Java 파일 유형 가져오기 – 문서 메타데이터 추출 가이드

<repositories>
   <repository>
      <id>repository.groupdocs.com</id>
      <name>GroupDocs Repository</name>
      <url>https://releases.groupdocs.com/comparison/java/</url>
   </repository>
</repositories>
<dependencies>
   <dependency>
      <groupId>com.groupdocs</groupId>
      <artifactId>groupdocs-comparison</artifactId>
      <version>25.2</version>
   </dependency>
</dependencies>

import com.groupdocs.comparison.Comparer;

public class SetupTest {
    public static void main(String[] args) {
        System.out.println("GroupDocs.Comparison is ready to use!");
        // We'll add actual functionality next
    }
}

import com.groupdocs.comparison.Comparer;
import java.io.IOException;

try (Comparer comparer = new Comparer("YOUR_DOCUMENT_DIRECTORY/source_document.docx")) {
    // We'll extract info here
} catch (Exception e) {
    System.err.println("Error initializing comparer: " + e.getMessage());
}

import com.groupdocs.comparison.interfaces.IDocumentInfo;

try (Comparer comparer = new Comparer("YOUR_DOCUMENT_DIRECTORY/source_document.docx")) {
    try (IDocumentInfo info = comparer.getSource().getDocumentInfo()) {
        // Extract metadata here
    }
} catch (Exception e) {
    System.err.println("Error retrieving document info: " + e.getMessage());
}

try (Comparer comparer = new Comparer("YOUR_DOCUMENT_DIRECTORY/source_document.docx")) {
    try (IDocumentInfo info = comparer.getSource().getDocumentInfo()) {
        // Extract key information
        String fileType = info.getFileType().getFileFormat();
        int pageCount = info.getPageCount();
        long fileSize = info.getSize();
        
        // Display the results
        System.out.printf("File type: %s\n", fileType);
        System.out.printf("Number of pages: %d\n", pageCount);
        System.out.printf("Document size: %d bytes (%.2f KB)\n", 
                         fileSize, fileSize / 1024.0);
    }
} catch (Exception e) {
    System.err.println("Error extracting document info: " + e.getMessage());
}

import com.groupdocs.comparison.Comparer;
import com.groupdocs.comparison.interfaces.IDocumentInfo;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;

public class DocumentMetadataExtractor {
    
    public static void extractDocumentInfo(String filePath) {
        // First, check if file exists
        Path path = Paths.get(filePath);
        if (!Files.exists(path)) {
            System.err.println("File not found: " + filePath);
            return;
        }
        
        try (Comparer comparer = new Comparer(filePath)) {
            try (IDocumentInfo info = comparer.getSource().getDocumentInfo()) {
                displayDocumentInfo(info, filePath);
            }
        } catch (Exception e) {
            System.err.println("Error processing file " + filePath + ": " + e.getMessage());
        }
    }
    
    private static void displayDocumentInfo(IDocumentInfo info, String filePath) {
        String fileName = Paths.get(filePath).getFileName().toString();
        String fileType = info.getFileType().getFileFormat();
        int pageCount = info.getPageCount();
        long fileSize = info.getSize();
        
        System.out.println("=== Document Information ===");
        System.out.printf("File name: %s\n", fileName);
        System.out.printf("File type: %s\n", fileType);
        System.out.printf("Pages: %d\n", pageCount);
        System.out.printf("Size: %d bytes (%.2f KB)\n", fileSize, fileSize / 1024.0);
        System.out.println("============================\n");
    }
    
    public static void main(String[] args) {
        // Test with different file types
        extractDocumentInfo("path/to/your/document.docx");
        extractDocumentInfo("path/to/your/document.pdf");
    }
}

Path filePath = Paths.get(documentPath);
if (!Files.exists(filePath)) {
    throw new IllegalArgumentException("File does not exist: " + documentPath);
}
if (!Files.isReadable(filePath)) {
    throw new IllegalArgumentException("File is not readable: " + documentPath);
}

// Always use try-with-resources
try (Comparer comparer = new Comparer(filePath)) {
    // Process immediately and don't store large objects
    processDocumentInfo(comparer.getSource().getDocumentInfo());
} // Resources automatically cleaned up here

public static boolean isSupportedFormat(String filePath) {
    String extension = FilenameUtils.getExtension(filePath).toLowerCase();
    return Arrays.asList("docx", "doc", "pdf", "txt", "rtf", "odt").contains(extension);
}

// Apply license at application startup
License license = new License();
license.setLicense("path/to/your/license.lic");

// Good - resources cleaned up automatically
try (Comparer comparer = new Comparer(filePath);
     IDocumentInfo info = comparer.getSource().getDocumentInfo()) {
    // Process info
}

// Bad - potential memory leaks
Comparer comparer = new Comparer(filePath);
IDocumentInfo info = comparer.getSource().getDocumentInfo();
// Processing code
// Resources might not be cleaned up properly

public DocumentInfo extractSafely(String filePath) {
    try {
        return extractDocumentInfo(filePath);
    } catch (SecurityException e) {
        log.warn("Access denied for file: " + filePath, e);
        return null;
    } catch (IOException e) {
        log.error("I/O error processing file: " + filePath, e);
        return null;
    } catch (Exception e) {
        log.error("Unexpected error processing file: " + filePath, e);
        return null;
    }
}

public List<DocumentInfo> processDocumentBatch(List<String> filePaths) {
    return filePaths.parallelStream()
                   .map(this::extractSafely)
                   .filter(Objects::nonNull)
                   .collect(Collectors.toList());
}