}

    /**
     * Gets the pattern for extracting charset from meta tags.
     *
     * @return the meta charset pattern
     */
    public Pattern getMetaCharsetPattern() {
        return metaCharsetPattern;
    }

    /**
     * Sets the pattern for extracting charset from meta tags.
     *
     * @param metaCharsetPattern the meta charset pattern to set
     */

 *
 * <p>
 * The class uses a logger to log debug messages.
 * It also uses an AtomicBoolean to track whether the thread is running.
 * </p>
 *
 * <p>
 * The expired method is called when a timeout occurs.
 * It interrupts the running thread up to a maximum number of times.
 * The stop method is called to stop the timeout target.
 * </p>
 */

        return sessionId == null ? null : sessionId.toString();
    }

    /**
     * Extracts the session ID from the target object using reflection.
     *
     * @param target The target object.
     * @return The session ID string, or null if not found.
     */
    private String getSessionId(final Object target) {
        final BeanDesc beanDesc = BeanDescFactory.getBeanDesc(target.getClass());

                    target.setUrl(getFieldValue(fields.get("url"), String.class));
                    target.setExecutionTime(getFieldValue(fields.get("executionTime"), Integer.class));
                    target.setContentLength(getFieldValue(fields.get("contentLength"), Long.class));
                    target.setRuleId(getFieldValue(fields.get("ruleId"), String.class));

package org.codelibs.fess.crawler.filter;

/**
 * UrlFilter checks if a given url is a target one.
 *
 * @author shinsuke
 *
 */
public interface UrlFilter {

    /**
     * Initialize a url filter by sessionId.
     *
     * @param sessionId Session ID
     */
    void init(String sessionId);

    /**
     * Check if a given url is a target.
     *
     * @param url URL
     * @return true if url is matched

     *
     * @return the charset
     */
    public String getCharset() {
        return charset;
    }

    /**
     * Sets the character set used for SMB1 operations.
     *
     * @param charset the charset to set
     */
    public void setCharset(final String charset) {
        this.charset = charset;
    }

    /**

     * Adds a conversion rule.
     *
     * @param target The target string.
     * @param replacement The replacement string.
     */
    public void add(final String target, final String replacement) {
        if (target == null || replacement == null) {
            throw new CrawlerSystemException("Target or replacement cannot be null.");
        }
        convertMap.put(target, replacement);
    }

    /**

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

import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.apache.http.Header;
import org.apache.http.HttpEntity;
import org.apache.http.HttpHost;

 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>

    protected CrawlerContainer crawlerContainer;

    /**
     * The name of the component to be retrieved from the CrawlerContainer.
     */
    protected String componentName;

    /**
     * The listener that is called when a pooled object is destroyed.
     */
    protected OnDestroyListener<T> onDestroyListener;

    /**
     * Creates a new object instance from the crawler container.