JTidy errors to Log4j

By default JTidy logs all the errors on the standard output, kind of an old fashion way of doing logging. So I spent some time to integrate it with log4j to clean up my standard output.

First, you need a PrintWriter as a bridge from JTidy to Log4j:

public class Log4jPrintWriter extends PrintWriter {
    Priority level;
    Category cat;
    StringBuffer text = new StringBuffer("");

    public Log4jPrintWriter(org.apache.log4j.Category cat, org.apache.log4j.Priority level) {
        super(System.err);  // PrintWriter doesn't have default constructor.
        this.level =level;
        this.cat   = cat;
    }

    // overrides all the print and println methods for 'print' it to the constructor's Category
    public void close(){
        flush();
    }
    public void flush(){
        if (!text.toString().equals("")){
            cat.log(level,text.toString());
            text.setLength(0);
        }
    }
    public void print(boolean b){
        text.append(b);
    }

    public void print(char c){
        text.append(c);
    }
    public void print(char[] s){
        text.append(s);
    }
    public void print(double d){
        text.append(d);
    }
    public void print(float f){
        text.append(f);
    }
    public void print(int i){
        text.append(i);
    }
    public void print(long l){
        text.append(l);
    }
    public void print(Object obj){
        text.append(obj);
    }
    public void print(String s){
        text.append(s);
    }
    public void println(){
        if (!text.toString().equals("")){
            cat.log(level,text.toString());
            text.setLength(0);
        }
    }
    public void println(boolean x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(char x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(char[] x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(double x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(float x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(int x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(long x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(Object x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
    public void println(String x){
        text.append(x);
        cat.log(level,text.toString());
        text.setLength(0);
    }
}

Thanks to JD Evora for this.

Then, declare your Logger and your PrintWriter

private static Logger log = Logger.getLogger(HtmlProcessor.class);
    private static Log4jPrintWriter log4j = new Log4jPrintWriter(log, Level.DEBUG);

And finally, make JTidy work with it:

InputStream pageStream =  new ByteArrayInputStream(html.getBytes("UTF-8"));
Tidy tidy = new Tidy();

tidy.setOnlyErrors(true); //<------------------

tidy.setInputEncoding("UTF-8");
tidy.setOutputEncoding("UTF-8");
tidy.setQuiet(true);
tidy.setShowWarnings(false);
tidy.setErrout(log4j);
dom = tidy.parseDOM(pageStream, null);
dom.normalize();
...

Enjoy your clean catalina.out!