Swift

Regular Expression with Capture Groups

See more Regular Expressions Examples

Note: Chilkat uses PCRE2. See PCRE2 Regular Expressions
Also see: PCRE2 Performance

Demonstrates the following PCRE2 regular expression:

See the sample code below.

Name:\s+(\w+)\s+(\w+),\s+Email:\s+(\S+)

And apply it to this string:

Name: John Smith, Email: john.smith@example.com

---

Regex Components Explained

Part	Meaning	Matched Text
"Name:"	Matches the literal text "Name:"	"Name:"
"\s+"	Matches one or more whitespace characters (spaces, tabs, etc.)	(space)
"(\w+)"	Capture Group 1: One or more word characters ("a-zA-Z0-9_")	"John"
"\s+"	More whitespace	(space)
"(\w+)"	Capture Group 2: Another word (the last name)	"Smith"
","	A literal comma	","
"\s+"	Whitespace again	(space)
"Email:"	Matches the literal "Email:"	"Email:"
"\s+"	Whitespace	(space)
"(\S+)"	Capture Group 3: One or more non-whitespace characters	"john.smith@example.com"

---

Matches for Your Example String

String:

"Name: John Smith, Email: john.smith@example.com"

Regex Match Groups:

Group	Captured Value
Group 1	"John"
Group 2	"Smith"
Group 3	"john.smith@example.com"

---

Notes on Character Classes

• \w matches [a-zA-Z0-9_] — so it doesn’t include punctuation like a period.
• \S matches any non-whitespace character, so it’s good for capturing an email.

Swift

func chilkatTest() {
    var success: Bool = false

    var subject: String? = "Name: John Smith, Email: john.smith@example.com"
    var pattern: String? = "Name:\\s+(\\w+)\\s+(\\w+),\\s+Email:\\s+(\\S+)"

    let sb = CkoStringBuilder()!
    sb.append(value: subject)

    let json = CkoJsonObject()!
    json.emitCompact = false

    var timeoutMs: Int = 2000
    var numMatches: Int = sb.regexMatch(pattern: pattern, json: json, timeoutMs: timeoutMs).intValue
    if numMatches < 0 {
        // Probably an error in the regular expression.
        // Suggestion: Use AI to help create and/or diagnose regular expressions.
        print("\(sb.lastErrorText!)")
        return
    }

    // Examine the matches:
    print("\(json.emit()!)")

    // This is the JSON with the match information.
    // See the JSON parsing code below to get the matched capture group values.

    // Important:  Capture group 0 always contains the entire match — that is, the portion of the input string that matches the full regular expression.

    // {
    //   "match": [
    //     {
    //       "group": [
    //         {
    //           "cap": "Name: John Smith, Email: john.smith@example.com",
    //           "idx": 0,
    //           "len": 47
    //         },
    //         {
    //           "cap": "John",
    //           "idx": 6,
    //           "len": 4
    //         },
    //         {
    //           "cap": "Smith",
    //           "idx": 11,
    //           "len": 5
    //         },
    //         {
    //           "cap": "john.smith@example.com",
    //           "idx": 25,
    //           "len": 22
    //         }
    //       ]
    //     }
    //   ]
    // }

    var cap: String?
    var i: Int = 0
    var matchCount: Int = json.size(ofArray: "match").intValue
    while i < matchCount {
        print("Match \(i + 1):")
        json.i = i
        var j: Int = 0
        var numCaptureGroups: Int = json.size(ofArray: "match[i].group").intValue
        while j < numCaptureGroups {
            json.j = j
            cap = json.string(of: "match[i].group[j].cap")
            print("\(j): \(cap!)")
            j = j + 1
        }

        i = i + 1
    }

    // Capture group 0 always contains the entire match — that is, the portion of the input string that matches the full regular expression.

    // Output

    // Match 1:
    // 0: Name: John Smith, Email: john.smith@example.com
    // 1: John
    // 2: Smith
    // 3: john.smith@example.com

}