Page MenuHomePhabricator
Paste P1843

HTML5Tidy.java
ActivePublic
Actions

Authored by tstarling on Aug 6 2015, 11:27 AM.
Tags
None
Referenced Files
F608982: HTML5Tidy.java
Aug 6 2015, 11:27 AM
Subscribers
Ricordisamoa
package org.wikimedia.html5tidy;
import javax.servlet.*;
import java.io.IOException;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.util.Enumeration;
import java.nio.charset.Charset;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import nu.validator.encoding.Encoding;
import nu.validator.htmlparser.common.XmlViolationPolicy;
import nu.validator.htmlparser.sax.HtmlParser;
import nu.validator.htmlparser.sax.HtmlSerializer;
public class HTML5Tidy extends GenericServlet {
public void service(ServletRequest req, ServletResponse res)
throws ServletException, IOException
{
req.setCharacterEncoding("UTF-8");
String text = req.getParameter("text");
if (text == null) {
throw new ServletException("The text parameter must be given");
}
Charset utf8;
try {
utf8 = Charset.forName("UTF-8");
} catch (IllegalArgumentException e) {
throw new ServletException("No UTF-8", e);
}
byte[] input = req.getParameter("text").getBytes(utf8);
ByteArrayOutputStream sink = new ByteArrayOutputStream();
ContentHandler serializer = new HtmlSerializer(sink);
HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALLOW);
parser.setContentHandler(serializer);
try {
parser.setProperty("http://xml.org/sax/properties/lexical-handler",
serializer);
InputSource source = new InputSource(new ByteArrayInputStream(input));
source.setEncoding("UTF-8");
parser.parse(source);
} catch (SAXException e) {
throw new ServletException("Error parsing HTML", e);
}
// HtmlSerializer writes UTF-8 by default
res.setContentType("text/html;charset=UTF-8");
res.getOutputStream().write(sink.toByteArray());
}
};
Content licensed under Creative Commons Attribution-ShareAlike (CC BY-SA) 4.0 unless otherwise noted; code licensed under GNU General Public License (GPL) 2.0 or later and other open source licenses. By using this site, you agree to the Terms of Use, Privacy Policy, and Code of Conduct. · Wikimedia Foundation · Privacy Policy · Code of Conduct · Terms of Use · Disclaimer · CC-BY-SA · GPL