* <p>
 * The thread also manages the active thread count using {@code crawlerContext.activeThreadCountLock}
 * and provides methods for logging messages using {@link LogHelper}.
 * </p>
 *
 * <p>
 * The crawling process continues until the crawler status is {@link CrawlerStatus#DONE} or the
 * {@link #isContinue(int)} method returns {@code false}.
 * </p>
 *
 */
public class CrawlerThread implements Runnable {
    /**

            throw e;
        }
    }

    /**
     * FtpInfo is a helper class that encapsulates information about an FTP URL.
     * It parses the URL and provides methods to retrieve the host, port, parent directory,
     * and file name. It also provides methods to construct URLs for child paths.
     *
     * <p>
     * Usage example:
     * </p>
     *
     * <pre>
     * {@code

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

import java.io.InputStream;
import java.util.Map;

/**
 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.
 * It allows content type detection based on the stream's content and/or filename.
 */
public interface MimeTypeHelper {
    /**

        throw new CrawlerSystemException("GET method is not supported.");
    }

    /**
     * Performs a HEAD request.
     * @param url The URL to request.
     * @return The ResponseData.
     */
    protected ResponseData doHead(final String url) {
        throw new CrawlerSystemException("HEAD method is not supported.");
    }

    /**
     * Performs a POST request.

{
    "properties": {
      "depth": {
        "type": "integer"
      },
      "parentUrl": {
        "type": "keyword"
      },
      "method": {
        "type": "keyword"
      },
      "weight": {
        "type": "float"
      },
      "createTime": {
        "type": "long"
      },
      "lastModified": {
        "type": "long"
      },
      "sessionId": {
        "type": "keyword"
      },

     * Constructs a new exception with the specified detail message and cause.
     *
     * @param message the detail message
     * @param cause the cause (which is saved for later retrieval by the {@link Throwable#getCause()} method)
     */
    public ExecutionTimeoutException(final String message, final Throwable cause) {
        super(message, cause);
    }

    /**
     * Constructs a new exception with the specified detail message.

 * This class provides methods to add, retrieve, and manage extractors based on a key.
 * It also includes a builder for creating extractors.
 *
 * <p>
 * The factory maintains a map of keys to an array of {@link Extractor} objects.
 * When multiple extractors are associated with a single key, they are sorted by weight
 * in descending order. The {@link #getExtractor(String)} method returns a composite

 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>
 * The transform method takes a ResponseData object, checks if it has a response body,
 * and then reads the body into a byte array. This byte array is then set as the data
 * in the ResultData object.
 * </p>
 *
 * <p>

     * @return this builder instance for method chaining
     */
    public ExtractorBuilder mimeType(final String mimeType) {
        this.mimeType = mimeType;
        return this;
    }

    /**
     * Sets the filename of the content to extract.
     *
     * @param filename the filename to set
     * @return this builder instance for method chaining
     */

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

import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**