Unicode C

Regular Expression with Multiple Matches and Named Capture Groups

See more Regular Expressions Examples

Demonstrates regular expressions with named capture groups and multiple matches. Unicode C

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

void ChilkatSample(void)
    {
    BOOL success;
    HCkStringBuilderW sb;
    BOOL crlf;
    const wchar_t *pattern;
    HCkJsonObjectW json;
    int timeoutMs;
    int numMatches;
    int idx_first;
    int idx_last;
    int i;
    int matchCount;

    success = FALSE;

    sb = CkStringBuilderW_Create();
    crlf = TRUE;
    CkStringBuilderW_AppendLine(sb,L"Name: John Smith",crlf);
    CkStringBuilderW_AppendLine(sb,L"Name: Jack Johnson",crlf);
    CkStringBuilderW_AppendLine(sb,L"Name: Mary Adams",crlf);

    wprintf(L"%s\n",CkStringBuilderW_getAsString(sb));

    //  We have the following string:
    //  Name: John Smith
    //  Name: Jack Johnson
    //  Name: Mary Adams

    pattern = L"Name:\\s+(?<first>\\w+)\\s+(?<last>\\w+)";
    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": "Name: John Smith",
    //            "idx": 0,
    //            "len": 16
    //          },
    //          {
    //            "cap": "John",
    //            "idx": 6,
    //            "len": 4
    //          },
    //          {
    //            "cap": "Smith",
    //            "idx": 11,
    //            "len": 5
    //          }
    //        ]
    //      },
    //      {
    //        "group": [
    //          {
    //            "cap": "Name: Jack Johnson",
    //            "idx": 18,
    //            "len": 18
    //          },
    //          {
    //            "cap": "Jack",
    //            "idx": 24,
    //            "len": 4
    //          },
    //          {
    //            "cap": "Johnson",
    //            "idx": 29,
    //            "len": 7
    //          }
    //        ]
    //      },
    //      {
    //        "group": [
    //          {
    //            "cap": "Name: Mary Adams",
    //            "idx": 38,
    //            "len": 16
    //          },
    //          {
    //            "cap": "Mary",
    //            "idx": 44,
    //            "len": 4
    //          },
    //          {
    //            "cap": "Adams",
    //            "idx": 49,
    //            "len": 5
    //          }
    //        ]
    //      }
    //    ]
    //  }

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

    idx_first = CkJsonObjectW_IntOf(json,L"named.first");
    idx_last = CkJsonObjectW_IntOf(json,L"named.last");

    i = 0;
    matchCount = CkJsonObjectW_SizeOfArray(json,L"match");
    while (i < matchCount) {
        wprintf(L"Match %d:\n",i + 1);
        CkJsonObjectW_putI(json,i);

        CkJsonObjectW_putJ(json,idx_first);
        wprintf(L"first: %s\n",CkJsonObjectW_stringOf(json,L"match[i].group[j].cap"));

        CkJsonObjectW_putJ(json,idx_last);
        wprintf(L"first: %s\n",CkJsonObjectW_stringOf(json,L"match[i].group[j].cap"));

        wprintf(L"\n");
        i = i + 1;
    }

    //  Output is: 

    //  Match 1:
    //  first: John
    //  first: Smith
    //  
    //  Match 2:
    //  first: Jack
    //  first: Johnson
    //  
    //  Match 3:
    //  first: Mary
    //  first: Adams


    CkStringBuilderW_Dispose(sb);
    CkJsonObjectW_Dispose(json);

    }