- ✅ Whitespace and empty string handling

---

### 3. ArchiveExtractorErrorHandlingTest.java
**Purpose**: Test improved error handling in archive extractors.

**Key Test Areas**:
- Enhanced error messages
- Partial extraction (continues on failure)
- Invalid archive handling
- Empty archive handling
- Mixed valid/invalid entries

**Covered Extractors**:
- ZipExtractor
- TarExtractor

**Test Count**: 12 tests

            assertTrue("Error message should indicate failure",
                    e.getMessage().contains("Failed to extract") || e.getMessage().contains("No entries could be processed"));
        }
    }

    /**
     * Test that TarExtractor handles invalid archive gracefully.

import java.io.BufferedInputStream;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ExtractData;

import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ExtractData;

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {

- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

## Architecture

### Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core framework

labels.pathmap_list=Lista de mapeo de rutas
labels.log_file_list=Lista de archivos de registro
labels.labeltype_list=Lista de tipos de etiquetas
labels.key_match_list=Lista de coincidencias de claves
labels.job_log_list=Lista de registros de trabajos
labels.group_list=Lista de grupos
labels.file_config_list=Lista de configuración de archivos
labels.file_auth_list=Lista de autenticación de archivos
labels.failure_url_list=Lista de URL fallidas

			<param name="jar.version" value="2.1.1" />
			<param name="file.version" value="2.1.1" />
		</antcall>
		<!-- kopf -->
		<get dest="${target.dir}/kopf.zip">
			<url url="https://github.com/codelibs/fess-kopf/archive/${kopf.branch}.zip" />
		</get>
		<delete dir="${site.dir}/kopf" />
		<unzip dest="${site.dir}/kopf" src="${target.dir}/kopf.zip">
			<patternset>
				<include name="fess-kopf-${kopf.branch}/_site/**" />
			</patternset>

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<version>3.4.2</version>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.corelib</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-surefire-plugin</artifactId>
				<version>3.5.3</version>
			</plugin>

labels.facet_filetype_rtf=Texte enrichi
labels.facet_filetype_chm=Aide HTML compilée
labels.facet_filetype_zip=Archive ZIP
labels.facet_filetype_7z=Archive 7z
labels.facet_filetype_bz=Archive BZIP
labels.facet_filetype_bz2=Archive BZIP2
labels.facet_filetype_tar=Archive TAR
labels.facet_filetype_rar=Archive RAR
labels.facet_filetype_3gp=Vidéo 3gp
labels.facet_filetype_3g2=Vidéo 3g2
labels.facet_filetype_avi=Vidéo AVI