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
我的解决方案，它似乎可以在O(n)时间，因为哈希映射访问是O(1)，过滤器是O(n)。它还使用by闭包来选择按顺序区分元素的属性。
extension Sequence {
func distinct<T: Hashable>(by: (Element) -> T) -> [Element] {
var seen: [T: Bool] = [:]
return self.filter { seen.updateValue(true, forKey: by($0)) == nil }
}
}
其他回答
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]
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]
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。
var numbers = [1,2,3,4,5,10,10, 12, 12, 6,6,6,7,8,8, 8, 8, 8 , 7 , 1 , 1, 2 , 9]
var newArr : [Int] = []
for n in numbers {
if !newArr.contains(n) {
newArr.append(n)
}
}
输出- [1,2,3,4,5,10,12,6,7,8,9]
上面的解决方案保持了顺序，但是很慢，因为.contains一次又一次地迭代。 因此使用有序集。
这将打印有序数组。
Array(NSOrderedSet.init(array: numbers))
输出- [1,2,3,4,5,10,12,6,7,8,9]
这将打印一个无序数组。
let uniqueUnordered = Array(Set(numbers))
输出- [4,2,1,9,10,3,5,6,8,12,7]
斯威夫特4. x:
extension Sequence where Iterator.Element: Hashable {
func unique() -> [Iterator.Element] {
return Array(Set<Iterator.Element>(self))
}
func uniqueOrdered() -> [Iterator.Element] {
return reduce([Iterator.Element]()) { $0.contains($1) ? $0 : $0 + [$1] }
}
}
用法:
["Ljubljana", "London", "Los Angeles", "Ljubljana"].unique()
or
["Ljubljana", "London", "Los Angeles", "Ljubljana"].uniqueOrdered()
