/
usr
/
include
/
unicode
/
/usr/include/unicode
mkdir
upload
Name
Size
Mode
Actions
alphaindex.h
27158
0644
edit
dl
rm
appendable.h
8739
0644
edit
dl
rm
basictz.h
10163
0644
edit
dl
rm
brkiter.h
28478
0644
edit
dl
rm
bytestream.h
11013
0644
edit
dl
rm
bytestrie.h
21268
0644
edit
dl
rm
bytestriebuilder.h
7640
0644
edit
dl
rm
calendar.h
108424
0644
edit
dl
rm
caniter.h
7621
0644
edit
dl
rm
casemap.h
25933
0644
edit
dl
rm
char16ptr.h
7393
0644
edit
dl
rm
chariter.h
24638
0644
edit
dl
rm
choicfmt.h
24544
0644
edit
dl
rm
coleitr.h
14102
0644
edit
dl
rm
coll.h
57615
0644
edit
dl
rm
compactdecimalformat.h
7047
0644
edit
dl
rm
curramt.h
3869
0644
edit
dl
rm
currpinf.h
7479
0644
edit
dl
rm
currunit.h
4112
0644
edit
dl
rm
datefmt.h
41690
0644
edit
dl
rm
dbbi.h
1223
0644
edit
dl
rm
dcfmtsym.h
21101
0644
edit
dl
rm
decimfmt.h
89676
0644
edit
dl
rm
docmain.h
7380
0644
edit
dl
rm
dtfmtsym.h
39126
0644
edit
dl
rm
dtintrv.h
3935
0644
edit
dl
rm
dtitvfmt.h
50448
0644
edit
dl
rm
dtitvinf.h
19072
0644
edit
dl
rm
dtptngen.h
26692
0644
edit
dl
rm
dtrule.h
8898
0644
edit
dl
rm
edits.h
21237
0644
edit
dl
rm
enumset.h
2130
0644
edit
dl
rm
errorcode.h
4956
0644
edit
dl
rm
fieldpos.h
8906
0644
edit
dl
rm
filteredbrk.h
5501
0644
edit
dl
rm
fmtable.h
25020
0644
edit
dl
rm
format.h
12802
0644
edit
dl
rm
formattedvalue.h
9987
0644
edit
dl
rm
fpositer.h
3107
0644
edit
dl
rm
gender.h
3408
0644
edit
dl
rm
gregocal.h
32642
0644
edit
dl
rm
icudataver.h
1049
0644
edit
dl
rm
icuplug.h
12109
0644
edit
dl
rm
idna.h
13000
0644
edit
dl
rm
listformatter.h
9004
0644
edit
dl
rm
localebuilder.h
11350
0644
edit
dl
rm
localematcher.h
27467
0644
edit
dl
rm
localpointer.h
19825
0644
edit
dl
rm
locdspnm.h
7292
0644
edit
dl
rm
locid.h
48804
0644
edit
dl
rm
measfmt.h
11690
0644
edit
dl
rm
measunit.h
107613
0644
edit
dl
rm
measure.h
4431
0644
edit
dl
rm
messagepattern.h
34517
0644
edit
dl
rm
msgfmt.h
45278
0644
edit
dl
rm
normalizer2.h
34466
0644
edit
dl
rm
normlzr.h
31690
0644
edit
dl
rm
nounit.h
2305
0644
edit
dl
rm
numberformatter.h
94505
0644
edit
dl
rm
numberrangeformatter.h
25790
0644
edit
dl
rm
numfmt.h
51034
0644
edit
dl
rm
numsys.h
7509
0644
edit
dl
rm
parseerr.h
3155
0644
edit
dl
rm
parsepos.h
5699
0644
edit
dl
rm
platform.h
28768
0644
edit
dl
rm
plurfmt.h
25847
0644
edit
dl
rm
plurrule.h
21316
0644
edit
dl
rm
ptypes.h
3577
0644
edit
dl
rm
putil.h
6471
0644
edit
dl
rm
rbbi.h
28413
0644
edit
dl
rm
rbnf.h
50021
0644
edit
dl
rm
rbtz.h
16210
0644
edit
dl
rm
regex.h
86385
0644
edit
dl
rm
region.h
9402
0644
edit
dl
rm
reldatefmt.h
22751
0644
edit
dl
rm
rep.h
9599
0644
edit
dl
rm
resbund.h
18513
0644
edit
dl
rm
schriter.h
6511
0644
edit
dl
rm
scientificnumberformatter.h
6589
0644
edit
dl
rm
search.h
22755
0644
edit
dl
rm
selfmt.h
14686
0644
edit
dl
rm
simpleformatter.h
12888
0644
edit
dl
rm
simpletz.h
46798
0644
edit
dl
rm
smpdtfmt.h
72778
0644
edit
dl
rm
sortkey.h
11452
0644
edit
dl
rm
std_string.h
1076
0644
edit
dl
rm
strenum.h
10157
0644
edit
dl
rm
stringoptions.h
5926
0644
edit
dl
rm
stringpiece.h
10287
0644
edit
dl
rm
stringtriebuilder.h
15842
0644
edit
dl
rm
stsearch.h
21926
0644
edit
dl
rm
symtable.h
4374
0644
edit
dl
rm
tblcoll.h
37801
0644
edit
dl
rm
timezone.h
44858
0644
edit
dl
rm
tmunit.h
3479
0644
edit
dl
rm
tmutamt.h
5029
0644
edit
dl
rm
tmutfmt.h
7602
0644
edit
dl
rm
translit.h
67397
0644
edit
dl
rm
tzfmt.h
43961
0644
edit
dl
rm
tznames.h
17251
0644
edit
dl
rm
tzrule.h
36450
0644
edit
dl
rm
tztrans.h
6278
0644
edit
dl
rm
ubidi.h
91759
0644
edit
dl
rm
ubiditransform.h
13003
0644
edit
dl
rm
ubrk.h
25043
0644
edit
dl
rm
ucal.h
62463
0644
edit
dl
rm
ucasemap.h
15579
0644
edit
dl
rm
ucat.h
5478
0644
edit
dl
rm
uchar.h
148111
0644
edit
dl
rm
ucharstrie.h
23066
0644
edit
dl
rm
ucharstriebuilder.h
7645
0644
edit
dl
rm
uchriter.h
13747
0644
edit
dl
rm
uclean.h
11468
0644
edit
dl
rm
ucnv.h
85051
0644
edit
dl
rm
ucnvsel.h
6339
0644
edit
dl
rm
ucnv_cb.h
6738
0644
edit
dl
rm
ucnv_err.h
21481
0644
edit
dl
rm
ucol.h
62987
0644
edit
dl
rm
ucoleitr.h
10056
0644
edit
dl
rm
uconfig.h
12356
0644
edit
dl
rm
ucpmap.h
5663
0644
edit
dl
rm
ucptrie.h
23044
0644
edit
dl
rm
ucsdet.h
15043
0644
edit
dl
rm
ucurr.h
17122
0644
edit
dl
rm
udat.h
63902
0644
edit
dl
rm
udata.h
16004
0644
edit
dl
rm
udateintervalformat.h
12218
0644
edit
dl
rm
udatpg.h
27405
0644
edit
dl
rm
udisplaycontext.h
6084
0644
edit
dl
rm
uenum.h
7981
0644
edit
dl
rm
ufieldpositer.h
4513
0644
edit
dl
rm
uformattable.h
11233
0644
edit
dl
rm
uformattedvalue.h
12600
0644
edit
dl
rm
ugender.h
2106
0644
edit
dl
rm
uidna.h
34229
0644
edit
dl
rm
uiter.h
23299
0644
edit
dl
rm
uldnames.h
10733
0644
edit
dl
rm
ulistformatter.h
11043
0644
edit
dl
rm
uloc.h
55936
0644
edit
dl
rm
ulocdata.h
11572
0644
edit
dl
rm
umachine.h
16439
0644
edit
dl
rm
umisc.h
1365
0644
edit
dl
rm
umsg.h
24832
0644
edit
dl
rm
umutablecptrie.h
8490
0644
edit
dl
rm
unifilt.h
4091
0644
edit
dl
rm
unifunct.h
4151
0644
edit
dl
rm
unimatch.h
6244
0644
edit
dl
rm
unirepl.h
3464
0644
edit
dl
rm
uniset.h
68108
0644
edit
dl
rm
unistr.h
174627
0644
edit
dl
rm
unorm.h
21042
0644
edit
dl
rm
unorm2.h
25269
0644
edit
dl
rm
unum.h
56269
0644
edit
dl
rm
unumberformatter.h
31177
0644
edit
dl
rm
unumberrangeformatter.h
15737
0644
edit
dl
rm
unumsys.h
7430
0644
edit
dl
rm
uobject.h
10934
0644
edit
dl
rm
upluralrules.h
8997
0644
edit
dl
rm
uregex.h
73719
0644
edit
dl
rm
uregion.h
10047
0644
edit
dl
rm
ureldatefmt.h
17448
0644
edit
dl
rm
urename.h
137853
0644
edit
dl
rm
urep.h
5507
0644
edit
dl
rm
ures.h
37418
0644
edit
dl
rm
uscript.h
28291
0644
edit
dl
rm
usearch.h
40153
0644
edit
dl
rm
uset.h
45503
0644
edit
dl
rm
usetiter.h
9910
0644
edit
dl
rm
ushape.h
18430
0644
edit
dl
rm
uspoof.h
67425
0644
edit
dl
rm
usprep.h
8382
0644
edit
dl
rm
ustdio.h
39482
0644
edit
dl
rm
ustream.h
1934
0644
edit
dl
rm
ustring.h
74096
0644
edit
dl
rm
ustringtrie.h
3224
0644
edit
dl
rm
utext.h
59471
0644
edit
dl
rm
utf.h
8057
0644
edit
dl
rm
utf8.h
31572
0644
edit
dl
rm
utf16.h
23910
0644
edit
dl
rm
utf32.h
763
0644
edit
dl
rm
utf_old.h
46929
0644
edit
dl
rm
utmscale.h
14107
0644
edit
dl
rm
utrace.h
17595
0644
edit
dl
rm
utrans.h
26157
0644
edit
dl
rm
utypes.h
31807
0644
edit
dl
rm
uvernum.h
6839
0644
edit
dl
rm
uversion.h
6137
0644
edit
dl
rm
vtzone.h
21303
0644
edit
dl
rm
Edit:
/usr/include/unicode/brkiter.h
(28478B)
// © 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. * <p> * Line boundary analysis determines where a text string can be broken * when line-wrapping. The mechanism correctly handles punctuation and * hyphenated words. * <p> * Sentence boundary analysis allows selection with correct * interpretation of periods within numbers and abbreviations, and * trailing punctuation marks such as quotation marks and parentheses. * <p> * 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. * <p> * 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. * <p> * 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/. * <p> * 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 * <p> * 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. * <P> * 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(void) const override = 0; /** * Return a CharacterIterator over the text being analyzed. * @stable ICU 2.0 */ virtual CharacterIterator& getText(void) 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 NULL, 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(void) = 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(void) = 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(void) = 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(void) = 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(void) 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. * <p> * For break iterator types that do not support a rule status, * a default value of 0 is returned. * <p> * @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. * <p> * For break iterator types that do not support rule status, * no values are returned. * <p> * 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. * <p> * @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. * <p><b>Note:</b> 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 </p> * @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 NULL 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(void); #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(void); #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]; }; #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
Save
cmd:
run