import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
import java.io.InputStreamReader;
import java.io.Reader;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;

import org.apache.xerces.parsers.XMLDocumentParser;
import org.apache.xerces.xni.Augmentations;
import org.apache.xerces.xni.NamespaceContext;
import org.apache.xerces.xni.QName;
import org.apache.xerces.xni.XMLAttributes;
import org.apache.xerces.xni.XMLLocator;
import org.apache.xerces.xni.XNIException;
import org.apache.xerces.xni.parser.XMLInputSource;
import org.apache.xerces.xni.parser.XMLParserConfiguration;

public class XniTest extends XMLDocumentParser {
	
	static final String DEFAULT_PARSER_CONFIG = "org.apache.xerces.parsers.XIncludeAwareParserConfiguration";
	static final String NAMESPACE_PREFIXES_FEATURE_ID = "http://xml.org/sax/features/namespace-prefixes";
    protected static final String SCHEMA_VALIDATION_FEATURE_ID =
        "http://apache.org/xml/features/validation/schema";
    protected static final String HONOUR_ALL_SCHEMA_LOCATIONS_ID = 
        "http://apache.org/xml/features/honour-all-schemaLocations";

	public static final String PATH = "\\work\\data\\special_char.xml";

	static Map startPositions = new HashMap();
	static Map endPositions = new HashMap();
	
	private XMLLocator locator;

	public XniTest(XMLParserConfiguration configuration) {
		super(configuration);
	}

    public void startDocument(XMLLocator locator, String encoding, NamespaceContext namespaceContext, Augmentations augs)
    throws XNIException {
    	this.locator = locator;
    }
	
    public void startElement(QName element, XMLAttributes attrs, Augmentations augs)
    throws XNIException {
		// insert the element
    	startPositions.put(element.localpart, Integer.valueOf(locator.getCharacterOffset()));
	}

    static public void run() {
    	XMLParserConfiguration parserConfig = null;
    	try {
            parserConfig = (XMLParserConfiguration)ObjectFactory.newInstance(DEFAULT_PARSER_CONFIG,
                ObjectFactory.findClassLoader(), true);
            parserConfig.addRecognizedFeatures(new String[] {
                NAMESPACE_PREFIXES_FEATURE_ID,
            });
            parserConfig.setFeature(HONOUR_ALL_SCHEMA_LOCATIONS_ID, true);
            
            XMLDocumentParser parser = new XniTest(parserConfig);
            parser.parse(new XMLInputSource(null, PATH, null));
            
            String content = getDocument(PATH);
            
            // loop through all the starting elements
            for (Iterator it=startPositions.keySet().iterator(); 
            it.hasNext();) {
            	String element = (String)it.next();
            	int start = ((Integer)startPositions.get(element)).intValue();
            	int end = ((Integer)endPositions.get(element)).intValue();
            	System.out.println("Element:"+element);
            	System.out.println(content.substring(start, end));
            	System.out.println();
            }
        }
        catch (Exception e) {
            e.printStackTrace();
        }
    	
    }

    /**
	 * @param args
	 */
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		run();

	}

	public void endElement(QName arg0, Augmentations arg1) throws XNIException {
		endPositions.put(arg0.localpart, Integer.valueOf(locator.getCharacterOffset()));
	}


	// read the content of the file into a string
	static String getDocument(String path) throws Exception {
		StringBuffer doc = new StringBuffer();
		//CLOB clob = new CLOB();
		char buf[] = new char[10240];
		int start = 0;
		Reader reader = new InputStreamReader(new FileInputStream(path));
		do {
			int len = reader.read(buf, 0, 10240);
			doc.append(new String(buf, 0, len));
			if (len < 10240) {
				break;
			} else {
				start += len;
			}
		} while (true);
		return doc.toString();
	}
	
	
}