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

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * NullResponseProcessor is a class that implements the ResponseProcessor interface.

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

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.impl.UrlFilterServiceImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

 * 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>

labels.crawling_info_delete_all_cancel=Annulla
labels.crawling_info_thread_dump=Dump thread
labels.crawling_info_CrawlerStartTime=Ora di inizio crawler
labels.crawling_info_CrawlerEndTime=Ora di fine crawler
labels.crawling_info_CrawlerExecTime=Tempo di esecuzione crawler
labels.crawling_info_CrawlerStatus=Stato crawler
labels.crawling_info_WebFsCrawlExecTime=Tempo di esecuzione scansione (Web/File)

 */
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;

- **Web Framework**: LastaFlute (MVC framework)
- **DI Container**: Lasta Di
- **Data Access**: DBFlute (type-safe ORM for OpenSearch)
- **Search Engine**: OpenSearch
- **App Server**: Embedded Tomcat
- **Crawler**: fess-crawler library
- **Scheduler**: Lasta Job

## Key Directories

```
src/main/java/org/codelibs/fess/
├── FessBoot.java              # Application entry point
├── app/

 * 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