XmlTextExtractor.java

/*
 * Copyright 2004 Outerthought bvba and Schaubroeck nv
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package com.xpn.xwiki.plugin.lucene.textextraction;

import java.io.ByteArrayInputStream;

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

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

/**
 * Extracts all text between tags in an XML document. Only works (of course) for well formed XML
 * documents.
 */
public class XmlTextExtractor implements MimetypeTextExtractor
{
    public String getText(byte[] data) throws Exception
    {
        SAXParserFactory factory = SAXParserFactory.newInstance();
        SAXParser parser = factory.newSAXParser();
        MyHandler handler = new MyHandler();
        parser.parse(new ByteArrayInputStream(data), handler);
        return handler.getText();
    }

    private static class MyHandler extends DefaultHandler
    {
        StringBuffer text = new StringBuffer();

        public void characters(char ch[], int start, int length) throws SAXException
        {
            text.append(ch, start, length);
        }

        public String getText()
        {
            return text.toString();
        }
    }
}