<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>

				<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-*" />

## 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;