import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
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;

/**

 * 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>

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

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

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.IOException;

import org.apache.commons.io.IOUtils;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

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

/**
 * Exception thrown during sitemaps processing in the crawler.
 * This exception extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException}
 * and provides constructors for wrapping other exceptions or creating a new exception with a message.
 */

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;
import org.codelibs.fess.crawler.util.FieldConfigs;
import org.codelibs.fess.mylasta.direction.FessConfig;

index.document.suggest.index=fess
# Index name for crawler documents.
index.document.crawler.index=fess_crawler
# Number of primary shards for crawler queue index.
index.document.crawler.queue.number_of_shards=10
# Number of primary shards for crawler data index.
index.document.crawler.data.number_of_shards=10
# Number of primary shards for crawler filter index.
index.document.crawler.filter.number_of_shards=10

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

import java.util.LinkedHashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.

import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;

 */
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;