C Requires Chilkat v11.7.0+

Extract Right-to-Left (Hebrew, Arabic) Text in Logical Order

See more PDF Text Extraction Examples

Demonstrates the "bidi" clean-up option. PDFs draw right-to-left text in visual order (the order of the glyphs on the page); by default the extracted text is reordered into logical order, so that it reads and compares correctly. Set "bidi" to false to get the glyphs in the order they are drawn. 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 hebrew_line.pdf

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

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

    //  The page has a line of Hebrew with a Latin word (PDF) and a number (2026) embedded in it.
    //  In logical order the line reads: kovetz PDF mishnat 2026 muchan ("the PDF file from 2026 is ready"),
    //  with the Hebrew words in reading order and "PDF" and "2026" kept left to right.
    success = CkPdf_ExtractText(pdf,"text",json,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("---- default (bidi: true, logical order) ----\n");
    printf("%s\n",CkJsonObject_stringOf(jsonOut,"text"));

    //  Without reordering, the Hebrew words come out reversed and in the opposite order, as drawn.
    CkJsonObject_UpdateBool(json,"bidi",FALSE);
    success = CkPdf_ExtractText(pdf,"text",json,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("---- bidi: false (as drawn) ----\n");
    printf("%s\n",CkJsonObject_stringOf(jsonOut,"text"));

    //  Sample output (the Hebrew is shown here transliterated):

    //  ---- default (bidi: true, logical order) ----
    //  Right-to-Left Text
    //  
    //  The line below is Hebrew with a Latin word and a number embedded in it:
    //  
    //  kovetz PDF mishnat 2026 muchan
    //  ---- bidi: false (as drawn) ----
    //  Right-to-Left Text
    //  
    //  The line below is Hebrew with a Latin word and a number embedded in it:
    //  
    //  nachum 2026 tanshim PDF ztevok    (the words in reverse order, each Hebrew word with its letters reversed)


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

    }