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

对于元素既不是哈希也不是可比的数组(例如复杂对象,字典或结构),这个扩展提供了一种通用的方法来删除重复:

extension Array
{
   func filterDuplicate<T:Hashable>(_ keyValue:(Element)->T) -> [Element]
   {
      var uniqueKeys = Set<T>()
      return filter{uniqueKeys.insert(keyValue($0)).inserted}
   }

   func filterDuplicate<T>(_ keyValue:(Element)->T) -> [Element]
   { 
      return filterDuplicate{"\(keyValue($0))"}
   }
}

// example usage: (for a unique combination of attributes):

peopleArray = peopleArray.filterDuplicate{ ($0.name, $0.age, $0.sex) }

or...

peopleArray = peopleArray.filterDuplicate{ "\(($0.name, $0.age, $0.sex))" }

您不必为使值可哈希而烦恼,它允许您使用不同的字段组合来实现惟一性。

注:对于更健壮的方法,请参阅下面评论中Coeur提出的解决方案。

stackoverflow.com/a/55684308/1033581

Swift 4的替代方案

在Swift 4.2中,你可以更容易地使用hash类来构建散列。上面的扩展可以改变,以利用这一点:

extension Array
{
    func filterDuplicate(_ keyValue:((AnyHashable...)->AnyHashable,Element)->AnyHashable) -> [Element]
    {
        func makeHash(_ params:AnyHashable ...) -> AnyHashable
        { 
           var hash = Hasher()
           params.forEach{ hash.combine($0) }
           return hash.finalize()
        }  
        var uniqueKeys = Set<AnyHashable>()
        return filter{uniqueKeys.insert(keyValue(makeHash,$0)).inserted}     
    }
}

调用语法略有不同,因为闭包接收了一个额外的参数,其中包含一个函数,用于散列可变数量的值(这些值必须是单独可散列的)

peopleArray = peopleArray.filterDuplicate{ $0($1.name, $1.age, $1.sex) } 

它也可以使用单一唯一性值(使用$1而忽略$0)。

peopleArray = peopleArray.filterDuplicate{ $1.name } 

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。

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]

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 }
    }
}

使用Set或NSOrderedSet删除重复项,然后转换回数组:

let uniqueUnordered = Array(Set(array))
let uniqueOrdered = Array(NSOrderedSet(array: array))