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
像函数式程序员一样思考:)
要根据元素是否已经出现来筛选列表,需要索引。可以使用enumeration获取索引,并使用map返回值列表。
let unique = myArray
.enumerated()
.filter{ myArray.firstIndex(of: $0.1) == $0.0 }
.map{ $0.1 }
这保证了秩序。如果你不介意顺序,那么Array(Set(myArray))的现有答案更简单,可能更有效。
更新:一些关于效率和正确性的注意事项
一些人对效率进行了评论。我肯定是先写正确而简单的代码,然后再找出瓶颈,尽管我知道这是否比Array(Set(Array))更清楚是有争议的。
这个方法比Array(Set(Array))慢很多。正如评论中所指出的,它确实保持了顺序,并对非Hashable的元素起作用。
然而,@Alain T的方法也保持了秩序,也快得多。所以除非你的元素类型是不可哈希的,或者你只是需要一个快速的一行,那么我建议采用他们的解决方案。
以下是MacBook Pro(2014)在Xcode 11.3.1 (Swift 5.1)发布模式下的一些测试。
profiler函数和两个比较方法:
func printTimeElapsed(title:String, operation:()->()) {
var totalTime = 0.0
for _ in (0..<1000) {
let startTime = CFAbsoluteTimeGetCurrent()
operation()
let timeElapsed = CFAbsoluteTimeGetCurrent() - startTime
totalTime += timeElapsed
}
let meanTime = totalTime / 1000
print("Mean time for \(title): \(meanTime) s")
}
func method1<T: Hashable>(_ array: Array<T>) -> Array<T> {
return Array(Set(array))
}
func method2<T: Equatable>(_ array: Array<T>) -> Array<T>{
return array
.enumerated()
.filter{ array.firstIndex(of: $0.1) == $0.0 }
.map{ $0.1 }
}
// Alain T.'s answer (adapted)
func method3<T: Hashable>(_ array: Array<T>) -> Array<T> {
var uniqueKeys = Set<T>()
return array.filter{uniqueKeys.insert($0).inserted}
}
以及少量的测试输入:
func randomString(_ length: Int) -> String {
let letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
return String((0..<length).map{ _ in letters.randomElement()! })
}
let shortIntList = (0..<100).map{_ in Int.random(in: 0..<100) }
let longIntList = (0..<10000).map{_ in Int.random(in: 0..<10000) }
let longIntListManyRepetitions = (0..<10000).map{_ in Int.random(in: 0..<100) }
let longStringList = (0..<10000).map{_ in randomString(1000)}
let longMegaStringList = (0..<10000).map{_ in randomString(10000)}
给出输出:
Mean time for method1 on shortIntList: 2.7358531951904296e-06 s
Mean time for method2 on shortIntList: 4.910230636596679e-06 s
Mean time for method3 on shortIntList: 6.417632102966309e-06 s
Mean time for method1 on longIntList: 0.0002518167495727539 s
Mean time for method2 on longIntList: 0.021718120217323302 s
Mean time for method3 on longIntList: 0.0005312927961349487 s
Mean time for method1 on longIntListManyRepetitions: 0.00014377200603485108 s
Mean time for method2 on longIntListManyRepetitions: 0.0007293639183044434 s
Mean time for method3 on longIntListManyRepetitions: 0.0001843773126602173 s
Mean time for method1 on longStringList: 0.007168249964714051 s
Mean time for method2 on longStringList: 0.9114790915250778 s
Mean time for method3 on longStringList: 0.015888616919517515 s
Mean time for method1 on longMegaStringList: 0.0525397013425827 s
Mean time for method2 on longMegaStringList: 1.111266262292862 s
Mean time for method3 on longMegaStringList: 0.11214958941936493 s
其他回答
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。
从数组中删除重复项的另一个Swift 3.0解决方案。该解决方案改进了许多已经提出的其他解决方案:
保留输入数组中元素的顺序 线性复杂度O(n):单通滤波器O(n) +集插入O(1)
给定整数数组:
let numberArray = [10, 1, 2, 3, 2, 1, 15, 4, 5, 6, 7, 3, 2, 12, 2, 5, 5, 6, 10, 7, 8, 3, 3, 45, 5, 15, 6, 7, 8, 7]
功能代码:
func orderedSet<T: Hashable>(array: Array<T>) -> Array<T> {
var unique = Set<T>()
return array.filter { element in
return unique.insert(element).inserted
}
}
orderedSet(array: numberArray) // [10, 1, 2, 3, 15, 4, 5, 6, 7, 12, 8, 45]
数组扩展代码:
extension Array where Element:Hashable {
var orderedSet: Array {
var unique = Set<Element>()
return filter { element in
return unique.insert(element).inserted
}
}
}
numberArray.orderedSet // [10, 1, 2, 3, 15, 4, 5, 6, 7, 12, 8, 45]
这段代码利用了Set上的插入操作返回的结果,该操作在O(1)上执行,并返回一个元组,指示该项是否被插入,或者该项是否已经存在于Set中。
如果项目在集合中,过滤器将从最终结果中排除它。
斯威夫特2
用uniq函数回答:
func uniq<S: SequenceType, E: Hashable where E==S.Generator.Element>(source: S) -> [E] {
var seen: [E:Bool] = [:]
return source.filter({ (v) -> Bool in
return seen.updateValue(true, forKey: v) == nil
})
}
use:
var test = [1,2,3,4,5,6,7,8,9,9,9,9,9,9]
print(uniq(test)) //1,2,3,4,5,6,7,8,9
这只是一个非常简单和方便的实现。具有相等元素的数组扩展中的计算属性。
extension Array where Element: Equatable {
/// Array containing only _unique_ elements.
var unique: [Element] {
var result: [Element] = []
for element in self {
if !result.contains(element) {
result.append(element)
}
}
return result
}
}
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")