(C) Regular Expression with Multiple Matches and Capture Groups

See more Regular Expressions Examples

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

Note: This example requires Chilkat v11.1.0 or greater.

Chilkat C/C++ Library Downloads
MS Visual C/C++ C++ Builder Linux C/C++ Alpine Linux C/C++	MacOS C/C++ iOS C/C++ Android C/C++ MinGW C/C++

#include <C_CkStringBuilder.h>
#include <C_CkJsonObject.h>

void ChilkatSample(void)
    {
    BOOL success;
    const char *pattern;
    HCkStringBuilder sb;
    BOOL crlf;
    HCkJsonObject json;
    int timeoutMs;
    int numMatches;
    const char *cap;
    int i;
    int matchCount;
    int j;
    int numCaptureGroups;

    success = FALSE;

    pattern = "Name:\\s+(\\w+)\\s+(\\w+),\\s+Email:\\s+(\\S+)";

    sb = CkStringBuilder_Create();
    crlf = TRUE;
    CkStringBuilder_AppendLine(sb,"Name: John Smith, Email: john.smith@example.com",crlf);
    CkStringBuilder_AppendLine(sb,"Name: Jack Johnson, Email: jack.johnson@example.com",crlf);
    CkStringBuilder_AppendLine(sb,"Name: Mary Adams, Email: mary.adams@example.com",crlf);

    printf("%s\n",CkStringBuilder_getAsString(sb));

    // We have the following string:
    // Name: John Smith, Email: john.smith@example.com
    // Name: Jack Johnson, Email: jack.johnson@example.com
    // Name: Mary Adams, Email: mary.adams@example.com

    json = CkJsonObject_Create();
    CkJsonObject_putEmitCompact(json,FALSE);

    timeoutMs = 2000;
    numMatches = CkStringBuilder_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.
        printf("%s\n",CkStringBuilder_lastErrorText(sb));
        CkStringBuilder_Dispose(sb);
        CkJsonObject_Dispose(json);
        return;
    }

    // Examine the matches:
    printf("%s\n",CkJsonObject_emit(json));

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

    // {
    //   "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
    //         }
    //       ]
    //     },
    //     {
    //       "group": [
    //         {
    //           "cap": "Name: Jack Johnson, Email: jack.johnson@example.com",
    //           "idx": 49,
    //           "len": 51
    //         },
    //         {
    //           "cap": "Jack",
    //           "idx": 55,
    //           "len": 4
    //         },
    //         {
    //           "cap": "Johnson",
    //           "idx": 60,
    //           "len": 7
    //         },
    //         {
    //           "cap": "jack.johnson@example.com",
    //           "idx": 76,
    //           "len": 24
    //         }
    //       ]
    //     },
    //     {
    //       "group": [
    //         {
    //           "cap": "Name: Mary Adams, Email: mary.adams@example.com",
    //           "idx": 102,
    //           "len": 47
    //         },
    //         {
    //           "cap": "Mary",
    //           "idx": 108,
    //           "len": 4
    //         },
    //         {
    //           "cap": "Adams",
    //           "idx": 113,
    //           "len": 5
    //         },
    //         {
    //           "cap": "mary.adams@example.com",
    //           "idx": 127,
    //           "len": 22
    //         }
    //       ]
    //     }
    //   ]
    // }

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

    i = 0;
    matchCount = CkJsonObject_SizeOfArray(json,"match");
    while (i < matchCount) {
        printf("Match %d:\n",i + 1);
        CkJsonObject_putI(json,i);
        j = 0;
        numCaptureGroups = CkJsonObject_SizeOfArray(json,"match[i].group");
        while (j < numCaptureGroups) {
            CkJsonObject_putJ(json,j);
            cap = CkJsonObject_stringOf(json,"match[i].group[j].cap");
            printf("%d: %s\n",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
    // Match 2:
    // 0: Name: Jack Johnson, Email: jack.johnson@example.com
    // 1: Jack
    // 2: Johnson
    // 3: jack.johnson@example.com
    // Match 3:
    // 0: Name: Mary Adams, Email: mary.adams@example.com
    // 1: Mary
    // 2: Adams
    // 3: mary.adams@example.co


    CkStringBuilder_Dispose(sb);
    CkJsonObject_Dispose(json);

    }