Conforming a new protocol to Sequence with a default makeIterator() implementation - swift

I made a (very basic) BinaryTree protocol:
public enum BinaryTreeChildSide {
case left, right
}
public protocol BinaryTree {
associatedtype Element
associatedtype Index
func child(of index: Index, side: BinaryTreeChildSide) -> Index?
var rootIndex: Index? { get }
subscript(position: Index) -> Element { get }
}
For a basic iterative in-order traversal, I made a BinaryTreeIterator (note that I don't implement Sequence just yet):
public extension BinaryTree {
func makeIterator() -> BinaryTreeIterator<Self> {
return BinaryTreeIterator(self)
}
}
public struct BinaryTreeIterator<Tree: BinaryTree>: IteratorProtocol {
private let tree: Tree
private var stack: [Tree.Index]
private var index: Tree.Index?
private init(_ tree: Tree) {
self.tree = tree
stack = []
index = tree.rootIndex
}
public mutating func next() -> Tree.Element? {
while let theIndex = index {
stack.append(theIndex)
index = tree.child(of: theIndex, side: .left)
}
guard let currentIndex = stack.popLast() else { return nil }
defer { index = tree.child(of: currentIndex, side: .right) }
return tree[currentIndex]
}
}
Implementing a binary heap to this protocol is also pretty straight-forward:
public struct BinaryHeap<Element> {
private var elements: [Element]
public init(_ elements: [Element]) {
self.elements = elements
}
}
extension BinaryHeap: BinaryTree {
private func safeIndexOrNil(_ index: Int) -> Int? {
return elements.indices.contains(index) ? index : nil
}
public func child(of index: Int, side: BinaryTreeChildSide) -> Int? {
switch side {
case .left: return safeIndexOrNil(index * 2 + 1)
case .right: return safeIndexOrNil(index * 2 + 2)
}
}
public var rootIndex: Int? { return safeIndexOrNil(0) }
public subscript(position: Int) -> Element {
return elements[position]
}
}
So far, so good. I can now make a simple heap and iterate through its elements:
let heap = BinaryHeap([4, 2, 6, 1, 3, 5, 7])
var iterator = heap.makeIterator()
while let next = iterator.next() {
print(next, terminator: " ")
}
// 1 2 3 4 5 6 7
This works, but of course the goal of implementing makeIterator() is to conform to Sequence. however, if I replace
public protocol BinaryTree {
with
public protocol BinaryTree: Sequence {
then the compiler complains that BinaryHeap doesn't implement Sequence because the associated type Iterator couldn't be inferred. If I manually specify the Iterator type with
extension BinaryHeap: BinaryTree {
typealias Iterator = BinaryTreeIterator<BinaryHeap>
...
}
then the compiler shows an error that Iterator circularly references itself. So that might be why the Iterator type couldn't be inferred.
Interestingly, it works if I wrap my custom BinaryTreeIterator in an AnyIterator instance:
public extension BinaryTree {
func makeIterator() -> AnyIterator<Element> {
return AnyIterator(BinaryTreeIterator(self))
}
}
let heap = BinaryHeap([4, 2, 6, 1, 3, 5, 7])
for number in heap {
print(number, terminator: " ")
}
// 1 2 3 4 5 6 7
Apple's own IndexingIterator seems to work in a similar fashion to my BinaryTreeIterator:
public struct IndexingIterator<
Elements : IndexableBase
// FIXME(compiler limitation):
// Elements : Collection
> : IteratorProtocol, Sequence {
...
}
From the source code. Maybe the problem I'm facing might also be because of the compiler limitation mentioned there, but I don't know for sure.
Is there a way to conform BinaryTree to Sequence without using AnyIterator?

This is the farthest I could take it. Now the compiler will still complain about the heap not containing any makeIterator member
(which I thought was included by default once someone conforms to sequence—wrong turns out one must conform to Sequence ​and​ IteratorProtocol for the default implementation) and having a next—but once you add those methods its smooth sailing.
So makeIterator + next method to make Mr/Mrs/Preferred Gender Pronoun compiler happy.
public enum BinaryTreeChildSide {
case left, right
}
public struct BinaryTreeIterator<Tree: BinaryTree>: Sequence, IteratorProtocol {
private let tree: Tree
private var stack: [Tree.Index]
private var index: Tree.Index?
private init(_ tree: Tree) {
self.tree = tree
stack = []
index = tree.rootIndex
}
public mutating func next() -> Tree.Element? {
while let theIndex = index {
stack.append(theIndex)
index = tree.child(of: theIndex, side: .left)
}
guard let currentIndex = stack.popLast() else { return nil }
defer { index = tree.child(of: currentIndex, side: .right) }
return tree[currentIndex]
}
}
public protocol BinaryTree: Sequence {
associatedtype Element
associatedtype Index
func child(of index: Index, side: BinaryTreeChildSide) -> Index?
var rootIndex: Index? { get }
subscript(position: Index) -> Element { get }
}
extension BinaryTree {
func makeIterator() -> BinaryTreeIterator<Self> {
return BinaryTreeIterator(self)
}
}
extension BinaryHeap {
private func safeIndexOrNil(_ index: Int) -> Int? {
return elements.indices.contains(index) ? index : nil
}
public func child(of index: Int, side: BinaryTreeChildSide) -> Int? {
switch side {
case .left: return safeIndexOrNil(index * 2 + 1)
case .right: return safeIndexOrNil(index * 2 + 2)
}
}
public var rootIndex: Int? { return safeIndexOrNil(0) }
public subscript(position: Int) -> Element {
return elements[position]
}
}
public struct BinaryHeap<Element> {
private var elements: [Element]
public init(_ elements: [Element]) {
self.elements = elements
}
}
let heap = BinaryHeap([4, 2, 6, 1, 3, 5, 7])
var iterator = heap.makeIterator()
while let next = iterator.next() {
print(next, terminator: " ")
}

Apparently it was a Swift bug: my code compiles fine using Swift 3.1.

Related

how to store away sequence variables with constraints in swift

I wanted to create a "where_non_null" operation that works on any swift sequence - which is easy if you return an array, but obviously that is potentially bad performance wise - because you are forcing the entire sequence to resolve in memory - so I created the following that just goes line by line:
//
// this iterates through the underlying sequence, and returns only the values that are not null
//
public class Not_null_iterator<T> : IteratorProtocol
{
public typealias Element = T
private let next_function : () -> T?
init<T_iterator: IteratorProtocol>( _ source: T_iterator ) where T_iterator.Element == Optional<T>
{
var iterator = source
next_function =
{
while (true)
{
if let next_value = iterator.next()
{
if let not_null_value = next_value
{
return not_null_value
}
}
else
{
return nil
}
}
}
}
public func next() -> T? {
next_function()
}
}
//
// a sequence wrapping an underlying sequence, that removes any nulls as we go through
//
public class Not_null_sequence<T > : Sequence
{
private var iterator_creator : () -> Not_null_iterator<T>
init<T_source_sequence : Sequence >( _ source : T_source_sequence ) where T_source_sequence.Element == Optional<T>
{
iterator_creator =
{
Not_null_iterator(source.makeIterator())
}
}
public func makeIterator() -> Not_null_iterator<T>
{
iterator_creator()
}
}
extension Sequence
{
//
// return only the not null values in the sequence without ever resolving more than one item in memory at one time and remove the optionality on the type
//
func where_not_null<T>() -> Not_null_sequence<T> where Element == Optional<T>
{
return Not_null_sequence( self)
}
}
class Where_not_null_tests : XCTestCase
{
public func test_where_not_null()
{
let source = [1, 2, 3, nil, 4]
let checked : [Int] = Array(source.where_not_null())
XCTAssertEqual([1,2,3,4],checked)
}
}
which works great - however I had to define the next() and make_iterator() functions in the constructor, because I couldn't find any type safe way of putting the source into a class level variable.
Is there a way of doing that?
[and yes, I'm aware swift people prefer camel case]
Rather than just using one generic parameter, you'd need two generic parameters. You can't just constrain one generic parameter to say that it has to be some sequence with an element of some Optional. You need another generic parameter to say what the optional's type is:
class NotNilIterator<T: IteratorProtocol, U>: IteratorProtocol where T.Element == U? {
typealias Element = U
var iterator: T
init(_ source: T) {
iterator = source
}
func next() -> Element? {
// I feel this is clearer what is going on
while true {
switch iterator.next() {
case .some(.none):
continue
case .none:
return nil
case .some(.some(let element)):
return element
}
}
}
}
class NotNilSequence<T: Sequence, U> : Sequence where T.Element == U?
{
let sequence: T
init(_ source : T)
{
sequence = source
}
public func makeIterator() -> NotNilIterator<T.Iterator, U>
{
.init(sequence.makeIterator())
}
}
whereNotNil would then be declared like this:
func whereNotNil<T>() -> NotNilSequence<Self, T> where Self.Element == T?
{
return .init(self)
}
Note the use of self types. The first parameter is the type of the underlying sequence, the second is the non-optional type.
Note that this sort of "lazily computed sequence" is already built into Swift. To lazily filter out the nils, do:
let array = [1, 2, 3, nil, 4]
let arrayWithoutNil = array.lazy.compactMap { $0 }
The downside is that the type names are quite long. arrayWithoutNil is of type
LazyMapSequence<LazyFilterSequence<LazyMapSequence<LazySequence<[Int?]>.Elements, Int?>>, Int>
But you can indeed get non-optional Ints out of it, so it does work.
The way swift generics work can sometimes be very confusing (but has it's advantages). Instead of declaring that a variable is of a generic protocol (resp. a protocol with associated types), you instead declare another generic type which itself conforms to your protocol. Here's your iterator as an example (I have taken the liberty to clean up the code a bit):
public class Not_null_iterator<T, T_iterator> : IteratorProtocol where
T_iterator: IteratorProtocol,
T_iterator.Element == Optional<T>
{
private var source: T_iterator
init(_ source: T_iterator) {
self.source = source
}
public func next() -> T? {
while let next_value = source.next()
{
if let not_null_value = next_value
{
return not_null_value
}
}
return nil
}
}
The non-null sequence works analogous:
public class Not_null_sequence<T, Source>: Sequence where
Source: Sequence,
Source.Element == Optional<T>
{
private var source: Source
init(_ source: Source) {
self.source = source
}
public func makeIterator() -> Not_null_iterator<T, Source.Iterator> {
Not_null_iterator(self.source.makeIterator())
}
}
Using this some IteratorProtocol is just a nice way to let the compiler figure out the type. It is equivalent to saying Not_null_iterator<T, Source.Iterator>
As a (potentially) interesting side-note, to clean up the generic mess even more, you can nest the iterator class inside the Not_null_sequence:
public class Not_null_sequence<T, Source>: Sequence where
Source: Sequence,
Source.Element == Optional<T>
{
private var source: Source
init(_ source: Source) {
self.source = source
}
public func makeIterator() -> Iterator{
Iterator(self.source.makeIterator())
}
public class Iterator: IteratorProtocol {
private var source: Source.Iterator
init(_ source: Source.Iterator) {
self.source = source
}
public func next() -> T? {
while let next_value = source.next()
{
if let not_null_value = next_value
{
return not_null_value
}
}
return nil
}
}
}

Swift how to make a set with multiplicity (multiset)

I am substracting two Array of Integers. I did the substraction using sets :
let numbersA = [1, 2, 3]
let numbersB = [3, 4, 5]
Set(numbersA).subtracting(numbersB)
but I then realized that I have multiplicity in my arrays, and I should take it into account. What is the data structure for multisets in Swift?
In swift 5, there is no Multiset implementation in the core library.
You can reproduce the Multiset behavior by using a dictionary [Element:Multiplicity].
Your code will be:
let numbersA = [1, 2, 3, 3]
let numbersB = [3, 4, 5]
Set(numbersA).subtracting(numbersB) // [1, 2, 3]
As pointed out by Leo Dabus in comment, this gives you an unordered collection as a result.
You can find a good tutorial on multisets at https://github.com/raywenderlich/swift-algorithm-club/tree/master/Multiset
Here is a ready to use implementation of multiset. I added to it the substracting implementation. Notice it can be considered an incomplet implementation of a Multiset since, for exemple, it doesn't extends the Collection protocol.
//
// Multiset.swift
// Multiset
//
// Created by Simon Whitaker on 28/08/2017.
//
// Extended by Jeremy Cochoy on 17/11/2019
import Foundation
public struct Multiset<T: Hashable> {
private var storage: [T: UInt] = [:]
public private(set) var count: UInt = 0
public init() {}
public init<C: Collection>(_ collection: C) where C.Element == T {
for element in collection {
self.add(element)
}
}
public mutating func add (_ elem: T) {
storage[elem, default: 0] += 1
count += 1
}
public mutating func remove (_ elem: T) {
if let currentCount = storage[elem] {
if currentCount > 1 {
storage[elem] = currentCount - 1
} else {
storage.removeValue(forKey: elem)
}
count -= 1
}
}
public func isSubSet (of superset: Multiset<T>) -> Bool {
for (key, count) in storage {
let supersetcount = superset.storage[key] ?? 0
if count > supersetcount {
return false
}
}
return true
}
public func count(for key: T) -> UInt {
return storage[key] ?? 0
}
public var allItems: [T] {
var result = [T]()
for (key, count) in storage {
for _ in 0 ..< count {
result.append(key)
}
}
return result
}
public func subtracting(_ elems: [T]) -> Multiset<T> {
var resultSet = self
elems.forEach { resultSet.remove($0) }
return resultSet
}
}
// MARK: - Equatable
extension Multiset: Equatable {
public static func == (lhs: Multiset<T>, rhs: Multiset<T>) -> Bool {
if lhs.storage.count != rhs.storage.count {
return false
}
for (lkey, lcount) in lhs.storage {
let rcount = rhs.storage[lkey] ?? 0
if lcount != rcount {
return false
}
}
return true
}
}
// MARK: - ExpressibleByArrayLiteral
extension Multiset: ExpressibleByArrayLiteral {
public init(arrayLiteral elements: T...) {
self.init(elements)
}
}
As you say, swift does not have Multiset as a native type.
I implemented a fairly thorough implementation of Multiset in Swift here:
https://github.com/Cortado-J/Multiset
and full documentation of that library with usage examples here:
https://cortado-j.github.io/Multiset/Structs/Multiset.html

Extensions of generic types in Swift 4

I have two protocols and a generic struct:
public protocol OneDimensionalDataPoint {
/// the y value
var y: Double { get }
}
public protocol TwoDimensionalDataPoint: OneDimensionalDataPoint {
/// the x value
var x: Double { get }
}
public struct DataSet<Element: OneDimensionalDataPoint> {
/// the entries that this dataset represents
private var _values: [Element]
//...implementation
}
extension DataSet: MutableCollection {
public typealias Element = OneDimensionalDataPoint
public typealias Index = Int
public var startIndex: Index {
return _values.startIndex
}
public var endIndex: Index {
return _values.endIndex
}
public func index(after: Index) -> Index {
return _values.index(after: after)
}
public subscript(position: Index) -> Element {
get{ return _values[position] }
set{ self._values[position] = newValue }
}
}
There is a large number of methods that apply to DataSet only when it's Element is a TwoDimensionalDataPoint. So I made an extension like so:
extension DataSet where Element: TwoDimensionalDataPoint {
public mutating func calcMinMaxX(entry e: Element) {
if e.x < _xMin {
_xMin = e.x
}
if e.x > _xMax {
_xMax = e.x
}
}
}
The compiler doesn't like this, and says:
Value of type 'DataSet.Element' (aka
'OneDimensionalDataPoint') has no member 'x'
Shouldn't this be fine since I constrained Element to TwoDimensionalDataPoint in the extension?
After I popped it into Xcode I was able to get a better understanding of what was going on,
Your issue is your type alias is overriding your generic type,
Rename your generic name to T and assign Element to T
public typealias Element = T
or your typealias like:
public typealias DataElement = OneDimensionalDataPoint
or just drop the typealias all together.

Adopting CollectionType (Collection) in Swift

I'm writing a graphics library to display data in a graph. Since most of the projects I do tend to have a large learning component in them, I decided to create a generically typed struct to manage my data set DataSet<T: Plottable> (note here that Plottable is also Comparable).
In trying to conform to MutableCollectionType, I've run across an error. I'd like to use the default implementation of sort(), but the compiler is giving the following error when trying to use the sorting function.
Ambiguous reference to member 'sort()'
Here's a code example:
var data = DataSet<Int>(elements: [1,2,3,4])
data.sort() //Ambiguous reference to member 'sort()'
The compiler suggests two candidates, but will not actually display them to me. Note that the compiler error goes away if I explicitly implement sort() on my struct.
But the bigger question remains for me. What am I not seeing that I expect the default implementation to be providing? Or am I running across a bug in Swift 3 (this rarely is the case... usually I have overlooked something).
Here's the balance of the struct:
struct DataSet<T: Plottable>: MutableCollection, BidirectionalCollection {
typealias Element = T
typealias Iterator = DataSetIterator<T>
typealias Index = Int
/**
The list of elements in the data set. Private.
*/
private var elements: [Element] = []
/**
Initalize the data set with an array of data.
*/
init(elements data: [T] = []) {
self.elements = data
}
//MARK: Sequence Protocol
func makeIterator() -> DataSetIterator<T> {
return DataSetIterator(self)
}
//MARK: Collection Protocol
subscript(_ index:DataSet<T>.Index) -> DataSet<T>.Iterator.Element {
set {
elements[index] = newValue
}
get {
return elements[index]
}
}
subscript(_ inRange:Range<DataSet<T>.Index>) -> DataSet<T> {
set {
elements.replaceSubrange(inRange, with: newValue)
}
get {
return DataSet<T>(elements: Array(elements[inRange]))
}
}
//required index for MutableCollection and BidirectionalCollection
var endIndex: Int {
return elements.count
}
var startIndex: Int {
return 0
}
func index(after i: Int) -> Int {
return i+1
}
func index(before i: Int) -> Int {
return i-1
}
mutating func append(_ newElement: T) {
elements.append(newElement)
}
// /**
// Sorts the elements of the DataSet from lowest value to highest value.
// Commented because I'd like to use the default implementation.
// - note: This is equivalent to calling `sort(by: { $0 < $1 })`
// */
// mutating func sort() {
// self.sort(by: { $0 < $1 })
// }
//
// /**
// Sorts the elements of the DataSet by an abritrary block.
// */
// mutating func sort(by areInIncreasingOrder: #noescape (T, T) -> Bool) {
// self.elements = self.elements.sorted(by: areInIncreasingOrder)
// }
/**
Returns a `DataSet<T>` with the elements sorted by a provided block.
This is the default implementation `sort()` modified to return `DataSet<T>` rather than `Array<T>`.
- returns: A sorted `DataSet<T>` by the provided block.
*/
func sorted(by areInIncreasingOrder: #noescape (T, T) -> Bool) -> DataSet<T> {
return DataSet<T>(elements: self.elements.sorted(by: areInIncreasingOrder))
}
func sorted() -> DataSet<T> {
return self.sorted(by: { $0 < $1 })
}
}
Your DataSet is a BidirectionalCollection. The sort() you're trying to use requires a RandomAccessCollection. The most important thing you need to add is an Indicies typealias.
typealias Indices = Array<Element>.Indices
Here's my version of your type:
protocol Plottable: Comparable {}
extension Int: Plottable {}
struct DataSet<Element: Plottable>: MutableCollection, RandomAccessCollection {
private var elements: [Element] = []
typealias Indices = Array<Element>.Indices
init(elements data: [Element] = []) {
self.elements = data
}
var startIndex: Int {
return elements.startIndex
}
var endIndex: Int {
return elements.endIndex
}
func index(after i: Int) -> Int {
return elements.index(after: i)
}
func index(before i: Int) -> Int {
return elements.index(before: i)
}
subscript(position: Int) -> Element {
get {
return elements[position]
}
set {
elements[position] = newValue
}
}
subscript(bounds: Range<Int>) -> DataSet<Element> {
get {
return DataSet(elements: Array(elements[bounds]))
}
set {
elements[bounds] = ArraySlice(newValue.elements)
}
}
}
var data = DataSet(elements: [4,2,3,1])
data.sort()
print(data.elements) // [1,2,3,4]
You don't actually need an Iterator if you don't want one. Swift will give you Sequence automatically if you implement Collection.

Swift subscript with different signature for the getter and setter

Is it possible to have a subscript in Swift that has different signatures for the getter and setter?
For example, I want the getter to return a Set<Int> and the setter to take an Int (not a Set<Int>).
This code won't compile but it gives you an idea of what I'm trying to do:
struct Foo{
subscript(index: Int)->String{
get{
return "bar" // returns a String
}
set(newValue: String?){ // takes a String? instead of a String
print(newValue)
}
}
}
How can I do this?
This is very ugly, and I strongly discourage you from doing so, but technically this is possible:
struct Foo {
subscript(concreteValueFor index: Int) -> String {
return "Get concrete \(index)"
}
subscript(optionalValueFor index: Int) -> String? {
get { return nil }
set { print("Set optional \(index)") }
}
}
var foo = Foo()
foo[concreteValueFor: 1] // Returns "Get concrete 1"
foo[optionalValueFor: 2] = "" // Prints "Set optional 2"
For a multimap some time ago I made something like this:
public struct Multimap<Key: Hashable, Value: Hashable>: CollectionType {
public typealias _Element = Set<Value>
public typealias Element = (Key, _Element)
public typealias Index = DictionaryIndex<Key, _Element>
public typealias Generator = DictionaryGenerator<Key, _Element>
private typealias Storage = [Key: _Element]
private var storage = Storage()
public var startIndex: Index { return storage.startIndex }
public var endIndex: Index { return storage.endIndex }
public subscript(position: Index) -> _Element { return storage[position].1 }
public subscript(position: Index) -> Element { return storage[position] }
subscript(key: Key) -> Set<Value> {
get { return storage[key] ?? Set<Value>() }
set { storage[key] = newValue.isEmpty ? nil : newValue }
}
public func generate() -> Generator { return storage.generate() }
}
Usage:
var foo = Multimap<Int, String>()
foo[0] // Returns an emtpy Set<String>
foo[0].insert("Ook") // Inserts a value at index 0
foo[0].insert("Eek")
foo[0] // Now this returns a set { "Ook", "Eek" }
foo[1].insert("Banana")
foo[1].insert("Book")
foo[0].unionInPlace(foo[1])
foo[0] // Returns a set { "Banana", "Ook", "Eek", "Book" }