Sample code for 30+ languages & platforms
Unicode C

Drop/Undrop Text Formatting Tags

See more HTML-to-XML/Text Examples

Demonstrates how the DropTextFormattingTags and UndropTextFormattingTags methods work in the Html-to-Xml API.

Chilkat Unicode C Downloads

Unicode C
#include <C_CkHtmlToXmlW.h>

void ChilkatSample(void)
    {
    const wchar_t *html;
    HCkHtmlToXmlW h2x;

    //  This example assumes the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    html = L"<html><body><p><b>Hello</b> World!<p>This is a test</body></html>";

    //  Convert the above to XML
    h2x = CkHtmlToXmlW_Create();

    //  By default, text formatting tags are dropped. Text formatting HTML tags are: b, font, i, u, br, center, em, strong, big, tt, s, small, strike, sub, and sup
    CkHtmlToXmlW_putHtml(h2x,html);
    wprintf(L"%s\n",CkHtmlToXmlW_toXml(h2x));

    //  The resulting XML is:

    //  <?xml version="1.0" encoding="utf-8"?>
    //  <root>
    //      <html>
    //          <body>
    //              <p>
    //                  <text>Hello World!</text>
    //              </p>
    //              <p>
    //                  <text>This is a test</text>
    //              </p>
    //          </body>
    //      </html>
    //  </root>

    //  To preserve text formatting tags, put the h2x instance into the mode where text formatting tags are not dropped:
    CkHtmlToXmlW_UndropTextFormattingTags(h2x);

    //  Convert again to see the difference:
    wprintf(L"%s\n",CkHtmlToXmlW_toXml(h2x));

    //  The resulting XML is:

    //  <?xml version="1.0" encoding="utf-8"?>
    //  <root>
    //      <html>
    //          <body>
    //              <p>
    //                  <b>
    //                      <text>Hello</text>
    //                  </b>
    //                  <text> World!</text>
    //              </p>
    //              <p>
    //                  <text>This is a test</text>
    //              </p>
    //          </body>
    //      </html>
    //  </root>

    //  Call DropTextFormattingTags to put the h2x instance back in "drop" mode.
    CkHtmlToXmlW_DropTextFormattingTags(h2x);

    //  Convert again to see the difference:
    wprintf(L"%s\n",CkHtmlToXmlW_toXml(h2x));

    //  The resulting XML is:

    //  <?xml version="1.0" encoding="utf-8"?>
    //  <root>
    //      <html>
    //          <body>
    //              <p>
    //                  <text>Hello World!</text>
    //              </p>
    //              <p>
    //                  <text>This is a test</text>
    //              </p>
    //          </body>
    //      </html>
    //  </root>


    CkHtmlToXmlW_Dispose(h2x);

    }