The BreakIterator class implements methods for finding the location of boundaries in text. More...

#include <brkiter.h>

Inheritance diagram for icu::BreakIterator:

Public Types
enum	{ DONE = static_cast<int32_t>(-1) }

Public Member Functions
virtual	~BreakIterator ()
	destructor

virtual bool	operator== (const BreakIterator &) const =0
	Return true if another object is semantically equal to this one.

bool	operator!= (const BreakIterator &rhs) const
	Returns the complement of the result of operator==.

virtual BreakIterator *	clone () const =0
	Return a polymorphic copy of this object.

virtual UClassID	getDynamicClassID () const override=0
	Return a polymorphic class ID for this object.

virtual CharacterIterator &	getText () const =0
	Return a CharacterIterator over the text being analyzed.

virtual UText *	getUText (UText *fillIn, UErrorCode &status) const =0
	Get a UText for the text being analyzed.

virtual void	setText (const UnicodeString &text)=0
	Change the text over which this operates.

virtual void	setText (UText *text, UErrorCode &status)=0
	Reset the break iterator to operate over the text represented by the UText.

virtual void	adoptText (CharacterIterator *it)=0
	Change the text over which this operates.

virtual int32_t	first ()=0
	Sets the current iteration position to the beginning of the text, position zero.

virtual int32_t	last ()=0
	Set the iterator position to the index immediately BEYOND the last character in the text being scanned.

virtual int32_t	previous ()=0
	Set the iterator position to the boundary preceding the current boundary.

virtual int32_t	next ()=0
	Advance the iterator to the boundary following the current boundary.

virtual int32_t	current () const =0
	Return character index of the current iterator position within the text.

virtual int32_t	following (int32_t offset)=0
	Advance the iterator to the first boundary following the specified offset.

virtual int32_t	preceding (int32_t offset)=0
	Set the iterator position to the first boundary preceding the specified offset.

virtual UBool	isBoundary (int32_t offset)=0
	Return true if the specified position is a boundary position.

virtual int32_t	next (int32_t n)=0
	Set the iterator position to the nth boundary from the current boundary.

virtual int32_t	getRuleStatus () const
	For RuleBasedBreakIterators, return the status tag from the break rule that determined the boundary at the current iteration position.

virtual int32_t	getRuleStatusVec (int32_t *fillInVec, int32_t capacity, UErrorCode &status)
	For RuleBasedBreakIterators, get the status (tag) values from the break rule(s) that determined the boundary at the current iteration position.

virtual BreakIterator *	createBufferClone (void *stackBuffer, int32_t &BufferSize, UErrorCode &status)=0
	Deprecated functionality.

UBool	isBufferClone ()
	Determine whether the BreakIterator was created in user memory by createBufferClone(), and thus should not be deleted.

Locale	getLocale (ULocDataLocaleType type, UErrorCode &status) const
	Returns the locale for this break iterator.

const char *	getLocaleID (ULocDataLocaleType type, UErrorCode &status) const
	Get the locale for this break iterator object.

virtual BreakIterator &	refreshInputText (UText *input, UErrorCode &status)=0
	Set the subject text string upon which the break iterator is operating without changing any other aspect of the matching state.

Public Member Functions inherited from icu::UObject
virtual	~UObject ()
	Destructor.

Static Public Member Functions
static BreakIterator *	createWordInstance (const Locale &where, UErrorCode &status)
	Create BreakIterator for word-breaks using the given locale.

static BreakIterator *	createLineInstance (const Locale &where, UErrorCode &status)
	Create BreakIterator for line-breaks using specified locale.

static BreakIterator *	createCharacterInstance (const Locale &where, UErrorCode &status)
	Create BreakIterator for character-breaks using specified locale Returns an instance of a BreakIterator implementing character breaks.

static BreakIterator *	createSentenceInstance (const Locale &where, UErrorCode &status)
	Create BreakIterator for sentence-breaks using specified locale Returns an instance of a BreakIterator implementing sentence breaks.

static BreakIterator *	createTitleInstance (const Locale &where, UErrorCode &status)
	Create BreakIterator for title-casing breaks using the specified locale Returns an instance of a BreakIterator implementing title breaks.

static const Locale *	getAvailableLocales (int32_t &count)
	Get the set of Locales for which TextBoundaries are installed.

static UnicodeString &	getDisplayName (const Locale &objectLocale, const Locale &displayLocale, UnicodeString &name)
	Get name of the object for the desired Locale, in the desired language.

static UnicodeString &	getDisplayName (const Locale &objectLocale, UnicodeString &name)
	Get name of the object for the desired Locale, in the language of the default locale.

static URegistryKey	registerInstance (BreakIterator *toAdopt, const Locale &locale, UBreakIteratorType kind, UErrorCode &status)
	Register a new break iterator of the indicated kind, to use in the given locale.

static UBool	unregister (URegistryKey key, UErrorCode &status)
	Unregister a previously-registered BreakIterator using the key returned from the register call.

static StringEnumeration *	getAvailableLocales ()
	Return a StringEnumeration over the locales available at the time of the call, including registered locales.

Protected Member Functions
	BreakIterator ()

	BreakIterator (const BreakIterator &other)

	BreakIterator (const Locale &valid, const Locale &actual)

BreakIterator &	operator= (const BreakIterator &other)

Friends
class	ICUBreakIteratorFactory

class	ICUBreakIteratorService

Detailed Description

The BreakIterator class implements methods for finding the location of boundaries in text.

BreakIterator is an abstract base class. Instances of BreakIterator maintain a current position and scan over text returning the index of characters where boundaries occur.

Line boundary analysis determines where a text string can be broken when line-wrapping. The mechanism correctly handles punctuation and hyphenated words.

Sentence boundary analysis allows selection with correct interpretation of periods within numbers and abbreviations, and trailing punctuation marks such as quotation marks and parentheses.

Word boundary analysis is used by search and replace functions, as well as within text editing applications that allow the user to select words with a double click. Word selection provides correct interpretation of punctuation marks within and following words. Characters that are not part of a word, such as symbols or punctuation marks, have word-breaks on both sides.

Character boundary analysis allows users to interact with characters as they expect to, for example, when moving the cursor through a text string. Character boundary analysis provides correct navigation of through character strings, regardless of how the character is stored. For example, an accented character might be stored as a base character and a diacritical mark. What users consider to be a character can differ between languages.

The text boundary positions are found according to the rules described in Unicode Standard Annex #29, Text Boundaries, and Unicode Standard Annex #14, Line Breaking Properties. These are available at http://www.unicode.org/reports/tr14/ and http://www.unicode.org/reports/tr29/.

In addition to the C++ API defined in this header file, a plain C API with equivalent functionality is defined in the file ubrk.h

Code snippets illustrating the use of the Break Iterator APIs are available in the ICU User Guide, https://unicode-org.github.io/icu/userguide/boundaryanalysis/ and in the sample program icu/source/samples/break/break.cpp

Definition at line 106 of file brkiter.h.

Member Enumeration Documentation

◆ anonymous enum

anonymous enum

Enumerator
DONE	DONE is returned by previous() and next() after all valid boundaries have been returned. Stable: ICU 2.0

Definition at line 216 of file brkiter.h.

Constructor & Destructor Documentation

◆ ~BreakIterator()

virtual icu::BreakIterator::~BreakIterator ( )

virtual

destructor

Stable:: ICU 2.0

◆ BreakIterator() [1/3]

icu::BreakIterator::BreakIterator ( )

protected

Internal:: Do not use. This API is for internal use only.

◆ BreakIterator() [2/3]

icu::BreakIterator::BreakIterator ( const BreakIterator & other )

protected

Internal:: Do not use. This API is for internal use only.

◆ BreakIterator() [3/3]

icu::BreakIterator::BreakIterator	(	const Locale &	valid,
		const Locale &	actual
	)

protected

Internal:: Do not use. This API is for internal use only.

Member Function Documentation

◆ adoptText()

virtual void icu::BreakIterator::adoptText ( CharacterIterator * it )

pure virtual

Change the text over which this operates.

The text boundary is reset to the start. Note that setText(UText *) provides similar functionality to this function, and is more efficient.

Parameters

it	The CharacterIterator used to change the text.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ clone()

virtual BreakIterator * icu::BreakIterator::clone ( ) const

pure virtual

Return a polymorphic copy of this object.

This is an abstract method which subclasses implement.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ createBufferClone()

virtual BreakIterator * icu::BreakIterator::createBufferClone	(	void *	stackBuffer,
		int32_t &	BufferSize,
		UErrorCode &	status
	)

pure virtual

Deprecated functionality.

Use clone() instead.

Thread safe client-buffer-based cloning operation Do NOT call delete on a safeclone, since 'new' is not used to create it.

Parameters

stackBuffer	user allocated space for the new clone. If nullptr new memory will be allocated. If buffer is not large enough, new memory will be allocated.
BufferSize	reference to size of allocated space. If BufferSize == 0, a sufficient size for use in cloning will be returned ('pre-flighting') If BufferSize is not enough for a stack-based safe clone, new memory will be allocated.
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.

Returns: pointer to the new clone

Deprecated:: ICU 52. Use clone() instead.

Implemented in icu::RuleBasedBreakIterator.

◆ createCharacterInstance()

static BreakIterator * icu::BreakIterator::createCharacterInstance	(	const Locale &	where,
		UErrorCode &	status
	)

static

Create BreakIterator for character-breaks using specified locale Returns an instance of a BreakIterator implementing character breaks.

Character breaks are boundaries of combining character sequences.

Parameters

where	the locale.
status	The error code.

Returns: A BreakIterator for character-breaks. The UErrorCode& status parameter is used to return status information to the user. To check whether the construction succeeded or not, you should check the value of U_SUCCESS(err). If you wish more detailed information, you can check for informational error results which still indicate success. U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For example, 'de_CH' was requested, but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that the default locale data was used; neither the requested locale nor any of its fall back locales could be found. The caller owns the returned object and is responsible for deleting it.

Stable:: ICU 2.0

◆ createLineInstance()

static BreakIterator * icu::BreakIterator::createLineInstance	(	const Locale &	where,
		UErrorCode &	status
	)

static

Create BreakIterator for line-breaks using specified locale.

Returns an instance of a BreakIterator implementing line breaks. Line breaks are logically possible line breaks, actual line breaks are usually determined based on display width. LineBreak is useful for word wrapping text.

Parameters

where	the locale.
status	The error code.

Returns: A BreakIterator for line-breaks. The UErrorCode& status parameter is used to return status information to the user. To check whether the construction succeeded or not, you should check the value of U_SUCCESS(err). If you wish more detailed information, you can check for informational error results which still indicate success. U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For example, 'de_CH' was requested, but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that the default locale data was used; neither the requested locale nor any of its fall back locales could be found. The caller owns the returned object and is responsible for deleting it.

Stable:: ICU 2.0

◆ createSentenceInstance()

static BreakIterator * icu::BreakIterator::createSentenceInstance	(	const Locale &	where,
		UErrorCode &	status
	)

static

Create BreakIterator for sentence-breaks using specified locale Returns an instance of a BreakIterator implementing sentence breaks.

Parameters

where	the locale.
status	The error code.

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

Stable:: ICU 2.0

◆ createTitleInstance()

static BreakIterator * icu::BreakIterator::createTitleInstance	(	const Locale &	where,
		UErrorCode &	status
	)

static

Create BreakIterator for title-casing breaks using the specified locale Returns an instance of a BreakIterator implementing title breaks.

The iterator returned locates title boundaries as described for Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, please use a word boundary iterator. See createWordInstance.

Parameters

where	the locale.
status	The error code.

Returns: A BreakIterator for title-breaks. The UErrorCode& status parameter is used to return status information to the user. To check whether the construction succeeded or not, you should check the value of U_SUCCESS(err). If you wish more detailed information, you can check for informational error results which still indicate success. U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For example, 'de_CH' was requested, but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that the default locale data was used; neither the requested locale nor any of its fall back locales could be found. The caller owns the returned object and is responsible for deleting it.

Deprecated:: ICU 64 Use createWordInstance instead.

◆ createWordInstance()

static BreakIterator * icu::BreakIterator::createWordInstance	(	const Locale &	where,
		UErrorCode &	status
	)

static

Create BreakIterator for word-breaks using the given locale.

Returns an instance of a BreakIterator implementing word breaks. WordBreak is useful for word selection (ex. double click)

Parameters

where	the locale.
status	the error code

Returns: A BreakIterator for word-breaks. The UErrorCode& status parameter is used to return status information to the user. To check whether the construction succeeded or not, you should check the value of U_SUCCESS(err). If you wish more detailed information, you can check for informational error results which still indicate success. U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For example, 'de_CH' was requested, but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that the default locale data was used; neither the requested locale nor any of its fall back locales could be found. The caller owns the returned object and is responsible for deleting it.

Stable:: ICU 2.0

◆ current()

virtual int32_t icu::BreakIterator::current ( ) const

pure virtual

Return character index of the current iterator position within the text.

Returns: The boundary most recently returned.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ first()

virtual int32_t icu::BreakIterator::first ( )

pure virtual

Sets the current iteration position to the beginning of the text, position zero.

Returns: The offset of the beginning of the text, zero.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ following()

virtual int32_t icu::BreakIterator::following ( int32_t offset )

pure virtual

Advance the iterator to the first boundary following the specified offset.

The value returned is always greater than the offset or the value BreakIterator.DONE

Parameters

offset the offset to begin scanning.

Returns: The first boundary after the specified offset.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ getAvailableLocales() [1/2]

static StringEnumeration * icu::BreakIterator::getAvailableLocales ( )

static

Return a StringEnumeration over the locales available at the time of the call, including registered locales.

Returns: a StringEnumeration over the locales available at the time of the call

Stable:: ICU 2.4

◆ getAvailableLocales() [2/2]

static const Locale * icu::BreakIterator::getAvailableLocales ( int32_t & count )

static

Get the set of Locales for which TextBoundaries are installed.

Note: this will not return locales added through the register call. To see the registered locales too, use the getAvailableLocales function that returns a StringEnumeration object

Parameters

count the output parameter of number of elements in the locale list

Returns: available locales

Stable:: ICU 2.0

◆ getDisplayName() [1/2]

static UnicodeString & icu::BreakIterator::getDisplayName	(	const Locale &	objectLocale,
		const Locale &	displayLocale,
		UnicodeString &	name
	)

static

Get name of the object for the desired Locale, in the desired language.

Parameters

objectLocale	must be from getAvailableLocales.
displayLocale	specifies the desired locale for output.
name	the fill-in parameter of the return value Uses best match.

Returns: user-displayable name

Stable:: ICU 2.0

◆ getDisplayName() [2/2]

static UnicodeString & icu::BreakIterator::getDisplayName	(	const Locale &	objectLocale,
		UnicodeString &	name
	)

static

Get name of the object for the desired Locale, in the language of the default locale.

Parameters

objectLocale	must be from getMatchingLocales
name	the fill-in parameter of the return value

Returns: user-displayable name

Stable:: ICU 2.0

◆ getDynamicClassID()

virtual UClassID icu::BreakIterator::getDynamicClassID ( ) const

overridepure virtual

Return a polymorphic class ID for this object.

Different subclasses will return distinct unequal values.

Stable:: ICU 2.0

Reimplemented from icu::UObject.

Implemented in icu::RuleBasedBreakIterator.

◆ getLocale()

Locale icu::BreakIterator::getLocale	(	ULocDataLocaleType	type,
		UErrorCode &	status
	)		const

Returns the locale for this break iterator.

Two flavors are available: valid and actual locale.

Stable:: ICU 2.8

◆ getLocaleID()

const char * icu::BreakIterator::getLocaleID	(	ULocDataLocaleType	type,
		UErrorCode &	status
	)		const

Get the locale for this break iterator object.

You can choose between valid and actual locale.

Parameters

type	type of the locale we're looking for (valid or actual)
status	error code for the operation

Returns: the locale

Internal:: Do not use. This API is for internal use only.

◆ getRuleStatus()

virtual int32_t icu::BreakIterator::getRuleStatus ( ) const

virtual

For RuleBasedBreakIterators, return the status tag from the break rule that determined the boundary at the current iteration position.

For break iterator types that do not support a rule status, a default value of 0 is returned.

Returns: the status from the break rule that determined the boundary at the current iteration position.

See also: RuleBaseBreakIterator::getRuleStatus(); UWordBreak

Stable:: ICU 52

Reimplemented in icu::RuleBasedBreakIterator.

◆ getRuleStatusVec()

virtual int32_t icu::BreakIterator::getRuleStatusVec	(	int32_t *	fillInVec,
		int32_t	capacity,
		UErrorCode &	status
	)

virtual

For RuleBasedBreakIterators, get the status (tag) values from the break rule(s) that determined the boundary at the current iteration position.

For break iterator types that do not support rule status, no values are returned.

The returned status value(s) are stored into an array provided by the caller. The values are stored in sorted (ascending) order. If the capacity of the output array is insufficient to hold the data, the output will be truncated to the available length, and a U_BUFFER_OVERFLOW_ERROR will be signaled.

See also: RuleBaseBreakIterator::getRuleStatusVec

Parameters

fillInVec	an array to be filled in with the status values.
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.
status	receives error codes.

Returns: The number of rule status values from rules that determined the boundary at the current iteration position. In the event of a U_BUFFER_OVERFLOW_ERROR, the return value is the total number of status values that were available, not the reduced number that were actually returned.

See also: getRuleStatus

Stable:: ICU 52

Reimplemented in icu::RuleBasedBreakIterator.

◆ getText()

virtual CharacterIterator & icu::BreakIterator::getText ( ) const

pure virtual

Return a CharacterIterator over the text being analyzed.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ getUText()

virtual UText * icu::BreakIterator::getUText	(	UText *	fillIn,
		UErrorCode &	status
	)		const

pure virtual

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.

Parameters

fillIn	A UText to be filled in. If nullptr, a new UText will be allocated to hold the result.
status	receives any error codes.

Returns: The current UText for this break iterator. If an input UText was provided, it will always be returned.

Stable:: ICU 3.4

Implemented in icu::RuleBasedBreakIterator.

◆ isBoundary()

virtual UBool icu::BreakIterator::isBoundary ( int32_t offset )

pure virtual

Return true if the specified position is a boundary position.

As a side effect, the current position of the iterator is set to the first boundary position at or following the specified offset.

Parameters

offset the offset to check.

Returns: True if "offset" is a boundary position.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ isBufferClone()

UBool icu::BreakIterator::isBufferClone ( )

inline

Determine whether the BreakIterator was created in user memory by createBufferClone(), and thus should not be deleted.

Such objects must be closed by an explicit call to the destructor (not delete).

Deprecated:: ICU 52. Always delete the BreakIterator.

Definition at line 656 of file brkiter.h.

◆ last()

virtual int32_t icu::BreakIterator::last ( )

pure virtual

Set the iterator position to the index immediately BEYOND the last character in the text being scanned.

Returns: The index immediately BEYOND the last character in the text being scanned.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ next() [1/2]

virtual int32_t icu::BreakIterator::next ( )

pure virtual

Advance the iterator to the boundary following the current boundary.

Returns: The character index of the next text boundary or DONE if all boundaries have been returned.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ next() [2/2]

virtual int32_t icu::BreakIterator::next ( int32_t n )

pure virtual

Set the iterator position to the nth boundary from the current boundary.

Parameters

n	the number of boundaries to move by. A value of 0 does nothing. Negative values move to previous boundaries and positive values move to later boundaries.

Returns: The new iterator position, or DONE if there are fewer than |n| boundaries in the specified direction.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ operator!=()

bool icu::BreakIterator::operator!= ( const BreakIterator & rhs ) const

inline

Returns the complement of the result of operator==.

Parameters

rhs	The BreakIterator to be compared for inequality

Returns: the complement of the result of operator==

Stable:: ICU 2.0

Definition at line 135 of file brkiter.h.

References icu::operator==().

◆ operator=()

BreakIterator & icu::BreakIterator::operator= ( const BreakIterator & other )

protected

Internal:: Do not use. This API is for internal use only.. Assignment Operator, used by RuleBasedBreakIterator.

◆ operator==()

virtual bool icu::BreakIterator::operator== ( const BreakIterator & ) const

pure virtual

Return true if another object is semantically equal to this one.

The other object should be an instance of the same subclass of BreakIterator. Objects of different subclasses are considered unequal.

Return true if this BreakIterator is at the same position in the same text, and is the same class and type (word, line, etc.) of BreakIterator, as the argument. Text is considered the same if it contains the same characters, it need not be the same object, and styles are not considered.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

Referenced by icu::RuleBasedBreakIterator::operator!=().

◆ preceding()

virtual int32_t icu::BreakIterator::preceding ( int32_t offset )

pure virtual

Set the iterator position to the first boundary preceding the specified offset.

The value returned is always smaller than the offset or the value BreakIterator.DONE

Parameters

offset the offset to begin scanning.

Returns: The first boundary before the specified offset.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ previous()

virtual int32_t icu::BreakIterator::previous ( )

pure virtual

Set the iterator position to the boundary preceding the current boundary.

Returns: The character index of the previous text boundary or DONE if all boundaries have been returned.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ refreshInputText()

virtual BreakIterator & icu::BreakIterator::refreshInputText	(	UText *	input,
		UErrorCode &	status
	)

pure virtual

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.

Parameters

input	The new (moved) text string.
status	Receives errors detected by this function.

Returns: *this

Stable:: ICU 49

Implemented in icu::RuleBasedBreakIterator.

◆ registerInstance()

static URegistryKey icu::BreakIterator::registerInstance	(	BreakIterator *	toAdopt,
		const Locale &	locale,
		UBreakIteratorType	kind,
		UErrorCode &	status
	)

static

Register a new break iterator of the indicated kind, to use in the given locale.

The break iterator will be adopted. Clones of the iterator will be returned if a request for a break iterator of the given kind matches or falls back to this locale. Because ICU may choose to cache BreakIterators internally, this must be called at application startup, prior to any calls to BreakIterator::createXXXInstance to avoid undefined behavior.

Parameters

toAdopt	the BreakIterator instance to be adopted
locale	the Locale for which this instance is to be registered
kind	the type of iterator for which this instance is to be registered
status	the in/out status code, no special meanings are assigned

Returns: a registry key that can be used to unregister this instance

Stable:: ICU 2.4

◆ setText() [1/2]

virtual void icu::BreakIterator::setText ( const UnicodeString & text )

pure virtual

Change the text over which this operates.

The text boundary is reset to the start.

The BreakIterator will retain a reference to the supplied string. The caller must not modify or delete the text while the BreakIterator retains the reference.

Parameters

text	The UnicodeString used to change the text.

Stable:: ICU 2.0

Implemented in icu::RuleBasedBreakIterator.

◆ setText() [2/2]

virtual void icu::BreakIterator::setText	(	UText *	text,
		UErrorCode &	status
	)

pure virtual

Reset the break iterator to operate over the text represented by the UText.

The iterator position is reset to the start.

This function makes a shallow clone of the supplied UText. This means that the caller is free to immediately close or otherwise reuse the Utext that was passed as a parameter, but that the underlying text itself must not be altered while being referenced by the break iterator.

All index positions returned by break iterator functions are native indices from the UText. For example, when breaking UTF-8 encoded text, the break positions returned by next(), previous(), etc. will be UTF-8 string indices, not UTF-16 positions.

Parameters

text	The UText used to change the text.
status	receives any error codes.

Stable:: ICU 3.4

Implemented in icu::RuleBasedBreakIterator.

◆ unregister()

static UBool icu::BreakIterator::unregister	(	URegistryKey	key,
		UErrorCode &	status
	)

static

Unregister a previously-registered BreakIterator using the key returned from the register call.

Key becomes invalid after a successful call and should not be used again. The BreakIterator corresponding to the key will be deleted. Because ICU may choose to cache BreakIterators internally, this should be called during application shutdown, after all calls to BreakIterator::createXXXInstance to avoid undefined behavior.

Parameters

key	the registry key returned by a previous call to registerInstance
status	the in/out status code, no special meanings are assigned

Returns: true if the iterator for the key was successfully unregistered

Stable:: ICU 2.4

Friends And Related Symbol Documentation

◆ ICUBreakIteratorFactory

friend class ICUBreakIteratorFactory

friend

Definition at line 629 of file brkiter.h.

◆ ICUBreakIteratorService

friend class ICUBreakIteratorService

friend

Definition at line 630 of file brkiter.h.

The documentation for this class was generated from the following file:

common/unicode/brkiter.h

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Friends

Detailed Description

Member Enumeration Documentation

◆ anonymous enum

Constructor & Destructor Documentation

◆ ~BreakIterator()

◆ BreakIterator() [1/3]

◆ BreakIterator() [2/3]

◆ BreakIterator() [3/3]

Member Function Documentation

◆ adoptText()

◆ clone()

◆ createBufferClone()

◆ createCharacterInstance()

◆ createLineInstance()

◆ createSentenceInstance()

◆ createTitleInstance()

◆ createWordInstance()

◆ current()

◆ first()

◆ following()

◆ getAvailableLocales() [1/2]

◆ getAvailableLocales() [2/2]

◆ getDisplayName() [1/2]

◆ getDisplayName() [2/2]

◆ getDynamicClassID()

◆ getLocale()

◆ getLocaleID()

◆ getRuleStatus()

◆ getRuleStatusVec()

◆ getText()

◆ getUText()

◆ isBoundary()

◆ isBufferClone()

◆ last()

◆ next() [1/2]

◆ next() [2/2]

◆ operator!=()

◆ operator=()

◆ operator==()

◆ preceding()

◆ previous()

◆ refreshInputText()

◆ registerInstance()

◆ setText() [1/2]

◆ setText() [2/2]

◆ unregister()

Friends And Related Symbol Documentation

◆ ICUBreakIteratorFactory

◆ ICUBreakIteratorService