import Foundation
// WARNING: You included a flag that Swift doesn't support: u
// When this flag is set, it makes the pattern and subject strings to be treated as unicode.
// Swift already treats the pattern and subject strings as unicode by default, so including this flag is redundant.
let pattern = ##"(?:([-‐‑‒–—―−⁃﹘﹣-])|(?:&(?:(?:#x(2d|201[0-5]|2212|2043|fe58|fe63|ff0d))|(?:#(45|820[89]|821[0123]|8722|8259|65112|65123|65293))|(hyphen|[nm]?dash|hybull|horbar|minus));?))"##
let regex = try! NSRegularExpression(pattern: pattern, options: .anchorsMatchLines)
let testString = ##"""
This captures an entity even if it lacks the ';', which is commonly encountered in the wild.
kbdash - - - - -; -
dash ‐ ‐ ‐ ‐ ‐ ‐; ‐
hyphen ‑ ‐ ‑ ‑ ‑ ‑; ‑
figure ‒ ‒ ‒ ‒ ‒; ‒
em – – – – – –; –
en — — — — — —; —
horbar ― ― ― ― ― ―; ―
minus − − − − − −; −
hybull ⁃ ⁃ ⁃ ⁃ ⁃ ⁃; ⁃
fe58 ﹘ ﹘ ﹘ ﹘ ﹘; ﹘
fe63 ﹣ ﹣ ﹣ ﹣ ﹣; ﹣
ff0d - - - - -; -
(?:([-‐‑‒–—―−⁃﹘﹣-])|(?:&(?:(?:#x(2d|201[0-5]|2212|2043|fe58|fe63|ff0d))|(?:#(45|820[89]|821[0123]|8722|8259|65112|65123|65293))|(hyphen|[nm]?dash|hybull|horbar|minus));?))
"""##
let stringRange = NSRange(location: 0, length: testString.utf16.count)
let matches = regex.matches(in: testString, range: stringRange)
var result: [[String]] = []
for match in matches {
var groups: [String] = []
for rangeIndex in 1 ..< match.numberOfRanges {
let nsRange = match.range(at: rangeIndex)
guard !NSEqualRanges(nsRange, NSMakeRange(NSNotFound, 0)) else { continue }
let string = (testString as NSString).substring(with: nsRange)
groups.append(string)
}
if !groups.isEmpty {
result.append(groups)
}
}
print(result)
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Swift 5.2, please visit: https://developer.apple.com/documentation/foundation/nsregularexpression