* </pre>
 *
 * @see com.ibm.icu.text.Transliterator
 */
public class ICUNormalizer implements Normalizer {
    /** The transliterator used for normalization. */
    protected Transliterator transliterator;

    /**
     * Constructor for ICUNormalizer.
     * @param transliteratorId The ID of the transliterator to use.
     */
    public ICUNormalizer(final String transliteratorId) {

     * @param name the name of the component
     * @param cls the class of the component
     * @param initializer the initializer consumer for the component
     * @param destroyer the destroyer consumer for the component
     * @return this container instance for method chaining
     */
    public <T> StandardCrawlerContainer singleton(final String name, final Class<T> cls, final Consumer<T> initializer,

we first engineer the change to keep as many existing programs working as possible.
For the remaining programs,
we define a new GODEBUG setting that
allows individual programs to opt back in to the old behavior.
A GODEBUG setting may not be added if doing so is infeasible,
but that should be extremely rare.

GODEBUG settings added for compatibility will be maintained
for a minimum of two years (four Go releases).

    /**
     * Adds a URL to the include filter list for the specified session.
     *
     * @param sessionId the ID of the session for which the URL filter is being added
     * @param url the URL to be included in the filter list
     */
    void addIncludeUrlFilter(String sessionId, String url);

    /**
     * Adds a list of URLs to the include filter for a given session.
     *

 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.client.http;

import java.util.Date;

import org.apache.http.client.methods.HttpUriRequest;

     * Filter type for exclude filters.
     */
    private static final String EXCLUDE = "exclude";

    /**
     * Cache for include filters.
     */
    protected LoadingCache<String, List<Pattern>> includeFilterCache;

    /**
     * Cache for exclude filters.
     */
    protected LoadingCache<String, List<Pattern>> excludeFilterCache;

    /**
     * The expiration time for the filter cache in seconds.
     */

    /** The unique identifier for the access result data. */
    protected IDTYPE id;

    /** The name of the transformer associated with this access result data. */
    protected String transformerName;

    /** The data as a byte array. */
    protected byte[] data;

    /** The encoding used for the access result data. */
    protected String encoding;

    /**

 *   <li>activeExternalHost: The external IP address to use for active mode FTP.</li>
 *   <li>activeMinPort: The minimum port number for active mode FTP.</li>
 *   <li>activeMaxPort: The maximum port number for active mode FTP.</li>
 *   <li>autodetectEncoding: Whether to automatically detect UTF-8 encoding.</li>
 *   <li>connectTimeout: The timeout for establishing a connection to the FTP server.</li>

 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.File;
import java.io.IOException;
import java.util.List;

 * </p>
 *
 * <p>
 * The class uses a {@link CrawlerContainer} for managing crawler components and
 * supports dependency injection via the {@link Resource} annotation.
 * </p>
 */
public class ExtractorFactory {

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

    /** Container for managing crawler components */
    @Resource