/**
     * The date of last modification of the file. This date should be in W3C
     * Datetime format. This format allows you to omit the time portion, if
     * desired, and use YYYY-MM-DD.
     *
     * Note that this tag is separate from the If-Modified-Since (304) header
     * the server can return, and search engines may use the information from
     * both sources differently.
     */
    private String lastmod;

    /**

        request.setSize(size);
        return this;
    }

    /**
     * Adds a tag to filter by.
     * @param tag The tag.
     * @return This builder instance.
     */
    public PopularWordsRequestBuilder addTag(final String tag) {
        request.addTag(tag);
        return this;
    }

    /**
     * Adds a role to filter by.
     * @param role The role.

     */
    public void setWindowSize(final int windowSize) {
        this.windowSize = windowSize;
    }

    /**
     * Adds a tag to filter by.
     * @param tag The tag.
     */
    public void addTag(final String tag) {
        tags.add(tag);
    }

    /**
     * Adds a role to filter by.
     * @param role The role.
     */
    public void addRole(final String role) {

        request.setQuery(query);
        return this;
    }

    /**
     * Adds a tag to filter by.
     * @param tag The tag.
     * @return This builder instance.
     */
    public SuggestRequestBuilder addTag(final String tag) {
        request.addTag(tag);
        return this;
    }

    /**
     * Adds a role to filter by.
     * @param role The role.

        xmlEncodingPattern = metaCharsetPattern;
    }

    /**
     * Returns the XML tag pattern.
     * @return The XML tag pattern.
     */
    public Pattern getXmlTagPattern() {
        return xmlTagPattern;
    }

    /**
     * Sets the XML tag pattern.
     * @param htmlTagPattern The XML tag pattern.
     */
    public void setXmlTagPattern(final Pattern htmlTagPattern) {

		<connection>scm:git:******@****.***:codelibs/fess-crawler.git</connection>
		<developerConnection>scm:git:******@****.***:codelibs/fess-crawler.git</developerConnection>
		<url>******@****.***:codelibs/fess-crawler.git</url>
	  <tag>HEAD</tag>
  </scm>
	<parent>
		<groupId>org.codelibs.fess</groupId>
		<artifactId>fess-parent</artifactId>
		<version>15.3.0-SNAPSHOT</version>
	</parent>
	<modules>
		<module>fess-crawler</module>

		<connection>scm:git:******@****.***:codelibs/fess-suggest.git</connection>
		<developerConnection>scm:git:******@****.***:codelibs/fess-suggest.git</developerConnection>
		<url>https://github.com/codelibs/fess-suggest</url>
	  <tag>HEAD</tag>
  </scm>
	<parent>
		<groupId>org.codelibs.fess</groupId>
		<artifactId>fess-parent</artifactId>
		<version>15.3.0-SNAPSHOT</version>
		<relativePath />
	</parent>
	<build>
		<plugins>
			<plugin>

 * </ul>
 *
 * <h2>Usage Example:</h2>
 * <pre>
 * {@code
 * String escapedXml = XmlUtil.escapeXml("<tag>value</tag>");
 * Map<String, Object> dataMap = XmlUtil.getDataMap(accessResultData);
 * }
 * </pre>
 *
 * <h2>Thread Safety:</h2>
 * <p>
 * This class is thread-safe as it does not maintain any state.
 * </p>
 *

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */

    /**
     * Identifies the time that the corresponding Sitemap file was modified. It
     * does not correspond to the time that any of the pages listed in that
     * Sitemap were changed. The value for the lastmod tag should be in W3C
     * Datetime format.
     *
     * By providing the last modification timestamp, you enable search engine
     * crawlers to retrieve only a subset of the Sitemaps in the index i.e. a