Gecko [ dallasfobana2023.variationbd.com ]

Name	Size	Permission
alphaindex.h	26.42 KB	-rw-r--r--
appendable.h	8.43 KB	-rw-r--r--
basictz.h	8.84 KB	-rw-r--r--
brkiter.h	27.64 KB	-rw-r--r--
bytestream.h	9.54 KB	-rw-r--r--
bytestrie.h	19.26 KB	-rw-r--r--
bytestriebuilder.h	7.02 KB	-rw-r--r--
calendar.h	105.06 KB	-rw-r--r--
caniter.h	7.37 KB	-rw-r--r--
casemap.h	25.26 KB	-rw-r--r--
char16ptr.h	7.16 KB	-rw-r--r--
chariter.h	24 KB	-rw-r--r--
choicfmt.h	23.85 KB	-rw-r--r--
coleitr.h	13.7 KB	-rw-r--r--
coll.h	55.59 KB	-rw-r--r--
compactdecimalformat.h	6.81 KB	-rw-r--r--
curramt.h	3.69 KB	-rw-r--r--
currpinf.h	7.24 KB	-rw-r--r--
currunit.h	3.99 KB	-rw-r--r--
datefmt.h	40.37 KB	-rw-r--r--
dbbi.h	1.11 KB	-rw-r--r--
dcfmtsym.h	20.1 KB	-rw-r--r--
decimfmt.h	87.82 KB	-rw-r--r--
docmain.h	6.96 KB	-rw-r--r--
dtfmtsym.h	37.64 KB	-rw-r--r--
dtintrv.h	3.78 KB	-rw-r--r--
dtitvfmt.h	46.56 KB	-rw-r--r--
dtitvinf.h	18.46 KB	-rw-r--r--
dtptngen.h	25.08 KB	-rw-r--r--
dtrule.h	8.62 KB	-rw-r--r--
edits.h	20.67 KB	-rw-r--r--
enumset.h	2.08 KB	-rw-r--r--
errorcode.h	4.78 KB	-rw-r--r--
fieldpos.h	8.63 KB	-rw-r--r--
filteredbrk.h	5.24 KB	-rw-r--r--
fmtable.h	24.36 KB	-rw-r--r--
format.h	12.44 KB	-rw-r--r--
formattedvalue.h	9.73 KB	-rw-r--r--
fpositer.h	2.98 KB	-rw-r--r--
gender.h	3.27 KB	-rw-r--r--
gregocal.h	31.57 KB	-rw-r--r--
icudataver.h	1.03 KB	-rw-r--r--
icuplug.h	11.88 KB	-rw-r--r--
idna.h	12.63 KB	-rw-r--r--
listformatter.h	9.42 KB	-rw-r--r--
localebuilder.h	10.54 KB	-rw-r--r--
localpointer.h	19.69 KB	-rw-r--r--
locdspnm.h	7.06 KB	-rw-r--r--
locid.h	44.94 KB	-rw-r--r--
measfmt.h	11.44 KB	-rw-r--r--
measunit.h	88.17 KB	-rw-r--r--
measure.h	4.26 KB	-rw-r--r--
messagepattern.h	33.65 KB	-rw-r--r--
msgfmt.h	44.04 KB	-rw-r--r--
normalizer2.h	33.97 KB	-rw-r--r--
normlzr.h	30.74 KB	-rw-r--r--
nounit.h	2.63 KB	-rw-r--r--
numberformatter.h	84.62 KB	-rw-r--r--
numberrangeformatter.h	29.93 KB	-rw-r--r--
numfmt.h	49.35 KB	-rw-r--r--
numsys.h	7.13 KB	-rw-r--r--
parseerr.h	3.08 KB	-rw-r--r--
parsepos.h	5.5 KB	-rw-r--r--
platform.h	27.1 KB	-rw-r--r--
plurfmt.h	25.18 KB	-rw-r--r--
plurrule.h	18.33 KB	-rw-r--r--
ptypes.h	3.49 KB	-rw-r--r--
putil.h	6.33 KB	-rw-r--r--
rbbi.h	26.42 KB	-rw-r--r--
rbnf.h	49.79 KB	-rw-r--r--
rbtz.h	15.47 KB	-rw-r--r--
regex.h	84.3 KB	-rw-r--r--
region.h	9.12 KB	-rw-r--r--
reldatefmt.h	22.37 KB	-rw-r--r--
rep.h	9.5 KB	-rw-r--r--
resbund.h	18.01 KB	-rw-r--r--
schriter.h	6.26 KB	-rw-r--r--
scientificnumberformatter.h	6.32 KB	-rw-r--r--
search.h	22.21 KB	-rw-r--r--
selfmt.h	14.24 KB	-rw-r--r--
simpleformatter.h	12.53 KB	-rw-r--r--
simpletz.h	45.3 KB	-rw-r--r--
smpdtfmt.h	70.9 KB	-rw-r--r--
sortkey.h	11.12 KB	-rw-r--r--
std_string.h	1015 B	-rw-r--r--
strenum.h	10.04 KB	-rw-r--r--
stringoptions.h	5.79 KB	-rw-r--r--
stringpiece.h	6.46 KB	-rw-r--r--
stringtriebuilder.h	15.27 KB	-rw-r--r--
stsearch.h	21.29 KB	-rw-r--r--
symtable.h	4.21 KB	-rw-r--r--
tblcoll.h	36.4 KB	-rw-r--r--
timezone.h	41.2 KB	-rw-r--r--
tmunit.h	3.29 KB	-rw-r--r--
tmutamt.h	4.8 KB	-rw-r--r--
tmutfmt.h	7.79 KB	-rw-r--r--
translit.h	65.76 KB	-rw-r--r--
tzfmt.h	42.82 KB	-rw-r--r--
tznames.h	16.79 KB	-rw-r--r--
tzrule.h	35.32 KB	-rw-r--r--
tztrans.h	6.07 KB	-rw-r--r--
ubidi.h	89.56 KB	-rw-r--r--
ubiditransform.h	12.65 KB	-rw-r--r--
ubrk.h	23.97 KB	-rw-r--r--
ucal.h	55.54 KB	-rw-r--r--
ucasemap.h	15.18 KB	-rw-r--r--
ucat.h	5.36 KB	-rw-r--r--
uchar.h	140.66 KB	-rw-r--r--
ucharstrie.h	21.06 KB	-rw-r--r--
ucharstriebuilder.h	7.14 KB	-rw-r--r--
uchriter.h	13.14 KB	-rw-r--r--
uclean.h	11.21 KB	-rw-r--r--
ucnv.h	83.09 KB	-rw-r--r--
ucnv_cb.h	6.59 KB	-rw-r--r--
ucnv_err.h	20.99 KB	-rw-r--r--
ucnvsel.h	6.14 KB	-rw-r--r--
ucol.h	61.39 KB	-rw-r--r--
ucoleitr.h	9.46 KB	-rw-r--r--
uconfig.h	12.05 KB	-rw-r--r--
ucpmap.h	5.58 KB	-rw-r--r--
ucptrie.h	22.29 KB	-rw-r--r--
ucsdet.h	14.67 KB	-rw-r--r--
ucurr.h	16.15 KB	-rw-r--r--
udat.h	60.81 KB	-rw-r--r--
udata.h	15.53 KB	-rw-r--r--
udateintervalformat.h	10.03 KB	-rw-r--r--
udatpg.h	25.94 KB	-rw-r--r--
udisplaycontext.h	5.89 KB	-rw-r--r--
uenum.h	7.78 KB	-rw-r--r--
ufieldpositer.h	4.36 KB	-rw-r--r--
uformattable.h	10.94 KB	-rw-r--r--
uformattedvalue.h	12.14 KB	-rw-r--r--
ugender.h	2 KB	-rw-r--r--
uidna.h	33.37 KB	-rw-r--r--
uiter.h	22.77 KB	-rw-r--r--
uldnames.h	10.45 KB	-rw-r--r--
ulistformatter.h	8.83 KB	-rw-r--r--
uloc.h	50.75 KB	-rw-r--r--
ulocdata.h	11.26 KB	-rw-r--r--
umachine.h	13.19 KB	-rw-r--r--
umisc.h	1.33 KB	-rw-r--r--
umsg.h	24.23 KB	-rw-r--r--
umutablecptrie.h	8.28 KB	-rw-r--r--
unifilt.h	3.63 KB	-rw-r--r--
unifunct.h	3.98 KB	-rw-r--r--
unimatch.h	6.04 KB	-rw-r--r--
unirepl.h	3.32 KB	-rw-r--r--
uniset.h	64.88 KB	-rw-r--r--
unistr.h	170.39 KB	-rw-r--r--
unorm.h	20.45 KB	-rw-r--r--
unorm2.h	24.66 KB	-rw-r--r--
unum.h	53.55 KB	-rw-r--r--
unumberformatter.h	25.19 KB	-rw-r--r--
unumsys.h	7.21 KB	-rw-r--r--
uobject.h	10.85 KB	-rw-r--r--
upluralrules.h	7.88 KB	-rw-r--r--
uregex.h	72.05 KB	-rw-r--r--
uregion.h	9.84 KB	-rw-r--r--
ureldatefmt.h	17.26 KB	-rw-r--r--
urename.h	131.4 KB	-rw-r--r--
urep.h	5.38 KB	-rw-r--r--
ures.h	36.54 KB	-rw-r--r--
uscript.h	26.87 KB	-rw-r--r--
usearch.h	38.12 KB	-rw-r--r--
uset.h	40 KB	-rw-r--r--
usetiter.h	9.49 KB	-rw-r--r--
ushape.h	18 KB	-rw-r--r--
uspoof.h	66.03 KB	-rw-r--r--
usprep.h	8.14 KB	-rw-r--r--
ustdio.h	38.54 KB	-rw-r--r--
ustream.h	1.8 KB	-rw-r--r--
ustring.h	72.47 KB	-rw-r--r--
ustringtrie.h	3.15 KB	-rw-r--r--
utext.h	58.11 KB	-rw-r--r--
utf.h	7.86 KB	-rw-r--r--
utf16.h	22.33 KB	-rw-r--r--
utf32.h	763 B	-rw-r--r--
utf8.h	29.96 KB	-rw-r--r--
utf_old.h	43.78 KB	-rw-r--r--
utmscale.h	13.78 KB	-rw-r--r--
utrace.h	13.89 KB	-rw-r--r--
utrans.h	25.54 KB	-rw-r--r--
utypes.h	30.38 KB	-rw-r--r--
uvernum.h	6.67 KB	-rw-r--r--
uversion.h	6.7 KB	-rw-r--r--
vtzone.h	20.17 KB	-rw-r--r--

Code Editor : rbbi.h

// © 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"

/**
 * \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 BreakIterator* 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);

/**
     * 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 BreakIterator *  createBufferClone(void *stackBuffer,
                                               int32_t &BufferSize,
                                               UErrorCode &status);

/**
     * 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

${this.title}

Code Editor : rbbi.h