<version>${jhighlight.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi</artifactId>
			<version>${poi.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>${poi.version}</version>
			<exclusions>
				<exclusion>
					<groupId>stax</groupId>

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

            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final org.apache.poi.hssf.extractor.ExcelExtractor excelExtractor =
                    new org.apache.poi.hssf.extractor.ExcelExtractor(new HSSFWorkbook(in));
            return new ExtractData(excelExtractor.getText());
        } catch (final IOException e) {

        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(in);
            return new ExtractData(wordExtractor.getText());
        } catch (final IOException e) {
            throw new ExtractException(e);
        }
    }

 * 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.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;

/**

 * 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.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**

				<include name="dataformat/commons-compress-*" />
				<include name="dataformat/commons-math3-*" />
				<include name="dataformat/curvesapi-*" />
				<include name="dataformat/orangesignal-csv-*" />
				<include name="dataformat/poi-*" />
				<include name="dataformat/SparseBitSet-*" />
				<include name="dataformat/stax-api-*" />
				<include name="dataformat/xmlbeans-*" />
				<include name="minhash/guava-*" />

				max="${backup.max.history}" compressionLevel="9" />
		</RollingFile>
		<Rewrite name="AppFile">
			<AppenderRef ref="AppRollingFile" />
			<ErrorToWarnRewritePolicy loggers="org.apache.fontbox,org.apache.pdfbox,org.apache.poi" />
		</Rewrite>
		<RollingFile name="StatsFile" fileName="${log.file.basedir}/fess-urls.log"
			filePattern="${log.file.basedir}/fess-urls${backup.date.suffix}-%i.log.gz">
			<PatternLayout>

## Technology Stack

- **Java**: 21+ (requires Java 21 or higher)
- **Build System**: Maven 3.x
- **DI Container**: LastaFlute DI
- **HTTP Client**: Apache HttpComponents
- **Content Extraction**: Apache Tika, Apache POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Testcontainers
- **Storage Backends**: OpenSearch, Memory-based

## Quick Start

### Prerequisites

- Java 21 or higher
- Maven 3.6 or higher

### Installation

import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.poi.util.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;