<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>

        } catch (final RuntimeException e) {
            // POI may throw IllegalArgumentException or other RuntimeExceptions
            // for invalid data, which is also acceptable
            assertNotNull("Exception message should not be null", e.getMessage());
        }
    }

    /**
     * Test that MsExcelExtractor throws appropriate exception for invalid data.
     * POI may throw various exceptions depending on the type of invalid data.

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

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+
- **Extraction**: Apache Tika 3.0+, POI 5.3+, PDFBox 3.0+
- **Testing**: JUnit 4, UTFlute, Mockito 5.7.0
- **Storage**: In-memory (default), OpenSearch (optional)

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt

## 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 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;