* </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>
 *   <li>Handling unsupported URLs</li>
 *   <li>Checking last modified dates</li>
 *   <li>Getting content</li>
 *   <li>Handling redirects</li>
 *   <li>Processing responses</li>
 *   <li>Handling exceptions during crawling and child URL processing</li>
 *   <li>Handling cases where no URL is in the queue</li>

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * UnsupportedExtractException is thrown when the content extraction is not supported.
 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */
public class UnsupportedExtractException extends ExtractException {

        return clientFactory.getClient(url);
    }

    /**
     * Checks if the content has been updated since the last crawl.
     * @param client The crawler client.
     * @param urlQueue The URL queue entry.
     * @return true if content is updated, false otherwise.
     */
    protected boolean isContentUpdated(final CrawlerClient client, final UrlQueue<?> urlQueue) {

import org.opensearch.action.update.UpdateRequest;
import org.opensearch.action.update.UpdateRequestBuilder;
import org.opensearch.action.update.UpdateResponse;
import org.opensearch.common.action.ActionFuture;
import org.opensearch.common.settings.Settings;
import org.opensearch.common.unit.TimeValue;
import org.opensearch.core.action.ActionListener;
import org.opensearch.core.action.ActionResponse;
import org.opensearch.index.IndexNotFoundException;

 */
package org.codelibs.opensearch.extension.analysis;

import java.io.Reader;

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

    public static final String CREATE_TIME = "createTime";

    /**
     * Field name for execution time.
     */
    public static final String EXECUTION_TIME = "executionTime";

    /**
     * Field name for content length.
     */
    public static final String CONTENT_LENGTH = "contentLength";

    /**
     * Field name for last modified timestamp.
     */
    public static final String LAST_MODIFIED = "lastModified";

 */
package org.codelibs.opensearch.extension.kuromoji.index.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ja.JapaneseNumberFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.codelibs.analysis.ja.KanjiNumberFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from an input stream as plain text.
 */
public class TextExtractor extends AbstractExtractor {

    /**
     * The encoding for text.
     */
    protected String encoding = Constants.UTF_8;

    /**