* </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

    /**
     * Gets the pattern used for matching HTML tags.
     *
     * @return the HTML tag pattern
     */
    public Pattern getHtmlTagPattern() {
        return htmlTagPattern;
    }

    /**
     * Sets the pattern used for matching HTML tags.
     *
     * @param htmlTagPattern the HTML tag pattern to set
     */
    public void setHtmlTagPattern(final Pattern htmlTagPattern) {

    public SuggestIndexer setSupportedFields(final String[] supportedFields) {
        this.supportedFields = supportedFields;
        return this;
    }

    /**
     * Sets the tag field names.
     * @param tagFieldNames The tag field names.
     * @return This SuggestIndexer instance.
     */
    public SuggestIndexer setTagFieldNames(final String[] tagFieldNames) {
        this.tagFieldNames = tagFieldNames;

        final List<String> tagList = new ArrayList<>(item1.getTags().length + item2.getTags().length);
        Collections.addAll(tagList, item1.getTags());
        for (final String tag : item2.getTags()) {
            if (!tagList.contains(tag)) {
                tagList.add(tag);
            }
        }
        mergedItem.tags = tagList.toArray(new String[tagList.size()]);

        /** Index key. */
        public static final String INDEX = "index";
        /** Supported fields key. */
        public static final String SUPPORTED_FIELDS = "supportedFields";
        /** Tag field name key. */
        public static final String TAG_FIELD_NAME = "tagFieldName";
        /** Role field name key. */
        public static final String ROLE_FIELD_NAME = "roleFieldName";

				"text/directory",
				"text/dns",
				"text/ecmascript",
				"text/enriched",
				"text/example",
				"text/parityfec",
				"text/plain",
				"text/prs.fallenstein.rst",
				"text/prs.lines.tag",
				"text/red",
				"text/rfc822-headers",
				"text/richtext",
				"text/rtp-enc-aescm128",
				"text/rtx",
				"text/sgml",
				"text/t140",
				"text/tab-separated-values",

b=a.replace(cb,db);return function(a){return a.getAttribute("id")===b}}):(delete d.find.ID,d.filter.ID=function(a){var b=a.replace(cb,db);return function(a){var c=typeof a.getAttributeNode!==C&&a.getAttributeNode("id");return c&&c.value===b}}),d.find.TAG=c.getElementsByTagName?function(a,b){return typeof b.getElementsByTagName!==C?b.getElementsByTagName(a):void 0}:function(a,b){var c,d=[],e=0,f=b.getElementsByTagName(a);if("*"===a){while(c=f[e++])1===c.nodeType&&d.push(c);return d}return f},d.find....

    <glob pattern="*.xtest"/>
    <glob pattern="*.xweb"/>
    <glob pattern="*.xwelcome"/>
  </mime-type>

  <mime-type type="text/prs.fallenstein.rst"/>
  <mime-type type="text/prs.lines.tag">
    <glob pattern="*.dsc"/>
  </mime-type>
  <mime-type type="text/red"/>
  <mime-type type="text/rfc822-headers"/>
  <mime-type type="text/richtext">
    <glob pattern="*.rtx"/>
  </mime-type>