Java EE (Java Enterprise Edition) General Discussion

I want to parse log files using the SAX parser. In the log file, at the beginning of the file I have normal text that are not in xml tags, then xml tags, followed by normal text not in xml tags.

How do I make my program ignore the normal text not in xml tags in the file and just parse the xml tags.

This is my code:

import java.io.*;

import org.xml.sax.*;
import org.xml.sax.helpers.DefaultHandler;

import javax.xml.parsers.SAXParserFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;

public class LogParser extends DefaultHandler
{
    public static void main(String argv[])
    {
        if (argv.length != 1) {
            System.err.println("Usage: cmd filename");
            System.exit(1);
        }
        
        // Use an instance of ourselves as the SAX event handler
        DefaultHandler handler = new LogParser();
        // Use the default (non-validating) parser
        SAXParserFactory factory = SAXParserFactory.newInstance();
        try {
            // Set up output stream
            out = new OutputStreamWriter(System.out, "UTF8");

            // Parse the input
            SAXParser saxParser = factory.newSAXParser();
            saxParser.parse( new File(argv[0]), handler);

        } catch (Throwable t) {
            t.printStackTrace();
        }
        System.exit(0);
    }

    static private Writer  out;
    private String indentString = "    "; // Amount to indent
    private int indentLevel = 0;

    //===========================================================
    // SAX DocumentHandler methods
    //===========================================================

    public void startDocument()
    throws SAXException
    {
        nl();
        nl();
        emit("START DOCUMENT");
        nl();
        emit("<?xml version='1.0' encoding='UTF-8'?>");
    }

    public void endDocument()
    throws SAXException
    {
        nl(); emit("END DOCUMENT");
        try {
            nl();
            out.flush();
        } catch (IOException e) {
            throw new SAXException("I/O error", e);
        }
    }

    public void startElement(String namespaceURI,
                             String lName, // local name
                             String qName, // qualified name
                             Attributes attrs)
    throws SAXException
    {
        indentLevel++;
        nl(); emit("ELEMENT: ");
        String eName = lName; // element name
        if ("".equals(eName)) eName = qName; // namespaceAware = false
        emit("<"+eName);
        if (attrs != null) {
            for (int i = 0; i < attrs.getLength(); i++) {
                String aName = attrs.getLocalName(i); // Attr name 
                if ("".equals(aName)) aName = attrs.getQName(i);
                nl();
                emit("   ATTR: ");
                emit(aName);
                emit("\t\"");
                emit(attrs.getValue(i));
                emit("\"");
            }
        }
        if (attrs.getLength() > 0) nl();
        emit(">");
    }

    public void endElement(String namespaceURI,
                           String sName, // simple name
                           String qName  // qualified name
                          )
    throws SAXException
    {
        nl();
        emit("END_ELM: ");
        emit("</"+sName+">");
        indentLevel--;
    }

    public void characters(char buf[], int offset, int len)
    throws SAXException
    {
        nl(); emit("CHARS:   ");
        String s = new String(buf, offset, len);
        if (!s.trim().equals("")) emit(s);
    }

    //===========================================================
    // Utility Methods ...
    //===========================================================

    // Wrap I/O exceptions in SAX exceptions, to
    // suit handler signature requirements
    private void emit(String s)
    throws SAXException
    {
        try {
            out.write(s);
            out.flush();
        } catch (IOException e) {
            throw new SAXException("I/O error", e);
        }
    }

    // Start a new line
    // and indent the next line appropriately
    private void nl()
    throws SAXException
    {
        String lineEnd =  System.getProperty("line.separator");
        try {
            out.write(lineEnd);
            for (int i=0; i < indentLevel; i++) out.write(indentString);
        } catch (IOException e) {
            throw new SAXException("I/O error", e);
        }
    }
}

When I run the code with my log file I get the following error message:

org.xml.sax.SAXParseException: Content is not allowed in prolog.
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(Unknown Source)
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(Unknown Source)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(Unknown Source)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(Unknown Source)
at com.sun.org.apache.xerces.internal.impl.XMLScanner.reportFatalError(Unknown Source)