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
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")
其他回答
如果你把两个扩展都放在你的代码中,更快的Hashable版本将在可能的情况下使用,Equatable版本将用作备用版本。
public extension Sequence where Element: Hashable {
/// The elements of the sequence, with duplicates removed.
/// - Note: Has equivalent elements to `Set(self)`.
@available(
swift, deprecated: 5.4,
message: "Doesn't compile without the constant in Swift 5.3."
)
var firstUniqueElements: [Element] {
let getSelf: (Element) -> Element = \.self
return firstUniqueElements(getSelf)
}
}
public extension Sequence where Element: Equatable {
/// The elements of the sequence, with duplicates removed.
/// - Note: Has equivalent elements to `Set(self)`.
@available(
swift, deprecated: 5.4,
message: "Doesn't compile without the constant in Swift 5.3."
)
var firstUniqueElements: [Element] {
let getSelf: (Element) -> Element = \.self
return firstUniqueElements(getSelf)
}
}
public extension Sequence {
/// The elements of the sequences, with "duplicates" removed
/// based on a closure.
func firstUniqueElements<Hashable: Swift.Hashable>(
_ getHashable: (Element) -> Hashable
) -> [Element] {
var set: Set<Hashable> = []
return filter { set.insert(getHashable($0)).inserted }
}
/// The elements of the sequence, with "duplicates" removed,
/// based on a closure.
func firstUniqueElements<Equatable: Swift.Equatable>(
_ getEquatable: (Element) -> Equatable
) -> [Element] {
reduce(into: []) { uniqueElements, element in
if zip(
uniqueElements.lazy.map(getEquatable),
AnyIterator { [equatable = getEquatable(element)] in equatable }
).allSatisfy(!=) {
uniqueElements.append(element)
}
}
}
}
如果顺序不重要,那么你总是可以使用这个Set初始化式。
Daniel Krom的Swift 2答案的更简洁的语法版本,使用了一个尾随闭包和简写参数名,这似乎是基于Airspeed Velocity的原始答案:
func uniq<S: SequenceType, E: Hashable where E == S.Generator.Element>(source: S) -> [E] {
var seen = [E: Bool]()
return source.filter { seen.updateValue(true, forKey: $0) == nil }
}
实现一个可以与uniq(_:)一起使用的自定义类型的示例(必须符合Hashable,因此符合Equatable,因为Hashable扩展了Equatable):
func ==(lhs: SomeCustomType, rhs: SomeCustomType) -> Bool {
return lhs.id == rhs.id // && lhs.someOtherEquatableProperty == rhs.someOtherEquatableProperty
}
struct SomeCustomType {
let id: Int
// ...
}
extension SomeCustomType: Hashable {
var hashValue: Int {
return id
}
}
在上面的代码中…
在==重载中使用的id可以是任何Equatable类型(或返回Equatable类型的方法,例如someMethodThatReturnsAnEquatableType())。注释掉的代码演示了扩展相等性检查,其中someOtherEquatableProperty是Equatable类型的另一个属性(但也可以是返回Equatable类型的方法)。
在hashValue计算属性中使用的id(必须符合Hashable)可以是任何Hashable(因此是Equatable)属性(或返回Hashable类型的方法)。
使用uniq(_:)的示例:
var someCustomTypes = [SomeCustomType(id: 1), SomeCustomType(id: 2), SomeCustomType(id: 3), SomeCustomType(id: 1)]
print(someCustomTypes.count) // 4
someCustomTypes = uniq(someCustomTypes)
print(someCustomTypes.count) // 3
这里有很多答案,但我错过了这个简单的扩展,适合Swift 2及以上:
extension Array where Element:Equatable {
func removeDuplicates() -> [Element] {
var result = [Element]()
for value in self {
if result.contains(value) == false {
result.append(value)
}
}
return result
}
}
这非常简单。可以这样调用:
let arrayOfInts = [2, 2, 4, 4]
print(arrayOfInts.removeDuplicates()) // Prints: [2, 4]
基于属性的过滤
要根据属性筛选数组,你可以使用这个方法:
extension Array {
func filterDuplicates(@noescape includeElement: (lhs:Element, rhs:Element) -> Bool) -> [Element]{
var results = [Element]()
forEach { (element) in
let existingElements = results.filter {
return includeElement(lhs: element, rhs: $0)
}
if existingElements.count == 0 {
results.append(element)
}
}
return results
}
}
你可以这样调用它:
let filteredElements = myElements.filterDuplicates { $0.PropertyOne == $1.PropertyOne && $0.PropertyTwo == $1.PropertyTwo }
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]
让我提出一个类似于斯科特·加德纳的答案,但使用了更简洁的reduce语法。 此解决方案从自定义对象数组中删除重复项(保持初始顺序)
// Custom Struct. Can be also class.
// Need to be `equitable` in order to use `contains` method below
struct CustomStruct : Equatable {
let name: String
let lastName : String
}
// conform to Equatable protocol. feel free to change the logic of "equality"
func ==(lhs: CustomStruct, rhs: CustomStruct) -> Bool {
return (lhs.name == rhs.name && lhs.lastName == rhs.lastName)
}
let categories = [CustomStruct(name: "name1", lastName: "lastName1"),
CustomStruct(name: "name2", lastName: "lastName1"),
CustomStruct(name: "name1", lastName: "lastName1")]
print(categories.count) // prints 3
// remove duplicates (and keep initial order of elements)
let uniq1 : [CustomStruct] = categories.reduce([]) { $0.contains($1) ? $0 : $0 + [$1] }
print(uniq1.count) // prints 2 - third element has removed
如果你想知道这个约简魔法是如何工作的,这里是完全相同的,只是使用了更扩展的约简语法
let uniq2 : [CustomStruct] = categories.reduce([]) { (result, category) in
var newResult = result
if (newResult.contains(category)) {}
else {
newResult.append(category)
}
return newResult
}
uniq2.count // prints 2 - third element has removed
你可以简单地复制粘贴这段代码到Swift Playground中。