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 = #"""
^
(?:
[ \t]*[(][ \t]*
(\d+)
[ \t]*,[ \t]*
(\d+)
[ \t]*,[ \t]*
(\S+)
[ \t]*[)][ \t]*
)?
$
"""#
let regex = try! NSRegularExpression(pattern: pattern, options: [.anchorsMatchLines, .allowCommentsAndWhitespace])
let testString = #"""
( 0, 12, Tokenization )
( 13 , 15 , is )
( 16, 22, widely)
( 23, 31, regarded )
(32, 34, as )
(35, 36, a)
(37, 43, solved )
(44, 51, problem)
(52, 55, due)
(56, 58, to)
(59, 62, the)
(63, 67, high)
(68, 76, accuracy)
(77, 81, that)
(82, 91, rulebased)
(92, 102, tokenizers)
(103, 110, achieve)
(110, 111, .)
(0, 3, But)
(4, 14, rule-based)
(15, 25, tokenizers)
(26, 29, are)
(30, 34, hard)
(35, 37, to)
(38, 46, maintain)
(47, 50, and)
(51, 56, their)
(57, 62, rules)
(63, 71, language)
(72, 80, specific)
(80, 81, .)
(0, 2, We)
(3, 7, show)
(8, 12, that)
(13, 17, high)
(18, 26, accuracy)
(27, 31, word)
(32, 35, and)
(36, 44, sentence)
(45, 57, segmentation)
(58, 61, can)
(62, 64, be)
(65, 73, achieved)
(74, 76, by)
(77, 82, using)
(83, 93, supervised)
(94, 102, sequence)
(103, 111, labeling)
(112, 114, on)
(115, 118, the)
(119, 128, character)
(129, 134, level)
(135, 143, combined)
(144, 148, with)
(149, 161, unsupervised)
(162, 169, feature)
(170, 178, learning)
(178, 179, .)
(0, 2, We)
(3, 12, evaluated)
(13, 16, our)
(17, 23, method)
(24, 26, on)
(27, 32, three)
(33, 42, languages)
(43, 46, and)
(47, 55, obtained)
(56, 61, error)
(62, 67, rates)
(68, 70, of)
(71, 75, 0.27)
(76, 77, ‰)
(78, 79, ()
(79, 86, English)
(86, 87, ))
(87, 88, ,)
(89, 93, 0.35)
(94, 95, ‰)
(96, 97, ( )
(97, 102, Dutch)
(102, 103, ) )
(104, 107, and)
(108, 112, 0.76)
(113, 114, ‰)
(115, 116, ()
(116, 123, Italian)
(123, 124, ))
(125, 128, for)
(129, 132, our)
(133, 137, best)
(138, 144, models)
(144, 145, .)
"""#
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