C Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). C

#include <C_CkPdf.h>
#include <C_CkJsonObject.h>

void ChilkatSample(void)
    {
    BOOL success;
    HCkPdf pdf;
    HCkJsonObject json;
    HCkJsonObject jsonOut;
    int i;
    int count_i;

    success = FALSE;

    //  This example requires the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    //  The PDF used in this example is available at order_records.pdf

    pdf = CkPdf_Create();
    success = CkPdf_LoadFile(pdf,"qa_data/pdf/order_records.pdf");
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        return;
    }

    json = CkJsonObject_Create();
    jsonOut = CkJsonObject_Create();

    //  Find every order number.  With regex set to true, the query is a regular expression.
    CkJsonObject_UpdateString(json,"query","ORD-[0-9]{4}-[0-9]{4}");
    CkJsonObject_UpdateBool(json,"regex",TRUE);
    //  We only want the matched text, so no context is needed.
    CkJsonObject_UpdateInt(json,"context",0);

    success = CkPdf_ExtractText(pdf,"search",json,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("Order numbers found: %d\n",CkJsonObject_IntOf(jsonOut,"count"));
    i = 0;
    count_i = CkJsonObject_SizeOfArray(jsonOut,"matches");
    while (i < count_i) {
        CkJsonObject_putI(jsonOut,i);
        printf("%s\n",CkJsonObject_stringOf(jsonOut,"matches[i].text"));
        i = i + 1;
    }

    //  Find the e-mail addresses, but stop after the first three.
    CkJsonObject_UpdateString(json,"query","[a-z0-9._]+@[a-z]+[.][a-z]+");
    CkJsonObject_UpdateInt(json,"maxResults",3);
    success = CkPdf_ExtractText(pdf,"search",json,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("First three e-mail addresses:\n");
    i = 0;
    count_i = CkJsonObject_SizeOfArray(jsonOut,"matches");
    while (i < count_i) {
        CkJsonObject_putI(jsonOut,i);
        printf("%s\n",CkJsonObject_stringOf(jsonOut,"matches[i].text"));
        i = i + 1;
    }

    //  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
    //  but it is also inside "catalog" and "category".
    CkJsonObject_Delete(json,"maxResults");
    CkJsonObject_UpdateBool(json,"regex",FALSE);
    CkJsonObject_UpdateString(json,"query","cat");
    success = CkPdf_ExtractText(pdf,"search",json,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("Occurrences of cat (any): %d\n",CkJsonObject_IntOf(jsonOut,"count"));

    CkJsonObject_UpdateBool(json,"wholeWord",TRUE);
    success = CkPdf_ExtractText(pdf,"search",json,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("Occurrences of cat (whole word): %d\n",CkJsonObject_IntOf(jsonOut,"count"));

    //  Sample output:

    //  Order numbers found: 9
    //  ORD-2026-0301
    //  ORD-2026-0302
    //  ORD-2026-0303
    //  ORD-2026-0304
    //  ORD-2026-0305
    //  ORD-2026-0306
    //  ORD-2026-0307
    //  ORD-2026-0308
    //  ORD-2026-0307
    //  First three e-mail addresses:
    //  alice.moore@example.com
    //  bkumar@example.org
    //  carla@example.net
    //  Occurrences of cat (any): 3
    //  Occurrences of cat (whole word): 1


    CkPdf_Dispose(pdf);
    CkJsonObject_Dispose(json);
    CkJsonObject_Dispose(jsonOut);

    }