*/
package org.codelibs.fess.suggest.request;

import org.codelibs.fess.suggest.concurrent.Deferred;
import org.opensearch.transport.client.Client;

/**
 * An abstract class that serves as a builder for creating and executing requests.
 *
 * @param <Req> the type of the request
 * @param <Res> the type of the response
 */

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

import java.io.IOException;
import java.io.InputStream;

/**
 * A wrapper for an {@link InputStream} that ignores the {@link #close()} method call.
 * This can be useful when you want to prevent the underlying input stream from being closed.
 *
 * <p>All other methods delegate to the wrapped input stream.</p>
 *
 */

 */
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 {

    private static final long serialVersionUID = 1L;

    /**
     * Constructor.

     */
    public void add(final FtpAuthentication auth) {
        if (auth != null) {
            authenticationList.add(auth);
        }
    }

    /**
     * Retrieves an FtpAuthentication object that matches the given path.
     * @param path The path to match.
     * @return The matching FtpAuthentication object, or null if no match is found.
     */
    public FtpAuthentication get(final String path) {

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.normalizer;

import com.ibm.icu.text.Transliterator;

/**
 * ICUNormalizer is a class that implements the Normalizer interface and provides
 * functionality to normalize text using ICU4J's Transliterator.
 *
 * <p>This class uses a specified Transliterator to perform text normalization.

import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>

 * HostIntervalController is an implementation of {@link org.codelibs.fess.crawler.interval.IntervalController}
 * that controls the interval between requests to the same host.
 * It uses a ConcurrentMap to store the last access time for each host.
 * The delayBeforeProcessing method is overridden to introduce a delay before processing a URL,
 * ensuring that requests to the same host are not made too frequently.

/**
 * RegexRule is a rule implementation that uses regular expressions to match against the ResponseData.
 * It allows defining multiple regular expressions for different fields of the ResponseData.
 * The rule can be configured to require all regular expressions to match (allRequired = true) or
 * only one of them (allRequired = false). It also supports a default rule that always matches.
 *
 * <p>

     * @param fields The fields to extract from the document.
     * @param tagFieldNames The names of the fields that contain tags.
     * @param roleFieldName The name of the field that contains role information.
     * @param langFieldName The name of the field that contains language information.
     * @param readingConverter The converter to use for reading fields.

     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**
     * The priority of this URL relative to other URLs on your site. Valid