import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**

/**
 * The {@code MemoryDataHelper} class provides a helper for managing crawler data in memory.
 * It stores URL queues, access results, and URL patterns for inclusion and exclusion.
 * This class is designed to be used in a single-threaded environment or with external synchronization.
 *
 * <p>It uses {@code Map} and {@code Queue} data structures to hold the data. The class provides

import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(TarExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**

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

public class CharTypeFilterFactory extends AbstractTokenFilterFactory {

    private final boolean alphabetic;

    private final boolean digit;

    private final boolean letter;

 * </ul>
 *
 * <p>Supported languages are defined in the SUPPORTED_LANGUAGES array.</p>
 *
 * <p>Inner class:</p>
 * <ul>
 *   <li>DefaultContentsAnalyzer: Implements the SuggestAnalyzer interface to analyze text and retrieve tokens using
 *       the configured analyzers.</li>
 * </ul>
 *
 * <p>Protected static class:</p>
 * <ul>

 *
 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *
 * <p>It also handles the exclusion of search words based on certain criteria and manages the
 * maximum length of analyzed content.</p>
 *
 * <p>Methods in this class may throw SuggesterException in case of failures during the parsing process.</p>

        container.singleton("pdfExtractor", PdfExtractor.class)//
                .singleton("pdfExtractorForPdfPassword", PdfExtractor.class)//
                .singleton("mimeTypeHelper", MimeTypeHelperImpl.class)//
                .singleton("tikaExtractor", TikaExtractor.class)//
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {

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

/**
 * @author shinsuke
 *
 */
public class TextExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(TextExtractorTest.class);

    public TextExtractor textExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

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

	<component name="robotsTxtHelper" class="org.codelibs.fess.crawler.helper.RobotsTxtHelper"
		instance="prototype">
	</component>

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

public class PatternConcatenationFilterFactory extends AbstractTokenFilterFactory {

    private Pattern pattern1;

    private Pattern pattern2;