FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27118	0644	edit dl rm
appendable.h	8694	0644	edit dl rm
basictz.h	9491	0644	edit dl rm
brkiter.h	28464	0644	edit dl rm
bytestream.h	11037	0644	edit dl rm
bytestrie.h	21266	0644	edit dl rm
bytestriebuilder.h	7248	0644	edit dl rm
calendar.h	108278	0644	edit dl rm
caniter.h	7611	0644	edit dl rm
casemap.h	25933	0644	edit dl rm
char16ptr.h	7393	0644	edit dl rm
chariter.h	24632	0644	edit dl rm
choicfmt.h	24482	0644	edit dl rm
coleitr.h	14094	0644	edit dl rm
coll.h	57581	0644	edit dl rm
compactdecimalformat.h	7047	0644	edit dl rm
curramt.h	3851	0644	edit dl rm
currpinf.h	7473	0644	edit dl rm
currunit.h	4094	0644	edit dl rm
datefmt.h	41641	0644	edit dl rm
dbbi.h	1223	0644	edit dl rm
dcfmtsym.h	20897	0644	edit dl rm
decimfmt.h	89278	0644	edit dl rm
docmain.h	7142	0644	edit dl rm
dtfmtsym.h	38609	0644	edit dl rm
dtintrv.h	3930	0644	edit dl rm
dtitvfmt.h	47634	0644	edit dl rm
dtitvinf.h	19064	0644	edit dl rm
dtptngen.h	26419	0644	edit dl rm
dtrule.h	8888	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	8899	0644	edit dl rm
filteredbrk.h	5501	0644	edit dl rm
fmtable.h	25007	0644	edit dl rm
format.h	12802	0644	edit dl rm
formattedvalue.h	9987	0644	edit dl rm
fpositer.h	3109	0644	edit dl rm
gender.h	3408	0644	edit dl rm
gregocal.h	32472	0644	edit dl rm
icudataver.h	1051	0644	edit dl rm
icuplug.h	12166	0644	edit dl rm
idna.h	13000	0644	edit dl rm
listformatter.h	9493	0644	edit dl rm
localebuilder.h	11502	0644	edit dl rm
localematcher.h	25147	0644	edit dl rm
localpointer.h	19829	0644	edit dl rm
locdspnm.h	7292	0644	edit dl rm
locid.h	48821	0644	edit dl rm
measfmt.h	11603	0644	edit dl rm
measunit.h	97563	0644	edit dl rm
measure.h	4423	0644	edit dl rm
messagepattern.h	34521	0644	edit dl rm
msgfmt.h	45168	0644	edit dl rm
normalizer2.h	34851	0644	edit dl rm
normlzr.h	31682	0644	edit dl rm
nounit.h	2754	0644	edit dl rm
numberformatter.h	86276	0644	edit dl rm
numberrangeformatter.h	28617	0644	edit dl rm
numfmt.h	50950	0644	edit dl rm
numsys.h	7500	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5692	0644	edit dl rm
platform.h	28751	0644	edit dl rm
plurfmt.h	25800	0644	edit dl rm
plurrule.h	18780	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6487	0644	edit dl rm
rbbi.h	27218	0644	edit dl rm
rbnf.h	49899	0644	edit dl rm
rbtz.h	15979	0644	edit dl rm
regex.h	86367	0644	edit dl rm
region.h	9404	0644	edit dl rm
reldatefmt.h	22801	0644	edit dl rm
rep.h	9599	0644	edit dl rm
resbund.h	18503	0644	edit dl rm
schriter.h	6475	0644	edit dl rm
scientificnumberformatter.h	6553	0644	edit dl rm
search.h	22757	0644	edit dl rm
selfmt.h	14643	0644	edit dl rm
simpleformatter.h	12888	0644	edit dl rm
simpletz.h	46527	0644	edit dl rm
smpdtfmt.h	72713	0644	edit dl rm
sortkey.h	11444	0644	edit dl rm
std_string.h	1076	0644	edit dl rm
strenum.h	10158	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	10597	0644	edit dl rm
stringtriebuilder.h	15698	0644	edit dl rm
stsearch.h	21810	0644	edit dl rm
symtable.h	4374	0644	edit dl rm
tblcoll.h	37489	0644	edit dl rm
timezone.h	42005	0644	edit dl rm
tmunit.h	3461	0644	edit dl rm
tmutamt.h	5015	0644	edit dl rm
tmutfmt.h	8042	0644	edit dl rm
translit.h	67400	0644	edit dl rm
tzfmt.h	43916	0644	edit dl rm
tznames.h	17252	0644	edit dl rm
tzrule.h	36215	0644	edit dl rm
tztrans.h	6271	0644	edit dl rm
ubidi.h	91711	0644	edit dl rm
ubiditransform.h	12950	0644	edit dl rm
ubrk.h	24547	0644	edit dl rm
ucal.h	58265	0644	edit dl rm
ucasemap.h	15546	0644	edit dl rm
ucat.h	5484	0644	edit dl rm
uchar.h	144630	0644	edit dl rm
ucharstrie.h	23120	0644	edit dl rm
ucharstriebuilder.h	7378	0644	edit dl rm
uchriter.h	13521	0644	edit dl rm
uclean.h	11474	0644	edit dl rm
ucnv.h	85085	0644	edit dl rm
ucnvsel.h	6283	0644	edit dl rm
ucnv_cb.h	6748	0644	edit dl rm
ucnv_err.h	21492	0644	edit dl rm
ucol.h	62939	0644	edit dl rm
ucoleitr.h	9684	0644	edit dl rm
uconfig.h	12356	0644	edit dl rm
ucpmap.h	5663	0644	edit dl rm
ucptrie.h	23002	0644	edit dl rm
ucsdet.h	15018	0644	edit dl rm
ucurr.h	16507	0644	edit dl rm
udat.h	62851	0644	edit dl rm
udata.h	15930	0644	edit dl rm
udateintervalformat.h	10995	0644	edit dl rm
udatpg.h	27447	0644	edit dl rm
udisplaycontext.h	6029	0644	edit dl rm
uenum.h	7970	0644	edit dl rm
ufieldpositer.h	4461	0644	edit dl rm
uformattable.h	11198	0644	edit dl rm
uformattedvalue.h	12413	0644	edit dl rm
ugender.h	2052	0644	edit dl rm
uidna.h	34169	0644	edit dl rm
uiter.h	23319	0644	edit dl rm
uldnames.h	10702	0644	edit dl rm
ulistformatter.h	11086	0644	edit dl rm
uloc.h	54432	0644	edit dl rm
ulocdata.h	11533	0644	edit dl rm
umachine.h	14884	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24812	0644	edit dl rm
umutablecptrie.h	8435	0644	edit dl rm
unifilt.h	4055	0644	edit dl rm
unifunct.h	4141	0644	edit dl rm
unimatch.h	6244	0644	edit dl rm
unirepl.h	3464	0644	edit dl rm
uniset.h	66459	0644	edit dl rm
unistr.h	174523	0644	edit dl rm
unorm.h	21015	0644	edit dl rm
unorm2.h	25254	0644	edit dl rm
unum.h	54743	0644	edit dl rm
unumberformatter.h	25824	0644	edit dl rm
unumsys.h	7387	0644	edit dl rm
uobject.h	10936	0644	edit dl rm
upluralrules.h	8013	0644	edit dl rm
uregex.h	73784	0644	edit dl rm
uregion.h	10073	0644	edit dl rm
ureldatefmt.h	17409	0644	edit dl rm
urename.h	134449	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37415	0644	edit dl rm
uscript.h	27867	0644	edit dl rm
usearch.h	39039	0644	edit dl rm
uset.h	40958	0644	edit dl rm
usetiter.h	9781	0644	edit dl rm
ushape.h	18432	0644	edit dl rm
uspoof.h	67480	0644	edit dl rm
usprep.h	8331	0644	edit dl rm
ustdio.h	39469	0644	edit dl rm
ustream.h	1934	0644	edit dl rm
ustring.h	74211	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59527	0644	edit dl rm
utf.h	8046	0644	edit dl rm
utf8.h	31700	0644	edit dl rm
utf16.h	23878	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	46929	0644	edit dl rm
utmscale.h	14113	0644	edit dl rm
utrace.h	17706	0644	edit dl rm
utrans.h	26130	0644	edit dl rm
utypes.h	31481	0644	edit dl rm
uvernum.h	6832	0644	edit dl rm
uversion.h	6145	0644	edit dl rm
vtzone.h	20784	0644	edit dl rm

Edit: /usr/include/unicode/rbbi.h (27218B)

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************
*   Copyright (C) 1999-2016 International Business Machines Corporation   *
*   and others. All rights reserved.                                      *
***************************************************************************

**********************************************************************
*   Date        Name        Description
*   10/22/99    alan        Creation.
*   11/11/99    rgillam     Complete port from Java.
**********************************************************************
*/

#ifndef RBBI_H
#define RBBI_H

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

/**
 * \file
 * \brief C++ API: Rule Based Break Iterator
 */

#if !UCONFIG_NO_BREAK_ITERATION

#include "unicode/brkiter.h"
#include "unicode/udata.h"
#include "unicode/parseerr.h"
#include "unicode/schriter.h"

U_NAMESPACE_BEGIN

/** @internal */
class  LanguageBreakEngine;
struct RBBIDataHeader;
class  RBBIDataWrapper;
class  UnhandledEngine;
class  UStack;

/**
 *
 * A subclass of BreakIterator whose behavior is specified using a list of rules.
 * Instances of this class are most commonly created by the factory methods of
 * BreakIterator::createWordInstance(), BreakIterator::createLineInstance(), etc.,
 * and then used via the abstract API in class BreakIterator
 *
 * See the ICU User Guide for information on Break Iterator Rules.
 *
 * This class is not intended to be subclassed.
 */
class U_COMMON_API RuleBasedBreakIterator /*U_FINAL*/ : public BreakIterator {

private:
    /**
     * The UText through which this BreakIterator accesses the text
     * @internal (private)
     */
    UText  fText;

#ifndef U_HIDE_INTERNAL_API
public:
#endif /* U_HIDE_INTERNAL_API */
    /**
     * The rule data for this BreakIterator instance.
     * Not for general use; Public only for testing purposes.
     * @internal
     */
    RBBIDataWrapper    *fData;
private:

/**
 * The current position of the iterator. Pinned, 0 < fPosition <= text.length.
 * Never has the value UBRK_DONE (-1).
 */
 int32_t fPosition;

/**
      * TODO:
      */
    int32_t         fRuleStatusIndex;

/**
     *   Cache of previously determined boundary positions.
     */
    class BreakCache;
    BreakCache         *fBreakCache;

/**
     *  Cache of boundary positions within a region of text that has been
     *  sub-divided by dictionary based breaking.
     */
    class DictionaryCache;
    DictionaryCache *fDictionaryCache;

/**
     *
     * If present, UStack of LanguageBreakEngine objects that might handle
     * dictionary characters. Searched from top to bottom to find an object to
     * handle a given character.
     * @internal (private)
     */
    UStack              *fLanguageBreakEngines;

/**
     *
     * If present, the special LanguageBreakEngine used for handling
     * characters that are in the dictionary set, but not handled by any
     * LanguageBreakEngine.
     * @internal (private)
     */
    UnhandledEngine     *fUnhandledBreakEngine;

/**
     * Counter for the number of characters encountered with the "dictionary"
     *   flag set.
     * @internal (private)
     */
    uint32_t            fDictionaryCharCount;

/**
     *   A character iterator that refers to the same text as the UText, above.
     *   Only included for compatibility with old API, which was based on CharacterIterators.
     *   Value may be adopted from outside, or one of fSCharIter or fDCharIter, below.
     */
    CharacterIterator  *fCharIter;

/**
     *   When the input text is provided by a UnicodeString, this will point to
     *    a characterIterator that wraps that data.  Needed only for the
     *    implementation of getText(), a backwards compatibility issue.
     */
    StringCharacterIterator fSCharIter;

/**
      * True when iteration has run off the end, and iterator functions should return UBRK_DONE.
      */
    UBool           fDone;

//=======================================================================
    // constructors
    //=======================================================================

/**
     * Constructor from a flattened set of RBBI data in malloced memory.
     *             RulesBasedBreakIterators built from a custom set of rules
     *             are created via this constructor; the rules are compiled
     *             into memory, then the break iterator is constructed here.
     *
     *             The break iterator adopts the memory, and will
     *             free it when done.
     * @internal (private)
     */
    RuleBasedBreakIterator(RBBIDataHeader* data, UErrorCode &status);

/** @internal */
    friend class RBBIRuleBuilder;
    /** @internal */
    friend class BreakIterator;

public:

/** Default constructor.  Creates an empty shell of an iterator, with no
     *  rules or text to iterate over.   Object can subsequently be assigned to.
     *  @stable ICU 2.2
     */
    RuleBasedBreakIterator();

/**
     * Copy constructor.  Will produce a break iterator with the same behavior,
     * and which iterates over the same text, as the one passed in.
     * @param that The RuleBasedBreakIterator passed to be copied
     * @stable ICU 2.0
     */
    RuleBasedBreakIterator(const RuleBasedBreakIterator& that);

/**
     * Construct a RuleBasedBreakIterator from a set of rules supplied as a string.
     * @param rules The break rules to be used.
     * @param parseError  In the event of a syntax error in the rules, provides the location
     *                    within the rules of the problem.
     * @param status Information on any errors encountered.
     * @stable ICU 2.2
     */
    RuleBasedBreakIterator( const UnicodeString    &rules,
                             UParseError           &parseError,
                             UErrorCode            &status);

/**
     * Construct a RuleBasedBreakIterator from a set of precompiled binary rules.
     * Binary rules are obtained from RulesBasedBreakIterator::getBinaryRules().
     * Construction of a break iterator in this way is substantially faster than
     * construction from source rules.
     *
     * 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.
     *
     * The compiled rules are not compatible across different major versions of ICU.
     * The compiled rules are compatible only between machines with the same
     * byte ordering (little or big endian) and the same base character set family
     * (ASCII or EBCDIC).
     *
     * @see #getBinaryRules
     * @param compiledRules A pointer to the compiled break rules to be used.
     * @param ruleLength The length of the compiled break rules, in bytes.  This
     *   corresponds to the length value produced by getBinaryRules().
     * @param status Information on any errors encountered, including invalid
     *   binary rules.
     * @stable ICU 4.8
     */
    RuleBasedBreakIterator(const uint8_t *compiledRules,
                           uint32_t       ruleLength,
                           UErrorCode    &status);

/**
     * This constructor uses the udata interface to create a BreakIterator
     * whose internal tables live in a memory-mapped file.  "image" is an
     * ICU UDataMemory handle for the pre-compiled break iterator tables.
     * @param image handle to the memory image for the break iterator data.
     *        Ownership of the UDataMemory handle passes to the Break Iterator,
     *        which will be responsible for closing it when it is no longer needed.
     * @param status Information on any errors encountered.
     * @see udata_open
     * @see #getBinaryRules
     * @stable ICU 2.8
     */
    RuleBasedBreakIterator(UDataMemory* image, UErrorCode &status);

/**
     * Destructor
     *  @stable ICU 2.0
     */
    virtual ~RuleBasedBreakIterator();

/**
     * Assignment operator.  Sets this iterator to have the same behavior,
     * and iterate over the same text, as the one passed in.
     * @param that The RuleBasedBreakItertor passed in
     * @return the newly created RuleBasedBreakIterator
     *  @stable ICU 2.0
     */
    RuleBasedBreakIterator& operator=(const RuleBasedBreakIterator& that);

/**
     * Equality operator.  Returns TRUE if both BreakIterators are of the
     * same class, have the same behavior, and iterate over the same text.
     * @param that The BreakIterator to be compared for equality
     * @return TRUE if both BreakIterators are of the
     * same class, have the same behavior, and iterate over the same text.
     *  @stable ICU 2.0
     */
    virtual UBool operator==(const BreakIterator& that) const;

/**
     * Not-equal operator.  If operator== returns TRUE, this returns FALSE,
     * and vice versa.
     * @param that The BreakIterator to be compared for inequality
     * @return TRUE if both BreakIterators are not same.
     *  @stable ICU 2.0
     */
    inline UBool operator!=(const BreakIterator& that) const;

/**
     * Returns a newly-constructed RuleBasedBreakIterator with the same
     * behavior, and iterating over the same text, as this one.
     * Differs from the copy constructor in that it is polymorphic, and
     * will correctly clone (copy) a derived class.
     * clone() is thread safe.  Multiple threads may simultaneously
     * clone the same source break iterator.
     * @return a newly-constructed RuleBasedBreakIterator
     * @stable ICU 2.0
     */
    virtual RuleBasedBreakIterator* clone() const;

/**
     * Compute a hash code for this BreakIterator
     * @return A hash code
     *  @stable ICU 2.0
     */
    virtual int32_t hashCode(void) const;

/**
     * Returns the description used to create this iterator
     * @return the description used to create this iterator
     *  @stable ICU 2.0
     */
    virtual const UnicodeString& getRules(void) const;

//=======================================================================
    // BreakIterator overrides
    //=======================================================================

/**
 * 
 * Return a CharacterIterator over the text being analyzed.
 * The returned character iterator is owned by the break iterator, and must
 * not be deleted by the caller. Repeated calls to this function may
 * return the same CharacterIterator.
 * 
 * 
 * The returned character iterator must not be used concurrently with
 * the break iterator. If concurrent operation is needed, clone the
 * returned character iterator first and operate on the clone.
 * 
 * 
 * When the break iterator is operating on text supplied via a UText,
 * this function will fail. Lacking any way to signal failures, it
 * returns an CharacterIterator containing no text.
 * The function getUText() provides similar functionality,
 * is reliable, and is more efficient.
 * 
 *
 * TODO: deprecate this function?
 *
 * @return An iterator over the text being analyzed.
 * @stable ICU 2.0
 */
 virtual CharacterIterator& getText(void) const;

/**
      *  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;

/**
     * Set the iterator to analyze a new piece of text.  This function resets
     * the current iteration position to the beginning of the text.
     * @param newText An iterator over the text to analyze.  The BreakIterator
     * takes ownership of the character iterator.  The caller MUST NOT delete it!
     *  @stable ICU 2.0
     */
    virtual void adoptText(CharacterIterator* newText);

/**
     * Set the iterator to analyze a new piece of text.  This function resets
     * the current iteration position to the beginning of the text.
     *
     * 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 newText The text to analyze.
     *  @stable ICU 2.0
     */
    virtual void setText(const UnicodeString& newText);

/**
     * 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.
     *
     * @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);

/**
     * 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);

/**
     * Sets the current iteration position to the end of the text.
     * @return The text's past-the-end offset.
     *  @stable ICU 2.0
     */
    virtual int32_t last(void);

/**
     * Advances the iterator either forward or backward the specified number of steps.
     * Negative values move backward, and positive values move forward.  This is
     * equivalent to repeatedly calling next() or previous().
     * @param n The number of steps to move.  The sign indicates the direction
     * (negative is backwards, and positive is forwards).
     * @return The character offset of the boundary position n boundaries away from
     * the current one.
     *  @stable ICU 2.0
     */
    virtual int32_t next(int32_t n);

/**
     * Advances the iterator to the next boundary position.
     * @return The position of the first boundary after this one.
     *  @stable ICU 2.0
     */
    virtual int32_t next(void);

/**
     * Moves the iterator backwards, to the last boundary preceding this one.
     * @return The position of the last boundary position preceding this one.
     *  @stable ICU 2.0
     */
    virtual int32_t previous(void);

/**
     * Sets the iterator to refer to the first boundary position following
     * the specified position.
     * @param offset The position from which to begin searching for a break position.
     * @return The position of the first break after the current position.
     *  @stable ICU 2.0
     */
    virtual int32_t following(int32_t offset);

/**
     * Sets the iterator to refer to the last boundary position before the
     * specified position.
     * @param offset The position to begin searching for a break from.
     * @return The position of the last boundary before the starting position.
     *  @stable ICU 2.0
     */
    virtual int32_t preceding(int32_t offset);

/**
     * 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 offset the offset to check.
     * @return True if "offset" is a boundary position.
     *  @stable ICU 2.0
     */
    virtual UBool isBoundary(int32_t offset);

/**
     * Returns the current iteration position. Note that UBRK_DONE is never
     * returned from this function; if iteration has run to the end of a
     * string, current() will return the length of the string while
     * next() will return UBRK_DONE).
     * @return The current iteration position.
     * @stable ICU 2.0
     */
    virtual int32_t current(void) const;

/**
 * Return the status tag from the break rule that determined the boundary at
 * the current iteration position. For break rules that do not specify a
 * status, a default value of 0 is returned. If more than one break rule
 * would cause a boundary to be located at some position in the text,
 * the numerically largest of the applicable status values is returned.
 * 
 * Of the standard types of ICU break iterators, only word break and
 * line break provide status values. The values are defined in
 * the header file ubrk.h. For Word breaks, the status allows distinguishing between words
 * that contain alphabetic letters, "words" that appear to be numbers,
 * punctuation and spaces, words containing ideographic characters, and
 * more. For Line Break, the status distinguishes between hard (mandatory) breaks
 * and soft (potential) break positions.
 * 
 * <code>getRuleStatus()</code> can be called after obtaining a boundary
 * position from <code>next()</code>, <code>previous()</code>, or
 * any other break iterator functions that returns a boundary position.
 * 
 * Note that <code>getRuleStatus()</code> returns the value corresponding to
 * <code>current()</code> index even after <code>next()</code> has returned DONE.
 * 
 * When creating custom break rules, one is free to define whatever
 * status values may be convenient for the application.
 * 
 * @return the status from the break rule that determined the boundary
 * at the current iteration position.
 *
 * @see UWordBreak
 * @stable ICU 2.2
 */
 virtual int32_t getRuleStatus() const;

/**
 * Get the status (tag) values from the break rule(s) that determined the boundary
 * at the current iteration position.
 * 
 * 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.
 *
 * @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 the 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 3.0
 */
 virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status);

/**
     * Returns a unique class ID POLYMORPHICALLY.  Pure virtual override.
     * This method is to implement a simple version of RTTI, since not all
     * C++ compilers support genuine RTTI.  Polymorphic operator==() and
     * clone() methods call this method.
     *
     * @return          The class ID for this object. All objects of a
     *                  given class have the same class ID.  Objects of
     *                  other classes have different class IDs.
     * @stable ICU 2.0
     */
    virtual UClassID getDynamicClassID(void) const;

/**
     * Returns the class ID for this class.  This is useful only for
     * comparing to a return value from getDynamicClassID().  For example:
     *
     *      Base* polymorphic_pointer = createPolymorphicObject();
     *      if (polymorphic_pointer->getDynamicClassID() ==
     *          Derived::getStaticClassID()) ...
     *
     * @return          The class ID for all objects of this class.
     * @stable ICU 2.0
     */
    static UClassID U_EXPORT2 getStaticClassID(void);

#ifndef U_FORCE_HIDE_DEPRECATED_API
    /**
     * Deprecated functionality. Use clone() instead.
     *
     * Create a clone (copy) of this break iterator in memory provided
     *  by the caller.  The idea is to increase performance by avoiding
     *  a storage allocation.  Use of this function is NOT RECOMMENDED.
     *  Performance gains are minimal, and correct buffer management is
     *  tricky.  Use clone() instead.
     *
     * @param stackBuffer  The pointer to the memory into which the cloned object
     *                     should be placed.  If NULL,  allocate heap memory
     *                     for the cloned object.
     * @param BufferSize   The size of the buffer.  If zero, return the required
     *                     buffer size, but do not clone the object.  If the
     *                     size was too small (but not zero), allocate heap
     *                     storage for the cloned object.
     *
     * @param status       Error status.  U_SAFECLONE_ALLOCATED_WARNING will be
     *                     returned if the provided buffer was too small, and
     *                     the clone was therefore put on the heap.
     *
     * @return  Pointer to the clone object.  This may differ from the stackBuffer
     *          address if the byte alignment of the stack buffer was not suitable
     *          or if the stackBuffer was too small to hold the clone.
     * @deprecated ICU 52. Use clone() instead.
     */
    virtual RuleBasedBreakIterator *createBufferClone(void *stackBuffer,
                                                      int32_t &BufferSize,
                                                      UErrorCode &status);
#endif  // U_FORCE_HIDE_DEPRECATED_API

/**
     * Return the binary form of compiled break rules,
     * which can then be used to create a new break iterator at some
     * time in the future.  Creating a break iterator from pre-compiled rules
     * is much faster than building one from the source form of the
     * break rules.
     *
     * The binary data can only be used with the same version of ICU
     *  and on the same platform type (processor endian-ness)
     *
     * @param length Returns the length of the binary data.  (Out parameter.)
     *
     * @return   A pointer to the binary (compiled) rule data.  The storage
     *           belongs to the RulesBasedBreakIterator object, not the
     *           caller, and must not be modified or deleted.
     * @stable ICU 4.8
     */
    virtual const uint8_t *getBinaryRules(uint32_t &length);

/**
     *  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 RuleBasedBreakIterator &refreshInputText(UText *input, UErrorCode &status);

private:
    //=======================================================================
    // implementation
    //=======================================================================
    /**
     * Dumps caches and performs other actions associated with a complete change
     * in text or iteration position.
     * @internal (private)
     */
    void reset(void);

/**
      * Common initialization function, used by constructors and bufferClone.
      * @internal (private)
      */
    void init(UErrorCode &status);

/**
     * Iterate backwards from an arbitrary position in the input text using the
     * synthesized Safe Reverse rules.
     * This locates a "Safe Position" from which the forward break rules
     * will operate correctly. A Safe Position is not necessarily a boundary itself.
     *
     * @param fromPosition the position in the input text to begin the iteration.
     * @internal (private)
     */
    int32_t handleSafePrevious(int32_t fromPosition);

/**
     * Find a rule-based boundary by running the state machine.
     * Input
     *    fPosition, the position in the text to begin from.
     * Output
     *    fPosition:           the boundary following the starting position.
     *    fDictionaryCharCount the number of dictionary characters encountered.
     *                         If > 0, the segment will be further subdivided
     *    fRuleStatusIndex     Info from the state table indicating which rules caused the boundary.
     *
     * @internal (private)
     */
    int32_t handleNext();

/**
     * This function returns the appropriate LanguageBreakEngine for a
     * given character c.
     * @param c         A character in the dictionary set
     * @internal (private)
     */
    const LanguageBreakEngine *getLanguageBreakEngine(UChar32 c);

public:
#ifndef U_HIDE_INTERNAL_API
    /**
     *   Debugging function only.
     *   @internal
     */
     void dumpCache();

/**
     * Debugging function only.
     * @internal
     */
    void dumpTables();

#endif  /* U_HIDE_INTERNAL_API */
};

//------------------------------------------------------------------------------
//
//   Inline Functions Definitions ...
//
//------------------------------------------------------------------------------

inline UBool RuleBasedBreakIterator::operator!=(const BreakIterator& that) const {
    return !operator==(that);
}

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_BREAK_ITERATION */

#endif /* U_SHOW_CPLUSPLUS_API */

#endif

cmd: