为 Swift 3 更新
字符串和字符
对于将来访问此问题的几乎每个人，String都会Character为您提供答案。
直接在代码中设置 Unicode 值：
var str: String = "I want to visit 北京, Москва, मुंबई, القاهرة, and 서울시. "
var character: Character = ""
使用十六进制设置值
var str: String = "\u{61}\u{5927}\u{1F34E}\u{3C0}" // a大π
var character: Character = "\u{65}\u{301}" // é = "e" + accent mark
请注意，Swift 字符可以由多个 Unicode 代码点组成，但似乎是单个字符。这称为扩展字素簇。
另请参阅此问题。
转换为 Unicode 值：
str.utf8
str.utf16
str.unicodeScalars // UTF-32
String(character).utf8
String(character).utf16
String(character).unicodeScalars
从 Unicode 十六进制值转换：
let hexValue: UInt32 = 0x1F34E
// convert hex value to UnicodeScalar
guard let scalarValue = UnicodeScalar(hexValue) else {
// early exit if hex does not form a valid unicode value
return
}
// convert UnicodeScalar to String
let myString = String(scalarValue) //
或者：
let hexValue: UInt32 = 0x1F34E
if let scalarValue = UnicodeScalar(hexValue) {
let myString = String(scalarValue)
}
再举几个例子
let value0: UInt8 = 0x61
let value1: UInt16 = 0x5927
let value2: UInt32 = 0x1F34E
let string0 = String(UnicodeScalar(value0)) // a
let string1 = String(UnicodeScalar(value1)) // 大
let string2 = String(UnicodeScalar(value2)) //
// convert hex array to String
let myHexArray = [0x43, 0x61, 0x74, 0x203C, 0x1F431] // an Int array
var myString = ""
for hexValue in myHexArray {
myString.append(UnicodeScalar(hexValue))
}
print(myString) // Cat‼
请注意，对于 UTF-8 和 UTF-16，转换并不总是那么容易。（请参阅UTF-8、UTF-16和UTF-32问题。）
NSString 和 unichar
也可以使用SwiftNSString和unichar在 Swift 中工作，但您应该意识到，除非您熟悉 Objective C 并且擅长将语法转换为 Swift，否则很难找到好的文档。
此外，unichar它是一个UInt16数组，如上所述，从UInt16Unicode 标量值转换并不总是那么容易（即，为上层代码平面中的表情符号和其他字符转换代理对）。
自定义字符串结构
由于问题中提到的原因，我最终没有使用上述任何方法。相反，我编写了自己的字符串结构，它基本上是一个UInt32保存 Unicode 标量值的数组。
同样，这不是大多数人的解决方案。如果您只需要扩展或一点点的功能，首先考虑使用扩展。StringCharacter
但是如果你真的需要专门使用 Unicode 标量值，你可以编写一个自定义结构。
优点是：
- 进行字符串操作时，不需要在类型（
String、Character、UnicodeScalar、UInt32等）之间不断切换。
- Unicode 操作完成后，最后的转换
String就很容易了。
- 在需要时轻松添加更多方法
- 简化从 Java 或其他语言转换代码
缺点是：
- 使其他 Swift 开发人员的代码可移植性和可读性降低
- 不如原生 Swift 类型经过测试和优化
- 它是另一个文件，每次需要时都必须包含在项目中
你可以自己做，但这里是我的参考。最难的部分是让它成为 Hashable。
// This struct is an array of UInt32 to hold Unicode scalar values
// Version 3.4.0 (Swift 3 update)
struct ScalarString: Sequence, Hashable, CustomStringConvertible {
fileprivate var scalarArray: [UInt32] = []
init() {
// does anything need to go here?
}
init(_ character: UInt32) {
self.scalarArray.append(character)
}
init(_ charArray: [UInt32]) {
for c in charArray {
self.scalarArray.append(c)
}
}
init(_ string: String) {
for s in string.unicodeScalars {
self.scalarArray.append(s.value)
}
}
// Generator in order to conform to SequenceType protocol
// (to allow users to iterate as in `for myScalarValue in myScalarString` { ... })
func makeIterator() -> AnyIterator<UInt32> {
return AnyIterator(scalarArray.makeIterator())
}
// append
mutating func append(_ scalar: UInt32) {
self.scalarArray.append(scalar)
}
mutating func append(_ scalarString: ScalarString) {
for scalar in scalarString {
self.scalarArray.append(scalar)
}
}
mutating func append(_ string: String) {
for s in string.unicodeScalars {
self.scalarArray.append(s.value)
}
}
// charAt
func charAt(_ index: Int) -> UInt32 {
return self.scalarArray[index]
}
// clear
mutating func clear() {
self.scalarArray.removeAll(keepingCapacity: true)
}
// contains
func contains(_ character: UInt32) -> Bool {
for scalar in self.scalarArray {
if scalar == character {
return true
}
}
return false
}
// description (to implement Printable protocol)
var description: String {
return self.toString()
}
// endsWith
func endsWith() -> UInt32? {
return self.scalarArray.last
}
// indexOf
// returns first index of scalar string match
func indexOf(_ string: ScalarString) -> Int? {
if scalarArray.count < string.length {
return nil
}
for i in 0...(scalarArray.count - string.length) {
for j in 0..<string.length {
if string.charAt(j) != scalarArray[i + j] {
break // substring mismatch
}
if j == string.length - 1 {
return i
}
}
}
return nil
}
// insert
mutating func insert(_ scalar: UInt32, atIndex index: Int) {
self.scalarArray.insert(scalar, at: index)
}
mutating func insert(_ string: ScalarString, atIndex index: Int) {
var newIndex = index
for scalar in string {
self.scalarArray.insert(scalar, at: newIndex)
newIndex += 1
}
}
mutating func insert(_ string: String, atIndex index: Int) {
var newIndex = index
for scalar in string.unicodeScalars {
self.scalarArray.insert(scalar.value, at: newIndex)
newIndex += 1
}
}
// isEmpty
var isEmpty: Bool {
return self.scalarArray.count == 0
}
// hashValue (to implement Hashable protocol)
var hashValue: Int {
// DJB Hash Function
return self.scalarArray.reduce(5381) {
($0 << 5) &+ $0 &+ Int($1)
}
}
// length
var length: Int {
return self.scalarArray.count
}
// remove character
mutating func removeCharAt(_ index: Int) {
self.scalarArray.remove(at: index)
}
func removingAllInstancesOfChar(_ character: UInt32) -> ScalarString {
var returnString = ScalarString()
for scalar in self.scalarArray {
if scalar != character {
returnString.append(scalar)
}
}
return returnString
}
func removeRange(_ range: CountableRange<Int>) -> ScalarString? {
if range.lowerBound < 0 || range.upperBound > scalarArray.count {
return nil
}
var returnString = ScalarString()
for i in 0..<scalarArray.count {
if i < range.lowerBound || i >= range.upperBound {
returnString.append(scalarArray[i])
}
}
return returnString
}
// replace
func replace(_ character: UInt32, withChar replacementChar: UInt32) -> ScalarString {
var returnString = ScalarString()
for scalar in self.scalarArray {
if scalar == character {
returnString.append(replacementChar)
} else {
returnString.append(scalar)
}
}
return returnString
}
func replace(_ character: UInt32, withString replacementString: String) -> ScalarString {
var returnString = ScalarString()
for scalar in self.scalarArray {
if scalar == character {
returnString.append(replacementString)
} else {
returnString.append(scalar)
}
}
return returnString
}
func replaceRange(_ range: CountableRange<Int>, withString replacementString: ScalarString) -> ScalarString {
var returnString = ScalarString()
for i in 0..<scalarArray.count {
if i < range.lowerBound || i >= range.upperBound {
returnString.append(scalarArray[i])
} else if i == range.lowerBound {
returnString.append(replacementString)
}
}
return returnString
}
// set (an alternative to myScalarString = "some string")
mutating func set(_ string: String) {
self.scalarArray.removeAll(keepingCapacity: false)
for s in string.unicodeScalars {
self.scalarArray.append(s.value)
}
}
// split
func split(atChar splitChar: UInt32) -> [ScalarString] {
var partsArray: [ScalarString] = []
if self.scalarArray.count == 0 {
return partsArray
}
var part: ScalarString = ScalarString()
for scalar in self.scalarArray {
if scalar == splitChar {
partsArray.append(part)
part = ScalarString()
} else {
part.append(scalar)
}
}
partsArray.append(part)
return partsArray
}
// startsWith
func startsWith() -> UInt32? {
return self.scalarArray.first
}
// substring
func substring(_ startIndex: Int) -> ScalarString {
// from startIndex to end of string
var subArray: ScalarString = ScalarString()
for i in startIndex..<self.length {
subArray.append(self.scalarArray[i])
}
return subArray
}
func substring(_ startIndex: Int, _ endIndex: Int) -> ScalarString {
// (startIndex is inclusive, endIndex is exclusive)
var subArray: ScalarString = ScalarString()
for i in startIndex..<endIndex {
subArray.append(self.scalarArray[i])
}
return subArray
}
// toString
func toString() -> String {
var string: String = ""
for scalar in self.scalarArray {
if let validScalor = UnicodeScalar(scalar) {
string.append(Character(validScalor))
}
}
return string
}
// trim
// removes leading and trailing whitespace (space, tab, newline)
func trim() -> ScalarString {
//var returnString = ScalarString()
let space: UInt32 = 0x00000020
let tab: UInt32 = 0x00000009
let newline: UInt32 = 0x0000000A
var startIndex = self.scalarArray.count
var endIndex = 0
// leading whitespace
for i in 0..<self.scalarArray.count {
if self.scalarArray[i] != space &&
self.scalarArray[i] != tab &&
self.scalarArray[i] != newline {
startIndex = i
break
}
}
// trailing whitespace
for i in stride(from: (self.scalarArray.count - 1), through: 0, by: -1) {
if self.scalarArray[i] != space &&
self.scalarArray[i] != tab &&
self.scalarArray[i] != newline {
endIndex = i + 1
break
}
}
if endIndex <= startIndex {
return ScalarString()
}
return self.substring(startIndex, endIndex)
}
// values
func values() -> [UInt32] {
return self.scalarArray
}
}
func ==(left: ScalarString, right: ScalarString) -> Bool {
return left.scalarArray == right.scalarArray
}
func +(left: ScalarString, right: ScalarString) -> ScalarString {
var returnString = ScalarString()
for scalar in left.values() {
returnString.append(scalar)
}
for scalar in right.values() {
returnString.append(scalar)
}
return returnString
}
