/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.
 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *
 * <p>
 * A Sitemap file provides search engines with a list of URLs available for crawling.
 * This class encapsulates the essential attributes of a Sitemap entry, allowing for efficient management

 * It provides functionality to manage passwords for different file patterns using regular expressions.
 *
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>
 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.

import org.apache.lucene.analysis.TokenizerFactory;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.opensearch.core.common.Strings;

import com.ibm.icu.text.Transliterator;

/**
 * {@link KatakanaConverter} converts input strings to katakana representation.
 * It utilizes a transliterator to convert hiragana to katakana and can optionally
 * use a tokenizer to process the input.
 *
 * <p>

 * and does not perform any validation on the input.</p>
 *
 * @see Normalizer
 */
public class HankakuKanaToZenkakuKana implements Normalizer {
    /**
     * Constructs a new {@link HankakuKanaToZenkakuKana}.
     */
    public HankakuKanaToZenkakuKana() {
        // nothing
    }

        childUrlRuleMap.put("//AREA", "href");
        childUrlRuleMap.put("//FRAME", "src");
        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");
        fileTransformer.setChildUrlRuleMap(childUrlRuleMap);
    }

    protected void setBaseDir() throws IOException {

        childUrlRuleMap.put("//AREA", "href");
        childUrlRuleMap.put("//FRAME", "src");
        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");
        htmlTransformer.setChildUrlRuleMap(childUrlRuleMap);
    }

    public void test_name() {

import org.opensearch.search.sort.SortOrder;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;
import jakarta.annotation.Resource;

/**
 * OpenSearchUrlQueueService is an implementation of {@link UrlQueueService} for OpenSearch.
 *
 * @author shinsuke
 *
 */
public class OpenSearchUrlQueueService extends AbstractCrawlerService implements UrlQueueService<OpenSearchUrlQueue> {
    /**
     * Logger instance.

import org.codelibs.core.collection.LruHashSet;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * The {@link CrawlerContext} class holds the context information for a crawler execution.
 * It contains various attributes related to the crawler's state, configuration, and runtime data.

      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions

 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.
 * The class also includes inner classes for handling XML sitemap and sitemap index parsing.