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

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;

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

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.RequestData.Method;

/**
 * Builder class for creating RequestData objects using a fluent interface.

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.mail.Address;
import jakarta.mail.BodyPart;

 */
package org.codelibs.fess.crawler.service.impl;

import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import org.codelibs.fess.crawler.entity.OpenSearchUrlFilter;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

    /**
     * Interval in milliseconds between crawler thread executions.
     * Used to control the rate at which new crawler threads are started
     * and the frequency of status checks.
     */
    protected long crawlingExecutionInterval = Constants.DEFAULT_CRAWLING_EXECUTION_INTERVAL;

    /**
     * Thread priority for crawler threads.
     * Defaults to normal thread priority.
     */

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

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

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

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

import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke

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

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

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

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */

 */
package org.codelibs.fess.crawler;

/**
 * Enum representing the status of a crawler.
 * It can be INITIALIZING, RUNNING, or DONE.
 */
public enum CrawlerStatus {
    /**
     * The crawler is initializing.
     */
    INITIALIZING,

    /**
     * The crawler is currently running.
     */
    RUNNING,

    /**
     * The crawler has completed its task.
     */
    DONE;

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

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */