will not return locales added through the register
 * call. To see the registered locales too, use the getAvailableLocales
 * function that returns a StringEnumeration object 
 * @param count the output parameter of number of elements in the locale list
 * @return available locales
 * @stable ICU 2.0
 */
 static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count);

/**
     * Get name of the object for the desired Locale, in the desired language.
     * @param objectLocale must be from getAvailableLocales.
     * @param displayLocale specifies the desired locale for output.
     * @param name the fill-in parameter of the return value
     * Uses best match.
     * @return user-displayable name
     * @stable ICU 2.0
     */
    static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
                                         const Locale& displayLocale,
                                         UnicodeString& name);

/**
     * Get name of the object for the desired Locale, in the language of the
     * default locale.
     * @param objectLocale must be from getMatchingLocales
     * @param name the fill-in parameter of the return value
     * @return user-displayable name
     * @stable ICU 2.0
     */
    static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
                                         UnicodeString& name);

#ifndef U_FORCE_HIDE_DEPRECATED_API
    /**
     * Deprecated functionality. Use clone() instead.
     *
     * Thread safe client-buffer-based cloning operation
     *    Do NOT call delete on a safeclone, since 'new' is not used to create it.
     * @param stackBuffer user allocated space for the new clone. If nullptr new memory will be allocated.
     * If buffer is not large enough, new memory will be allocated.
     * @param BufferSize reference to size of allocated space.
     * If BufferSize == 0, a sufficient size for use in cloning will
     * be returned ('pre-flighting')
     * If BufferSize is not enough for a stack-based safe clone,
     * new memory will be allocated.
     * @param status to indicate whether the operation went on smoothly or there were errors
     *  An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were
     *  necessary.
     * @return pointer to the new clone
     *
     * @deprecated ICU 52. Use clone() instead.
     */
    virtual BreakIterator *  createBufferClone(void *stackBuffer,
                                               int32_t &BufferSize,
                                               UErrorCode &status) = 0;
#endif  // U_FORCE_HIDE_DEPRECATED_API

#ifndef U_HIDE_DEPRECATED_API

/**
     *   Determine whether the BreakIterator was created in user memory by
     *   createBufferClone(), and thus should not be deleted.  Such objects
     *   must be closed by an explicit call to the destructor (not delete).
     * @deprecated ICU 52. Always delete the BreakIterator.
     */
    inline UBool isBufferClone();

#endif /* U_HIDE_DEPRECATED_API */

#if !UCONFIG_NO_SERVICE
    /**
     * Register a new break iterator of the indicated kind, to use in the given locale.
     * The break iterator will be adopted.  Clones of the iterator will be returned
     * if a request for a break iterator of the given kind matches or falls back to
     * this locale.
     * Because ICU may choose to cache BreakIterators internally, this must
     * be called at application startup, prior to any calls to
     * BreakIterator::createXXXInstance to avoid undefined behavior.
     * @param toAdopt the BreakIterator instance to be adopted
     * @param locale the Locale for which this instance is to be registered
     * @param kind the type of iterator for which this instance is to be registered
     * @param status the in/out status code, no special meanings are assigned
     * @return a registry key that can be used to unregister this instance
     * @stable ICU 2.4
     */
    static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt,
                                        const Locale& locale,
                                        UBreakIteratorType kind,
                                        UErrorCode& status);

/**
     * Unregister a previously-registered BreakIterator using the key returned from the
     * register call.  Key becomes invalid after a successful call and should not be used again.
     * The BreakIterator corresponding to the key will be deleted.
     * Because ICU may choose to cache BreakIterators internally, this should
     * be called during application shutdown, after all calls to
     * BreakIterator::createXXXInstance to avoid undefined behavior.
     * @param key the registry key returned by a previous call to registerInstance
     * @param status the in/out status code, no special meanings are assigned
     * @return true if the iterator for the key was successfully unregistered
     * @stable ICU 2.4
     */
    static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status);

/**
     * Return a StringEnumeration over the locales available at the time of the call,
     * including registered locales.
     * @return a StringEnumeration over the locales available at the time of the call
     * @stable ICU 2.4
     */
    static StringEnumeration* U_EXPORT2 getAvailableLocales();
#endif

/**
     * Returns the locale for this break iterator. Two flavors are available: valid and
     * actual locale.
     * @stable ICU 2.8
     */
    Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;

#ifndef U_HIDE_INTERNAL_API
    /** Get the locale for this break iterator object. You can choose between valid and actual locale.
     *  @param type type of the locale we're looking for (valid or actual)
     *  @param status error code for the operation
     *  @return the locale
     *  @internal
     */
    const char *getLocaleID(ULocDataLocaleType type, UErrorCode& status) const;
#endif  /* U_HIDE_INTERNAL_API */

/**
     *  Set the subject text string upon which the break iterator is operating
     *  without changing any other aspect of the matching state.
     *  The new and previous text strings must have the same content.
     *
     *  This function is intended for use in environments where ICU is operating on
     *  strings that may move around in memory.  It provides a mechanism for notifying
     *  ICU that the string has been relocated, and providing a new UText to access the
     *  string in its new position.
     *
     *  Note that the break iterator implementation never copies the underlying text
     *  of a string being processed, but always operates directly on the original text
     *  provided by the user. Refreshing simply drops the references to the old text
     *  and replaces them with references to the new.
     *
     *  Caution:  this function is normally used only by very specialized,
     *  system-level code.  One example use case is with garbage collection that moves
     *  the text in memory.
     *
     * @param input      The new (moved) text string.
     * @param status     Receives errors detected by this function.
     * @return           *this
     *
     * @stable ICU 49
     */
    virtual BreakIterator &refreshInputText(UText *input, UErrorCode &status) = 0;

private:
    static BreakIterator* buildInstance(const Locale& loc, const char *type, UErrorCode& status);
    static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status);
    static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status);

friend class ICUBreakIteratorFactory;
    friend class ICUBreakIteratorService;

protected:
    // Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API
    // or else the compiler will create a public ones.
    /** @internal */
    BreakIterator();
    /** @internal */
    BreakIterator (const BreakIterator &other);
#ifndef U_HIDE_INTERNAL_API
    /** @internal */
    BreakIterator (const Locale& valid, const Locale &actual);
    /** @internal. Assignment Operator, used by RuleBasedBreakIterator. */
    BreakIterator &operator = (const BreakIterator &other);
#endif  /* U_HIDE_INTERNAL_API */

private:

/** @internal (private) */
    char actualLocale[ULOC_FULLNAME_CAPACITY];
    char validLocale[ULOC_FULLNAME_CAPACITY];
    char requestLocale[ULOC_FULLNAME_CAPACITY];
};

#ifndef U_HIDE_DEPRECATED_API

inline UBool BreakIterator::isBufferClone()
{
    return false;
}

#endif /* U_HIDE_DEPRECATED_API */

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_BREAK_ITERATION */

#endif /* U_SHOW_CPLUSPLUS_API */

#endif // BRKITER_H
//eof

${this.title}

Code Editor : brkiter.h