C Requires Chilkat v11.7.0+

Code Blocks and Code Spans in PDF to Markdown

See more PDF Text Extraction Examples

Demonstrates how monospaced text is converted by the "markdown" operation: a monospaced block becomes a fenced code block and a monospaced run inside a sentence becomes a code span. Set "code" to false to treat it as ordinary text. C

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

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

    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 code_block.pdf

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

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

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

    printf("---- default (code: true) ----\n");
    printf("%s\n",CkJsonObject_stringOf(jsonOut,"markdown"));

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

    printf("---- code: false ----\n");
    printf("%s\n",CkJsonObject_stringOf(jsonOut,"markdown"));

    //  Sample output:

    //  ---- default (code: true) ----
    //  <!-- page 1 -->
    //  
    //  # Extracting Text
    //  
    //  Load the PDF and call `ExtractText` with the operation and an options object. The result is returned as JSON:
    //  
    //  ```
    //  new Pdf pdf;
    //  success = pdf.LoadFile("report.pdf");
    //  new JsonObject json;
    //  new JsonObject jsonOut;
    //  success = pdf.ExtractText("text",json,jsonOut);
    //  println jsonOut.StringOf("text");
    //  ```
    //  
    //  An empty options object extracts every page with the default clean-up. Set `pages` to limit the extraction.
    //  ---- code: false ----
    //  <!-- page 1 -->
    //  
    //  # Extracting Text
    //  
    //  Load the PDF and call ExtractText with the operation and an options object. The result is returned as JSON:
    //  
    //  new Pdf pdf; success = pdf.LoadFile("report.pdf"); new JsonObject json; new JsonObject jsonOut; success = pdf.ExtractText("text",json,jsonOut); println jsonOut.StringOf("text");
    //  
    //  An empty options object extracts every page with the default clean-up. Set pages to limit the extraction.


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

    }