import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {
        super();
    }

    /**
     * Extracts text from the Word input stream.

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 {

import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;
import org.opensearch.index.analysis.Analysis;

public class PosConcatenationFilterFactory extends AbstractTokenFilterFactory {

    private final Set<String> posTags = new HashSet<>();

    public PosConcatenationFilterFactory(final IndexSettings indexSettings, final Environment environment, final String name,

import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

public class ReloadableKeywordMarkerFilterFactory extends AbstractTokenFilterFactory {

    private final Path keywordPath;

    private final long reloadInterval;

import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

public class ReloadableStopFilterFactory extends AbstractTokenFilterFactory {

    private final Path stopwordPath;

    private final long reloadInterval;

    private final boolean ignoreCase;

import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractCharFilterFactory;

public class IterationMarkCharFilterFactory extends AbstractCharFilterFactory {

    public IterationMarkCharFilterFactory(final IndexSettings indexSettings, final Environment env, final String name,
            final Settings settings) {
        super(indexSettings, name);

 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *
 */
public class DefaultIntervalController extends AbstractIntervalController {

    /** Delay in milliseconds after processing a URL */
    protected long delayMillisAfterProcessing = 0L;

    /** Delay in milliseconds when no URL is in the queue */

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */
public interface UrlQueueService<QUEUE extends UrlQueue<?>> {

    /**
     * Updates the session ID.
     *
     * @param oldSessionId The old session ID.
     * @param newSessionId The new session ID.
     */

import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;
import org.opensearch.lucene.analysis.miscellaneous.DisableGraphAttribute;

public class DisableGraphFilterFactory extends AbstractTokenFilterFactory {

    public DisableGraphFilterFactory(final IndexSettings indexSettings, final Environment environment, final String name,
            final Settings settings) {

 */
package org.codelibs.fess.crawler.client.http.form;

import java.util.Collections;

import org.dbflute.utflute.core.PlainTestCase;

public class FormSchemeTest extends PlainTestCase {

    public void test_getTokenValue() {
        FormScheme formScheme = new FormScheme(Collections.emptyMap());

        String tokenPattern = "name=\"authenticity_token\" +value=\"([^\"]+)\"";