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 = #"(?<![\p{L}\p{N}_])gen"#
let regex = try! NSRegularExpression(pattern: pattern, options: .anchorsMatchLines)
let testString = #"""
To achieve this, I am using the regular expression /\bsea/gmi, which works perfectly with English characters. However, it fails to produce the desired results when applied to Swedish characters, like 'ä', 'å', and 'ö'. For example, if the search word is 'gen', the postfix 'gen' in the word 'vägen' is incorrectly highlighted. It seems that the regular expression treats these characters as special characters or something similar. I even tried adding unicode modifier u but that didt't help either.
gen
gena
agen
ägen
genä
"""#
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