Detecting Language

String+LanguageDetector.swift

// The result is not guaranteed to be accurate. Typically, the function requires 200-400 characters to reliably guess the language of a string.
// Reference: [CFStringTokenizerCopyBestStringLanguage(_:_:)](https://developer.apple.com/reference/corefoundation/1542136-cfstringtokenizercopybeststringl)
//
import Foundation

extension String {
    func guessLanguage() -> String {
        let length = self.utf16.count
        let languageCode = CFStringTokenizerCopyBestStringLanguage(self as CFString, CFRange(location: 0, length: length)) as String? ?? ""

        let locale = Locale(identifier: languageCode)
        return locale.localizedString(forLanguageCode: languageCode) ?? "Unknown"
    }
}

let names = ["明日香", "碇真嗣", "綾波零", "拓跋玉兒", "陳靖仇", "于小雪"]

for name in names {
    print("\(name) - \(name.guessLanguage())")
}