});

            // Keep only the specified number of versions
            for (int i = keepVersions; i < archives.size(); i++) {
                removeSessionKey(archives.get(i));
                removed++;
            }
        }

        if (removed > 0) {
            log.info("Cleaned up {} archived key versions", removed);
        }
    }

    private int extractVersion(String archivedKey) {

- ✅ 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

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;

            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.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 {

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

- **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

      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.