The RuleBasedCollator class provides the implementation of Collator, using data-driven tables. More...

#include <tblcoll.h>

Inheritance diagram for icu::RuleBasedCollator:

Public Member Functions
	RuleBasedCollator (const UnicodeString &rules, UErrorCode &status)
	RuleBasedCollator constructor. More...

	RuleBasedCollator (const UnicodeString &rules, ECollationStrength collationStrength, UErrorCode &status)
	RuleBasedCollator constructor. More...

	RuleBasedCollator (const UnicodeString &rules, UColAttributeValue decompositionMode, UErrorCode &status)
	RuleBasedCollator constructor. More...

	RuleBasedCollator (const UnicodeString &rules, ECollationStrength collationStrength, UColAttributeValue decompositionMode, UErrorCode &status)
	RuleBasedCollator constructor. More...

	RuleBasedCollator (const UnicodeString &rules, UParseError &parseError, UnicodeString &reason, UErrorCode &errorCode)
	TODO: document & propose as public API. More...

	RuleBasedCollator (const RuleBasedCollator &other)
	Copy constructor. More...

	RuleBasedCollator (const uint8_t bin, int32_t length, const RuleBasedCollator base, UErrorCode &status)
	Opens a collator from a collator binary image created using cloneBinary. More...

virtual	~RuleBasedCollator ()
	Destructor. More...

RuleBasedCollator &	operator= (const RuleBasedCollator &other)
	Assignment operator. More...

virtual UBool	operator== (const Collator &other) const
	Returns true if argument is the same as this object. More...

virtual Collator *	clone (void) const
	Makes a copy of this object. More...

virtual CollationElementIterator *	createCollationElementIterator (const UnicodeString &source) const
	Creates a collation element iterator for the source string. More...

virtual CollationElementIterator *	createCollationElementIterator (const CharacterIterator &source) const
	Creates a collation element iterator for the source. More...

virtual UCollationResult	compare (const UnicodeString &source, const UnicodeString &target, UErrorCode &status) const
	The comparison function compares the character data stored in two different strings. More...

virtual UCollationResult	compare (const UnicodeString &source, const UnicodeString &target, int32_t length, UErrorCode &status) const
	Does the same thing as compare but limits the comparison to a specified length. More...

virtual UCollationResult	compare (const char16_t source, int32_t sourceLength, const char16_t target, int32_t targetLength, UErrorCode &status) const
	The comparison function compares the character data stored in two different string arrays. More...

virtual UCollationResult	compare (UCharIterator &sIter, UCharIterator &tIter, UErrorCode &status) const
	Compares two strings using the Collator. More...

virtual UCollationResult	compareUTF8 (const StringPiece &source, const StringPiece &target, UErrorCode &status) const
	Compares two UTF-8 strings using the Collator. More...

virtual CollationKey &	getCollationKey (const UnicodeString &source, CollationKey &key, UErrorCode &status) const
	Transforms the string into a series of characters that can be compared with CollationKey.compare(). More...

virtual CollationKey &	getCollationKey (const char16_t *source, int32_t sourceLength, CollationKey &key, UErrorCode &status) const
	Transforms a specified region of the string into a series of characters that can be compared with CollationKey.compare. More...

virtual int32_t	hashCode () const
	Generates the hash code for the rule-based collation object. More...

virtual Locale	getLocale (ULocDataLocaleType type, UErrorCode &status) const
	Gets the locale of the Collator. More...

const UnicodeString &	getRules () const
	Gets the tailoring rules for this collator. More...

virtual void	getVersion (UVersionInfo info) const
	Gets the version information for a Collator. More...

int32_t	getMaxExpansion (int32_t order) const
	Returns the maximum length of any expansion sequences that end with the specified comparison order. More...

virtual UClassID	getDynamicClassID (void) const
	Returns a unique class ID POLYMORPHICALLY. More...

uint8_t *	cloneRuleData (int32_t &length, UErrorCode &status) const
	Do not use this method: The caller and the ICU library might use different heaps. More...

int32_t	cloneBinary (uint8_t *buffer, int32_t capacity, UErrorCode &status) const
	Creates a binary image of a collator. More...

void	getRules (UColRuleOption delta, UnicodeString &buffer) const
	Returns current rules. More...

virtual void	setAttribute (UColAttribute attr, UColAttributeValue value, UErrorCode &status)
	Universal attribute setter. More...

virtual UColAttributeValue	getAttribute (UColAttribute attr, UErrorCode &status) const
	Universal attribute getter. More...

virtual Collator &	setMaxVariable (UColReorderCode group, UErrorCode &errorCode)
	Sets the variable top to the top of the specified reordering group. More...

virtual UColReorderCode	getMaxVariable () const
	Returns the maximum reordering group whose characters are affected by UCOL_ALTERNATE_HANDLING. More...

virtual uint32_t	setVariableTop (const char16_t *varTop, int32_t len, UErrorCode &status)
	Sets the variable top to the primary weight of the specified string. More...

virtual uint32_t	setVariableTop (const UnicodeString &varTop, UErrorCode &status)
	Sets the variable top to the primary weight of the specified string. More...

virtual void	setVariableTop (uint32_t varTop, UErrorCode &status)
	Sets the variable top to the specified primary weight. More...

virtual uint32_t	getVariableTop (UErrorCode &status) const
	Gets the variable top value of a Collator. More...

virtual UnicodeSet *	getTailoredSet (UErrorCode &status) const
	Get a UnicodeSet that contains all the characters and sequences tailored in this collator. More...

virtual int32_t	getSortKey (const UnicodeString &source, uint8_t *result, int32_t resultLength) const
	Get the sort key as an array of bytes from a UnicodeString. More...

virtual int32_t	getSortKey (const char16_t source, int32_t sourceLength, uint8_t result, int32_t resultLength) const
	Get the sort key as an array of bytes from a char16_t buffer. More...

virtual int32_t	getReorderCodes (int32_t *dest, int32_t destCapacity, UErrorCode &status) const
	Retrieves the reordering codes for this collator. More...

virtual void	setReorderCodes (const int32_t *reorderCodes, int32_t reorderCodesLength, UErrorCode &status)
	Sets the ordering of scripts for this collator. More...

virtual UCollationResult	internalCompareUTF8 (const char left, int32_t leftLength, const char right, int32_t rightLength, UErrorCode &errorCode) const
	Implements ucol_strcollUTF8(). More...

virtual int32_t	internalGetShortDefinitionString (const char locale, char buffer, int32_t capacity, UErrorCode &status) const
	Get the short definition string for a collator. More...

virtual int32_t	internalNextSortKeyPart (UCharIterator iter, uint32_t state[2], uint8_t dest, int32_t count, UErrorCode &errorCode) const
	Implements ucol_nextSortKeyPart(). More...

	RuleBasedCollator ()
	Only for use in ucol_openRules(). More...

const char *	internalGetLocaleID (ULocDataLocaleType type, UErrorCode &errorCode) const
	Implements ucol_getLocaleByType(). More...

void	internalGetContractionsAndExpansions (UnicodeSet contractions, UnicodeSet expansions, UBool addPrefixes, UErrorCode &errorCode) const
	Implements ucol_getContractionsAndExpansions(). More...

void	internalAddContractions (UChar32 c, UnicodeSet &set, UErrorCode &errorCode) const
	Adds the contractions that start with character c to the set. More...

void	internalBuildTailoring (const UnicodeString &rules, int32_t strength, UColAttributeValue decompositionMode, UParseError outParseError, UnicodeString outReason, UErrorCode &errorCode)
	Implements from-rule constructors, and ucol_openRules(). More...

void	internalGetCEs (const UnicodeString &str, UVector64 &ces, UErrorCode &errorCode) const
	Appends the CEs for the string to the vector. More...

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

virtual UBool	operator!= (const Collator &other) const
	Returns true if "other" is not the same as "this". More...

virtual EComparisonResult	compare (const UnicodeString &source, const UnicodeString &target) const
	The comparison function compares the character data stored in two different strings. More...

virtual EComparisonResult	compare (const UnicodeString &source, const UnicodeString &target, int32_t length) const
	Does the same thing as compare but limits the comparison to a specified length. More...

virtual EComparisonResult	compare (const char16_t source, int32_t sourceLength, const char16_t target, int32_t targetLength) const
	The comparison function compares the character data stored in two different string arrays. More...

UBool	greater (const UnicodeString &source, const UnicodeString &target) const
	Convenience method for comparing two strings based on the collation rules. More...

UBool	greaterOrEqual (const UnicodeString &source, const UnicodeString &target) const
	Convenience method for comparing two strings based on the collation rules. More...

UBool	equals (const UnicodeString &source, const UnicodeString &target) const
	Convenience method for comparing two strings based on the collation rules. More...

virtual ECollationStrength	getStrength (void) const
	Determines the minimum strength that will be used in comparison or transformation. More...

virtual void	setStrength (ECollationStrength newStrength)
	Sets the minimum strength to be used in comparison or transformation. More...

virtual Collator *	safeClone (void) const
	Same as clone(). More...

UCollator *	toUCollator ()

const UCollator *	toUCollator () const

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

Static Public Member Functions
static UClassID	getStaticClassID (void)
	Returns the class ID for this class. More...

static RuleBasedCollator *	rbcFromUCollator (UCollator *uc)

static const RuleBasedCollator *	rbcFromUCollator (const UCollator *uc)

Static Public Member Functions inherited from icu::Collator
static Collator *	createInstance (UErrorCode &err)
	Creates the Collator object for the current default locale. More...

static Collator *	createInstance (const Locale &loc, UErrorCode &err)
	Gets the collation object for the desired locale. More...

static int32_t	getEquivalentReorderCodes (int32_t reorderCode, int32_t *dest, int32_t destCapacity, UErrorCode &status)
	Retrieves the reorder codes that are grouped with the given reorder code. More...

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

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

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

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

static StringEnumeration *	getKeywords (UErrorCode &status)
	Create a string enumerator of all possible keywords that are relevant to collation. More...

static StringEnumeration *	getKeywordValues (const char *keyword, UErrorCode &status)
	Given a keyword, create a string enumeration of all values for that keyword that are currently in use. More...

static StringEnumeration *	getKeywordValuesForLocale (const char *keyword, const Locale &locale, UBool commonlyUsed, UErrorCode &status)
	Given a key and a locale, returns an array of string values in a preferred order that would make a difference. More...

static Locale	getFunctionalEquivalent (const char *keyword, const Locale &locale, UBool &isAvailable, UErrorCode &status)
	Return the functionally equivalent locale for the given requested locale, with respect to given keyword, for the collation service. More...

static URegistryKey	registerInstance (Collator *toAdopt, const Locale &locale, UErrorCode &status)
	Register a new Collator. More...

static URegistryKey	registerFactory (CollatorFactory *toAdopt, UErrorCode &status)
	Register a new CollatorFactory. More...

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

static int32_t	getBound (const uint8_t source, int32_t sourceLength, UColBoundMode boundType, uint32_t noOfLevels, uint8_t result, int32_t resultLength, UErrorCode &status)
	Produce a bound for a given sortkey and a number of levels. More...

static Collator *	fromUCollator (UCollator *uc)

static const Collator *	fromUCollator (const UCollator *uc)

Protected Member Functions
virtual void	setLocales (const Locale &requestedLocale, const Locale &validLocale, const Locale &actualLocale)
	Used internally by registration to define the requested and valid locales. More...

Protected Member Functions inherited from icu::Collator
	Collator ()
	Default constructor. More...

	Collator (UCollationStrength collationStrength, UNormalizationMode decompositionMode)
	Constructor. More...

	Collator (const Collator &other)
	Copy constructor. More...

Friends
class	CollationElementIterator

class	Collator

Additional Inherited Members
Public Types inherited from icu::Collator
enum	ECollationStrength { PRIMARY = UCOL_PRIMARY, SECONDARY = UCOL_SECONDARY, TERTIARY = UCOL_TERTIARY, QUATERNARY = UCOL_QUATERNARY, IDENTICAL = UCOL_IDENTICAL }
	Base letter represents a primary difference. More...

enum	EComparisonResult { LESS = UCOL_LESS, EQUAL = UCOL_EQUAL, GREATER = UCOL_GREATER }
	LESS is returned if source string is compared to be less than target string in the compare() method. More...

Detailed Description

The RuleBasedCollator class provides the implementation of Collator, using data-driven tables.

The user can create a customized table-based collation.

For more information about the collation service see the User Guide.

Collation service provides correct sorting orders for most locales supported in ICU. If specific data for a locale is not available, the orders eventually falls back to the CLDR root sort order.

Sort ordering may be customized by providing your own set of rules. For more on this subject see the Collation Customization section of the User Guide.

Note, RuleBasedCollator is not to be subclassed.

See also: Collator

Definition at line 113 of file tblcoll.h.

Constructor & Destructor Documentation

◆ RuleBasedCollator() [1/8]

icu::RuleBasedCollator::RuleBasedCollator	(	const UnicodeString &	rules,
		UErrorCode &	status
	)

RuleBasedCollator constructor.

This takes the table rules and builds a collation table out of them. Please see RuleBasedCollator class description for more details on the collation rule syntax.

Parameters

rules	the collation rules to build the collation table from.
status	reporting a success or an error.

Stable:: ICU 2.0

◆ RuleBasedCollator() [2/8]

icu::RuleBasedCollator::RuleBasedCollator	(	const UnicodeString &	rules,
		ECollationStrength	collationStrength,
		UErrorCode &	status
	)

RuleBasedCollator constructor.

This takes the table rules and builds a collation table out of them. Please see RuleBasedCollator class description for more details on the collation rule syntax.

Parameters

rules	the collation rules to build the collation table from.
collationStrength	strength for comparison
status	reporting a success or an error.

Stable:: ICU 2.0

◆ RuleBasedCollator() [3/8]

icu::RuleBasedCollator::RuleBasedCollator	(	const UnicodeString &	rules,
		UColAttributeValue	decompositionMode,
		UErrorCode &	status
	)

RuleBasedCollator constructor.

This takes the table rules and builds a collation table out of them. Please see RuleBasedCollator class description for more details on the collation rule syntax.

Parameters

rules	the collation rules to build the collation table from.
decompositionMode	the normalisation mode
status	reporting a success or an error.

Stable:: ICU 2.0

◆ RuleBasedCollator() [4/8]

icu::RuleBasedCollator::RuleBasedCollator	(	const UnicodeString &	rules,
		ECollationStrength	collationStrength,
		UColAttributeValue	decompositionMode,
		UErrorCode &	status
	)

RuleBasedCollator constructor.

This takes the table rules and builds a collation table out of them. Please see RuleBasedCollator class description for more details on the collation rule syntax.

Parameters

rules	the collation rules to build the collation table from.
collationStrength	strength for comparison
decompositionMode	the normalisation mode
status	reporting a success or an error.

Stable:: ICU 2.0

◆ RuleBasedCollator() [5/8]

icu::RuleBasedCollator::RuleBasedCollator	(	const UnicodeString &	rules,
		UParseError &	parseError,
		UnicodeString &	reason,
		UErrorCode &	errorCode
	)

TODO: document & propose as public API.

Internal:: Do not use.

This API is for internal use only.

◆ RuleBasedCollator() [6/8]

icu::RuleBasedCollator::RuleBasedCollator ( const RuleBasedCollator & other )

Copy constructor.

Parameters

other the RuleBasedCollator object to be copied

Stable:: ICU 2.0

◆ RuleBasedCollator() [7/8]

icu::RuleBasedCollator::RuleBasedCollator	(	const uint8_t *	bin,
		int32_t	length,
		const RuleBasedCollator *	base,
		UErrorCode &	status
	)

Opens a collator from a collator binary image created using cloneBinary.

Binary image used in instantiation of the collator remains owned by the user and should stay around for the lifetime of the collator. The API also takes a base collator which must be the root collator.

Parameters

bin	binary image owned by the user and required through the lifetime of the collator
length	size of the image. If negative, the API will try to figure out the length of the image
base	Base collator, for lookup of untailored characters. Must be the root collator, must not be NULL. The base is required to be present through the lifetime of the collator.
status	for catching errors

Returns: newly created collator

See also: cloneBinary

Stable:: ICU 3.4

◆ ~RuleBasedCollator()

virtual icu::RuleBasedCollator::~RuleBasedCollator ( )

virtual

Destructor.

Stable:: ICU 2.0

◆ RuleBasedCollator() [8/8]

icu::RuleBasedCollator::RuleBasedCollator ( )

Only for use in ucol_openRules().

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

Member Function Documentation

◆ clone()

virtual Collator* icu::RuleBasedCollator::clone ( void ) const

virtual

Makes a copy of this object.

Returns: a copy of this object, owned by the caller

Stable:: ICU 2.0

Implements icu::Collator.

◆ cloneBinary()

int32_t icu::RuleBasedCollator::cloneBinary	(	uint8_t *	buffer,
		int32_t	capacity,
		UErrorCode &	status
	)		const

Creates a binary image of a collator.

This binary image can be stored and later used to instantiate a collator using ucol_openBinary. This API supports preflighting.

Parameters

buffer	a fill-in buffer to receive the binary image
capacity	capacity of the destination buffer
status	for catching errors

Returns: size of the image

See also: ucol_openBinary

Stable:: ICU 3.4

◆ cloneRuleData()

uint8_t* icu::RuleBasedCollator::cloneRuleData	(	int32_t &	length,
		UErrorCode &	status
	)		const

Do not use this method: The caller and the ICU library might use different heaps.

Use cloneBinary() instead which writes to caller-provided memory.

Returns a binary format of this collator.

Parameters

length	Returns the length of the data, in bytes
status	the error code status.

Returns: memory, owned by the caller, of size 'length' bytes.

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

◆ compare() [1/4]

virtual UCollationResult icu::RuleBasedCollator::compare	(	const UnicodeString &	source,
		const UnicodeString &	target,
		UErrorCode &	status
	)		const

virtual

The comparison function compares the character data stored in two different strings.

Returns information about whether a string is less than, greater than or equal to another string.

Parameters

source	the source string to be compared with.
target	the string that is to be compared with the source string.
status	possible error code

Returns: Returns an enum value. UCOL_GREATER if source is greater than target; UCOL_EQUAL if source is equal to target; UCOL_LESS if source is less than target

Stable:: ICU 2.6

Implements icu::Collator.

◆ compare() [2/4]

virtual UCollationResult icu::RuleBasedCollator::compare	(	const UnicodeString &	source,
		const UnicodeString &	target,
		int32_t	length,
		UErrorCode &	status
	)		const

virtual

Does the same thing as compare but limits the comparison to a specified length.

Parameters

source	the source string to be compared with.
target	the string that is to be compared with the source string.
length	the length the comparison is limited to
status	possible error code

Returns: Returns an enum value. UCOL_GREATER if source (up to the specified length) is greater than target; UCOL_EQUAL if source (up to specified length) is equal to target; UCOL_LESS if source (up to the specified length) is less than target.

Stable:: ICU 2.6

Implements icu::Collator.

◆ compare() [3/4]

virtual UCollationResult icu::RuleBasedCollator::compare	(	const char16_t *	source,
		int32_t	sourceLength,
		const char16_t *	target,
		int32_t	targetLength,
		UErrorCode &	status
	)		const

virtual

The comparison function compares the character data stored in two different string arrays.

Returns information about whether a string array is less than, greater than or equal to another string array.

Parameters

source	the source string array to be compared with.
sourceLength	the length of the source string array. If this value is equal to -1, the string array is null-terminated.
target	the string that is to be compared with the source string.
targetLength	the length of the target string array. If this value is equal to -1, the string array is null-terminated.
status	possible error code

Returns: Returns an enum value. UCOL_GREATER if source is greater than target; UCOL_EQUAL if source is equal to target; UCOL_LESS if source is less than target

Stable:: ICU 2.6

Implements icu::Collator.

◆ compare() [4/4]

virtual UCollationResult icu::RuleBasedCollator::compare	(	UCharIterator &	sIter,
		UCharIterator &	tIter,
		UErrorCode &	status
	)		const

virtual

Compares two strings using the Collator.

Returns whether the first one compares less than/equal to/greater than the second one. This version takes UCharIterator input.

Parameters

sIter	the first ("source") string iterator
tIter	the second ("target") string iterator
status	ICU status

Returns: UCOL_LESS, UCOL_EQUAL or UCOL_GREATER

Stable:: ICU 4.2

Reimplemented from icu::Collator.

◆ compareUTF8()

virtual UCollationResult icu::RuleBasedCollator::compareUTF8	(	const StringPiece &	source,
		const StringPiece &	target,
		UErrorCode &	status
	)		const

virtual

Compares two UTF-8 strings using the Collator.

Returns whether the first one compares less than/equal to/greater than the second one. This version takes UTF-8 input. Note that a StringPiece can be implicitly constructed from a std::string or a NUL-terminated const char * string.

Parameters

source	the first UTF-8 string
target	the second UTF-8 string
status	ICU status

Returns: UCOL_LESS, UCOL_EQUAL or UCOL_GREATER

Stable:: ICU 51

Reimplemented from icu::Collator.

◆ createCollationElementIterator() [1/2]

virtual CollationElementIterator* icu::RuleBasedCollator::createCollationElementIterator ( const UnicodeString & source ) const

virtual

Creates a collation element iterator for the source string.

The caller of this method is responsible for the memory management of the return pointer.

Parameters

source the string over which the CollationElementIterator will iterate.

Returns: the collation element iterator of the source string using this as the based Collator.

Stable:: ICU 2.2

◆ createCollationElementIterator() [2/2]

virtual CollationElementIterator* icu::RuleBasedCollator::createCollationElementIterator ( const CharacterIterator & source ) const

virtual

Creates a collation element iterator for the source.

The caller of this method is responsible for the memory management of the returned pointer.

Parameters

source the CharacterIterator which produces the characters over which the CollationElementItgerator will iterate.

Returns: the collation element iterator of the source using this as the based Collator.

Stable:: ICU 2.2

◆ getAttribute()

virtual UColAttributeValue icu::RuleBasedCollator::getAttribute	(	UColAttribute	attr,
		UErrorCode &	status
	)		const

virtual

Universal attribute getter.

Parameters

attr	attribute type
status	to indicate whether the operation went on smoothly or there were errors

Returns: attribute value

Stable:: ICU 2.2

Implements icu::Collator.

◆ getCollationKey() [1/2]

virtual CollationKey& icu::RuleBasedCollator::getCollationKey	(	const UnicodeString &	source,
		CollationKey &	key,
		UErrorCode &	status
	)		const

virtual

Transforms the string into a series of characters that can be compared with CollationKey.compare().

Note that sort keys are often less efficient than simply doing comparison. For more details, see the ICU User Guide.

Parameters

source	the source string.
key	the transformed key of the source string.
status	the error code status.

Returns: the transformed key.

See also: CollationKey

Stable:: ICU 2.0

Implements icu::Collator.

◆ getCollationKey() [2/2]

virtual CollationKey& icu::RuleBasedCollator::getCollationKey	(	const char16_t *	source,
		int32_t	sourceLength,
		CollationKey &	key,
		UErrorCode &	status
	)		const

virtual

Transforms a specified region of the string into a series of characters that can be compared with CollationKey.compare.

Note that sort keys are often less efficient than simply doing comparison. For more details, see the ICU User Guide.

Parameters

source	the source string.
sourceLength	the length of the source string.
key	the transformed key of the source string.
status	the error code status.

Returns: the transformed key.

See also: CollationKey

Stable:: ICU 2.0

Implements icu::Collator.

◆ getDynamicClassID()

virtual UClassID icu::RuleBasedCollator::getDynamicClassID ( void ) const

virtual

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.

Returns: 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

Implements icu::Collator.

◆ getLocale()

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

virtual

Gets the locale of the Collator.

Parameters

type	can be either requested, valid or actual locale. For more information see the definition of ULocDataLocaleType in uloc.h
status	the error code status.

Returns: locale where the collation data lives. If the collator was instantiated from rules, locale is empty.

Deprecated:: ICU 2.8 likely to change in ICU 3.0, based on feedback

Implements icu::Collator.

◆ getMaxExpansion()

int32_t icu::RuleBasedCollator::getMaxExpansion ( int32_t order ) const

Returns the maximum length of any expansion sequences that end with the specified comparison order.

This is specific to the kind of collation element values and sequences returned by the CollationElementIterator. Call CollationElementIterator::getMaxExpansion() instead.

Parameters

order a collation order returned by CollationElementIterator::previous or CollationElementIterator::next.

Returns: maximum size of the expansion sequences ending with the collation element, or 1 if the collation element does not occur at the end of any expansion sequence

See also: CollationElementIterator::getMaxExpansion

Deprecated:: ICU 51 Use CollationElementIterator::getMaxExpansion() instead.

◆ getMaxVariable()

virtual UColReorderCode icu::RuleBasedCollator::getMaxVariable ( ) const

virtual

Returns the maximum reordering group whose characters are affected by UCOL_ALTERNATE_HANDLING.

Returns: the maximum variable reordering group.

See also: setMaxVariable

Stable:: ICU 53

Reimplemented from icu::Collator.

◆ getReorderCodes()

virtual int32_t icu::RuleBasedCollator::getReorderCodes	(	int32_t *	dest,
		int32_t	destCapacity,
		UErrorCode &	status
	)		const

virtual

Retrieves the reordering codes for this collator.

Parameters

dest	The array to fill with the script ordering.
destCapacity	The length of dest. If it is 0, then dest may be NULL and the function will only return the length of the result without writing any codes (pre-flighting).
status	A reference to an error code value, which must not indicate a failure before the function call.

Returns: The length of the script ordering array.

See also: ucol_setReorderCodes; Collator::getEquivalentReorderCodes; Collator::setReorderCodes

Stable:: ICU 4.8

Reimplemented from icu::Collator.

◆ getRules() [1/2]

const UnicodeString& icu::RuleBasedCollator::getRules ( ) const

Gets the tailoring rules for this collator.

Returns: the collation tailoring from which this collator was created

Stable:: ICU 2.0

◆ getRules() [2/2]

void icu::RuleBasedCollator::getRules	(	UColRuleOption	delta,
		UnicodeString &	buffer
	)		const

Returns current rules.

Delta defines whether full rules are returned or just the tailoring.

getRules(void) should normally be used instead. See http://userguide.icu-project.org/collation/customization#TOC-Building-on-Existing-Locales

Parameters

delta	one of UCOL_TAILORING_ONLY, UCOL_FULL_RULES.
buffer	UnicodeString to store the result rules

Stable:: ICU 2.2

See also: UCOL_FULL_RULES

◆ getSortKey() [1/2]

virtual int32_t icu::RuleBasedCollator::getSortKey	(	const UnicodeString &	source,
		uint8_t *	result,
		int32_t	resultLength
	)		const

virtual

Get the sort key as an array of bytes from a UnicodeString.

Note that sort keys are often less efficient than simply doing comparison. For more details, see the ICU User Guide.

Parameters

source	string to be processed.
result	buffer to store result in. If NULL, number of bytes needed will be returned.
resultLength	length of the result buffer. If if not enough the buffer will be filled to capacity.

Returns: Number of bytes needed for storing the sort key

Stable:: ICU 2.0

Implements icu::Collator.

◆ getSortKey() [2/2]

virtual int32_t icu::RuleBasedCollator::getSortKey	(	const char16_t *	source,
		int32_t	sourceLength,
		uint8_t *	result,
		int32_t	resultLength
	)		const

virtual

Get the sort key as an array of bytes from a char16_t buffer.

Note that sort keys are often less efficient than simply doing comparison. For more details, see the ICU User Guide.

Parameters

source	string to be processed.
sourceLength	length of string to be processed. If -1, the string is 0 terminated and length will be decided by the function.
result	buffer to store result in. If NULL, number of bytes needed will be returned.
resultLength	length of the result buffer. If if not enough the buffer will be filled to capacity.

Returns: Number of bytes needed for storing the sort key

Stable:: ICU 2.2

Implements icu::Collator.

◆ getStaticClassID()

static UClassID icu::RuleBasedCollator::getStaticClassID ( void )

static

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()) ...

Returns: The class ID for all objects of this class.

Stable:: ICU 2.0

◆ getTailoredSet()

virtual UnicodeSet* icu::RuleBasedCollator::getTailoredSet ( UErrorCode & status ) const

virtual

Get a UnicodeSet that contains all the characters and sequences tailored in this collator.

Parameters

status error code of the operation

Returns: a pointer to a UnicodeSet object containing all the code points and sequences that may sort differently than in the root collator. The object must be disposed of by using delete

Stable:: ICU 2.4

Reimplemented from icu::Collator.

◆ getVariableTop()

virtual uint32_t icu::RuleBasedCollator::getVariableTop ( UErrorCode & status ) const

virtual

Gets the variable top value of a Collator.

Parameters

status error code (not changed by function). If error code is set, the return value is undefined.

Returns: the variable top primary weight

See also: getMaxVariable

Stable:: ICU 2.0

Implements icu::Collator.

◆ getVersion()

virtual void icu::RuleBasedCollator::getVersion ( UVersionInfo info ) const

virtual

Gets the version information for a Collator.

Parameters

info	the version # information, the result will be filled in

Stable:: ICU 2.0

Implements icu::Collator.

◆ hashCode()

virtual int32_t icu::RuleBasedCollator::hashCode ( ) const

virtual

Generates the hash code for the rule-based collation object.

Returns: the hash code.

Stable:: ICU 2.0

Implements icu::Collator.

◆ internalAddContractions()

void icu::RuleBasedCollator::internalAddContractions	(	UChar32	c,
		UnicodeSet &	set,
		UErrorCode &	errorCode
	)		const

Adds the contractions that start with character c to the set.

Ignores prefixes. Used by AlphabeticIndex.

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

◆ internalBuildTailoring()

void icu::RuleBasedCollator::internalBuildTailoring	(	const UnicodeString &	rules,
		int32_t	strength,
		UColAttributeValue	decompositionMode,
		UParseError *	outParseError,
		UnicodeString *	outReason,
		UErrorCode &	errorCode
	)

Implements from-rule constructors, and ucol_openRules().

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

◆ internalCompareUTF8()

virtual UCollationResult icu::RuleBasedCollator::internalCompareUTF8	(	const char *	left,
		int32_t	leftLength,
		const char *	right,
		int32_t	rightLength,
		UErrorCode &	errorCode
	)		const

virtual

Implements ucol_strcollUTF8().

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

Reimplemented from icu::Collator.

◆ internalGetCEs()

void icu::RuleBasedCollator::internalGetCEs	(	const UnicodeString &	str,
		UVector64 &	ces,
		UErrorCode &	errorCode
	)		const

Appends the CEs for the string to the vector.

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

◆ internalGetContractionsAndExpansions()

void icu::RuleBasedCollator::internalGetContractionsAndExpansions	(	UnicodeSet *	contractions,
		UnicodeSet *	expansions,
		UBool	addPrefixes,
		UErrorCode &	errorCode
	)		const

Implements ucol_getContractionsAndExpansions().

Gets this collator's sets of contraction strings and/or characters and strings that map to multiple collation elements (expansions). If addPrefixes is TRUE, then contractions that are expressed as prefix/pre-context rules are included.

Parameters

contractions	if not NULL, the set to hold the contractions
expansions	if not NULL, the set to hold the expansions
addPrefixes	include prefix contextual mappings
errorCode	in/out ICU error code

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

◆ internalGetLocaleID()

const char* icu::RuleBasedCollator::internalGetLocaleID	(	ULocDataLocaleType	type,
		UErrorCode &	errorCode
	)		const

Implements ucol_getLocaleByType().

Needed because the lifetime of the locale ID string must match that of the collator. getLocale() returns a copy of a Locale, with minimal lifetime in a C wrapper.

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

◆ internalGetShortDefinitionString()

virtual int32_t icu::RuleBasedCollator::internalGetShortDefinitionString	(	const char *	locale,
		char *	buffer,
		int32_t	capacity,
		UErrorCode &	status
	)		const

virtual

Get the short definition string for a collator.

This internal API harvests the collator's locale and the attribute set and produces a string that can be used for opening a collator with the same attributes using the ucol_openFromShortString API. This string will be normalized. The structure and the syntax of the string is defined in the "Naming collators" section of the users guide: http://userguide.icu-project.org/collation/concepts#TOC-Collator-naming-scheme This function supports preflighting.

This is internal, and intended to be used with delegate converters.

Parameters

locale	a locale that will appear as a collators locale in the resulting short string definition. If NULL, the locale will be harvested from the collator.
buffer	space to hold the resulting string
capacity	capacity of the buffer
status	for returning errors. All the preflighting errors are featured

Returns: length of the resulting string

See also: ucol_openFromShortString; ucol_normalizeShortDefinitionString; ucol_getShortDefinitionString

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

Reimplemented from icu::Collator.

◆ internalNextSortKeyPart()

virtual int32_t icu::RuleBasedCollator::internalNextSortKeyPart	(	UCharIterator *	iter,
		uint32_t	state[2],
		uint8_t *	dest,
		int32_t	count,
		UErrorCode &	errorCode
	)		const

virtual

Implements ucol_nextSortKeyPart().

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

Reimplemented from icu::Collator.

◆ operator=()

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

Assignment operator.

Parameters

other other RuleBasedCollator object to copy from.

Stable:: ICU 2.0

◆ operator==()

virtual UBool icu::RuleBasedCollator::operator== ( const Collator & other ) const

virtual

Returns true if argument is the same as this object.

Parameters

other Collator object to be compared.

Returns: true if arguments is the same as this object.

Stable:: ICU 2.0

Reimplemented from icu::Collator.

◆ rbcFromUCollator() [1/2]

static RuleBasedCollator* icu::RuleBasedCollator::rbcFromUCollator ( UCollator * uc )

inlinestatic

Internal:: Do not use.

This API is for internal use only.

Definition at line 780 of file tblcoll.h.

References icu::Collator::fromUCollator().

◆ rbcFromUCollator() [2/2]

static const RuleBasedCollator* icu::RuleBasedCollator::rbcFromUCollator ( const UCollator * uc )

inlinestatic

Internal:: Do not use.

This API is for internal use only.

Definition at line 784 of file tblcoll.h.

References icu::Collator::fromUCollator(), icu::Collator::setLocales(), U_CALLCONV, U_NAMESPACE_END, and UCOL_ATTRIBUTE_COUNT.

◆ setAttribute()

virtual void icu::RuleBasedCollator::setAttribute	(	UColAttribute	attr,
		UColAttributeValue	value,
		UErrorCode &	status
	)

virtual

Universal attribute setter.

Parameters

attr	attribute type
value	attribute value
status	to indicate whether the operation went on smoothly or there were errors

Stable:: ICU 2.2

Implements icu::Collator.

◆ setLocales()

virtual void icu::RuleBasedCollator::setLocales	(	const Locale &	requestedLocale,
		const Locale &	validLocale,
		const Locale &	actualLocale
	)

protectedvirtual

Used internally by registration to define the requested and valid locales.

Parameters

requestedLocale	the requested locale
validLocale	the valid locale
actualLocale	the actual locale

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

Reimplemented from icu::Collator.

◆ setMaxVariable()

virtual Collator& icu::RuleBasedCollator::setMaxVariable	(	UColReorderCode	group,
		UErrorCode &	errorCode
	)

virtual

Sets the variable top to the top of the specified reordering group.

The variable top determines the highest-sorting character which is affected by UCOL_ALTERNATE_HANDLING. If that attribute is set to UCOL_NON_IGNORABLE, then the variable top has no effect.

Parameters

group	one of UCOL_REORDER_CODE_SPACE, UCOL_REORDER_CODE_PUNCTUATION, UCOL_REORDER_CODE_SYMBOL, UCOL_REORDER_CODE_CURRENCY; or UCOL_REORDER_CODE_DEFAULT to restore the default max variable group
errorCode	Standard ICU error code. Its input value must pass the U_SUCCESS() test, or else the function returns immediately. Check for U_FAILURE() on output or use with function chaining. (See User Guide for details.)

Returns: *this

See also: getMaxVariable

Stable:: ICU 53

Reimplemented from icu::Collator.

◆ setReorderCodes()

virtual void icu::RuleBasedCollator::setReorderCodes	(	const int32_t *	reorderCodes,
		int32_t	reorderCodesLength,
		UErrorCode &	status
	)

virtual

Sets the ordering of scripts for this collator.

Parameters

reorderCodes	An array of script codes in the new order. This can be NULL if the length is also set to 0. An empty array will clear any reordering codes on the collator.
reorderCodesLength	The length of reorderCodes.
status	error code

See also: ucol_setReorderCodes; Collator::getReorderCodes; Collator::getEquivalentReorderCodes

Stable:: ICU 4.8

Reimplemented from icu::Collator.

◆ setVariableTop() [1/3]

virtual uint32_t icu::RuleBasedCollator::setVariableTop	(	const char16_t *	varTop,
		int32_t	len,
		UErrorCode &	status
	)

virtual

Sets the variable top to the primary weight of the specified string.

Beginning with ICU 53, the variable top is pinned to the top of one of the supported reordering groups, and it must not be beyond the last of those groups. See setMaxVariable().

Parameters

varTop	one or more (if contraction) char16_ts to which the variable top should be set
len	length of variable top string. If -1 it is considered to be zero terminated.
status	error code. If error code is set, the return value is undefined. Errors set by this function are: U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such contraction U_ILLEGAL_ARGUMENT_ERROR if the variable top is beyond the last reordering group supported by setMaxVariable()

Returns: variable top primary weight

Deprecated:: ICU 53 Call setMaxVariable() instead.

Implements icu::Collator.

◆ setVariableTop() [2/3]

virtual uint32_t icu::RuleBasedCollator::setVariableTop	(	const UnicodeString &	varTop,
		UErrorCode &	status
	)

virtual

Sets the variable top to the primary weight of the specified string.

Beginning with ICU 53, the variable top is pinned to the top of one of the supported reordering groups, and it must not be beyond the last of those groups. See setMaxVariable().

Parameters

varTop	a UnicodeString size 1 or more (if contraction) of char16_ts to which the variable top should be set
status	error code. If error code is set, the return value is undefined. Errors set by this function are: U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such contraction U_ILLEGAL_ARGUMENT_ERROR if the variable top is beyond the last reordering group supported by setMaxVariable()

Returns: variable top primary weight

Deprecated:: ICU 53 Call setMaxVariable() instead.

Implements icu::Collator.

◆ setVariableTop() [3/3]

virtual void icu::RuleBasedCollator::setVariableTop	(	uint32_t	varTop,
		UErrorCode &	status
	)

virtual

Sets the variable top to the specified primary weight.

Beginning with ICU 53, the variable top is pinned to the top of one of the supported reordering groups, and it must not be beyond the last of those groups. See setMaxVariable().

Parameters

varTop	primary weight, as returned by setVariableTop or ucol_getVariableTop
status	error code

Deprecated:: ICU 53 Call setMaxVariable() instead.

Implements icu::Collator.

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

tblcoll.h

Public Member Functions

Static Public Member Functions

Protected Member Functions

Friends

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ RuleBasedCollator() [1/8]

◆ RuleBasedCollator() [2/8]

◆ RuleBasedCollator() [3/8]

◆ RuleBasedCollator() [4/8]

◆ RuleBasedCollator() [5/8]

◆ RuleBasedCollator() [6/8]

◆ RuleBasedCollator() [7/8]

◆ ~RuleBasedCollator()

◆ RuleBasedCollator() [8/8]

Member Function Documentation

◆ clone()

◆ cloneBinary()

◆ cloneRuleData()

◆ compare() [1/4]

◆ compare() [2/4]

◆ compare() [3/4]

◆ compare() [4/4]

◆ compareUTF8()

◆ createCollationElementIterator() [1/2]

◆ createCollationElementIterator() [2/2]

◆ getAttribute()

◆ getCollationKey() [1/2]

◆ getCollationKey() [2/2]

◆ getDynamicClassID()

◆ getLocale()

◆ getMaxExpansion()

◆ getMaxVariable()

◆ getReorderCodes()

◆ getRules() [1/2]

◆ getRules() [2/2]

◆ getSortKey() [1/2]

◆ getSortKey() [2/2]

◆ getStaticClassID()

◆ getTailoredSet()

◆ getVariableTop()

◆ getVersion()

◆ hashCode()

◆ internalAddContractions()

◆ internalBuildTailoring()

◆ internalCompareUTF8()

◆ internalGetCEs()

◆ internalGetContractionsAndExpansions()

◆ internalGetLocaleID()

◆ internalGetShortDefinitionString()

◆ internalNextSortKeyPart()

◆ operator=()

◆ operator==()

◆ rbcFromUCollator() [1/2]

◆ rbcFromUCollator() [2/2]

◆ setAttribute()

◆ setLocales()

◆ setMaxVariable()

◆ setReorderCodes()

◆ setVariableTop() [1/3]

◆ setVariableTop() [2/3]

◆ setVariableTop() [3/3]