C Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. 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 three-page PDF used in this example is available at search_context.pdf

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

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

    //  The string to find.
    CkJsonObject_UpdateString(json,"query","chilkat");

    //  The number of characters returned before and after each match.  The default is 40.
    CkJsonObject_UpdateInt(json,"context",30);

    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;
    }

    //  "count" is the number of matches.  Each match has the page, the matched text as it appears
    //  in the PDF, and the text before and after it.
    printf("Matches: %d\n",CkJsonObject_IntOf(jsonOut,"count"));

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

    //  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
    CkJsonObject_UpdateBool(json,"caseSensitive",TRUE);
    CkJsonObject_UpdateString(json,"query","Chilkat");
    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("Case-sensitive matches for Chilkat: %d\n",CkJsonObject_IntOf(jsonOut,"count"));

    //  Sample output:

    //  Matches: 5
    //  page 1: ...[Chilkat] River Field Notes The Chilkat...
    //  page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
    //  page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
    //  page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
    //  page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
    //  Case-sensitive matches for Chilkat: 3


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

    }