import Foundation
let pattern = #"\(pp\.\s+\d+(?:[—–-]\d+)?\)|\b\d+(?:[—–-]\d+)?(?=\.)"#
let regex = try! NSRegularExpression(pattern: pattern, options: .anchorsMatchLines)
let testString = #"""
- Mitchell, J.A. (2017). Citation: Why is it so important. Mendeley Journal, 67(2), (pp. 81-95).
- Denhart, H. (2008). Deconstructing barriers: Perceptions of students labeled with learning disabilities in higher education. Journal of Learning Disabilities, 40,41, 483-497.
(pp. 81).
12-12
http://test.com/12-23
Usually the page numbers follow a commas and then there is a dot (like this: , 1-2. ) How can I change the code according to this? Same goes for when there is only one page listed , number. and the ` (pp. 12)` format.
"""#
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