基于获得的见解为什么像 ???????????????? 这样的表情符号在 Swift 字符串中的处理方式如此奇怪? https://stackoverflow.com/questions/43618487/why-is-treated-so-strangely-in-swift-strings,一个明智的方法可能是替换 Unicode 标量:
extension String {
func replacingFirstOccurrence(of target: UnicodeScalar, with replacement: UnicodeScalar) -> String {
let uc = self.unicodeScalars
guard let idx = uc.index(of: target) else { return self }
let prefix = uc[uc.startIndex..<idx]
let suffix = uc[uc.index(after: idx) ..< uc.endIndex]
return "\(prefix)\(replacement)\(suffix)"
}
}
Example:
let family1 = "????????????????"
print(family1.characters.map { Array(String($0).unicodeScalars) })
// [["\u{0001F469}", "\u{200D}"], ["\u{0001F469}", "\u{200D}"], ["\u{0001F467}", "\u{200D}"], ["\u{0001F466}"]]
let family2 = family1.replacingFirstOccurrence(of: "????", with: "????")
print(family2) // ????????????????
print(family2.characters.map { Array(String($0).unicodeScalars) })
// [["\u{0001F469}", "\u{200D}"], ["\u{0001F469}", "\u{200D}"], ["\u{0001F466}", "\u{200D}"], ["\u{0001F466}"]]
下面是一个可能的版本,它可以定位并替换任意字符串的 Unicode 标量:
extension String {
func replacingFirstOccurrence(of target: String, with replacement: String) -> String {
let uc = self.unicodeScalars
let tuc = target.unicodeScalars
// Target empty or too long:
if tuc.count == 0 || tuc.count > uc.count {
return self
}
// Current search position:
var pos = uc.startIndex
// Last possible position of `tuc` within `uc`:
let end = uc.index(uc.endIndex, offsetBy: tuc.count - 1)
// Locate first Unicode scalar
while let from = uc[pos..<end].index(of: tuc.first!) {
// Compare all Unicode scalars:
let to = uc.index(from, offsetBy: tuc.count)
if !zip(uc[from..<to], tuc).contains(where: { $0 != $1 }) {
let prefix = uc[uc.startIndex..<from]
let suffix = uc[to ..< uc.endIndex]
return "\(prefix)\(replacement)\(suffix)"
}
// Next search position:
uc.formIndex(after: &pos)
}
// Target not found.
return self
}
}