Unicode C

Regular Expression with Named Capture Groups

See more Regular Expressions Examples

Demonstrates regular expressions with named capture groups.

See the sample code below.

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

In PCRE2, named capture groups allow you to assign a name to a capturing group, making it easier to reference by name instead of number.

Syntax

(?<name>pattern)

or

(?'name'pattern)

Example

(?<first>\w+)\s+(?<last>\w+)

Applied to:

"John Smith"

Produces:

• first: John
• last: Smith

Unicode C

#include <C_CkStringBuilderW.h>
#include <C_CkJsonObjectW.h>

void ChilkatSample(void)
    {
    BOOL success;
    const wchar_t *subject;
    const wchar_t *pattern;
    HCkStringBuilderW sb;
    HCkJsonObjectW json;
    int timeoutMs;
    int numMatches;

    success = FALSE;

    subject = L"John Smith";
    pattern = L"(?<first>\\w+)\\s+(?<last>\\w+)";

    sb = CkStringBuilderW_Create();
    CkStringBuilderW_Append(sb,subject);

    json = CkJsonObjectW_Create();
    CkJsonObjectW_putEmitCompact(json,FALSE);

    timeoutMs = 2000;
    numMatches = CkStringBuilderW_RegexMatch(sb,pattern,json,timeoutMs);
    if (numMatches < 0) {
        // Probably an error in the regular expression.
        // Suggestion: Use AI to help create and/or diagnose regular expressions.
        wprintf(L"%s\n",CkStringBuilderW_lastErrorText(sb));
        CkStringBuilderW_Dispose(sb);
        CkJsonObjectW_Dispose(json);
        return;
    }

    // Examine the matches:
    wprintf(L"%s\n",CkJsonObjectW_emit(json));

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

    // {
    //   "named": {
    //     "first": 1,
    //     "last": 2
    //   },
    //   "match": [
    //     {
    //       "group": [
    //         {
    //           "cap": "John Smith",
    //           "idx": 0,
    //           "len": 10
    //         },
    //         {
    //           "cap": "John",
    //           "idx": 0,
    //           "len": 4
    //         },
    //         {
    //           "cap": "Smith",
    //           "idx": 5,
    //           "len": 5
    //         }
    //       ]
    //     }
    //   ]
    // }

    // The capture group index is obtained by looking up the name in the JSON result.
    // For example:

    CkJsonObjectW_putI(json,CkJsonObjectW_IntOf(json,L"named.first"));
    wprintf(L"first: %s\n",CkJsonObjectW_stringOf(json,L"match[0].group[i].cap"));

    CkJsonObjectW_putI(json,CkJsonObjectW_IntOf(json,L"named.last"));
    wprintf(L"last: %s\n",CkJsonObjectW_stringOf(json,L"match[0].group[i].cap"));

    // Output is: 

    // first: John
    // last: Smith


    CkStringBuilderW_Dispose(sb);
    CkJsonObjectW_Dispose(json);

    }