Last active
June 15, 2023 16:45
-
-
Save frankrausch/0d2c91fad5e417a84aaa43bfb9c9aec8 to your computer and use it in GitHub Desktop.
Returns a String with soft hyphens (U+00AD)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import Foundation | |
extension String { | |
func hyphenated(languageCode: String) -> String { | |
let locale = Locale(identifier: languageCode) | |
return self.hyphenated(locale: locale) | |
} | |
func hyphenated(locale: Locale) -> String { | |
guard CFStringIsHyphenationAvailableForLocale(locale as CFLocale) else { return self } | |
var s = self | |
let fullRange = CFRangeMake(0, s.utf16.count) | |
var hyphenationLocations = [CFIndex]() | |
for (i, _) in s.utf16.enumerated() { | |
let location: CFIndex = CFStringGetHyphenationLocationBeforeIndex(s as CFString, i, fullRange, 0, locale as CFLocale, nil) | |
if hyphenationLocations.last != location { | |
hyphenationLocations.append(location) | |
} | |
} | |
for l in hyphenationLocations.reversed() { | |
guard l > 0 else { continue } | |
let strIndex = String.UTF16View.Index(encodedOffset: l) | |
// insert soft hyphen: | |
s.insert("\u{00AD}", at: strIndex) | |
// or insert a regular hyphen to debug: | |
// s.insert("-", at: strIndex) | |
} | |
return s | |
} | |
} | |
// print(""" | |
// Here’s to the crazy ones, the misfits, the rebels, the troublemakers, the round pegs in the square holes…the ones who see things differently—they’re not fond of rules…You can quote them, disagree with them, glorify or vilify them, but the only thing you can’t do is ignore them because they change things…they push the human race forward, and while some may see them as the crazy ones, we see genius, because the ones who are crazy enough to think that they can change the world, are the ones who do. | |
// """.hyphenated(languageCode: "en")) | |
String.UTF16View.Index(encodedOffset: l) is deprecated in Swift 5
use let strIndex = String.Index(utf16Offset: l, in: s) instead
A one-pass solution for Swift 4.2
On iOS 12.2 the previous solution made some accented characters appear really awful.
`
import Foundation
extension String {
func hungarianHyphenated() -> String {
return hyphenated(locale: Locale(identifier: "hu_HU"))
}
func hyphenated(languageCode: String) -> String {
let locale = Locale(identifier: languageCode)
return self.hyphenated(locale: locale)
}
func hyphenated(locale: Locale) -> String {
guard CFStringIsHyphenationAvailableForLocale(locale as CFLocale) else { return self }
var s = self
let fullRange = CFRangeMake(0, s.utf16.count)
var hyphenationLocations = [CFIndex]()
for i in s.utf16.indices.reversed() {
let location: CFIndex = CFStringGetHyphenationLocationBeforeIndex(s as CFString, i.utf16Offset(in: self), fullRange, 0, locale as CFLocale, nil)
if location < 0 {
return s
}
if hyphenationLocations.last != location {
hyphenationLocations.append(location)
let strIndex = String.Index(utf16Offset: location, in: s)
s.insert("\u{00AD}", at: strIndex)
}
}
return s
}
}
`
Any idea how to make this work with words like "lady" and "project"? They both have 2 syllables but this solution does not seem to recognize that.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Loosely based on this Objective-C implementation: https://stackoverflow.com/a/19858601