Added in API level 24

UnicodeSet


open class UnicodeSet : UnicodeFilter, MutableIterable<String!>, Comparable<UnicodeSet!>, Freezable<UnicodeSet!>
kotlin.Any
   ↳ android.icu.text.UnicodeFilter
   ↳ android.icu.text.UnicodeSet

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. Note: method freeze() will not only make the set immutable, but also makes important methods much higher performance: contains(c), containsNone(...), span(...), spanBack(...) etc. After the object is frozen, any subsequent call that wants to change the object will throw UnsupportedOperationException.

The UnicodeSet class is not designed to be subclassed.

UnicodeSet supports two APIs. The first is the operand API that allows the caller to modify the value of a UnicodeSet object. It conforms to Java 2's java.util.Set interface, although UnicodeSet 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 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()/toPattern() 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() sets all attributes of a UnicodeSet at once, based on a string pattern.

Pattern syntax

Patterns are accepted by the constructors and the applyPattern() methods and returned by the toPattern() 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 the Unicode Pattern_White_Space property, 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().removeAllStrings() . 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.

[a] The set containing 'a'
[a-z] The set containing 'a' through 'z' and all letters in between, in Unicode order
[^a-z] The set containing all characters but 'a' through 'z', that is, U+0000 through 'a'-1 and 'z'+1 through U+10FFFF
[[pat1][pat2]] The union of sets specified by pat1 and pat2
[[pat1]&[pat2]] The intersection of sets specified by pat1 and pat2
[[pat1]-[pat2]] The asymmetric difference of sets specified by pat1 and pat2
[:Lu:] or \p{Lu} The set of characters having the specified Unicode property; in this case, Unicode uppercase letters
[:^Lu:] or \P{Lu} The set of characters not having the given Unicode property

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

To iterate over contents of UnicodeSet, the following are available:

  • ranges() to iterate through the ranges
  • strings() to iterate through the strings
  • iterator() to iterate through the entire contents in a single loop. That method is, however, not particularly efficient, since it "boxes" each code point into a String.
All of the above can be used in for loops. The UnicodeSetIterator can also be used, but not in for loops.

To replace, count elements, or delete spans, see UnicodeSetSpanner.

Summary

Nested classes

Comparison style enums used by UnicodeSet#compareTo(UnicodeSet, ComparisonStyle).

open

A struct-like class used for iteration through ranges, for faster iteration than by String.

Argument values for whether span() and similar functions continue while the current character is contained vs.

Constants
static Int

Adds all case mappings for each element in the set.

static Int

Alias for CASE_INSENSITIVE.

static Int

Enable case insensitive matching.

static Int

Bitmask for constructor and applyPattern() indicating that white space should be ignored.

static Int

Maximum value that can be stored in a UnicodeSet.

static Int

Minimum value that can be stored in a UnicodeSet.

Public constructors

Constructs an empty set.

Constructs a copy of an existing set.

UnicodeSet(start: Int, end: Int)

Constructs a set containing the given range.

UnicodeSet(vararg pairs: Int)

Quickly constructs a set from a set of ranges <s0, e0, s1, e1, s2, e2, .

UnicodeSet(pattern: String!)

Constructs a set from the given pattern.

UnicodeSet(pattern: String!, ignoreWhitespace: Boolean)

Constructs a set from the given pattern.

UnicodeSet(pattern: String!, options: Int)

Constructs a set from the given pattern.

UnicodeSet(pattern: String!, pos: ParsePosition!, symbols: SymbolTable!)

Constructs a set from the given pattern.

UnicodeSet(pattern: String!, pos: ParsePosition!, symbols: SymbolTable!, options: Int)

Constructs a set from the given pattern.

Public methods
open StringBuffer!
_generatePattern(result: StringBuffer!, escapeUnprintable: Boolean)

Generate and append a string representation of this set to result.

open StringBuffer!
_generatePattern(result: StringBuffer!, escapeUnprintable: Boolean, includeStrings: Boolean)

Generate and append a string representation of this set to result.

open UnicodeSet!
add(start: Int, end: Int)

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

UnicodeSet!
add(c: Int)

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

UnicodeSet!

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

open UnicodeSet!
add(source: MutableIterable<*>!)

Add the contents of the collection (as strings) into this UnicodeSet.

open UnicodeSet!
addAll(start: Int, end: Int)

Adds all characters in range (uses preferred naming convention).

UnicodeSet!

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

open UnicodeSet!

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

open UnicodeSet!
addAll(source: MutableIterable<*>!)

Add a collection (as strings) into this UnicodeSet.

open UnicodeSet!
addAll(vararg collection: T)

open T
addAllTo(target: T)

Add the contents of the UnicodeSet (as strings) into a collection.

open Unit

Implementation of UnicodeMatcher API.

open UnicodeSet!
applyIntPropertyValue(prop: Int, value: Int)

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

UnicodeSet!
applyPattern(pattern: String!)

Modifies this set to represent the set specified by the given pattern.

open UnicodeSet!
applyPattern(pattern: String!, ignoreWhitespace: Boolean)

Modifies this set to represent the set specified by the given pattern, optionally ignoring whitespace.

open UnicodeSet!
applyPattern(pattern: String!, options: Int)

Modifies this set to represent the set specified by the given pattern, optionally ignoring whitespace.

open UnicodeSet!
applyPropertyAlias(propertyAlias: String!, valueAlias: String!)

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

open UnicodeSet!
applyPropertyAlias(propertyAlias: String!, valueAlias: String!, symbols: SymbolTable!)

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

open Int
charAt(index: Int)

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

open UnicodeSet!

Removes all of the elements from this set.

open Any

Return a new set that is equivalent to this one.

open UnicodeSet!

Clone a thawed version of this class, according to the Freezable interface.

open UnicodeSet!
closeOver(attribute: Int)

Close this set over the given attribute.

open UnicodeSet!

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

open Int

Compares UnicodeSets, where shorter come first, and otherwise lexicographically (according to the comparison of the first characters that differ).

open Int

Compares UnicodeSets, in three different ways.

open Int

open UnicodeSet!
complement(start: Int, end: Int)

Complements the specified range in this set.

UnicodeSet!

Complements the specified character in this set.

open UnicodeSet!

This is equivalent to complement(MIN_VALUE, MAX_VALUE).

UnicodeSet!

Complement the specified string in this set.

UnicodeSet!

Complement EACH of the characters in this string.

open UnicodeSet!

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

open Boolean

Returns true if this set contains the given character.

open Boolean
contains(start: Int, end: Int)

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

Boolean

Returns true if this set contains the given multicharacter string.

open Boolean

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

open Boolean

Returns true if there is a partition of the string such that this set contains each of the partitioned strings.

open Boolean
containsAll(collection: MutableIterable<T>!)

open Boolean
containsNone(start: Int, end: Int)

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

open Boolean

Returns true if none of the characters or strings in this UnicodeSet appears in the string.

open Boolean

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

open Boolean
containsNone(collection: MutableIterable<T>!)

Boolean
containsSome(start: Int, end: Int)

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

Boolean

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

Boolean

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

Boolean
containsSome(collection: MutableIterable<T>!)

open Boolean
equals(other: Any?)

Compares the specified object with this set for equality.

open UnicodeSet!

Freeze this class, according to the Freezable interface.

open static UnicodeSet!

Makes a set from a multicharacter string.

open static UnicodeSet!

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

open Int

Iteration method that returns the number of ranges contained in this set.

open Int
getRangeEnd(index: Int)

Iteration method that returns the last character in the specified range of this set.

open Int

Iteration method that returns the first character in the specified range of this set.

open Boolean

open Int

Returns the hash code value for this set.

open Int

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

open Boolean

Returns true if this set contains no elements.

open Boolean

Is this frozen, according to the Freezable interface?

open MutableIterator<String!>

Returns a string iterator.

open Int
matches(text: Replaceable!, offset: IntArray!, limit: Int, incremental: Boolean)

Implementation of UnicodeMatcher.

open Boolean

Implementation of UnicodeMatcher API.

open MutableIterable<UnicodeSet.EntryRange!>!

Provide for faster iteration than by String.

open UnicodeSet!
remove(start: Int, end: Int)

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

UnicodeSet!
remove(c: Int)

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

UnicodeSet!

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

UnicodeSet!

Remove EACH of the characters in this string.

open UnicodeSet!

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

open UnicodeSet!
removeAll(collection: MutableIterable<T>!)

UnicodeSet!

Remove all strings from this UnicodeSet

open UnicodeSet!
retain(start: Int, end: Int)

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

UnicodeSet!
retain(c: Int)

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

UnicodeSet!

Retain the specified string in this set if it is present.

UnicodeSet!

Retains EACH of the characters in this string.

open UnicodeSet!

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

open UnicodeSet!
retainAll(collection: MutableIterable<T>!)

open UnicodeSet!
set(start: Int, end: Int)

Make this object represent the range start - end.

open UnicodeSet!
set(other: UnicodeSet!)

Make this object represent the same set as other.

open Int

Returns the number of elements in this set (its cardinality) Note than the elements of a set may include both individual codepoints and strings.

open Int

Span a string using this UnicodeSet.

open Int
span(s: CharSequence!, start: Int, spanCondition: UnicodeSet.SpanCondition!)

Span a string using this UnicodeSet.

open Int

Span a string backwards (from the end) using this UnicodeSet.

open Int
spanBack(s: CharSequence!, fromIndex: Int, spanCondition: UnicodeSet.SpanCondition!)

Span a string backwards (from the fromIndex) using this UnicodeSet.

open MutableCollection<String!>!

For iterating through the strings in the set.

open String!
toPattern(escapeUnprintable: Boolean)

Returns a string representation of this set.

open String

Return a programmer-readable string representation of this object.

Properties
static UnicodeSet!

Constant for the set of all code points.

static UnicodeSet!

Constant for the empty set.

Constants

ADD_CASE_MAPPINGS

Added in API level 24
static val ADD_CASE_MAPPINGS: Int

Adds all case mappings for each element in the set. This adds the full lower-, title-, and uppercase mappings as well as the full case folding of each existing element in the set.

This value is an options bit set value for some constructors, applyPattern(), and closeOver(). It can be ORed together with other, unrelated options.

Unlike the “case insensitive” options, this does not perform a closure. For example, it does not add 'ſ' (U+017F long s) for 's', 'K' (U+212A Kelvin sign) for 'k', or replace set strings by their case-folded versions.

Value: 4

CASE

Added in API level 24
Deprecated in API level 35
static val CASE: Int

Deprecated: ICU 73 Use CASE_INSENSITIVE instead.

Alias for CASE_INSENSITIVE.

Value: 2

CASE_INSENSITIVE

Added in API level 24
static val CASE_INSENSITIVE: Int

Enable case insensitive matching. E.g., "[ab]" with this flag will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will match all except 'a', 'A', 'b', and 'B'. This performs a full closure over case mappings, e.g. 'ſ' (U+017F long s) for 's'.

This value is an options bit set value for some constructors, applyPattern(), and closeOver(). It can be ORed together with other, unrelated options.

The resulting set is a superset of the input for the code points but not for the strings. It performs a case mapping closure of the code points and adds full case folding strings for the code points, and reduces strings of the original set to their full case folding equivalents.

This is designed for case-insensitive matches, for example in regular expressions. The full code point case closure allows checking of an input character directly against the closure set. Strings are matched by comparing the case-folded form from the closure set with an incremental case folding of the string in question.

The closure set will also contain single code points if the original set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.). This is not necessary (that is, redundant) for the above matching method but results in the same closure sets regardless of whether the original set contained the code point or a string.

Value: 2

IGNORE_SPACE

Added in API level 24
static val IGNORE_SPACE: Int

Bitmask for constructor and applyPattern() indicating that white space should be ignored. If set, ignore Unicode Pattern_White_Space characters, unless they are quoted or escaped. This may be ORed together with other selectors.

Value: 1

MAX_VALUE

Added in API level 24
static val MAX_VALUE: Int

Maximum value that can be stored in a UnicodeSet.

Value: 1114111

MIN_VALUE

Added in API level 24
static val MIN_VALUE: Int

Minimum value that can be stored in a UnicodeSet.

Value: 0

Public constructors

UnicodeSet

Added in API level 24
UnicodeSet()

Constructs an empty set.

UnicodeSet

Added in API level 24
UnicodeSet(other: UnicodeSet!)

Constructs a copy of an existing set.

UnicodeSet

Added in API level 24
UnicodeSet(
    start: Int,
    end: Int)

Constructs a set containing the given range. If end > start then an empty set is created.

Parameters
start Int: first character, inclusive, of range
end Int: last character, inclusive, of range

UnicodeSet

Added in API level 24
UnicodeSet(vararg pairs: Int)

Quickly constructs a set from a set of ranges <s0, e0, s1, e1, s2, e2, ..., sn, en>. There must be an even number of integers, and they must be all greater than zero, all less than or equal to Character.MAX_CODE_POINT. In each pair (..., si, ei, ...) it must be true that si <= ei Between adjacent pairs (...ei, sj...), it must be true that ei+1 < sj

Parameters
pairs Int: pairs of character representing ranges

UnicodeSet

Added in API level 24
UnicodeSet(pattern: String!)

Constructs a set from the given pattern. See the class description for the syntax of the pattern language. Whitespace is ignored.

Parameters
pattern String!: a string specifying what characters are in the set
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

UnicodeSet

Added in API level 24
UnicodeSet(
    pattern: String!,
    ignoreWhitespace: Boolean)

Constructs a set from the given pattern. See the class description for the syntax of the pattern language.

Parameters
pattern String!: a string specifying what characters are in the set
ignoreWhitespace Boolean: if true, ignore Unicode Pattern_White_Space characters
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

UnicodeSet

Added in API level 24
UnicodeSet(
    pattern: String!,
    options: Int)

Constructs a set from the given pattern. See the class description for the syntax of the pattern language.

Parameters
pattern String!: a string specifying what characters are in the set
options Int: a bitmask indicating which options to apply. Valid options are IGNORE_SPACE and at most one of CASE_INSENSITIVE, ADD_CASE_MAPPINGS, #SIMPLE_CASE_INSENSITIVE. These case options are mutually exclusive.
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

UnicodeSet

Added in API level 24
UnicodeSet(
    pattern: String!,
    pos: ParsePosition!,
    symbols: SymbolTable!)

Constructs a set from the given pattern. See the class description for the syntax of the pattern language.

Parameters
pattern String!: a string specifying what characters are in the set
pos ParsePosition!: on input, the position in pattern at which to start parsing. On output, the position after the last character parsed.
symbols SymbolTable!: a symbol table mapping variables to char[] arrays and chars to UnicodeSets
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

UnicodeSet

Added in API level 24
UnicodeSet(
    pattern: String!,
    pos: ParsePosition!,
    symbols: SymbolTable!,
    options: Int)

Constructs a set from the given pattern. See the class description for the syntax of the pattern language.

Parameters
pattern String!: a string specifying what characters are in the set
pos ParsePosition!: on input, the position in pattern at which to start parsing. On output, the position after the last character parsed.
symbols SymbolTable!: a symbol table mapping variables to char[] arrays and chars to UnicodeSets
options Int: a bitmask indicating which options to apply. Valid options are IGNORE_SPACE and at most one of CASE_INSENSITIVE, ADD_CASE_MAPPINGS, #SIMPLE_CASE_INSENSITIVE. These case options are mutually exclusive.
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

Public methods

_generatePattern

Added in API level 24
open fun _generatePattern(
    result: StringBuffer!,
    escapeUnprintable: Boolean
): StringBuffer!

Generate and append a string representation of this set to result. This does not use this.pat, the cleaned up copy of the string passed to applyPattern().

Parameters
result StringBuffer!: the buffer into which to generate the pattern
escapeUnprintable Boolean: escape unprintable characters if true

_generatePattern

Added in API level 24
open fun _generatePattern(
    result: StringBuffer!,
    escapeUnprintable: Boolean,
    includeStrings: Boolean
): StringBuffer!

Generate and append a string representation of this set to result. This does not use this.pat, the cleaned up copy of the string passed to applyPattern().

Parameters
result StringBuffer!: the buffer into which to generate the pattern
escapeUnprintable Boolean: escape unprintable characters if true
includeStrings Boolean: if false, doesn't include the strings.

add

Added in API level 24
open fun add(
    start: Int,
    end: Int
): UnicodeSet!

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.

Parameters
start Int: first character, inclusive, of range to be added to this set.
end Int: last character, inclusive, of range to be added to this set.

add

Added in API level 24
fun add(c: Int): UnicodeSet!

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.

add

Added in API level 24
fun add(s: CharSequence!): UnicodeSet!

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"}

Parameters
s CharSequence!: the source string
Return
UnicodeSet! this object, for chaining

add

Added in API level 24
open fun add(source: MutableIterable<*>!): UnicodeSet!

Add the contents of the collection (as strings) into this UnicodeSet. The collection must not contain null.

Parameters
source MutableIterable<*>!: the collection to add
Return
UnicodeSet! a reference to this object

addAll

Added in API level 24
open fun addAll(
    start: Int,
    end: Int
): UnicodeSet!

Adds all characters in range (uses preferred naming convention).

Parameters
start Int: The index of where to start on adding all characters.
end Int: The index of where to end on adding all characters.
Return
UnicodeSet! a reference to this object

addAll

Added in API level 24
fun addAll(s: CharSequence!): UnicodeSet!

Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"} If this set already any particular character, it has no effect on that character.

Parameters
s CharSequence!: the source string
Return
UnicodeSet! this object, for chaining

addAll

Added in API level 24
open fun addAll(c: UnicodeSet!): UnicodeSet!

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.

Parameters
c UnicodeSet!: set whose elements are to be added to this set.

addAll

Added in API level 24
open fun addAll(source: MutableIterable<*>!): UnicodeSet!

Add a collection (as strings) into this UnicodeSet. Uses standard naming convention.

Parameters
source MutableIterable<*>!: collection to add into
Return
UnicodeSet! a reference to this object

addAll

Added in API level 24
open fun <T : CharSequence!> addAll(vararg collection: T): UnicodeSet!

addAllTo

Added in API level 24
open fun <T : MutableCollection<String!>!> addAllTo(target: T): T

Add the contents of the UnicodeSet (as strings) into a collection.

Parameters
target T: collection to add into

addMatchSetTo

Added in API level 24
open fun addMatchSetTo(toUnionTo: UnicodeSet!): Unit

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

Parameters
toUnionTo UnicodeSet!: the set into which to union the source characters

applyIntPropertyValue

Added in API level 24
open fun applyIntPropertyValue(
    prop: Int,
    value: Int
): UnicodeSet!

Modifies this set to contain those code points which have the given value for the given binary or enumerated property, as returned by UCharacter.getIntPropertyValue. Prior contents of this set are lost.

Parameters
prop Int: a property in the range UProperty.BIN_START..UProperty.BIN_LIMIT-1 or UProperty.INT_START..UProperty.INT_LIMIT-1 or. UProperty.MASK_START..UProperty.MASK_LIMIT-1.
value Int: a value in the range UCharacter.getIntPropertyMinValue(prop).. UCharacter.getIntPropertyMaxValue(prop), with one exception. If prop is UProperty.GENERAL_CATEGORY_MASK, then value should not be a UCharacter.getType() result, but rather a mask value produced by logically ORing (1 << UCharacter.getType()) values together. This allows grouped categories such as [:L:] to be represented.
Return
UnicodeSet! a reference to this set

applyPattern

Added in API level 24
fun applyPattern(pattern: String!): UnicodeSet!

Modifies this set to represent the set specified by the given pattern. See the class description for the syntax of the pattern language. Whitespace is ignored.

Parameters
pattern String!: a string specifying what characters are in the set
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

applyPattern

Added in API level 24
open fun applyPattern(
    pattern: String!,
    ignoreWhitespace: Boolean
): UnicodeSet!

Modifies this set to represent the set specified by the given pattern, optionally ignoring whitespace. See the class description for the syntax of the pattern language.

Parameters
pattern String!: a string specifying what characters are in the set
ignoreWhitespace Boolean: if true then Unicode Pattern_White_Space characters are ignored
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

applyPattern

Added in API level 24
open fun applyPattern(
    pattern: String!,
    options: Int
): UnicodeSet!

Modifies this set to represent the set specified by the given pattern, optionally ignoring whitespace. See the class description for the syntax of the pattern language.

Parameters
pattern String!: a string specifying what characters are in the set
options Int: a bitmask indicating which options to apply. Valid options are IGNORE_SPACE and at most one of CASE_INSENSITIVE, ADD_CASE_MAPPINGS, #SIMPLE_CASE_INSENSITIVE. These case options are mutually exclusive.
Exceptions
java.lang.IllegalArgumentException if the pattern contains a syntax error.

applyPropertyAlias

Added in API level 24
open fun applyPropertyAlias(
    propertyAlias: String!,
    valueAlias: String!
): UnicodeSet!

Modifies this set to contain those code points which have the given value for the given property. Prior contents of this set are lost.

Parameters
propertyAlias String!: a property alias, either short or long. The name is matched loosely. See PropertyAliases.txt for names and a description of loose matching. If the value string is empty, then this string is interpreted as either a General_Category value alias, a Script value alias, a binary property alias, or a special ID. Special IDs are matched loosely and correspond to the following sets: "ANY" = [\\u0000-\\U0010FFFF], "ASCII" = [\\u0000-\\u007F].
valueAlias String!: a value alias, either short or long. The name is matched loosely. See PropertyValueAliases.txt for names and a description of loose matching. In addition to aliases listed, numeric values and canonical combining classes may be expressed numerically, e.g., ("nv", "0.5") or ("ccc", "220"). The value string may also be empty.
Return
UnicodeSet! a reference to this set

applyPropertyAlias

Added in API level 24
open fun applyPropertyAlias(
    propertyAlias: String!,
    valueAlias: String!,
    symbols: SymbolTable!
): UnicodeSet!

Modifies this set to contain those code points which have the given value for the given property. Prior contents of this set are lost.

Parameters
propertyAlias String!: A string of the property alias.
valueAlias String!: A string of the value alias.
symbols SymbolTable!: if not null, then symbols are first called to see if a property is available. If true, then everything else is skipped.
Return
UnicodeSet! this set

charAt

Added in API level 24
open fun charAt(index: Int): Int

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, return -1. The inverse of this method is indexOf().

Parameters
index Int: an index from 0..size()-1
Return
Int the character at the given index, or -1.

clear

Added in API level 24
open fun clear(): UnicodeSet!

Removes all of the elements from this set. This set will be empty after this call returns.

clone

Added in API level 24
open fun clone(): Any

Return a new set that is equivalent to this one.

Return
Any a clone of this instance.
Exceptions
java.lang.CloneNotSupportedException if the object's class does not support the Cloneable interface. Subclasses that override the clone method can also throw this exception to indicate that an instance cannot be cloned.

cloneAsThawed

Added in API level 24
open fun cloneAsThawed(): UnicodeSet!

Clone a thawed version of this class, according to the Freezable interface.

Return
UnicodeSet! the clone, not frozen

closeOver

Added in API level 24
open fun closeOver(attribute: Int): UnicodeSet!

Close this set over the given attribute. For the attribute CASE_INSENSITIVE, the result is to modify this set so that:

  1. For each character or string 'a' in this set, all strings 'b' such that foldCase(a) == foldCase(b) are added to this set. (For most 'a' that are single characters, 'b' will have b.length() == 1.)
  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 UCharacter.foldCase(x, true), and a == b actually denotes a.equals(b), not pointer comparison.)

Parameters
attribute Int: bitmask for attributes to close over. Valid options: At most one of CASE_INSENSITIVE, ADD_CASE_MAPPINGS, #SIMPLE_CASE_INSENSITIVE. These case options are mutually exclusive. Unrelated options bits are ignored.
Return
UnicodeSet! a reference to this set.

compact

Added in API level 24
open fun compact(): UnicodeSet!

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

compareTo

Added in API level 24
open fun compareTo(other: UnicodeSet!): Int

Compares UnicodeSets, where shorter come first, and otherwise lexicographically (according to the comparison of the first characters that differ).

Parameters
o the object to be compared.
Return
Int a negative integer, zero, or a positive integer as this object is less than, equal to, or greater than the specified object.
Exceptions
java.lang.NullPointerException if the specified object is null
java.lang.ClassCastException if the specified object's type prevents it from being compared to this object.

compareTo

Added in API level 24
open fun compareTo(
    o: UnicodeSet!,
    style: UnicodeSet.ComparisonStyle!
): Int

Compares UnicodeSets, in three different ways.

compareTo

Added in API level 24
open fun compareTo(other: MutableIterable<String!>!): Int

complement

Added in API level 24
open fun complement(
    start: Int,
    end: Int
): UnicodeSet!

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.

Parameters
start Int: first character, inclusive, of range
end Int: last character, inclusive, of range

complement

Added in API level 24
fun complement(c: Int): UnicodeSet!

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.

complement

Added in API level 24
open fun complement(): UnicodeSet!

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().removeAllStrings() .

complement

Added in API level 24
fun complement(s: CharSequence!): UnicodeSet!

Complement the specified string in this set. The set will not contain the specified string once the call returns.

Parameters
s CharSequence!: the string to complement
Return
UnicodeSet! this object, for chaining

complementAll

Added in API level 24
fun complementAll(s: CharSequence!): UnicodeSet!

Complement EACH of the characters in this string. Note: "ch" == {"c", "h"} If this set already any particular character, it has no effect on that character.

Parameters
s CharSequence!: the source string
Return
UnicodeSet! this object, for chaining

complementAll

Added in API level 24
open fun complementAll(c: UnicodeSet!): UnicodeSet!

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.

Parameters
c UnicodeSet!: set that defines which elements will be complemented from this set.

contains

Added in API level 24
open fun contains(c: Int): Boolean

Returns true if this set contains the given character.

Parameters
c Int: character to be checked for containment
Return
Boolean true if the test condition is met

contains

Added in API level 24
open fun contains(
    start: Int,
    end: Int
): Boolean

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

Parameters
start Int: first character, inclusive, of the range
end Int: last character, inclusive, of the range
Return
Boolean true if the test condition is met

contains

Added in API level 24
fun contains(s: CharSequence!): Boolean

Returns true if this set contains the given multicharacter string.

Parameters
s CharSequence!: string to be checked for containment
Return
Boolean true if this set contains the specified string

containsAll

Added in API level 24
open fun containsAll(b: UnicodeSet!): Boolean

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

Parameters
b UnicodeSet!: set to be checked for containment
Return
Boolean true if the test condition is met

containsAll

Added in API level 24
open fun containsAll(s: String!): Boolean

Returns true if there is a partition of the string such that this set contains each of the partitioned strings. For example, for the Unicode set [a{bc}{cd}]
containsAll is true for each of: "a", "bc", ""cdbca"
containsAll is false for each of: "acb", "bcda", "bcx"

Parameters
s String!: string containing characters to be checked for containment
Return
Boolean true if the test condition is met

containsAll

Added in API level 24
open fun <T : CharSequence!> containsAll(collection: MutableIterable<T>!): Boolean

containsNone

Added in API level 24
open fun containsNone(
    start: Int,
    end: Int
): Boolean

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

Parameters
start Int: first character, inclusive, of the range
end Int: last character, inclusive, of the range
Return
Boolean true if the test condition is met

containsNone

Added in API level 24
open fun containsNone(b: UnicodeSet!): Boolean

Returns true if none of the characters or strings in this UnicodeSet appears in the string. For example, for the Unicode set [a{bc}{cd}]
containsNone is true for: "xy", "cb"
containsNone is false for: "a", "bc", "bcd"

Parameters
b UnicodeSet!: set to be checked for containment
Return
Boolean true if the test condition is met

containsNone

Added in API level 24
open fun containsNone(s: CharSequence!): Boolean

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

Parameters
s CharSequence!: string containing characters to be checked for containment
Return
Boolean true if the test condition is met

containsNone

Added in API level 24
open fun <T : CharSequence!> containsNone(collection: MutableIterable<T>!): Boolean

containsSome

Added in API level 24
fun containsSome(
    start: Int,
    end: Int
): Boolean

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

Parameters
start Int: first character, inclusive, of the range
end Int: last character, inclusive, of the range
Return
Boolean true if the condition is met

containsSome

Added in API level 24
fun containsSome(s: UnicodeSet!): Boolean

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

Parameters
s UnicodeSet!: set to be checked for containment
Return
Boolean true if the condition is met

containsSome

Added in API level 24
fun containsSome(s: CharSequence!): Boolean

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

Parameters
s CharSequence!: string containing characters to be checked for containment
Return
Boolean true if the condition is met

containsSome

Added in API level 24
fun <T : CharSequence!> containsSome(collection: MutableIterable<T>!): Boolean

equals

Added in API level 24
open fun equals(other: Any?): Boolean

Compares the specified object with this set for equality. Returns true if the specified object is also a set, 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
obj the reference object with which to compare.
o Object to be compared for equality with this set.
Return
Boolean true if the specified Object is equal to this set.

freeze

Added in API level 24
open fun freeze(): UnicodeSet!

Freeze this class, according to the Freezable interface.

Return
UnicodeSet! this

from

Added in API level 24
open static fun from(s: CharSequence!): UnicodeSet!

Makes a set from a multicharacter string. Thus "ch" => {"ch"}

Parameters
s CharSequence!: the source string
Return
UnicodeSet! a newly created set containing the given string

fromAll

Added in API level 24
open static fun fromAll(s: CharSequence!): UnicodeSet!

Makes a set from each of the characters in the string. Thus "ch" => {"c", "h"}

Parameters
s CharSequence!: the source string
Return
UnicodeSet! a newly created set containing the given characters

getRangeCount

Added in API level 24
open fun getRangeCount(): Int

Iteration method that returns the number of ranges contained in this set.

getRangeEnd

Added in API level 24
open fun getRangeEnd(index: Int): Int

Iteration method that returns the last character in the specified range of this set.

Exceptions
java.lang.ArrayIndexOutOfBoundsException if index is outside the range 0..getRangeCount()-1

getRangeStart

Added in API level 24
open fun getRangeStart(index: Int): Int

Iteration method that returns the first character in the specified range of this set.

Exceptions
java.lang.ArrayIndexOutOfBoundsException if index is outside the range 0..getRangeCount()-1

hasStrings

Added in API level 34
open fun hasStrings(): Boolean
Return
Boolean true if this set contains multi-character strings or the empty string.

hashCode

Added in API level 24
open fun hashCode(): Int

Returns the hash code value for this set.

Return
Int the hash code value for this set.

indexOf

Added in API level 24
open fun indexOf(c: Int): Int

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().

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

isEmpty

Added in API level 24
open fun isEmpty(): Boolean

Returns true if this set contains no elements.

Return
Boolean true if this set contains no elements.

isFrozen

Added in API level 24
open fun isFrozen(): Boolean

Is this frozen, according to the Freezable interface?

Return
Boolean value

iterator

Added in API level 24
open fun iterator(): MutableIterator<String!>

Returns a string iterator. Uses the same order of iteration as UnicodeSetIterator.

Warning: For speed, UnicodeSet iteration does not check for concurrent modification. Do not alter the UnicodeSet while iterating.

Return
MutableIterator<String!> an Iterator.

See Also

    matches

    Added in API level 24
    open fun matches(
        text: Replaceable!,
        offset: IntArray!,
        limit: Int,
        incremental: Boolean
    ): Int

    Implementation of UnicodeMatcher.matches(). Always matches the longest possible multichar string.

    Parameters
    text Replaceable!: the text to be matched
    offset IntArray!: on input, the index into text at which to begin matching. On output, the limit of the matched text. The number of matched characters is the output value of offset minus the input value. Offset should always point to the HIGH SURROGATE (leading code unit) of a pair of surrogates, both on entry and upon return.
    limit Int: the limit index of text to be matched. Greater than offset for a forward direction match, less than offset for a backward direction match. The last character to be considered for matching will be text.charAt(limit-1) in the forward direction or text.charAt(limit+1) in the backward direction.
    incremental Boolean: if true, then assume further characters may be inserted at limit and check for partial matching. Otherwise assume the text as given is complete.
    Return
    Int a match degree value indicating a full match, a partial match, or a mismatch. If incremental is false then U_PARTIAL_MATCH should never be returned.

    matchesIndexValue

    Added in API level 24
    open fun matchesIndexValue(v: Int): Boolean

    Implementation of UnicodeMatcher API. Returns true if this set contains any character whose low byte is the given value. This is used by RuleBasedTransliterator for indexing.

    ranges

    Added in API level 24
    open fun ranges(): MutableIterable<UnicodeSet.EntryRange!>!

    Provide for faster iteration than by String. Returns an Iterable/Iterator over ranges of code points. The UnicodeSet must not be altered during the iteration. The EntryRange instance is the same each time; the contents are just reset.

    Warning: To iterate over the full contents, you have to also iterate over the strings.

    Warning: For speed, UnicodeSet iteration does not check for concurrent modification. Do not alter the UnicodeSet while iterating.

    // Sample code
      for (EntryRange range : us1.ranges()) {
          // do something with code points between range.codepoint and range.codepointEnd;
      }
      for (String s : us1.strings()) {
          // do something with each string;
      }
      

    remove

    Added in API level 24
    open fun remove(
        start: Int,
        end: Int
    ): UnicodeSet!

    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.

    Parameters
    start Int: first character, inclusive, of range to be removed from this set.
    end Int: last character, inclusive, of range to be removed from this set.

    remove

    Added in API level 24
    fun remove(c: Int): UnicodeSet!

    Removes the specified character from this set if it is present. The set will not contain the specified character once the call returns.

    Parameters
    c Int: the character to be removed
    Return
    UnicodeSet! this object, for chaining

    remove

    Added in API level 24
    fun remove(s: CharSequence!): UnicodeSet!

    Removes the specified string from this set if it is present. The set will not contain the specified string once the call returns.

    Parameters
    s CharSequence!: the string to be removed
    Return
    UnicodeSet! this object, for chaining

    removeAll

    Added in API level 24
    fun removeAll(s: CharSequence!): UnicodeSet!

    Remove EACH of the characters in this string. Note: "ch" == {"c", "h"} If this set already any particular character, it has no effect on that character.

    Parameters
    s CharSequence!: the source string
    Return
    UnicodeSet! this object, for chaining

    removeAll

    Added in API level 24
    open fun removeAll(c: UnicodeSet!): UnicodeSet!

    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.

    Parameters
    c UnicodeSet!: set that defines which elements will be removed from this set.

    removeAll

    Added in API level 24
    open fun <T : CharSequence!> removeAll(collection: MutableIterable<T>!): UnicodeSet!

    removeAllStrings

    Added in API level 24
    fun removeAllStrings(): UnicodeSet!

    Remove all strings from this UnicodeSet

    Return
    UnicodeSet! this object, for chaining

    retain

    Added in API level 24
    open fun retain(
        start: Int,
        end: Int
    ): UnicodeSet!

    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.

    Parameters
    start Int: first character, inclusive, of range
    end Int: last character, inclusive, of range

    retain

    Added in API level 24
    fun retain(c: Int): UnicodeSet!

    Retain the specified character from this set if it is present. Upon return this set will be empty if it did not contain c, or will only contain c if it did contain c.

    Parameters
    c Int: the character to be retained
    Return
    UnicodeSet! this object, for chaining

    retain

    Added in API level 24
    fun retain(cs: CharSequence!): UnicodeSet!

    Retain the specified string in 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.

    Parameters
    cs CharSequence!: the string to be retained
    Return
    UnicodeSet! this object, for chaining

    retainAll

    Added in API level 24
    fun retainAll(s: CharSequence!): UnicodeSet!

    Retains EACH of the characters in this string. Note: "ch" == {"c", "h"} If this set already any particular character, it has no effect on that character.

    Parameters
    s CharSequence!: the source string
    Return
    UnicodeSet! this object, for chaining

    retainAll

    Added in API level 24
    open fun retainAll(c: UnicodeSet!): UnicodeSet!

    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.

    Parameters
    c UnicodeSet!: set that defines which elements this set will retain.

    retainAll

    Added in API level 24
    open fun <T : CharSequence!> retainAll(collection: MutableIterable<T>!): UnicodeSet!

    set

    Added in API level 24
    open fun set(
        start: Int,
        end: Int
    ): UnicodeSet!

    Make this object represent the range start - end. If start > end then this object is set to an empty range.

    Parameters
    start Int: first character in the set, inclusive
    end Int: last character in the set, inclusive

    set

    Added in API level 24
    open fun set(other: UnicodeSet!): UnicodeSet!

    Make this object represent the same set as other.

    Parameters
    other UnicodeSet!: a UnicodeSet whose value will be copied to this object

    size

    Added in API level 24
    open fun size(): Int

    Returns the number of elements in this set (its cardinality) Note than the elements of a set may include both individual codepoints and strings.

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

    span

    Added in API level 24
    open fun span(
        s: CharSequence!,
        spanCondition: UnicodeSet.SpanCondition!
    ): Int

    Span a string using this UnicodeSet.

    To replace, count elements, or delete spans, see UnicodeSetSpanner.

    Parameters
    s CharSequence!: The string to be spanned
    spanCondition UnicodeSet.SpanCondition!: The span condition
    Return
    Int the length of the span

    span

    Added in API level 24
    open fun span(
        s: CharSequence!,
        start: Int,
        spanCondition: UnicodeSet.SpanCondition!
    ): Int

    Span a string using this UnicodeSet. If the start index is less than 0, span will start from 0. If the start index is greater than the string length, span returns the string length.

    To replace, count elements, or delete spans, see UnicodeSetSpanner.

    Parameters
    s CharSequence!: The string to be spanned
    start Int: The start index that the span begins
    spanCondition UnicodeSet.SpanCondition!: The span condition
    Return
    Int the string index which ends the span (i.e. exclusive)

    spanBack

    Added in API level 24
    open fun spanBack(
        s: CharSequence!,
        spanCondition: UnicodeSet.SpanCondition!
    ): Int

    Span a string backwards (from the end) using this UnicodeSet.

    To replace, count elements, or delete spans, see UnicodeSetSpanner.

    Parameters
    s CharSequence!: The string to be spanned
    spanCondition UnicodeSet.SpanCondition!: The span condition
    Return
    Int The string index which starts the span (i.e. inclusive).

    spanBack

    Added in API level 24
    open fun spanBack(
        s: CharSequence!,
        fromIndex: Int,
        spanCondition: UnicodeSet.SpanCondition!
    ): Int

    Span a string backwards (from the fromIndex) using this UnicodeSet. If the fromIndex is less than 0, spanBack will return 0. If fromIndex is greater than the string length, spanBack will start from the string length.

    To replace, count elements, or delete spans, see UnicodeSetSpanner.

    Parameters
    s CharSequence!: The string to be spanned
    fromIndex Int: The index of the char (exclusive) that the string should be spanned backwards
    spanCondition UnicodeSet.SpanCondition!: The span condition
    Return
    Int The string index which starts the span (i.e. inclusive).

    strings

    Added in API level 24
    open fun strings(): MutableCollection<String!>!

    For iterating through the strings in the set. Example:

    for (String key : myUnicodeSet.strings()) {
        doSomethingWith(key);
      }
      

    toPattern

    Added in API level 24
    open fun toPattern(escapeUnprintable: Boolean): String!

    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.

    Parameters
    escapeUnprintable Boolean: if true then convert unprintable character to their hex escape representations, \\uxxxx or \\Uxxxxxxxx. Unprintable characters are those other than U+000A, U+0020..U+007E.

    toString

    Added in API level 24
    open fun toString(): String

    Return a programmer-readable string representation of this object.

    Return
    String a string representation of the object.

    Properties

    ALL_CODE_POINTS

    Added in API level 24
    static val ALL_CODE_POINTS: UnicodeSet!

    Constant for the set of all code points. (Since UnicodeSets can include strings, does not include everything that a UnicodeSet can.)

    EMPTY

    Added in API level 24
    static val EMPTY: UnicodeSet!

    Constant for the empty set.