dist: xenial

sudo: required
services:
  - docker

language: java

jdk:
  - openjdk11

cache:
  directories:
    - $HOME/.m2/repository

before_script:
  - java -version

script:

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

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

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**

package org.codelibs.fess.crawler.rule;

import java.io.Serializable;

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

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic

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

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.log;

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {

 */
package org.codelibs.fess.crawler.extractor;

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

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

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and
 * optionally override the default weight value.
 */
public interface Extractor {

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

/**
 * The Transformer interface defines methods for transforming response data
 * and retrieving data from access results.
 */
public interface Transformer {

    /**
     * Transforms the given ResponseData into a ResultData.
     *

 * It encapsulates the delay logic and exception handling, allowing subclasses to focus on
 * defining the specific delay behavior for each stage.
 *
 * <p>
 * This class defines the contract for delaying the crawling process at various points, such as:
 * </p>
 * <ul>
 *   <li>Before processing a URL ({@link #delayBeforeProcessing()})</li>

     * @param settings the suggest settings to apply
     * @param index the name of the index from which documents will be deleted
     * @param queryBuilder the query that defines which documents to delete
     * @return a result object containing information about the delete operation
     */

/**
 * Abstract base class for CrawlerClient implementations.
 * Provides common functionality for handling initialization parameters,
 * content length checks, and default method implementations.
 * It defines the basic structure and configuration options for crawler clients.
 */
public abstract class AbstractCrawlerClient implements CrawlerClient {