FM / unicode

/usr/include/unicode

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/ubrk.h (25043B)

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
* Copyright (C) 1996-2015, International Business Machines Corporation and others.
* All Rights Reserved.
******************************************************************************
*/

#ifndef UBRK_H
#define UBRK_H

#include "unicode/utypes.h"
#include "unicode/uloc.h"
#include "unicode/utext.h"

#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif   // U_SHOW_CPLUSPLUS_API

/**
 * A text-break iterator.
 *  For usage in C programs.
 */
#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
#   define UBRK_TYPEDEF_UBREAK_ITERATOR
    /**
     *  Opaque type representing an ICU Break iterator object.
     *  @stable ICU 2.0
     */
    typedef struct UBreakIterator UBreakIterator;
#endif

#if !UCONFIG_NO_BREAK_ITERATION

#include "unicode/parseerr.h"

/**
 * \file
 * \brief C API: BreakIterator
 *
 * <h2> BreakIterator C API </h2>
 *
 * The BreakIterator C API defines methods for finding the location
 * of boundaries in text. Pointer to a UBreakIterator 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.
 * 
 * Note: The locale keyword "lb" can be used to modify line break
 * behavior according to the CSS level 3 line-break options, see
 * <http://dev.w3.org/csswg/css-text/#line-breaking>. For example:
 * "ja@lb=strict", "zh@lb=loose".
 * 
 * Sentence boundary analysis allows selection with correct
 * interpretation of periods within numbers and abbreviations, and
 * trailing punctuation marks such as quotation marks and parentheses.
 * 
 * Note: The locale keyword "ss" can be used to enable use of
 * segmentation suppression data (preventing breaks in English after
 * abbreviations such as "Mr." or "Est.", for example), as follows:
 * "en@ss=standard".
 * 
 * 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 identifies the boundaries of
 * "Extended Grapheme Clusters", which are groupings of codepoints
 * that should be treated as character-like units for many text operations.
 * Please see Unicode Standard Annex #29, Unicode Text Segmentation,
 * http://www.unicode.org/reports/tr29/ for additional information
 * on grapheme clusters and guidelines on their use.
 * 
 * Title boundary analysis locates all positions,
 * typically starts of words, that should be set to Title Case
 * when title casing the text.
 * 
 * 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 plain C API defined in this header file, an
 * object oriented C++ API with equivalent functionality is defined in the
 * file brkiter.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
 */

/** The possible types of text boundaries.  @stable ICU 2.0 */
typedef enum UBreakIteratorType {
  /** Character breaks  @stable ICU 2.0 */
  UBRK_CHARACTER = 0,
  /** Word breaks @stable ICU 2.0 */
  UBRK_WORD = 1,
  /** Line breaks @stable ICU 2.0 */
  UBRK_LINE = 2,
  /** Sentence breaks @stable ICU 2.0 */
  UBRK_SENTENCE = 3,

#ifndef U_HIDE_DEPRECATED_API
  /**
   * Title Case breaks
   * The iterator created using this type locates title boundaries as described for
   * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
   * please use Word Boundary iterator.
   *
   * @deprecated ICU 2.8 Use the word break iterator for titlecasing for Unicode 4 and later.
   */
  UBRK_TITLE = 4,
    /**
     * One more than the highest normal UBreakIteratorType value.
     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
     */
    UBRK_COUNT = 5
#endif  // U_HIDE_DEPRECATED_API
} UBreakIteratorType;

/** Value indicating all text boundaries have been returned.
 *  @stable ICU 2.0
 */
#define UBRK_DONE ((int32_t) -1)

/**
 *  Enum constants for the word break tags returned by
 *  getRuleStatus().  A range of values is defined for each category of
 *  word, to allow for further subdivisions of a category in future releases.
 *  Applications should check for tag values falling within the range, rather
 *  than for single individual values.
 *
 * The numeric values of all of these constants are stable (will not change).
 *
 * @stable ICU 2.2
*/
typedef enum UWordBreak {
    /** Tag value for "words" that do not fit into any of other categories.
     *  Includes spaces and most punctuation. */
    UBRK_WORD_NONE           = 0,
    /** Upper bound for tags for uncategorized words. */
    UBRK_WORD_NONE_LIMIT     = 100,
    /** Tag value for words that appear to be numbers, lower limit.    */
    UBRK_WORD_NUMBER         = 100,
    /** Tag value for words that appear to be numbers, upper limit.    */
    UBRK_WORD_NUMBER_LIMIT   = 200,
    /** Tag value for words that contain letters, excluding
     *  hiragana, katakana or ideographic characters, lower limit.    */
    UBRK_WORD_LETTER         = 200,
    /** Tag value for words containing letters, upper limit  */
    UBRK_WORD_LETTER_LIMIT   = 300,
    /** Tag value for words containing kana characters, lower limit */
    UBRK_WORD_KANA           = 300,
    /** Tag value for words containing kana characters, upper limit */
    UBRK_WORD_KANA_LIMIT     = 400,
    /** Tag value for words containing ideographic characters, lower limit */
    UBRK_WORD_IDEO           = 400,
    /** Tag value for words containing ideographic characters, upper limit */
    UBRK_WORD_IDEO_LIMIT     = 500
} UWordBreak;

/**
 *  Enum constants for the line break tags returned by getRuleStatus().
 *  A range of values is defined for each category of
 *  word, to allow for further subdivisions of a category in future releases.
 *  Applications should check for tag values falling within the range, rather
 *  than for single individual values.
 *
 * The numeric values of all of these constants are stable (will not change).
 *
 * @stable ICU 2.8
*/
typedef enum ULineBreakTag {
    /** Tag value for soft line breaks, positions at which a line break
      *  is acceptable but not required                */
    UBRK_LINE_SOFT            = 0,
    /** Upper bound for soft line breaks.              */
    UBRK_LINE_SOFT_LIMIT      = 100,
    /** Tag value for a hard, or mandatory line break  */
    UBRK_LINE_HARD            = 100,
    /** Upper bound for hard line breaks.              */
    UBRK_LINE_HARD_LIMIT      = 200
} ULineBreakTag;

/**
 *  Enum constants for the sentence break tags returned by getRuleStatus().
 *  A range of values is defined for each category of
 *  sentence, to allow for further subdivisions of a category in future releases.
 *  Applications should check for tag values falling within the range, rather
 *  than for single individual values.
 *
 * The numeric values of all of these constants are stable (will not change).
 *
 * @stable ICU 2.8
*/
typedef enum USentenceBreakTag {
    /** Tag value for for sentences  ending with a sentence terminator
      * ('.', '?', '!', etc.) character, possibly followed by a
      * hard separator (CR, LF, PS, etc.)
      */
    UBRK_SENTENCE_TERM       = 0,
    /** Upper bound for tags for sentences ended by sentence terminators.    */
    UBRK_SENTENCE_TERM_LIMIT = 100,
    /** Tag value for for sentences that do not contain an ending
      * sentence terminator ('.', '?', '!', etc.) character, but
      * are ended only by a hard separator (CR, LF, PS, etc.) or end of input.
      */
    UBRK_SENTENCE_SEP        = 100,
    /** Upper bound for tags for sentences ended by a separator.              */
    UBRK_SENTENCE_SEP_LIMIT  = 200
    /** Tag value for a hard, or mandatory line break  */
} USentenceBreakTag;

/**
 * Open a new UBreakIterator for locating text boundaries for a specified locale.
 * A UBreakIterator may be used for detecting character, line, word,
 * and sentence breaks in text.
 * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD,
 * UBRK_LINE, UBRK_SENTENCE
 * @param locale The locale specifying the text-breaking conventions. Note that
 * locale keys such as "lb" and "ss" may be used to modify text break behavior,
 * see general discussion of BreakIterator C API.
 * @param text The text to be iterated over. May be null, in which case ubrk_setText() is
 *        used to specify the text to be iterated.
 * @param textLength The number of characters in text, or -1 if null-terminated.
 * @param status A UErrorCode to receive any errors.
 * @return A UBreakIterator for the specified locale.
 * @see ubrk_openRules
 * @stable ICU 2.0
 */
U_CAPI UBreakIterator* U_EXPORT2
ubrk_open(UBreakIteratorType type,
      const char *locale,
      const UChar *text,
      int32_t textLength,
      UErrorCode *status);

/**
 * Open a new UBreakIterator for locating text boundaries using specified breaking rules.
 * The rule syntax is ... (TBD)
 * @param rules A set of rules specifying the text breaking conventions.
 * @param rulesLength The number of characters in rules, or -1 if null-terminated.
 * @param text The text to be iterated over.  May be null, in which case ubrk_setText() is
 *        used to specify the text to be iterated.
 * @param textLength The number of characters in text, or -1 if null-terminated.
 * @param parseErr   Receives position and context information for any syntax errors
 *                   detected while parsing the rules.
 * @param status A UErrorCode to receive any errors.
 * @return A UBreakIterator for the specified rules.
 * @see ubrk_open
 * @stable ICU 2.2
 */
U_CAPI UBreakIterator* U_EXPORT2
ubrk_openRules(const UChar     *rules,
               int32_t         rulesLength,
               const UChar     *text,
               int32_t          textLength,
               UParseError     *parseErr,
               UErrorCode      *status);

/**
 * Open a new UBreakIterator for locating text boundaries using precompiled binary rules.
 * Opening a UBreakIterator this way is substantially faster than using ubrk_openRules.
 * Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not
 * compatible across different major versions of ICU, nor across platforms of different
 * endianness or different base character set family (ASCII vs EBCDIC).
 * @param binaryRules A set of compiled binary rules specifying the text breaking
 *                    conventions. Ownership of the storage containing the compiled
 *                    rules remains with the caller of this function. The compiled
 *                    rules must not be modified or deleted during the life of the
 *                    break iterator.
 * @param rulesLength The length of binaryRules in bytes; must be >= 0.
 * @param text        The text to be iterated over.  May be null, in which case
 *                    ubrk_setText() is used to specify the text to be iterated.
 * @param textLength  The number of characters in text, or -1 if null-terminated.
 * @param status      Pointer to UErrorCode to receive any errors.
 * @return            UBreakIterator for the specified rules.
 * @see ubrk_getBinaryRules
 * @stable ICU 59
 */
U_CAPI UBreakIterator* U_EXPORT2
ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength,
                     const UChar *  text, int32_t textLength,
                     UErrorCode *   status);

#ifndef U_HIDE_DEPRECATED_API

/**
 * Thread safe cloning operation
 * @param bi iterator to be cloned
 * @param stackBuffer Deprecated functionality as of ICU 52, use NULL. 
 * 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.
 * Clients can use the U_BRK_SAFECLONE_BUFFERSIZE.
 * @param pBufferSize Deprecated functionality as of ICU 52, use NULL or 1. 
 * pointer to size of allocated space.
 * If *pBufferSize == 0, a sufficient size for use in cloning will
 * be returned ('pre-flighting')
 * If *pBufferSize 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 69 Use ubrk_clone() instead.
 */
U_CAPI UBreakIterator * U_EXPORT2
ubrk_safeClone(
 const UBreakIterator *bi,
 void *stackBuffer,
 int32_t *pBufferSize,
 UErrorCode *status);

#endif /* U_HIDE_DEPRECATED_API */

#ifndef U_HIDE_DRAFT_API

/**
 * Thread safe cloning operation.
 * @param bi iterator to be cloned
 * @param status to indicate whether the operation went on smoothly or there were errors
 * @return pointer to the new clone
 * @draft ICU 69
 */
U_CAPI UBreakIterator * U_EXPORT2
ubrk_clone(const UBreakIterator *bi,
           UErrorCode *status);

#endif  // U_HIDE_DRAFT_API

#ifndef U_HIDE_DEPRECATED_API

/**
  * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone().
  * @deprecated ICU 52. Do not rely on ubrk_safeClone() cloning into any provided buffer.
  */
#define U_BRK_SAFECLONE_BUFFERSIZE 1

#endif /* U_HIDE_DEPRECATED_API */

/**
* Close a UBreakIterator.
* Once closed, a UBreakIterator may no longer be used.
* @param bi The break iterator to close.
 * @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
ubrk_close(UBreakIterator *bi);

#if U_SHOW_CPLUSPLUS_API

U_NAMESPACE_BEGIN

/**
 * \class LocalUBreakIteratorPointer
 * "Smart pointer" class, closes a UBreakIterator via ubrk_close().
 * For most methods see the LocalPointerBase base class.
 *
 * @see LocalPointerBase
 * @see LocalPointer
 * @stable ICU 4.4
 */
U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close);

U_NAMESPACE_END

#endif

/**
 * Sets an existing iterator to point to a new piece of text.
 * The break iterator retains a pointer to the supplied text.
 * The caller must not modify or delete the text while the BreakIterator
 * retains the reference.
 *
 * @param bi The iterator to use
 * @param text The text to be set
 * @param textLength The length of the text
 * @param status The error code
 * @stable ICU 2.0
 */
U_CAPI void U_EXPORT2
ubrk_setText(UBreakIterator* bi,
             const UChar*    text,
             int32_t         textLength,
             UErrorCode*     status);

/**
 * Sets an existing iterator to point to a new piece of text.
 *
 * 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 \ref ubrk_next, \ref ubrk_previous, etc.
 * will be UTF-8 string indices, not UTF-16 positions.
 *
 * @param bi The iterator to use
 * @param text The text to be set.
 *             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.
 * @param status The error code
 * @stable ICU 3.4
 */
U_CAPI void U_EXPORT2
ubrk_setUText(UBreakIterator* bi,
             UText*          text,
             UErrorCode*     status);

/**
 * Determine the most recently-returned text boundary.
 *
 * @param bi The break iterator to use.
 * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous,
 * \ref ubrk_first, or \ref ubrk_last.
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_current(const UBreakIterator *bi);

/**
 * Advance the iterator to the boundary following the current boundary.
 *
 * @param bi The break iterator to use.
 * @return The character index of the next text boundary, or UBRK_DONE
 * if all text boundaries have been returned.
 * @see ubrk_previous
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_next(UBreakIterator *bi);

/**
 * Set the iterator position to the boundary preceding the current boundary.
 *
 * @param bi The break iterator to use.
 * @return The character index of the preceding text boundary, or UBRK_DONE
 * if all text boundaries have been returned.
 * @see ubrk_next
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_previous(UBreakIterator *bi);

/**
 * Set the iterator position to zero, the start of the text being scanned.
 * @param bi The break iterator to use.
 * @return The new iterator position (zero).
 * @see ubrk_last
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_first(UBreakIterator *bi);

/**
 * Set the iterator position to the index immediately beyond the last character in the text being scanned.
 * This is not the same as the last character.
 * @param bi The break iterator to use.
 * @return The character offset immediately beyond the last character in the
 * text being scanned.
 * @see ubrk_first
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_last(UBreakIterator *bi);

/**
 * Set the iterator position to the first boundary preceding the specified offset.
 * The new position is always smaller than offset, or UBRK_DONE.
 * @param bi The break iterator to use.
 * @param offset The offset to begin scanning.
 * @return The text boundary preceding offset, or UBRK_DONE.
 * @see ubrk_following
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_preceding(UBreakIterator *bi,
           int32_t offset);

/**
 * Advance the iterator to the first boundary following the specified offset.
 * The value returned is always greater than offset, or UBRK_DONE.
 * @param bi The break iterator to use.
 * @param offset The offset to begin scanning.
 * @return The text boundary following offset, or UBRK_DONE.
 * @see ubrk_preceding
 * @stable ICU 2.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_following(UBreakIterator *bi,
           int32_t offset);

/**
* Get a locale for which text breaking information is available.
* A UBreakIterator in a locale returned by this function will perform the correct
* text breaking for the locale.
* @param index The index of the desired locale.
* @return A locale for which number text breaking information is available, or 0 if none.
* @see ubrk_countAvailable
* @stable ICU 2.0
*/
U_CAPI const char* U_EXPORT2
ubrk_getAvailable(int32_t index);

/**
* Determine how many locales have text breaking information available.
* This function is most useful as determining the loop ending condition for
* calls to \ref ubrk_getAvailable.
* @return The number of locales for which text breaking information is available.
* @see ubrk_getAvailable
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_countAvailable(void);

/**
* Returns true if the specified position is a boundary position.  As a side
* effect, leaves the iterator pointing to the first boundary position at
* or after "offset".
* @param bi The break iterator to use.
* @param offset the offset to check.
* @return True if "offset" is a boundary position.
* @stable ICU 2.0
*/
U_CAPI  UBool U_EXPORT2
ubrk_isBoundary(UBreakIterator *bi, int32_t offset);

/**
 * Return the status from the break rule that determined the most recently
 * returned break position. The values appear in the rule source
 * within brackets, {123}, for example. For rules that do not specify a
 * status, a default value of 0 is returned.
 * 
 * For word break iterators, the possible values are defined in enum UWordBreak.
 * @stable ICU 2.2
 */
U_CAPI int32_t U_EXPORT2
ubrk_getRuleStatus(UBreakIterator *bi);

/**
 * Get the statuses from the break rules that determined the most recently
 * returned break position. The values appear in the rule source
 * within brackets, {123}, for example. The default status value for rules
 * that do not explicitly provide one is zero.
 * 
 * For word break iterators, the possible values are defined in enum UWordBreak.
 * @param bi The break iterator to use
 * @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 most recent boundary returned by the break iterator.
 * @stable ICU 3.0
 */
U_CAPI int32_t U_EXPORT2
ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status);

/**
 * Return the locale of the break iterator. You can choose between the valid and
 * the actual locale.
 * @param bi break iterator
 * @param type locale type (valid or actual)
 * @param status error code
 * @return locale string
 * @stable ICU 2.8
 */
U_CAPI const char* U_EXPORT2
ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status);

/**
  *  Set the subject text string upon which the break iterator is operating
  *  without changing any other aspect of the 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 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 bi         The break iterator.
  * @param text       The new (moved) text string.
  * @param status     Receives errors detected by this function.
  *
  * @stable ICU 49
  */
U_CAPI void U_EXPORT2
ubrk_refreshUText(UBreakIterator *bi,
                       UText          *text,
                       UErrorCode     *status);

/**
 * Get a compiled binary version of the rules specifying the behavior of a UBreakIterator.
 * The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator
 * more quickly than using ubrk_openRules. The compiled rules are not compatible across
 * different major versions of ICU, nor across platforms of different endianness or
 * different base character set family (ASCII vs EBCDIC). Supports preflighting (with
 * binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to
 * the binaryRules buffer. However, whether preflighting or not, if the actual length
 * is greater than INT32_MAX, then the function returns 0 and sets *status to
 * U_INDEX_OUTOFBOUNDS_ERROR.

* @param bi The break iterator to use.
 * @param binaryRules Buffer to receive the compiled binary rules; set to NULL for
 * preflighting.
 * @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for
 * preflighting. Must be >= 0.
 * @param status Pointer to UErrorCode to receive any errors, such as
 * U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or
 * U_ILLEGAL_ARGUMENT_ERROR.
 * @return The actual byte length of the binary rules, if <= INT32_MAX;
 * otherwise 0. If not preflighting and this is larger than
 * rulesCapacity, *status will be set to an error.
 * @see ubrk_openBinaryRules
 * @stable ICU 59
 */
U_CAPI int32_t U_EXPORT2
ubrk_getBinaryRules(UBreakIterator *bi,
 uint8_t * binaryRules, int32_t rulesCapacity,
 UErrorCode * status);

#endif /* #if !UCONFIG_NO_BREAK_ITERATION */

#endif

cmd: