<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">

	<component class="org.lastaflute.di.naming.StyledNamingConvention">
	</component>

	<!-- Container -->
	<component name="crawlerContainer"
		class="org.codelibs.fess.crawler.container.LastaCrawlerContainer">
	</component>

/**
 * 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

 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PasswordBasedExtractor.class);

    /** Map of regex patterns to passwords for static password configuration. */

 *
 */
/**
 * This class is an implementation of a URL filter.
 */
public class UrlFilterImpl implements UrlFilter {

    /**
     * Creates a new UrlFilterImpl instance.
     */
    public UrlFilterImpl() {
        // NOP
    }

    private static final Logger logger = LogManager.getLogger(UrlFilterImpl.class);

    /**
     * The crawler container.
     */

 * and handles potential exceptions during parsing.
 * The class also includes inner classes for handling XML sitemap and sitemap index parsing.
 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

    /** The size of the preload buffer for checking file format. */
    protected int preloadSize = 512;

    /**

import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractCharFilterFactory;

public class ProlongedSoundMarkCharFilterFactory extends AbstractCharFilterFactory {
    private char replacement;

    public ProlongedSoundMarkCharFilterFactory(final IndexSettings indexSettings, final Environment env, final String name,

 */
package org.codelibs.fess.crawler.entity;

import java.util.function.Function;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

public class ResultDataTest extends PlainTestCase {

    public void test_setRawData() {
        // ## Arrange ##
        final ResultData resultData = new ResultData();
        final Object rawData = new Object();

import java.util.ArrayList;
import java.util.List;

/**
 * Represents a set of Sitemaps, which can be either a UrlSet or an Index.
 * This class provides methods to manage a list of Sitemap objects and determine the type of the SitemapSet.
 *
 */
public class SitemapSet implements Serializable {

    private static final long serialVersionUID = 1L;

    /** Constant for UrlSet type. */

 * use a tokenizer to process the input.
 *
 * <p>
 * The class provides methods to initialize the converter, convert strings, and
 * check if a tokenizer is enabled. It also includes methods to create a token
 * stream and extract reading information from the stream's attributes, although
 * the tokenizer-related functionality is currently commented out.
 * </p>
 */
public class KatakanaConverter implements ReadingConverter {

import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * Extracts text content from HTML documents.
 */
public class HtmlExtractor extends AbstractXmlExtractor {
    /** Logger for this class. */
    protected static final Logger logger = LogManager.getLogger(HtmlExtractor.class);

    /** Pattern for extracting charset from meta tags. */