<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-*" />

- **License**: Apache 2.0
- **DI**: LastaFlute DI
- **Repo**: https://github.com/codelibs/fess-crawler

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+ and 5.x (switchable)
- **Extraction**: Apache Tika, POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Mockito, Testcontainers
- **Storage**: In-memory (default), OpenSearch (optional)
- **Cloud**: AWS SDK v2 (S3), Google Cloud Storage

### Protocols

## 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

				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>

import org.apache.commons.net.ftp.FTPSClient;
import org.apache.commons.net.util.TrustManagerUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.poi.util.StringUtil;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.timer.TimeoutManager;