ICU 77.1: icu::UnicodeSet Class Reference (original) (raw)

A mutable set of Unicode characters and multicharacter strings. More...

#include <[uniset.h](uniset%5F8h%5Fsource.html)>

Public Member Functions
UBool	isBogus () const
	Determine if this object contains a valid set. More...
void	setToBogus ()
	Make this UnicodeSet object invalid. More...
	UnicodeSet ()
	Constructs an empty set. More...
	UnicodeSet (UChar32 start, UChar32 end)
	Constructs a set containing the given range. More...
	UnicodeSet (const uint16_t buffer[], int32_t bufferLen, ESerialization serialization, UErrorCode &status)
	Constructs a set from the output of serialize(). More...
	UnicodeSet (const UnicodeString &pattern, UErrorCode &status)
	Constructs a set from the given pattern. More...
	UnicodeSet (const UnicodeString &pattern, uint32_t options, const SymbolTable *symbols, UErrorCode &status)
	Constructs a set from the given pattern. More...
	UnicodeSet (const UnicodeString &pattern, ParsePosition &pos, uint32_t options, const SymbolTable *symbols, UErrorCode &status)
	Constructs a set from the given pattern. More...
	UnicodeSet (const UnicodeSet &o)
	Constructs a set that is identical to the given UnicodeSet. More...
virtual	~UnicodeSet ()
	Destructs the set. More...
UnicodeSet &	operator= (const UnicodeSet &o)
	Assigns this object to be a copy of another. More...
virtual bool	operator== (const UnicodeSet &o) const
	Compares the specified object with this set for equality. More...
bool	operator!= (const UnicodeSet &o) const
	Compares the specified object with this set for equality. More...
virtual UnicodeSet *	clone () const override
	Returns a copy of this object. More...
virtual int32_t	hashCode () const
	Returns the hash code value for this set. More...
USet *	toUSet ()
	Produce a USet * pointer for this UnicodeSet. More...
const USet *	toUSet () const
	Produce a const USet * pointer for this UnicodeSet. More...
UBool	isFrozen () const
	Determines whether the set has been frozen (made immutable) or not. More...
UnicodeSet *	freeze ()
	Freeze the set (make it immutable). More...
UnicodeSet *	cloneAsThawed () const
	Clone the set and make the clone mutable. More...
UnicodeSet &	set (UChar32 start, UChar32 end)
	Make this object represent the range start - end. More...
UnicodeSet &	applyPattern (const UnicodeString &pattern, UErrorCode &status)
	Modifies this set to represent the set specified by the given pattern, ignoring Unicode Pattern_White_Space characters. More...
UnicodeSet &	applyPattern (const UnicodeString &pattern, uint32_t options, const SymbolTable *symbols, UErrorCode &status)
	Modifies this set to represent the set specified by the given pattern, optionally ignoring Unicode Pattern_White_Space characters. More...
UnicodeSet &	applyPattern (const UnicodeString &pattern, ParsePosition &pos, uint32_t options, const SymbolTable *symbols, UErrorCode &status)
	Parses the given pattern, starting at the given position. More...
virtual UnicodeString &	toPattern (UnicodeString &result, UBool escapeUnprintable=false) const override
	Returns a string representation of this set. More...
UnicodeSet &	applyIntPropertyValue (UProperty prop, int32_t value, UErrorCode &ec)
	Modifies this set to contain those code points which have the given value for the given binary or enumerated property, as returned by u_getIntPropertyValue. More...
UnicodeSet &	applyPropertyAlias (const UnicodeString &prop, const UnicodeString &value, UErrorCode &ec)
	Modifies this set to contain those code points which have the given value for the given property. More...
virtual int32_t	size () const
	Returns the number of elements in this set (its cardinality). More...
virtual UBool	isEmpty () const
	Returns true if this set contains no elements. More...
UBool	hasStrings () const
virtual UBool	contains (UChar32 c) const override
	Returns true if this set contains the given character. More...
virtual UBool	contains (UChar32 start, UChar32 end) const
	Returns true if this set contains every character of the given range. More...
UBool	contains (const UnicodeString &s) const
	Returns true if this set contains the given multicharacter string. More...
virtual UBool	containsAll (const UnicodeSet &c) const
	Returns true if this set contains all the characters and strings of the given set. More...
UBool	containsAll (const UnicodeString &s) const
	Returns true if this set contains all the characters of the given string. More...
UBool	containsNone (UChar32 start, UChar32 end) const
	Returns true if this set contains none of the characters of the given range. More...
UBool	containsNone (const UnicodeSet &c) const
	Returns true if this set contains none of the characters and strings of the given set. More...
UBool	containsNone (const UnicodeString &s) const
	Returns true if this set contains none of the characters of the given string. More...
UBool	containsSome (UChar32 start, UChar32 end) const
	Returns true if this set contains one or more of the characters in the given range. More...
UBool	containsSome (const UnicodeSet &s) const
	Returns true if this set contains one or more of the characters and strings of the given set. More...
UBool	containsSome (const UnicodeString &s) const
	Returns true if this set contains one or more of the characters of the given string. More...
int32_t	span (const char16_t *s, int32_t length, USetSpanCondition spanCondition) const
	Returns the length of the initial substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED). More...
int32_t	span (const UnicodeString &s, int32_t start, USetSpanCondition spanCondition) const
	Returns the end of the substring of the input string according to the USetSpanCondition. More...
int32_t	spanBack (const char16_t *s, int32_t length, USetSpanCondition spanCondition) const
	Returns the start of the trailing substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED). More...
int32_t	spanBack (const UnicodeString &s, int32_t limit, USetSpanCondition spanCondition) const
	Returns the start of the substring of the input string according to the USetSpanCondition. More...
int32_t	spanUTF8 (const char *s, int32_t length, USetSpanCondition spanCondition) const
	Returns the length of the initial substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED). More...
int32_t	spanBackUTF8 (const char *s, int32_t length, USetSpanCondition spanCondition) const
	Returns the start of the trailing substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED). More...
virtual UMatchDegree	matches (const Replaceable &text, int32_t &offset, int32_t limit, UBool incremental) override
	Implement UnicodeMatcher::matches() More...
virtual void	addMatchSetTo (UnicodeSet &toUnionTo) const override
	Implementation of UnicodeMatcher API. More...
int32_t	indexOf (UChar32 c) const
	Returns the index of the given character within this set, where the set is ordered by ascending code point. More...
UChar32	charAt (int32_t index) const
	Returns the character at the given index within this set, where the set is ordered by ascending code point. More...
U_HEADER_NESTED_NAMESPACE::USetCodePoints	codePoints () const
	Returns a C++ "range" for iterating over the code points of this set. More...
U_HEADER_NESTED_NAMESPACE::USetRanges	ranges () const
	Returns a C++ "range" for iterating over the code point ranges of this set. More...
U_HEADER_NESTED_NAMESPACE::USetStrings	strings () const
	Returns a C++ "range" for iterating over the empty and multi-character strings of this set. More...
U_HEADER_NESTED_NAMESPACE::USetElementIterator	begin () const
	Returns a C++ iterator for iterating over all of the elements of this set. More...
U_HEADER_NESTED_NAMESPACE::USetElementIterator	end () const
virtual UnicodeSet &	add (UChar32 start, UChar32 end)
	Adds the specified range to this set if it is not already present. More...
UnicodeSet &	add (UChar32 c)
	Adds the specified character to this set if it is not already present. More...
UnicodeSet &	add (const UnicodeString &s)
	Adds the specified multicharacter to this set if it is not already present. More...
UnicodeSet &	addAll (const UnicodeString &s)
	Adds each of the characters in this string to the set. More...
UnicodeSet &	retainAll (const UnicodeString &s)
	Retains EACH of the characters in this string. More...
UnicodeSet &	complementAll (const UnicodeString &s)
	Complement EACH of the characters in this string. More...
UnicodeSet &	removeAll (const UnicodeString &s)
	Remove EACH of the characters in this string. More...
virtual UnicodeSet &	retain (UChar32 start, UChar32 end)
	Retain only the elements in this set that are contained in the specified range. More...
UnicodeSet &	retain (UChar32 c)
	Retain the specified character from this set if it is present. More...
UnicodeSet &	retain (const UnicodeString &s)
	Retains only the specified string from this set if it is present. More...
virtual UnicodeSet &	remove (UChar32 start, UChar32 end)
	Removes the specified range from this set if it is present. More...
UnicodeSet &	remove (UChar32 c)
	Removes the specified character from this set if it is present. More...
UnicodeSet &	remove (const UnicodeString &s)
	Removes the specified string from this set if it is present. More...
virtual UnicodeSet &	complement ()
	This is equivalent to complement(MIN_VALUE, MAX_VALUE). More...
virtual UnicodeSet &	complement (UChar32 start, UChar32 end)
	Complements the specified range in this set. More...
UnicodeSet &	complement (UChar32 c)
	Complements the specified character in this set. More...
UnicodeSet &	complement (const UnicodeString &s)
	Complement the specified string in this set. More...
virtual UnicodeSet &	addAll (const UnicodeSet &c)
	Adds all of the elements in the specified set to this set if they're not already present. More...
virtual UnicodeSet &	retainAll (const UnicodeSet &c)
	Retains only the elements in this set that are contained in the specified set. More...
virtual UnicodeSet &	removeAll (const UnicodeSet &c)
	Removes from this set all of its elements that are contained in the specified set. More...
virtual UnicodeSet &	complementAll (const UnicodeSet &c)
	Complements in this set all elements contained in the specified set. More...
virtual UnicodeSet &	clear ()
	Removes all of the elements from this set. More...
UnicodeSet &	closeOver (int32_t attribute)
	Close this set over the given attribute. More...
virtual UnicodeSet &	removeAllStrings ()
	Remove all strings from this set. More...
virtual int32_t	getRangeCount () const
	Iteration method that returns the number of ranges contained in this set. More...
virtual UChar32	getRangeStart (int32_t index) const
	Iteration method that returns the first character in the specified range of this set. More...
virtual UChar32	getRangeEnd (int32_t index) const
	Iteration method that returns the last character in the specified range of this set. More...
int32_t	serialize (uint16_t *dest, int32_t destCapacity, UErrorCode &ec) const
	Serializes this set into an array of 16-bit integers. More...
virtual UnicodeSet &	compact ()
	Reallocate this objects internal structures to take up the least possible space, without changing this object's value. More...
virtual UClassID	getDynamicClassID () const override
	Implement UnicodeFunctor API. More...
Public Member Functions inherited from icu::UnicodeFilter
virtual	~UnicodeFilter ()
	Destructor. More...
virtual UnicodeMatcher *	toMatcher () const override
	UnicodeFunctor API. More...
virtual void	setData (const TransliterationRuleData *) override
	UnicodeFunctor API. More...
Public Member Functions inherited from icu::UnicodeFunctor
virtual	~UnicodeFunctor ()
	Destructor. More...
virtual UnicodeReplacer *	toReplacer () const
	Cast 'this' to a UnicodeReplacer* pointer and return the pointer, or null if this is not a UnicodeReplacer*. More...
Public Member Functions inherited from icu::UObject
virtual	~UObject ()
	Destructor. More...
Public Member Functions inherited from icu::UnicodeMatcher
virtual	~UnicodeMatcher ()
	Destructor. More...

Static Public Member Functions
static UnicodeSet *	fromUSet (USet *uset)
	Get a UnicodeSet pointer from a USet. More...
static const UnicodeSet *	fromUSet (const USet *uset)
	Get a UnicodeSet pointer from a const USet. More...
static UBool	resemblesPattern (const UnicodeString &pattern, int32_t pos)
	Return true if the given position, in the given pattern, appears to be the start of a UnicodeSet pattern. More...
static UnicodeSet *	createFrom (const UnicodeString &s)
	Makes a set from a multicharacter string. More...
static UnicodeSet *	createFromAll (const UnicodeString &s)
	Makes a set from each of the characters in the string. More...
static UClassID	getStaticClassID ()
	Return the class ID for this class. More...
Static Public Member Functions inherited from icu::UnicodeFilter
static UClassID	getStaticClassID ()
	ICU "poor man's RTTI", returns a UClassID for this class. More...
Static Public Member Functions inherited from icu::UnicodeFunctor
static UClassID	getStaticClassID ()
	Return the class ID for this class. More...

A mutable set of Unicode characters and multicharacter strings.

Objects of this class represent character classes used in regular expressions. A character specifies a subset of Unicode code points. Legal code points are U+0000 to U+10FFFF, inclusive.

The UnicodeSet class is not designed to be subclassed.

[UnicodeSet](classicu%5F1%5F1UnicodeSet.html "A mutable set of Unicode characters and multicharacter strings.") supports two APIs. The first is the operand API that allows the caller to modify the value of a [UnicodeSet](classicu%5F1%5F1UnicodeSet.html "A mutable set of Unicode characters and multicharacter strings.") object. It conforms to Java 2's java.util.Set interface, although [UnicodeSet](classicu%5F1%5F1UnicodeSet.html "A mutable set of Unicode characters and multicharacter strings.") does not actually implement that interface. All methods of Set are supported, with the modification that they take a character range or single character instead of an Object, and they take a [UnicodeSet](classicu%5F1%5F1UnicodeSet.html "A mutable set of Unicode characters and multicharacter strings.") instead of a Collection. The operand API may be thought of in terms of boolean logic: a boolean OR is implemented by add, a boolean AND is implemented by retain, a boolean XOR is implemented by complement taking an argument, and a boolean NOT is implemented by complement with no argument. In terms of traditional set theory function names, add is a union, retain is an intersection, remove is an asymmetric difference, and complement with no argument is a set complement with respect to the superset range MIN_VALUE-MAX_VALUE

The second API is the [applyPattern()](classicu%5F1%5F1UnicodeSet.html#a6b1bbf03728aedb1c5f62dd73bf79079 "Modifies this set to represent the set specified by the given pattern, ignoring Unicode Pattern_White...")/[toPattern()](classicu%5F1%5F1UnicodeSet.html#a5f3f3a782ed8a1bf5c7537070a6dd192 "Returns a string representation of this set.") API from the java.text.Format-derived classes. Unlike the methods that add characters, add categories, and control the logic of the set, the method [applyPattern()](classicu%5F1%5F1UnicodeSet.html#a6b1bbf03728aedb1c5f62dd73bf79079 "Modifies this set to represent the set specified by the given pattern, ignoring Unicode Pattern_White...") sets all attributes of a [UnicodeSet](classicu%5F1%5F1UnicodeSet.html "A mutable set of Unicode characters and multicharacter strings.") at once, based on a string pattern.

Pattern syntax

Patterns are accepted by the constructors and the [applyPattern()](classicu%5F1%5F1UnicodeSet.html#a6b1bbf03728aedb1c5f62dd73bf79079 "Modifies this set to represent the set specified by the given pattern, ignoring Unicode Pattern_White...") methods and returned by the [toPattern()](classicu%5F1%5F1UnicodeSet.html#a5f3f3a782ed8a1bf5c7537070a6dd192 "Returns a string representation of this set.") method. These patterns follow a syntax similar to that employed by version 8 regular expression character classes. Here are some simple examples:

[]	No characters
[a]	The character 'a'
[ae]	The characters 'a' and 'e'
[a-e]	The characters 'a' through 'e' inclusive, in Unicode code point order
[\u4E01]	The character U+4E01
[a{ab}{ac}]	The character 'a' and the multicharacter strings "ab" and "ac"
[\p{Lu}]	All characters in the general category Uppercase Letter

Any character may be preceded by a backslash in order to remove any special meaning. White space characters, as defined by UCharacter.isWhitespace(), are ignored, unless they are escaped.

Property patterns specify a set of characters having a certain property as defined by the Unicode standard. Both the POSIX-like "[:Lu:]" and the Perl-like syntax "\\p{Lu}" are recognized. For a complete list of supported property patterns, see the User's Guide for UnicodeSet at https://unicode-org.github.io/icu/userguide/strings/unicodeset. Actual determination of property data is defined by the underlying Unicode database as implemented by UCharacter.

Patterns specify individual characters, ranges of characters, and Unicode property sets. When elements are concatenated, they specify their union. To complement a set, place a '^' immediately after the opening '['. Property patterns are inverted by modifying their delimiters; "[:^foo]" and "\\P{foo}". In any other location, '^' has no special meaning.

Since ICU 70, "[^...]", "[:^foo]", "\\P{foo}", and "[:binaryProperty=No:]" perform a “code point complement” (all code points minus the original set), removing all multicharacter strings, equivalent to .[complement()](classicu%5F1%5F1UnicodeSet.html#a60460749e20685e496e819b368496089 "This is equivalent to complement(MIN_VALUE, MAX_VALUE).").[removeAllStrings()](classicu%5F1%5F1UnicodeSet.html#aa9878a9ab9d3555d578abf0d9e7d509e "Remove all strings from this set."). The complement() API function continues to perform a symmetric difference with all code points and thus retains all multicharacter strings.

Ranges are indicated by placing two a '-' between two characters, as in "a-z". This specifies the range of all characters from the left to the right, in Unicode order. If the left character is greater than or equal to the right character it is a syntax error. If a '-' occurs as the first character after the opening '[' or '[^', or if it occurs as the last character before the closing ']', then it is taken as a literal. Thus "[a\-b]", "[-ab]", and "[ab-]" all indicate the same set of three characters, 'a', 'b', and '-'.

Sets may be intersected using the '&' operator or the asymmetric set difference may be taken using the '-' operator, for example, "[[:L:]&[\\u0000-\\u0FFF]]" indicates the set of all Unicode letters with values less than 4096. Operators ('&' and '|') have equal precedence and bind left-to-right. Thus "[[:L:]-[a-z]-[\\u0100-\\u01FF]]" is equivalent to "[[[:L:]-[a-z]]-[\\u0100-\\u01FF]]". This only really matters for difference; intersection is commutative.

Formal syntax

pattern :=	('[' '^'? item* ']') | property
item :=	char | (char '-' char)	pattern-expr
pattern-expr :=	pattern | pattern-expr pattern	pattern-expr op pattern
op :=	'&' | '-'
special :=	'[' | ']'	'-'
char :=	any character that is not special | ('\' any character)	('\u' hex hex hex hex)
hex :=	'0' | '1'	'2'	'3'	'4'	'5'	'6'	'7'	'8'	'9'	'A'	'B'	'C'	'D'	'E'	'F'	'a'	'b'	'c'	'd'	'e'	'f'
property :=	a Unicode property set pattern

Legend:

a := b		a may be replaced by b
a?	zero or one instance of a
a*	one or more instances of a
a | b	either a or b
'a'	the literal string between the quotes

Note:

• Most UnicodeSet methods do not take a UErrorCode parameter because there are usually very few opportunities for failure other than a shortage of memory, error codes in low-level C++ string methods would be inconvenient, and the error code as the last parameter (ICU convention) would prevent the use of default parameter values. Instead, such methods set the UnicodeSet into a "bogus" state (see isBogus()) if an error occurs.

Stable:

ICU 2.0

Definition at line 285 of file uniset.h.

◆ anonymous enum

◆ ESerialization

Constructs an empty set.

Stable:

ICU 2.0

◆ UnicodeSet() [2/7]

Constructs a set containing the given range.

If end < start then an empty set is created.

Parameters

Stable:

ICU 2.4

◆ UnicodeSet() [3/7]

Constructs a set from the output of serialize().

Parameters

Internal:

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

◆ UnicodeSet() [4/7]

Constructs a set from the given pattern.

See the class description for the syntax of the pattern language.

Parameters

Stable:

ICU 2.0

◆ UnicodeSet() [5/7]

Constructs a set from the given pattern.

See the class description for the syntax of the pattern language.

Parameters

Internal:

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

◆ UnicodeSet() [6/7]

Constructs a set from the given pattern.

See the class description for the syntax of the pattern language.

Parameters

Stable:

ICU 2.8

◆ UnicodeSet() [7/7]

◆ ~UnicodeSet()

◆ add() [1/3]

Adds the specified multicharacter to this set if it is not already present.

If this set already contains the multicharacter, the call leaves this set unchanged. Thus "ch" => {"ch"} A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ add() [2/3]

Adds the specified character to this set if it is not already present.

If this set already contains the specified character, the call leaves this set unchanged. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.0

◆ add() [3/3]

Adds the specified range to this set if it is not already present.

If this set already contains the specified range, the call leaves this set unchanged. If start > end then an empty range is added, leaving the set unchanged. This is equivalent to a boolean logic OR, or a set UNION. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

◆ addAll() [1/2]

Adds all of the elements in the specified set to this set if they're not already present.

This operation effectively modifies this set so that its value is the union of the two sets. The behavior of this operation is unspecified if the specified collection is modified while the operation is in progress. A frozen set will not be modified.

Parameters

See also

add(UChar32, UChar32)

Stable:

ICU 2.0

◆ addAll() [2/2]

Adds each of the characters in this string to the set.

Note: "ch" => {"c", "h"} If this set already contains any particular character, it has no effect on that character. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ addMatchSetTo()

Implementation of UnicodeMatcher API.

Union the set of all characters that may be matched by this object into the given set.

Parameters

Stable:

ICU 2.4

Implements icu::UnicodeMatcher.

◆ applyIntPropertyValue()

Modifies this set to contain those code points which have the given value for the given binary or enumerated property, as returned by u_getIntPropertyValue.

Prior contents of this set are lost. A frozen set will not be modified.

Parameters

Returns

a reference to this set

Stable:

ICU 2.4

◆ applyPattern() [1/3]

Parses the given pattern, starting at the given position.

The character at pattern.charAt(pos.getIndex()) must be '[', or the parse fails. Parsing continues until the corresponding closing ']'. If a syntax error is encountered between the opening and closing brace, the parse fails. Upon return from a successful parse, the ParsePosition is updated to point to the character following the closing ']', and a StringBuffer containing a pairs list for the parsed pattern is returned. This method calls itself recursively to parse embedded subpatterns. Empties the set passed before applying the pattern. A frozen set will not be modified.

Parameters

Returns

a reference to this

Stable:

ICU 2.8

◆ applyPattern() [2/3]

Modifies this set to represent the set specified by the given pattern, ignoring Unicode Pattern_White_Space characters.

See the class description for the syntax of the pattern language. A frozen set will not be modified.

Parameters

Returns

a reference to this

Stable:

ICU 2.0

◆ applyPattern() [3/3]

Modifies this set to represent the set specified by the given pattern, optionally ignoring Unicode Pattern_White_Space characters.

See the class description for the syntax of the pattern language. A frozen set will not be modified.

Parameters

Returns

a reference to this

Internal:

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

◆ applyPropertyAlias()

Modifies this set to contain those code points which have the given value for the given property.

Prior contents of this set are lost. A frozen set will not be modified.

Parameters

"ANY" = [\u0000-\U0010FFFF], "ASCII" = [\u0000-\u007F], "Assigned" = [:^Cn:].

Parameters

Returns

a reference to this set

Stable:

ICU 2.4

◆ begin()

Returns a C++ iterator for iterating over all of the elements of this set.

Convenient all-in one iteration, but creates a std::u16string for each code point or string. (Similar to how Java UnicodeSet is an Iterable.)

Code points are returned first, then empty and multi-character strings.

for (auto el : set) {

UnicodeString us(el);

std::string u8;

printf("set.element length %ld \"%s\"\n", (long)us.length(), us.toUTF8String(u8).c_str());

}

UnicodeSet()

Constructs an empty set.

UnicodeSet & set(UChar32 start, UChar32 end)

Make this object represent the range start - end.

Returns

an all-elements iterator.

Draft:

This API may be changed in the future versions and was introduced in ICU 77

See also

end

[codePoints](classicu%5F1%5F1UnicodeSet.html#a537a13a1b3adcaebc140f715876aca63 "Returns a C++ "range" for iterating over the code points of this set.")

[ranges](classicu%5F1%5F1UnicodeSet.html#a689385fcc1e2e9e05996e9e19229ea3f "Returns a C++ "range" for iterating over the code point ranges of this set.")

[strings](classicu%5F1%5F1UnicodeSet.html#a054e7d9e1c1476acd1a9f3d9113395bd "Returns a C++ "range" for iterating over the empty and multi-character strings of this set.")

Definition at line 1203 of file uniset.h.

◆ charAt()

Returns the character at the given index within this set, where the set is ordered by ascending code point.

If the index is out of range for characters, returns (UChar32)-1. The inverse of this method is [indexOf()](classicu%5F1%5F1UnicodeSet.html#a526444bd8ff466b127009e38a7d63704 "Returns the index of the given character within this set, where the set is ordered by ascending code ...").

For iteration, this is slower than UnicodeSetIterator or getRangeCount()/getRangeStart()/getRangeEnd(), because for each call it skips linearly over index characters in the ranges.

Parameters

Returns

the character at the given index, or (UChar32)-1.

Stable:

ICU 2.4

◆ clear()

Removes all of the elements from this set.

This set will be empty after this call returns. A frozen set will not be modified.

Stable:

ICU 2.0

◆ clone()

◆ cloneAsThawed()

Clone the set and make the clone mutable.

See the ICU4J Freezable interface for details.

Returns

the mutable clone

See also

freeze

isFrozen

Stable:

ICU 3.8

◆ closeOver()

Close this set over the given attribute.

For the attribute USET_CASE_INSENSITIVE, the result is to modify this set so that:

1. For each character or string 'a' in this set, all strings or characters 'b' such that foldCase(a) == foldCase(b) are added to this set.
2. For each string 'e' in the resulting set, if e != foldCase(e), 'e' will be removed.

Example: [aq\u00DF{Bc}{bC}{Fi}] => [aAqQ\u00DF\uFB01{ss}{bc}{fi}]

(Here foldCase(x) refers to the operation u_strFoldCase, and a == b denotes that the contents are the same, not pointer comparison.)

A frozen set will not be modified.

Parameters

Returns

a reference to this set.

Stable:

ICU 4.2

◆ codePoints()

Returns a C++ "range" for iterating over the code points of this set.

printf("set.codePoint U+%04lx\n", (long)c);

}

U_HEADER_NESTED_NAMESPACE::USetCodePoints codePoints() const

Returns a C++ "range" for iterating over the code points of this set.

int32_t UChar32

Define UChar32 as a type for single Unicode code points.

Returns

a "range" object for iterating over the code points of this set.

Draft:

This API may be changed in the future versions and was introduced in ICU 76

See also

[ranges](classicu%5F1%5F1UnicodeSet.html#a689385fcc1e2e9e05996e9e19229ea3f "Returns a C++ "range" for iterating over the code point ranges of this set.")

[strings](classicu%5F1%5F1UnicodeSet.html#a054e7d9e1c1476acd1a9f3d9113395bd "Returns a C++ "range" for iterating over the empty and multi-character strings of this set.")

begin

end

Definition at line 1123 of file uniset.h.

◆ compact()

Reallocate this objects internal structures to take up the least possible space, without changing this object's value.

A frozen set will not be modified.

Stable:

ICU 2.4

◆ complement() [1/4]

This is equivalent to complement(MIN_VALUE, MAX_VALUE).

Note: This performs a symmetric difference with all code points and thus retains all multicharacter strings. In order to achieve a “code point complement” (all code points minus this set), the easiest is to .[complement()](classicu%5F1%5F1UnicodeSet.html#a60460749e20685e496e819b368496089 "This is equivalent to complement(MIN_VALUE, MAX_VALUE).").[removeAllStrings()](classicu%5F1%5F1UnicodeSet.html#aa9878a9ab9d3555d578abf0d9e7d509e "Remove all strings from this set.").

A frozen set will not be modified.

Stable:

ICU 2.0

◆ complement() [2/4]

Complement the specified string in this set.

The string will be removed if it is in this set, or will be added if it is not in this set. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ complement() [3/4]

Complements the specified character in this set.

The character will be removed if it is in this set, or will be added if it is not in this set. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.0

◆ complement() [4/4]

Complements the specified range in this set.

Any character in the range will be removed if it is in this set, or will be added if it is not in this set. If start > end then an empty range is complemented, leaving the set unchanged. This is equivalent to a boolean logic XOR. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

◆ complementAll() [1/2]

Complements in this set all elements contained in the specified set.

Any character in the other set will be removed if it is in this set, or will be added if it is not in this set. A frozen set will not be modified.

Parameters

Stable:

ICU 2.4

◆ complementAll() [2/2]

Complement EACH of the characters in this string.

Note: "ch" == {"c", "h"} A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ contains() [1/3]

Returns true if this set contains the given multicharacter string.

Parameters

Returns

true if this set contains the specified string

Stable:

ICU 2.4

◆ contains() [2/3]

Returns true if this set contains the given character.

This function works faster with a frozen set.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.0

Implements icu::UnicodeFilter.

◆ contains() [3/3]

Returns true if this set contains every character of the given range.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.0

◆ containsAll() [1/2]

Returns true if this set contains all the characters and strings of the given set.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.4

◆ containsAll() [2/2]

Returns true if this set contains all the characters of the given string.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.4

◆ containsNone() [1/3]

Returns true if this set contains none of the characters and strings of the given set.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.4

◆ containsNone() [2/3]

Returns true if this set contains none of the characters of the given string.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.4

◆ containsNone() [3/3]

Returns true if this set contains none of the characters of the given range.

Parameters

Returns

true if the test condition is met

Stable:

ICU 2.4

◆ containsSome() [1/3]

Returns true if this set contains one or more of the characters and strings of the given set.

Parameters

Returns

true if the condition is met

Stable:

ICU 2.4

Definition at line 1856 of file uniset.h.

◆ containsSome() [2/3]

Returns true if this set contains one or more of the characters of the given string.

Parameters

Returns

true if the condition is met

Stable:

ICU 2.4

Definition at line 1860 of file uniset.h.

◆ containsSome() [3/3]

Returns true if this set contains one or more of the characters in the given range.

Parameters

Returns

true if the condition is met

Stable:

ICU 2.4

Definition at line 1852 of file uniset.h.

◆ createFrom()

Makes a set from a multicharacter string.

Thus "ch" => {"ch"}

Parameters

Returns

a newly created set containing the given string. The caller owns the return object and is responsible for deleting it.

Stable:

ICU 2.4

◆ createFromAll()

Makes a set from each of the characters in the string.

Thus "ch" => {"c", "h"}

Parameters

Returns

a newly created set containing the given characters The caller owns the return object and is responsible for deleting it.

Stable:

ICU 2.4

◆ end()

Returns

an exclusive-end sentinel for iterating over all of the elements of this set.

Draft:

This API may be changed in the future versions and was introduced in ICU 77

See also

begin

[codePoints](classicu%5F1%5F1UnicodeSet.html#a537a13a1b3adcaebc140f715876aca63 "Returns a C++ "range" for iterating over the code points of this set.")

[ranges](classicu%5F1%5F1UnicodeSet.html#a689385fcc1e2e9e05996e9e19229ea3f "Returns a C++ "range" for iterating over the code point ranges of this set.")

[strings](classicu%5F1%5F1UnicodeSet.html#a054e7d9e1c1476acd1a9f3d9113395bd "Returns a C++ "range" for iterating over the empty and multi-character strings of this set.")

Definition at line 1215 of file uniset.h.

◆ freeze()

Freeze the set (make it immutable).

Once frozen, it cannot be unfrozen and is therefore thread-safe until it is deleted. See the ICU4J Freezable interface for details. Freezing the set may also make some operations faster, for example contains() and span(). A frozen set will not be modified. (It remains frozen.)

Returns

this set.

See also

isFrozen

cloneAsThawed

Stable:

ICU 3.8

◆ fromUSet() [1/2]

◆ fromUSet() [2/2]

◆ getDynamicClassID()

Implement UnicodeFunctor API.

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 2.4

Implements icu::UnicodeFunctor.

◆ getRangeCount()

◆ getRangeEnd()

◆ getRangeStart()

◆ getStaticClassID()

Return 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

◆ hashCode()

Returns the hash code value for this set.

Returns

the hash code value for this set.

See also

Object::hashCode()

Stable:

ICU 2.0

◆ hasStrings()

Returns

true if this set contains multi-character strings or the empty string.

Stable:

ICU 70

◆ indexOf()

Returns the index of the given character within this set, where the set is ordered by ascending code point.

If the character is not in this set, return -1. The inverse of this method is [charAt()](classicu%5F1%5F1UnicodeSet.html#a8629e7f0321bce9d6b17098f543ad179 "Returns the character at the given index within this set, where the set is ordered by ascending code ...").

Returns

an index from 0..size()-1, or -1

Stable:

ICU 2.4

◆ isBogus()

Determine if this object contains a valid set.

A bogus set has no value. It is different from an empty set. It can be used to indicate that no set value is available.

Returns

true if the set is bogus/invalid, false otherwise

See also

setToBogus()

Stable:

ICU 4.0

Definition at line 1864 of file uniset.h.

◆ isEmpty()

Returns true if this set contains no elements.

Returns

true if this set contains no elements.

Stable:

ICU 2.0

◆ isFrozen()

Determines whether the set has been frozen (made immutable) or not.

See the ICU4J Freezable interface for details.

Returns

true/false for whether the set has been frozen

See also

freeze

cloneAsThawed

Stable:

ICU 3.8

Definition at line 1848 of file uniset.h.

◆ matches()

◆ operator!=()

Compares the specified object with this set for equality.

Returns true if the specified set is not equal to this set.

Stable:

ICU 2.0

Definition at line 1844 of file uniset.h.

References icu::operator==().

◆ operator=()

Assigns this object to be a copy of another.

A frozen set will not be modified.

Stable:

ICU 2.0

◆ operator==()

Compares the specified object with this set for equality.

Returns true if the two sets have the same size, and every member of the specified set is contained in this set (or equivalently, every member of this set is contained in the specified set).

Parameters

Returns

true if the specified set is equal to this set.

Stable:

ICU 2.0

◆ ranges()

Returns a C++ "range" for iterating over the code point ranges of this set.

printf("set.range U+%04lx..U+%04lx\n", (long)start, (long)end);

}

printf("set.range.c U+%04lx\n", (long)c);

}

}

U_HEADER_NESTED_NAMESPACE::USetElementIterator end() const

U_HEADER_NESTED_NAMESPACE::USetRanges ranges() const

Returns a C++ "range" for iterating over the code point ranges of this set.

Returns

a "range" object for iterating over the code point ranges of this set.

Draft:

This API may be changed in the future versions and was introduced in ICU 76

See also

[codePoints](classicu%5F1%5F1UnicodeSet.html#a537a13a1b3adcaebc140f715876aca63 "Returns a C++ "range" for iterating over the code points of this set.")

[strings](classicu%5F1%5F1UnicodeSet.html#a054e7d9e1c1476acd1a9f3d9113395bd "Returns a C++ "range" for iterating over the empty and multi-character strings of this set.")

begin

end

Definition at line 1149 of file uniset.h.

◆ remove() [1/3]

Removes the specified string from this set if it is present.

The set will not contain the specified character once the call returns. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ remove() [2/3]

Removes the specified character from this set if it is present.

The set will not contain the specified range once the call returns. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.0

◆ remove() [3/3]

Removes the specified range from this set if it is present.

The set will not contain the specified range once the call returns. If start > end then an empty range is removed, leaving the set unchanged. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

◆ removeAll() [1/2]

Removes from this set all of its elements that are contained in the specified set.

This operation effectively modifies this set so that its value is the asymmetric set difference of the two sets. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

◆ removeAll() [2/2]

Remove EACH of the characters in this string.

Note: "ch" == {"c", "h"} A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ removeAllStrings()

Remove all strings from this set.

Returns

a reference to this set.

Stable:

ICU 4.2

◆ resemblesPattern()

Return true if the given position, in the given pattern, appears to be the start of a UnicodeSet pattern.

Stable:

ICU 2.4

◆ retain() [1/3]

Retains only the specified string from this set if it is present.

Upon return this set will be empty if it did not contain s, or will only contain s if it did contain s. A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 69

◆ retain() [2/3]

Retain the specified character from this set if it is present.

A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.0

◆ retain() [3/3]

Retain only the elements in this set that are contained in the specified range.

If start > end then an empty range is retained, leaving the set empty. This is equivalent to a boolean logic AND, or a set INTERSECTION. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

◆ retainAll() [1/2]

Retains only the elements in this set that are contained in the specified set.

In other words, removes from this set all of its elements that are not contained in the specified set. This operation effectively modifies this set so that its value is the intersection of the two sets. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

◆ retainAll() [2/2]

Retains EACH of the characters in this string.

Note: "ch" == {"c", "h"} A frozen set will not be modified.

Parameters

Returns

this object, for chaining

Stable:

ICU 2.4

◆ serialize()

Serializes this set into an array of 16-bit integers.

Serialization (currently) only records the characters in the set; multicharacter strings are ignored.

The array has following format (each line is one 16-bit integer):

length = (n+2*m) | (m!=0?0x8000:0) bmpLength = n; present if m!=0 bmp[0] bmp[1] ... bmp[n-1] supp-high[0] supp-low[0] supp-high[1] supp-low[1] ... supp-high[m-1] supp-low[m-1]

The array starts with a header. After the header are n bmp code points, then m supplementary code points. Either n or m or both may be zero. n+2*m is always <= 0x7FFF.

If there are no supplementary characters (if m==0) then the header is one 16-bit integer, 'length', with value n.

If there are supplementary characters (if m!=0) then the header is two 16-bit integers. The first, 'length', has value (n+2*m)|0x8000. The second, 'bmpLength', has value n.

After the header the code points are stored in ascending order. Supplementary code points are stored as most significant 16 bits followed by least significant 16 bits.

Parameters

Returns

the total length of the serialized format, including the header, that is, n+2*m+(m!=0?2:1), or 0 on error other than U_BUFFER_OVERFLOW_ERROR.

Stable:

ICU 2.4

◆ set()

Make this object represent the range start - end.

If start > end then this object is set to an empty range. A frozen set will not be modified.

Parameters

Stable:

ICU 2.4

◆ setToBogus()

Make this UnicodeSet object invalid.

The string will test true with isBogus().

A bogus set has no value. It is different from an empty set. It can be used to indicate that no set value is available.

This utility function is used throughout the UnicodeSet implementation to indicate that a UnicodeSet operation failed, and may be used in other functions, especially but not exclusively when such functions do not take a UErrorCode for simplicity.

See also

isBogus()

Stable:

ICU 4.0

◆ size()

Returns the number of elements in this set (its cardinality).

Note than the elements of a set may include both individual codepoints and strings.

This is slower than getRangeCount() because it counts the code points of all ranges.

Returns

the number of elements in this set (its cardinality).

Stable:

ICU 2.0

See also

getRangeCount

◆ span() [1/2]

Returns the length of the initial substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED).

See USetSpanCondition for details. Similar to the strspn() C library function. Unpaired surrogates are treated according to contains() of their surrogate code points. This function works faster with a frozen set and with a non-negative string length argument.

Parameters

Returns

the length of the initial substring according to the spanCondition; 0 if the start of the string does not fit the spanCondition

Stable:

ICU 3.8

See also

USetSpanCondition

◆ span() [2/2]

Returns the end of the substring of the input string according to the USetSpanCondition.

Same as start+span(s.getBuffer()+start, s.length()-start, spanCondition) after pinning start to 0<=start<=s.length().

Parameters

Returns

the exclusive end of the substring according to the spanCondition; the substring s.tempSubStringBetween(start, end) fulfills the spanCondition

Stable:

ICU 4.4

See also

USetSpanCondition

Definition at line 1884 of file uniset.h.

References icu::UnicodeString::getBuffer(), and icu::UnicodeString::length().

◆ spanBack() [1/2]

Returns the start of the trailing substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED).

See USetSpanCondition for details. Unpaired surrogates are treated according to contains() of their surrogate code points. This function works faster with a frozen set and with a non-negative string length argument.

Parameters

Returns

the start of the trailing substring according to the spanCondition; the string length if the end of the string does not fit the spanCondition

Stable:

ICU 3.8

See also

USetSpanCondition

◆ spanBack() [2/2]

Returns the start of the substring of the input string according to the USetSpanCondition.

Same as spanBack(s.getBuffer(), limit, spanCondition) after pinning limit to 0<=end<=s.length().

Parameters

Returns

the start of the substring according to the spanCondition; the substring s.tempSubStringBetween(start, limit) fulfills the spanCondition

Stable:

ICU 4.4

See also

USetSpanCondition

Definition at line 1894 of file uniset.h.

References icu::UnicodeString::getBuffer(), and icu::UnicodeString::length().

◆ spanBackUTF8()

Returns the start of the trailing substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED).

See USetSpanCondition for details. Malformed byte sequences are treated according to contains(0xfffd). This function works faster with a frozen set and with a non-negative string length argument.

Parameters

Returns

the start of the trailing substring according to the spanCondition; the string length if the end of the string does not fit the spanCondition

Stable:

ICU 3.8

See also

USetSpanCondition

◆ spanUTF8()

Returns the length of the initial substring of the input string which consists only of characters and strings that are contained in this set (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), or only of characters and strings that are not contained in this set (USET_SPAN_NOT_CONTAINED).

See USetSpanCondition for details. Similar to the strspn() C library function. Malformed byte sequences are treated according to contains(0xfffd). This function works faster with a frozen set and with a non-negative string length argument.

Parameters

Returns

the length of the initial substring according to the spanCondition; 0 if the start of the string does not fit the spanCondition

Stable:

ICU 3.8

See also

USetSpanCondition

◆ strings()

Returns a C++ "range" for iterating over the empty and multi-character strings of this set.

Returns each string as a std::u16string_view without copying its contents.

UnicodeString us(s);

std::string u8;

printf("set.string length %ld \"%s\"\n", (long)s.length(), us.toUTF8String(u8).c_str());

}

U_HEADER_NESTED_NAMESPACE::USetStrings strings() const

Returns a C++ "range" for iterating over the empty and multi-character strings of this set.

Returns

a "range" object for iterating over the strings of this set.

Draft:

This API may be changed in the future versions and was introduced in ICU 76

See also

[codePoints](classicu%5F1%5F1UnicodeSet.html#a537a13a1b3adcaebc140f715876aca63 "Returns a C++ "range" for iterating over the code points of this set.")

[ranges](classicu%5F1%5F1UnicodeSet.html#a689385fcc1e2e9e05996e9e19229ea3f "Returns a C++ "range" for iterating over the code point ranges of this set.")

begin

end

Definition at line 1173 of file uniset.h.

◆ toPattern()

Returns a string representation of this set.

If the result of calling this function is passed to a UnicodeSet constructor, it will produce another set that is equal to this one. A frozen set will not be modified.

Parameters

Stable:

ICU 2.0

Implements icu::UnicodeMatcher.

◆ toUSet() [1/2]

◆ toUSet() [2/2]

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

• common/unicode/uniset.h