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

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
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.core.io.FileUtil;
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.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.jodconverter.core.office.OfficeException;

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

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */

 */
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;

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

/**
 * The crawler login failure exception.
 * This exception is thrown when the crawler fails to login to a website.
 *
 */
public class CrawlerLoginFailureException extends CrawlerSystemException {
    private static final long serialVersionUID = 1L;

 */
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="encodingHelper" class="org.codelibs.fess.crawler.helper.EncodingHelper">
		<postConstruct name="addEncodingMapping">
			<arg>"unicode"</arg>
			<arg>"UTF-16LE"</arg>
		</postConstruct>
	</component>

#smart.deploy.mode.location = maihama_env.properties: lasta_di.smart.deploy.mode

# package for smart deploy target e.g. org.docksidestage.app
smart.package1 = org.codelibs.fess.crawler

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.

<!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>