C++
Drop/Undrop Text Formatting Tags

Demonstrates how the DropTextFormattingTags and UndropTextFormattingTags methods work in the Html-to-Xml API.
Chilkat C++ Downloads

C++
#include <CkHtmlToXml.h>

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

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

    //  Convert the above to XML
    CkHtmlToXml h2x;

    //  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
    h2x.put_Html(html);
    std::cout << h2x.toXml() << "\r\n";

    //  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:
    h2x.UndropTextFormattingTags();

    //  Convert again to see the difference:
    std::cout << h2x.toXml() << "\r\n";

    //  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.
    h2x.DropTextFormattingTags();

    //  Convert again to see the difference:
    std::cout << h2x.toXml() << "\r\n";

    //  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>
    }