OPC/opc_text_8c-example.html

/*

    Extract all text of an Word document as HTML.


    Ussage:

    opc_text FILENAME


    Sample:

    opc_text OOXMLI1.docx

*/


#include <opc/opc.h>

#include <stdio.h>

#include <time.h>

#ifdef WIN32

#include <crtdbg.h>

#endif


static void dumpText(mceTextReader_t *reader) {

    mce_skip_attributes(reader);

    mce_start_children(reader) {

        mce_start_element(reader, _X("http://schemas.openxmlformats.org/wordprocessingml/2006/main"), _X("t")) {

            mce_skip_attributes(reader);

            mce_start_children(reader) {

                mce_start_text(reader) {

                    for(const xmlChar *txt=xmlTextReaderConstValue(reader->reader);0!=*txt;txt++) {

                        switch(*txt) {

                        case '<':

                            printf("&lt;");

                            break;

                        case '>':

                            printf("&gt;");

                            break;

                        case '&':

                            printf("&amp;");

                            break;

                        default:

                            putc(*txt, stdout);

                            break;

                        }

                    }

                } mce_end_text(reader);

            } mce_end_children(reader);

        } mce_end_element(reader);

        mce_start_element(reader, _X("http://schemas.openxmlformats.org/wordprocessingml/2006/main"), _X("p")) {

            printf("<p>");

            dumpText(reader);

            printf("</p>\n");

        } mce_end_element(reader);

        mce_start_element(reader, NULL, NULL) {

            dumpText(reader);

        } mce_end_element(reader);

    } mce_end_children(reader);

}


int main( int argc, const char* argv[] )

{

#ifdef WIN32

     _CrtSetDbgFlag (_CRTDBG_ALLOC_MEM_DF | _CRTDBG_LEAK_CHECK_DF);

#endif


    opcInitLibrary();

    opcContainer *c=opcContainerOpen(_X(argv[1]), OPC_OPEN_READ_ONLY, NULL, NULL);

    if (NULL!=c) {

        mceTextReader_t reader;

        if (OPC_ERROR_NONE==opcXmlReaderOpen(c, &reader, _X("/word/document.xml"), NULL, 0, 0)) {

            mce_start_document(&reader) {

                mce_start_element(&reader, NULL, NULL) {

                    printf("<html>\n");

                    printf("<head>\n");

                    printf("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\">\n");

                    printf("</head>\n");

                    printf("<body>\n");

                    dumpText(&reader);

                    printf("<body>\n");

                    printf("</html>\n");

                } mce_end_element(&reader);

            } mce_end_document(&reader);

            mceTextReaderCleanup(&reader);

        }

        opcContainerClose(c, OPC_CLOSE_NOW);

    }

    opcFreeLibrary();

#ifdef WIN32

    OPC_ASSERT(!_CrtDumpMemoryLeaks());

#endif

    return 0;

}