Split string by regrex and get matching range

extension String {
	func splitWithRegex(by regexStr: String) -> [String] {
		guard let regex = try? NSRegularExpression(pattern: regexStr) else { return [] }
		let nsRange = NSRange(startIndex..., in: self)
		var index = startIndex
		var array = regex.matches(in: self, range: nsRange)
			.map { match -> String in
				let range = Range(match.range, in: self)!
				let result = self[index..<range.lowerBound]
				index = range.upperBound
				return String(result)
			}
		array.append(String(self[index...]))
		return array
	}
}

I use the above code to split a string on Swift using a regrex pattern and return an array of strings

How can I return an object of [(String, Range)] so I will use the split substrings as keys and it's range as the value.

For example:

let string = "This is a string"
let stringRange = string.splitWithRegex(by: "\\s+")

Result:

(This, 0...4)
(is, 5...7)
(a, 8...9)
(string, 10...16)

I guess that should do the trick, but I'm not totally sure:

func splitWithRegex2(by regexStr: String) -> [(String, Range<String.Index>)] {
    guard let regex = try? NSRegularExpression(pattern: regexStr) else { return [] }
    let nsRange = NSRange(startIndex..., in: self)
    var index = startIndex
    var array = regex.matches(in: self, range: nsRange)
        .compactMap { match -> (String, Range<String.Index>)? in
            guard let range = Range(match.range, in: self) else { return nil }
            let resultRange = index..<range.lowerBound
            let string = String(self[resultRange])
            index = range.upperBound
            guard !resultRange.isEmpty else { return nil } //This should fix the issue where the first match starts your string, in your case, an empty space
            let values = (string, resultRange)
            return values
        }

    //Append last value check: needed?
    if index < endIndex {
        array.append((String(self[index...]), index..<endIndex))
    }
    return array
}

To play:

let stringReg1 = "This  is a string"
let stringRange1 = stringReg1.splitWithRegex2(by: "\\s+")
print(stringRange1)
stringRange1.forEach { //More userfriendly than Range(Swift.String.Index(_rawBits: 65536)..<Swift.String.Index(_rawBits: 327680)))
    let nsRange = NSRange($0.1, in: stringReg1)
    print("\($0.0), \(nsRange.location)...\(nsRange.location + nsRange.length)")
}

Output:

$>[("This", Range(Swift.String.Index(_rawBits: 1)..<Swift.String.Index(_rawBits: 262144))), ("is", Range(Swift.String.Index(_rawBits: 393216)..<Swift.String.Index(_rawBits: 524288))), ("a", Range(Swift.String.Index(_rawBits: 589824)..<Swift.String.Index(_rawBits: 655360))), ("string", Range(Swift.String.Index(_rawBits: 720896)..<Swift.String.Index(_rawBits: 1114113)))]
$>This, 0...4
$>is, 6...8
$>a, 9...10
$>string, 11...17

let stringReg2 = "    This  is a string   "
let stringRange2 = stringReg2.splitWithRegex2(by: "\\s+")
print(stringRange2)
stringRange2.forEach { //More userfriendly than Range(Swift.String.Index(_rawBits: 65536)..<Swift.String.Index(_rawBits: 327680)))
    let nsRange = NSRange($0.1, in: stringReg2)
    print("\($0.0), \(nsRange.location)...\(nsRange.location + nsRange.length)")
}

Output:

$>[("This", Range(Swift.String.Index(_rawBits: 262144)..<Swift.String.Index(_rawBits: 524288))), ("is", Range(Swift.String.Index(_rawBits: 655360)..<Swift.String.Index(_rawBits: 786432))), ("a", Range(Swift.String.Index(_rawBits: 851968)..<Swift.String.Index(_rawBits: 917504))), ("string", Range(Swift.String.Index(_rawBits: 983040)..<Swift.String.Index(_rawBits: 1376256)))]
$>This, 4...8
$>is, 10...12
$>a, 13...14
$>string, 15...21