我可能有一个像下面这样的数组:
[1, 4, 2, 2, 6, 24, 15, 2, 60, 15, 6]
或者,实际上,任何类似类型的数据部分的序列。我要做的是确保每个相同的元素只有一个。例如,上面的数组将变成:
[1, 4, 2, 6, 24, 15, 60]
请注意,删除了2、6和15的重复项,以确保每个相同的元素中只有一个。Swift是否提供了一种容易做到这一点的方法,还是我必须自己做?
我可能有一个像下面这样的数组:
[1, 4, 2, 2, 6, 24, 15, 2, 60, 15, 6]
或者,实际上,任何类似类型的数据部分的序列。我要做的是确保每个相同的元素只有一个。例如,上面的数组将变成:
[1, 4, 2, 6, 24, 15, 60]
请注意,删除了2、6和15的重复项,以确保每个相同的元素中只有一个。Swift是否提供了一种容易做到这一点的方法,还是我必须自己做?
当前回答
斯威夫特5.7
使用有序集
您可以将具有重复元素的数组传递给以下通用函数,该函数处理有序Set并返回没有重复元素的新数组。
import Foundation
internal func withoutDuplicates<T>(_ array: [T]) -> [T] {
let orderedSet: NSMutableOrderedSet = []
var modifiedArray = [T]()
orderedSet.addObjects(from: array)
for i in 0...(orderedSet.count - 1) {
modifiedArray.append(orderedSet[i] as! T)
}
return modifiedArray
}
////////////////////////////////////////////////////////////
let arrayOfStrings: [String] = ["A","A","A","B","B","C","C"]
let arrayOfIntegers: [UInt8] = [1, 1, 1, 2, 2, 2, 3, 3]
let arrayOfBooleans: [Bool] = [true, false, false, true]
let ordered_01 = withoutDuplicates(arrayOfStrings)
let ordered_02 = withoutDuplicates(arrayOfIntegers)
let ordered_03 = withoutDuplicates(arrayOfBooleans)
结果:
// ordered_01 –––> ["A","B","C"]
// ordered_02 –––> [1, 2, 3]
// ordered_03 –––> [true, false]
使用无序集
如果新数组中元素的顺序对您来说并不重要,则在处理时使用无序集。无序集中的元素类型必须符合哈希协议。
import UIKit
fileprivate func noDuplicates<T: Hashable>(_ array: [T]) -> [T] {
var unorderedSet = Set<T>()
var modifiedArray: [T] = []
for i in 0...(array.count - 1) {
unorderedSet.insert(array[i])
}
for i in unorderedSet.indices {
modifiedArray.append(unorderedSet[i])
}
return modifiedArray
}
////////////////////////////////////////////////////////////
let arrayOfInts: [Int] = [10, 5, 7, 200, -500, 10, 7, 5]
let arrayOfStrs: [String] = ["A","A","A","B","B","C","C"]
let arrayOfBools: [Bool] = [true, false, false, true]
let unordered_01 = noDuplicates(arrayOfInts)
let unordered_02 = noDuplicates(arrayOfStrs)
let unordered_03 = noDuplicates(arrayOfBools)
结果:
// unordered_01 –––> [200, 7, 10, -500, 5]
// unordered_02 –––> ["B", "C", "A"]
// unordered_03 –––> [false, true]
其他回答
受https://www.swiftbysundell.com/posts/the-power-of-key-paths-in-swift的启发,我们可以声明一个更强大的工具,它能够过滤任何keyPath上的唯一性。感谢Alexander关于复杂性的各种答案的评论,下面的解决方案应该是最优的。
Non-mutating解决方案
我们扩展了一个函数,它可以过滤任意keyPath上的唯一性:
extension RangeReplaceableCollection {
/// Returns a collection containing, in order, the first instances of
/// elements of the sequence that compare equally for the keyPath.
func unique<T: Hashable>(for keyPath: KeyPath<Element, T>) -> Self {
var unique = Set<T>()
return filter { unique.insert($0[keyPath: keyPath]).inserted }
}
}
注意:在你的对象不符合RangeReplaceableCollection,但符合Sequence的情况下,你可以有这个额外的扩展,但返回类型将始终是一个数组:
extension Sequence {
/// Returns an array containing, in order, the first instances of
/// elements of the sequence that compare equally for the keyPath.
func unique<T: Hashable>(for keyPath: KeyPath<Element, T>) -> [Element] {
var unique = Set<T>()
return filter { unique.insert($0[keyPath: keyPath]).inserted }
}
}
使用
如果我们想要元素本身的唯一性,如问题中所示,我们使用keyPath \.self:
let a = [1, 4, 2, 2, 6, 24, 15, 2, 60, 15, 6]
let b = a.unique(for: \.self)
/* b is [1, 4, 2, 6, 24, 15, 60] */
如果我们想要其他东西的唯一性(比如对象集合的id),那么我们使用我们选择的keyPath:
let a = [CGPoint(x: 1, y: 1), CGPoint(x: 2, y: 1), CGPoint(x: 1, y: 2)]
let b = a.unique(for: \.y)
/* b is [{x 1 y 1}, {x 1 y 2}] */
变异的解决方案
我们扩展了一个变异函数,它能够过滤任意keyPath上的唯一性:
extension RangeReplaceableCollection {
/// Keeps only, in order, the first instances of
/// elements of the collection that compare equally for the keyPath.
mutating func uniqueInPlace<T: Hashable>(for keyPath: KeyPath<Element, T>) {
var unique = Set<T>()
removeAll { !unique.insert($0[keyPath: keyPath]).inserted }
}
}
使用
如果我们想要元素本身的唯一性,如问题中所示,我们使用keyPath \.self:
var a = [1, 4, 2, 2, 6, 24, 15, 2, 60, 15, 6]
a.uniqueInPlace(for: \.self)
/* a is [1, 4, 2, 6, 24, 15, 60] */
如果我们想要其他东西的唯一性(比如对象集合的id),那么我们使用我们选择的keyPath:
var a = [CGPoint(x: 1, y: 1), CGPoint(x: 2, y: 1), CGPoint(x: 1, y: 2)]
a.uniqueInPlace(for: \.y)
/* a is [{x 1 y 1}, {x 1 y 2}] */
你可以自己卷,比如这样:
func unique<S : Sequence, T : Hashable>(source: S) -> [T] where S.Iterator.Element == T {
var buffer = [T]()
var added = Set<T>()
for elem in source {
if !added.contains(elem) {
buffer.append(elem)
added.insert(elem)
}
}
return buffer
}
let vals = [1, 4, 2, 2, 6, 24, 15, 2, 60, 15, 6]
let uniqueVals = uniq(vals) // [1, 4, 2, 6, 24, 15, 60]
作为Array的扩展:
extension Array where Element: Hashable {
func uniqued() -> Array {
var buffer = Array()
var added = Set<Element>()
for elem in self {
if !added.contains(elem) {
buffer.append(elem)
added.insert(elem)
}
}
return buffer
}
}
或者更优雅一点(Swift 4/5):
extension Sequence where Element: Hashable {
func uniqued() -> [Element] {
var set = Set<Element>()
return filter { set.insert($0).inserted }
}
}
将被使用:
[1,2,4,2,1].uniqued() // => [1,2,4]
这里我对对象做了O(n)解。不是少行解决方案,而是……
struct DistinctWrapper <T>: Hashable {
var underlyingObject: T
var distinctAttribute: String
var hashValue: Int {
return distinctAttribute.hashValue
}
}
func distinct<S : SequenceType, T where S.Generator.Element == T>(source: S,
distinctAttribute: (T) -> String,
resolution: (T, T) -> T) -> [T] {
let wrappers: [DistinctWrapper<T>] = source.map({
return DistinctWrapper(underlyingObject: $0, distinctAttribute: distinctAttribute($0))
})
var added = Set<DistinctWrapper<T>>()
for wrapper in wrappers {
if let indexOfExisting = added.indexOf(wrapper) {
let old = added[indexOfExisting]
let winner = resolution(old.underlyingObject, wrapper.underlyingObject)
added.insert(DistinctWrapper(underlyingObject: winner, distinctAttribute: distinctAttribute(winner)))
} else {
added.insert(wrapper)
}
}
return Array(added).map( { return $0.underlyingObject } )
}
func == <T>(lhs: DistinctWrapper<T>, rhs: DistinctWrapper<T>) -> Bool {
return lhs.hashValue == rhs.hashValue
}
// tests
// case : perhaps we want to get distinct addressbook list which may contain duplicated contacts like Irma and Irma Burgess with same phone numbers
// solution : definitely we want to exclude Irma and keep Irma Burgess
class Person {
var name: String
var phoneNumber: String
init(_ name: String, _ phoneNumber: String) {
self.name = name
self.phoneNumber = phoneNumber
}
}
let persons: [Person] = [Person("Irma Burgess", "11-22-33"), Person("Lester Davidson", "44-66-22"), Person("Irma", "11-22-33")]
let distinctPersons = distinct(persons,
distinctAttribute: { (person: Person) -> String in
return person.phoneNumber
},
resolution:
{ (p1, p2) -> Person in
return p1.name.characters.count > p2.name.characters.count ? p1 : p2
}
)
// distinctPersons contains ("Irma Burgess", "11-22-33") and ("Lester Davidson", "44-66-22")
下面是SequenceType上的一个类别,它保留了数组的原始顺序,但使用Set来进行contains查找,以避免数组的contains(_:)方法上的O(n)代价。
public extension Sequence where Element: Hashable {
/// Return the sequence with all duplicates removed.
///
/// i.e. `[ 1, 2, 3, 1, 2 ].uniqued() == [ 1, 2, 3 ]`
///
/// - note: Taken from stackoverflow.com/a/46354989/3141234, as
/// per @Alexander's comment.
func uniqued() -> [Element] {
var seen = Set<Element>()
return self.filter { seen.insert($0).inserted }
}
}
如果你不是Hashable或Equatable,你可以传入一个谓词来进行相等性检查:
extension Sequence {
/// Return the sequence with all duplicates removed.
///
/// Duplicate, in this case, is defined as returning `true` from `comparator`.
///
/// - note: Taken from stackoverflow.com/a/46354989/3141234
func uniqued(comparator: @escaping (Element, Element) throws -> Bool) rethrows -> [Element] {
var buffer: [Element] = []
for element in self {
// If element is already in buffer, skip to the next element
if try buffer.contains(where: { try comparator(element, $0) }) {
continue
}
buffer.append(element)
}
return buffer
}
}
现在,如果你没有Hashable,但是是Equatable,你可以使用这个方法:
extension Sequence where Element: Equatable {
/// Return the sequence with all duplicates removed.
///
/// i.e. `[ 1, 2, 3, 1, 2 ].uniqued() == [ 1, 2, 3 ]`
///
/// - note: Taken from stackoverflow.com/a/46354989/3141234
func uniqued() -> [Element] {
return self.uniqued(comparator: ==)
}
}
最后,你可以添加一个unique的关键路径版本,如下所示:
extension Sequence {
/// Returns the sequence with duplicate elements removed, performing the comparison using the property at
/// the supplied keypath.
///
/// i.e.
///
/// ```
/// [
/// MyStruct(value: "Hello"),
/// MyStruct(value: "Hello"),
/// MyStruct(value: "World")
/// ].uniqued(\.value)
/// ```
/// would result in
///
/// ```
/// [
/// MyStruct(value: "Hello"),
/// MyStruct(value: "World")
/// ]
/// ```
///
/// - note: Taken from stackoverflow.com/a/46354989/3141234
///
func uniqued<T: Equatable>(_ keyPath: KeyPath<Element, T>) -> [Element] {
self.uniqued { $0[keyPath: keyPath] == $1[keyPath: keyPath] }
}
}
你可以把这两个都放在你的应用程序中,Swift会根据你的序列的迭代器选择正确的一个。元素类型。
对于El Capitan,您可以扩展此方法以包括多个键盘,如下所示:
/// Returns the sequence with duplicate elements removed, performing the comparison using the property at
/// the supplied keypaths.
///
/// i.e.
///
/// ```
/// [
/// MyStruct(value1: "Hello", value2: "Paula"),
/// MyStruct(value1: "Hello", value2: "Paula"),
/// MyStruct(value1: "Hello", value2: "Bean"),
/// MyStruct(value1: "World", value2: "Sigh")
/// ].uniqued(\.value1, \.value2)
/// ```
/// would result in
///
/// ```
/// [
/// MyStruct(value1: "Hello", value2: "Paula"),
/// MyStruct(value1: "Hello", value2: "Bean"),
/// MyStruct(value1: "World", value2: "Sigh")
/// ]
/// ```
///
/// - note: Taken from stackoverflow.com/a/46354989/3141234
///
func uniqued<T: Equatable, U: Equatable>(_ keyPath1: KeyPath<Element, T>, _ keyPath2: KeyPath<Element, U>) -> [Element] {
self.uniqued {
$0[keyPath: keyPath1] == $1[keyPath: keyPath1] && $0[keyPath: keyPath2] == $1[keyPath: keyPath2]
}
}
但是(恕我直言)你最好把你自己的block传递给self.unique。
斯威夫特5
extension Sequence where Element: Hashable {
func unique() -> [Element] {
NSOrderedSet(array: self as! [Any]).array as! [Element]
}
}