Unicode C Requires Chilkat v11.7.0+

Expand Ligatures and Normalize Unicode in Extracted PDF Text

See more PDF Text Extraction Examples

Demonstrates the "expandLigatures" and "normalize" clean-up options. Typeset PDFs use single glyphs for "fi" and "fl"; by default they are expanded to their letters. Unicode normalization is NFC by default; NFKC also folds compatibility characters such as circled digits, the trademark sign and vulgar fractions into plain characters, and "none" leaves the text as the PDF has it. Unicode C

#include <C_CkPdfW.h>
#include <C_CkJsonObjectW.h>

void ChilkatSample(void)
    {
    BOOL success;
    HCkPdfW pdf;
    HCkJsonObjectW json;
    HCkJsonObjectW 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 ligatures.pdf

    pdf = CkPdfW_Create();
    success = CkPdfW_LoadFile(pdf,L"qa_data/pdf/ligatures.pdf");
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        return;
    }

    json = CkJsonObjectW_Create();
    jsonOut = CkJsonObjectW_Create();

    //  The first line is set with the fi and fl ligature glyphs; the second has circled digits,
    //  a trademark sign and a vulgar fraction.
    success = CkPdfW_ExtractText(pdf,L"text",json,jsonOut);
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        CkJsonObjectW_Dispose(json);
        CkJsonObjectW_Dispose(jsonOut);
        return;
    }

    wprintf(L"---- default (expandLigatures: true, normalize: NFC) ----\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));

    //  Keep the ligature characters as they are in the PDF.
    CkJsonObjectW_UpdateBool(json,L"expandLigatures",FALSE);
    CkJsonObjectW_UpdateString(json,L"normalize",L"none");
    success = CkPdfW_ExtractText(pdf,L"text",json,jsonOut);
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        CkJsonObjectW_Dispose(json);
        CkJsonObjectW_Dispose(jsonOut);
        return;
    }

    wprintf(L"---- expandLigatures: false, normalize: none ----\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));

    //  NFKC folds the compatibility characters too (and expands ligatures on its own).
    CkJsonObjectW_UpdateString(json,L"normalize",L"NFKC");
    success = CkPdfW_ExtractText(pdf,L"text",json,jsonOut);
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        CkJsonObjectW_Dispose(json);
        CkJsonObjectW_Dispose(jsonOut);
        return;
    }

    wprintf(L"---- normalize: NFKC ----\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));

    //  Sample output (shown here in ASCII: (fi) and (fl) stand for the single ligature characters, (1) and (2) for the circled digits,
    //  (TM) for the trademark sign and 1/2 for the vulgar fraction; the NFKC output has plain "1", "2", "TM" and "1", fraction slash, "2"):

    //  ---- default (expandLigatures: true, normalize: NFC) ----
    //  Typeset Text
    //  
    //  The final flight of the season was officially confirmed on the fifth. Rooms (1) and (2) are reserved; the Harbor Cafe(TM) serves 1/2 portions.
    //  ---- expandLigatures: false, normalize: none ----
    //  Typeset Text
    //  
    //  The (fi)nal (fl)ight of the season was of(fi)cially con(fi)rmed on the (fi)fth. Rooms (1) and (2) are reserved; the Harbor Cafe(TM) serves 1/2 portions.
    //  ---- normalize: NFKC ----
    //  Typeset Text
    //  
    //  The final flight of the season was officially confirmed on the fifth. Rooms 1 and 2 are reserved; the Harbor CafeTM serves 1/2 portions.


    CkPdfW_Dispose(pdf);
    CkJsonObjectW_Dispose(json);
    CkJsonObjectW_Dispose(jsonOut);

    }