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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.exception.FessSystemException;

<!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="contentLengthHelper"
		class="org.codelibs.fess.crawler.helper.ContentLengthHelper" instance="singleton">
		<property name="defaultMaxLength">10485760</property><!-- 10M -->
		<postConstruct name="addMaxLength">
			<arg>"text/html"</arg>

    /**
     * The unique identifier of the crawling information entry being edited.
     * This is a required field for identifying which crawling info to update.
     */
    @Required
    @Size(max = 1000)
    public String id;

    /**
     * The session identifier of the crawling session.
     * This is a required field that identifies the specific crawling session.
     * Maximum length is 20 characters.
     */

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

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

import org.apache.poi.hslf.usermodel.HSLFShape;
import org.apache.poi.hslf.usermodel.HSLFSlideShow;
import org.apache.poi.hslf.usermodel.HSLFTextParagraph;
import org.apache.poi.sl.extractor.SlideShowExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;

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

import org.codelibs.fess.crawler.transformer.Transformer;

/**
 * An abstract base class for transformers.
 * Provides basic implementation for managing the transformer's name.
 *
 */

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

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

import org.apache.poi.hdgf.extractor.VisioTextExtractor;
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 . file.

 */
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

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.app.service.FileAuthenticationService;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.client.ftp.FtpAuthentication;
import org.codelibs.fess.crawler.client.smb.SmbAuthentication;
import org.codelibs.fess.helper.SystemHelper;
import org.codelibs.fess.opensearch.config.bsentity.BsFileConfig;

 */
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;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
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.