I want to extract substrings from a string that match a regex pattern.
So I'm looking for something like this:
func matchesForRegexInText(regex: String!, text: String!) -> [String] {
???
}
So this is what I have:
func matchesForRegexInText(regex: String!, text: String!) -> [String] {
var regex = NSRegularExpression(pattern: regex,
options: nil, error: nil)
var results = regex.matchesInString(text,
options: nil, range: NSMakeRange(0, countElements(text)))
as Array<NSTextCheckingResult>
/// ???
return ...
}
The problem is, that matchesInString delivers me an array of NSTextCheckingResult, where NSTextCheckingResult.range is of type NSRange.
NSRange is incompatible with Range<String.Index>, so it prevents me of using text.substringWithRange(...)
Any idea how to achieve this simple thing in swift without too many lines of code?
Even if the matchesInString() method takes a String as the first argument,
it works internally with NSString, and the range parameter must be given
using the NSString length and not as the Swift string length. Otherwise it will
fail for "extended grapheme clusters" such as "flags".
As of Swift 4 (Xcode 9), the Swift standard
library provides functions to convert between Range<String.Index>
and NSRange.
func matches(for regex: String, in text: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: regex)
let results = regex.matches(in: text,
range: NSRange(text.startIndex..., in: text))
return results.map {
String(text[Range($0.range, in: text)!])
}
} catch let error {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
Example:
let string = "🇩🇪€4€9"
let matched = matches(for: "[0-9]", in: string)
print(matched)
// ["4", "9"]
Note: The forced unwrap Range($0.range, in: text)! is safe because
the NSRange refers to a substring of the given string text.
However, if you want to avoid it then use
return results.flatMap {
Range($0.range, in: text).map { String(text[$0]) }
}
instead.
(Older answer for Swift 3 and earlier:)
So you should convert the given Swift string to an NSString and then extract the
ranges. The result will be converted to a Swift string array automatically.
(The code for Swift 1.2 can be found in the edit history.)
Swift 2 (Xcode 7.3.1) :
func matchesForRegexInText(regex: String, text: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: regex, options: [])
let nsString = text as NSString
let results = regex.matchesInString(text,
options: [], range: NSMakeRange(0, nsString.length))
return results.map { nsString.substringWithRange($0.range)}
} catch let error as NSError {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
Example:
let string = "🇩🇪€4€9"
let matches = matchesForRegexInText("[0-9]", text: string)
print(matches)
// ["4", "9"]
Swift 3 (Xcode 8)
func matches(for regex: String, in text: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: regex)
let nsString = text as NSString
let results = regex.matches(in: text, range: NSRange(location: 0, length: nsString.length))
return results.map { nsString.substring(with: $0.range)}
} catch let error {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
Example:
let string = "🇩🇪€4€9"
let matched = matches(for: "[0-9]", in: string)
print(matched)
// ["4", "9"]
My answer builds on top of given answers but makes regex matching more robust by adding additional support:
Returns not only matches but returns also all capturing groups for each match (see examples below)
Instead of returning an empty array, this solution supports optional matches
Avoids do/catch by not printing to the console and makes use of the guard construct
Adds matchingStrings as an extension to String
Swift 4.2
//: Playground - noun: a place where people can play
import Foundation
extension String {
func matchingStrings(regex: String) -> [[String]] {
guard let regex = try? NSRegularExpression(pattern: regex, options: []) else { return [] }
let nsString = self as NSString
let results = regex.matches(in: self, options: [], range: NSMakeRange(0, nsString.length))
return results.map { result in
(0..<result.numberOfRanges).map {
result.range(at: $0).location != NSNotFound
? nsString.substring(with: result.range(at: $0))
: ""
}
}
}
}
"prefix12 aaa3 prefix45".matchingStrings(regex: "fix([0-9])([0-9])")
// Prints: [["fix12", "1", "2"], ["fix45", "4", "5"]]
"prefix12".matchingStrings(regex: "(?:prefix)?([0-9]+)")
// Prints: [["prefix12", "12"]]
"12".matchingStrings(regex: "(?:prefix)?([0-9]+)")
// Prints: [["12", "12"]], other answers return an empty array here
// Safely accessing the capture of the first match (if any):
let number = "prefix12suffix".matchingStrings(regex: "fix([0-9]+)su").first?[1]
// Prints: Optional("12")
Swift 3
//: Playground - noun: a place where people can play
import Foundation
extension String {
func matchingStrings(regex: String) -> [[String]] {
guard let regex = try? NSRegularExpression(pattern: regex, options: []) else { return [] }
let nsString = self as NSString
let results = regex.matches(in: self, options: [], range: NSMakeRange(0, nsString.length))
return results.map { result in
(0..<result.numberOfRanges).map {
result.rangeAt($0).location != NSNotFound
? nsString.substring(with: result.rangeAt($0))
: ""
}
}
}
}
"prefix12 aaa3 prefix45".matchingStrings(regex: "fix([0-9])([0-9])")
// Prints: [["fix12", "1", "2"], ["fix45", "4", "5"]]
"prefix12".matchingStrings(regex: "(?:prefix)?([0-9]+)")
// Prints: [["prefix12", "12"]]
"12".matchingStrings(regex: "(?:prefix)?([0-9]+)")
// Prints: [["12", "12"]], other answers return an empty array here
// Safely accessing the capture of the first match (if any):
let number = "prefix12suffix".matchingStrings(regex: "fix([0-9]+)su").first?[1]
// Prints: Optional("12")
Swift 2
extension String {
func matchingStrings(regex: String) -> [[String]] {
guard let regex = try? NSRegularExpression(pattern: regex, options: []) else { return [] }
let nsString = self as NSString
let results = regex.matchesInString(self, options: [], range: NSMakeRange(0, nsString.length))
return results.map { result in
(0..<result.numberOfRanges).map {
result.rangeAtIndex($0).location != NSNotFound
? nsString.substringWithRange(result.rangeAtIndex($0))
: ""
}
}
}
}
The fastest way to return all matches and capture groups in Swift 5
extension String {
func match(_ regex: String) -> [[String]] {
let nsString = self as NSString
return (try? NSRegularExpression(pattern: regex, options: []))?.matches(in: self, options: [], range: NSMakeRange(0, nsString.length)).map { match in
(0..<match.numberOfRanges).map { match.range(at: $0).location == NSNotFound ? "" : nsString.substring(with: match.range(at: $0)) }
} ?? []
}
}
Returns a 2-dimentional array of strings:
"prefix12suffix fix1su".match("fix([0-9]+)su")
returns...
[["fix12su", "12"], ["fix1su", "1"]]
// First element of sub-array is the match
// All subsequent elements are the capture groups
If you want to extract substrings from a String, not just the position, (but the actual String including emojis). Then, the following maybe a simpler solution.
extension String {
func regex (pattern: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: pattern, options: NSRegularExpressionOptions(rawValue: 0))
let nsstr = self as NSString
let all = NSRange(location: 0, length: nsstr.length)
var matches : [String] = [String]()
regex.enumerateMatchesInString(self, options: NSMatchingOptions(rawValue: 0), range: all) {
(result : NSTextCheckingResult?, _, _) in
if let r = result {
let result = nsstr.substringWithRange(r.range) as String
matches.append(result)
}
}
return matches
} catch {
return [String]()
}
}
}
Example Usage:
"someText 👿🏅👿⚽️ pig".regex("👿⚽️")
Will return the following:
["👿⚽️"]
Note using "\w+" may produce an unexpected ""
"someText 👿🏅👿⚽️ pig".regex("\\w+")
Will return this String array
["someText", "️", "pig"]
I found that the accepted answer's solution unfortunately does not compile on Swift 3 for Linux. Here's a modified version, then, that does:
import Foundation
func matches(for regex: String, in text: String) -> [String] {
do {
let regex = try RegularExpression(pattern: regex, options: [])
let nsString = NSString(string: text)
let results = regex.matches(in: text, options: [], range: NSRange(location: 0, length: nsString.length))
return results.map { nsString.substring(with: $0.range) }
} catch let error {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
The main differences are:
Swift on Linux seems to require dropping the NS prefix on Foundation objects for which there is no Swift-native equivalent. (See Swift evolution proposal #86.)
Swift on Linux also requires specifying the options arguments for both the RegularExpression initialization and the matches method.
For some reason, coercing a String into an NSString doesn't work in Swift on Linux but initializing a new NSString with a String as the source does work.
This version also works with Swift 3 on macOS / Xcode with the sole exception that you must use the name NSRegularExpression instead of RegularExpression.
Swift 4 without NSString.
extension String {
func matches(regex: String) -> [String] {
guard let regex = try? NSRegularExpression(pattern: regex, options: [.caseInsensitive]) else { return [] }
let matches = regex.matches(in: self, options: [], range: NSMakeRange(0, self.count))
return matches.map { match in
return String(self[Range(match.range, in: self)!])
}
}
}
#p4bloch if you want to capture results from a series of capture parentheses, then you need to use the rangeAtIndex(index) method of NSTextCheckingResult, instead of range. Here's #MartinR 's method for Swift2 from above, adapted for capture parentheses. In the array that is returned, the first result [0] is the entire capture, and then individual capture groups begin from [1]. I commented out the map operation (so it's easier to see what I changed) and replaced it with nested loops.
func matches(for regex: String!, in text: String!) -> [String] {
do {
let regex = try NSRegularExpression(pattern: regex, options: [])
let nsString = text as NSString
let results = regex.matchesInString(text, options: [], range: NSMakeRange(0, nsString.length))
var match = [String]()
for result in results {
for i in 0..<result.numberOfRanges {
match.append(nsString.substringWithRange( result.rangeAtIndex(i) ))
}
}
return match
//return results.map { nsString.substringWithRange( $0.range )} //rangeAtIndex(0)
} catch let error as NSError {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
An example use case might be, say you want to split a string of title year eg "Finding Dory 2016" you could do this:
print ( matches(for: "^(.+)\\s(\\d{4})" , in: "Finding Dory 2016"))
// ["Finding Dory 2016", "Finding Dory", "2016"]
Most of the solutions above only give the full match as a result ignoring the capture groups e.g.: ^\d+\s+(\d+)
To get the capture group matches as expected you need something like (Swift4) :
public extension String {
public func capturedGroups(withRegex pattern: String) -> [String] {
var results = [String]()
var regex: NSRegularExpression
do {
regex = try NSRegularExpression(pattern: pattern, options: [])
} catch {
return results
}
let matches = regex.matches(in: self, options: [], range: NSRange(location:0, length: self.count))
guard let match = matches.first else { return results }
let lastRangeIndex = match.numberOfRanges - 1
guard lastRangeIndex >= 1 else { return results }
for i in 1...lastRangeIndex {
let capturedGroupIndex = match.range(at: i)
let matchedString = (self as NSString).substring(with: capturedGroupIndex)
results.append(matchedString)
}
return results
}
}
Update for iOS 16: Regex, RegexBuilder 👷♀️
Xcode previously supported Regex with the Find and Search tab. Many found Apple's NSRegularExpressions Swift API verbose and unwieldy, so Apple released Regex literal support and RegexBuilder this year.
The API has been simplified going forward to tidy up complex String range-based parsing logic in iOS 16 / macOS 13 as well as improve performance.
RegEx literals in Swift 5.7
func parseLine(_ line: Substring) throws -> MailmapEntry {
let regex = /\h*([^<#]+?)??\h*<([^>#]+)>\h*(?:#|\Z)/
guard let match = line.prefixMatch(of: regex) else {
throw MailmapError.badLine
}
return MailmapEntry(name: match.1, email: match.2)
}
At the moment, we are able to match using prefixMatch or wholeMatch to find a single match, but the API may improve in the future for multiple matches.
RegexBuilder in Swift 5.7
RegexBuilder is a new API released by Apple aimed at making RegEx code easier to write in Swift. We can translate the Regex literal /\h*([^<#]+?)??\h*<([^>#]+)>\h*(?:#|\Z)/ from above into a more declarative form using RegexBuilder if we want more readability.
Do note that we can use raw strings in a RegexBuilder and also interleave Regex Literals in the builder if we want to balance readability with conciseness.
import RegexBuilder
let regex = Regex {
ZeroOrMore(.horizontalWhitespace)
Optionally {
Capture(OneOrMore(.noneOf("<#")))
}
.repetitionBehavior(.reluctant)
ZeroOrMore(.horizontalWhitespace)
"<"
Capture(OneOrMore(.noneOf(">#")))
">"
ZeroOrMore(.horizontalWhitespace)
/#|\Z/
}
The RegEx literal /£|\Z/ is equivalent to:
ChoiceOf {
"#"
Anchor.endOfSubjectBeforeNewline
}
Composable RegexComponent
RegexBuilder syntax is similar to SwiftUI also in terms of composability because we can reuse RegexComponents within other RegexComponents:
struct MailmapLine: RegexComponent {
#RegexComponentBuilder
var regex: Regex<(Substring, Substring?, Substring)> {
ZeroOrMore(.horizontalWhitespace)
Optionally {
Capture(OneOrMore(.noneOf("<#")))
}
.repetitionBehavior(.reluctant)
ZeroOrMore(.horizontalWhitespace)
"<"
Capture(OneOrMore(.noneOf(">#")))
">"
ZeroOrMore(.horizontalWhitespace)
ChoiceOf {
"#"
Anchor.endOfSubjectBeforeNewline
}
}
}
This is how I did it, I hope it brings a new perspective how this works on Swift.
In this example below I will get the any string between []
var sample = "this is an [hello] amazing [world]"
var regex = NSRegularExpression(pattern: "\\[.+?\\]"
, options: NSRegularExpressionOptions.CaseInsensitive
, error: nil)
var matches = regex?.matchesInString(sample, options: nil
, range: NSMakeRange(0, countElements(sample))) as Array<NSTextCheckingResult>
for match in matches {
let r = (sample as NSString).substringWithRange(match.range)//cast to NSString is required to match range format.
println("found= \(r)")
}
This is a very simple solution that returns an array of string with the matches
Swift 3.
internal func stringsMatching(regularExpressionPattern: String, options: NSRegularExpression.Options = []) -> [String] {
guard let regex = try? NSRegularExpression(pattern: regularExpressionPattern, options: options) else {
return []
}
let nsString = self as NSString
let results = regex.matches(in: self, options: [], range: NSMakeRange(0, nsString.length))
return results.map {
nsString.substring(with: $0.range)
}
}
update #Mike Chirico's to Swift 5
extension String{
func regex(pattern: String) -> [String]?{
do {
let regex = try NSRegularExpression(pattern: pattern, options: NSRegularExpression.Options(rawValue: 0))
let all = NSRange(location: 0, length: count)
var matches = [String]()
regex.enumerateMatches(in: self, options: NSRegularExpression.MatchingOptions(rawValue: 0), range: all) {
(result : NSTextCheckingResult?, _, _) in
if let r = result {
let nsstr = self as NSString
let result = nsstr.substring(with: r.range) as String
matches.append(result)
}
}
return matches
} catch {
return nil
}
}
}
basic phone number matching
let phoneNumbers = ["+79990001101", "+7 (800) 000-11-02", "+34 507 574 147 ", "+1-202-555-0118"]
let match: (String) -> String = {
$0.replacingOccurrences(of: #"[^\d+]"#, with: "", options: .regularExpression)
}
print(phoneNumbers.map(match))
// ["+79990001101", "+78000001102", "+34507574147", "+12025550118"]
Big thanks to Lars Blumberg his answer for capturing groups and full matches with Swift 4, which helped me out a lot. I also made an addition to it for the people who do want an error.localizedDescription response when their regex is invalid:
extension String {
func matchingStrings(regex: String) -> [[String]] {
do {
let regex = try NSRegularExpression(pattern: regex)
let nsString = self as NSString
let results = regex.matches(in: self, options: [], range: NSMakeRange(0, nsString.length))
return results.map { result in
(0..<result.numberOfRanges).map {
result.range(at: $0).location != NSNotFound
? nsString.substring(with: result.range(at: $0))
: ""
}
}
} catch let error {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
}
For me having the localizedDescription as error helped understand what went wrong with escaping, since it's displays which final regex swift tries to implement.
You can use matching(regex:) on the string like:
let array = try "Your String To Search".matching(regex: ".")
using this simple extension:
public extension String {
func matching(regex: String) throws -> [String] {
let regex = try NSRegularExpression(pattern: regex)
let results = regex.matches(in: self, range: NSRange(startIndex..., in: self))
return results.map { String(self[Range($0.range, in: self)!]) }
}
}
My app supports 5 languages. I have a string which has some double quotes in it. This string is translated into 5 languages in the localizable.strings files.
Example:
title_identifier = "Hi \"how\", are \"you\"";
I would like to bold out "how" and "you" in this string by finding the range of these words. So I am trying to fetch these quoted words out of the string and the result would be an array containing "how" and "you" or their range.
func matches(for regex: String, in text: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: regex)
let results = regex.matches(in: text,
range: NSRange(text.startIndex..., in: text))
return results.map {
String(text[Range($0.range, in: text)!])
}
} catch let error {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
matches(for: "(?<=\")[^\"]*(?=\")", in: str)
The result is: ["how", ", are ", "you"] rather than ["how","you"]. I think this regex needs some addition to allow it to search for next quote once two quotes are found, so to avoid the words in between quotes.
Your problem is in the use of lookarounds that do not consume text but check if their patterns match and return either true or false. See your regex in action, the , are matches because the last " in the previous match was not consumed, the regex index remained right after w, so the next match could start with ". You need to use a consuming pattern here, "([^"]*)".
However, your code will only return full matches. You can just trim the first and last "s here with .map {$0.trimmingCharacters(in: ["\""])}, as the regex only matches one quote at the start and end:
matches(for: "\"[^\"]*\"", in: str).map {$0.trimmingCharacters(in: ["\""])}
Here is the regex demo.
Alternatively, access Group 1 value by appending (at: 1) after $0.range:
func matches(for regex: String, in text: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: regex)
let results = regex.matches(in: text,
range: NSRange(text.startIndex..., in: text))
return results.map {
String(text[Range($0.range(at: 1), in: text)!])
}
} catch let error {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
let str = "Hi \"how\", are \"you\""
print(matches(for: "\"([^\"]*)\"", in: str))
// => ["how", "you"]
I'm trying to create an internal function for the String class to get only AlphaNumeric characters and return a string. I'm running into a few errors with how to convert the matches back into a string using Regex. Can someone tell me how to fix the code or if there's an easier way?
I want something like this
let testString = "_<$abc$>_"
let alphaNumericString = testString.alphaNumeric() //abc
So far I have:
extension String {
internal func alphaNumeric() -> String {
let regex = try? NSRegularExpression(pattern: "[^a-z0-9]", options: .caseInsensitive)
let string = self as NSString
let results = regex?.matches(in: self, options: [], range: NSRange(location: 0, length: string.length))
let matches = results.map {
String(self[Range($0.range, in: self)!])
}
return matches.join()
}
}
You may directly use replacingOccurrences (that removes all non-overlapping matches from the input string) with [^A-Za-z0-9]+ pattern:
let str = "_<$abc$>_"
let pattern = "[^A-Za-z0-9]+"
let result = str.replacingOccurrences(of: pattern, with: "", options: [.regularExpression])
print(result) // => abc
The [^A-Za-z0-9]+ pattern is a negated character class that matches any char but the ones defined in the class, one or more occurrences (due to + quantifier).
See the regex demo.
Try below extension:
extension String {
var alphanumeric: String {
return self.components(separatedBy: CharacterSet.alphanumerics.inverted).joined().lowercased()
}
}
Usage: print("alphanumeric :", "_<$abc$>_".alphanumeric)
Output : abc
You can also use characterset for this like
extension String {
var alphaNumeric: String {
components(separatedBy: CharacterSet.alphanumerics.inverted).joined()
}
}