Java

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. Chilkat2 Java

import com.chilkatsoft.chilkat2.HtmlToXml;

public class ChilkatExample {

    public static void main(String[] args) {
        // This example assumes the Chilkat API to have been previously unlocked.
        // See Global Unlock Sample for sample code.

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

        // Convert the above to XML
        HtmlToXml h2x = new HtmlToXml();

        // 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.setHtml(html);
        System.out.println(h2x.toXml());

        // 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:
        System.out.println(h2x.toXml());

        // 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:
        System.out.println(h2x.toXml());

        // 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>
    }
}