* It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */
    protected static final Logger logger = LogManager.getLogger(AbstractXmlExtractor.class);

    /**
     * UTF-7 Byte Order Mark definition.
     */

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */
    public XmlExtractor() {
        super();
    }

    /**
     * Pattern for XML encoding.
     */

     *
     * @see
     * org.codelibs.fess.crawler.extractor.impl.AbstractXmlExtractor#getEncodingPattern()
     */
    @Override
    protected Pattern getEncodingPattern() {
        return metaCharsetPattern;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.impl.AbstractXmlExtractor#getTagPattern()
     */
    @Override
    protected Pattern getTagPattern() {

     *
     * @see
     * org.codelibs.fess.crawler.extractor.impl.AbstractXmlExtractor#getEncodingPattern()
     */
    @Override
    protected Pattern getEncodingPattern() {
        return metaCharsetPattern;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.impl.AbstractXmlExtractor#getTagPattern()
     */
    @Override
    protected Pattern getTagPattern() {