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

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.codelibs.core.exception.IORuntimeException;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.entity.ExtractData;

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="robotsTxtHelper" class="org.codelibs.fess.crawler.helper.RobotsTxtHelper"
		instance="prototype">
	</component>

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

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.SitemapFile;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.SitemapsException;
import org.xml.sax.Attributes;

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

import org.apache.http.auth.AuthScheme;
import org.apache.http.auth.AuthScope;
import org.apache.http.auth.Credentials;
import org.codelibs.fess.crawler.client.http.Authentication;

/**
 * Implementation of the {@link Authentication} interface.

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.util;

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

/**

 * 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.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *

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

import org.codelibs.core.lang.StringUtil;

/**
 * The CrawlerContainer interface provides methods for managing components
 * within a crawler container. It includes methods to retrieve components,
 * check availability, and destroy the container. Additionally, it provides

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.UnsupportedExtractException;

import jakarta.annotation.Resource;

/**
 * Factory class for managing and retrieving {@link Extractor} instances.
 * This class provides methods to add, retrieve, and manage extractors based on a key.