Java Get File Type – Trích xuất siêu dữ liệu tài liệu qua GroupDocs

<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 DocumentMetadataExtractor {
    public static void main(String[] args) {
        String sourceFilePath = "YOUR_DOCUMENT_DIRECTORY/sample.docx";
        
        try (Comparer comparer = new Comparer(sourceFilePath)) {
            System.out.println("GroupDocs.Comparison is ready to use!");
            // We'll add metadata extraction code here
        } catch (Exception e) {
            System.err.println("Error initializing GroupDocs: " + e.getMessage());
            e.printStackTrace();
        }
    }
}

import com.groupdocs.comparison.Comparer;
import com.groupdocs.comparison.result.IDocumentInfo;

public class FilePathMetadataExtraction {
    public static void extractMetadataFromPath(String filePath) {
        try (Comparer comparer = new Comparer(filePath)) {
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            
            System.out.printf("
File Analysis Results:
File type: %s
Number of pages: %d
Document size: %d bytes (%.2f KB)%n", 
                info.getFileType().getFileFormat(), 
                info.getPageCount(), 
                info.getSize(),
                info.getSize() / 1024.0);
        } catch (Exception e) {
            System.err.println("Failed to extract metadata: " + e.getMessage());
            e.printStackTrace();
        }
    }
    
    public static void main(String[] args) {
        String documentPath = "YOUR_DOCUMENT_DIRECTORY/sample.pdf";
        extractMetadataFromPath(documentPath);
    }
}

import com.groupdocs.comparison.Comparer;
import com.groupdocs.comparison.result.IDocumentInfo;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.IOException;

public class InputStreamMetadataExtraction {
    public static void extractMetadataFromStream(String filePath) {
        try (InputStream sourceStream = new FileInputStream(filePath);
             Comparer comparer = new Comparer(sourceStream)) {
            
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            
            System.out.println("Document Metadata Analysis:");
            System.out.println("==========================");
            System.out.printf("File Format: %s%n", info.getFileType().getFileFormat());
            System.out.printf("Total Pages: %d%n", info.getPageCount());
            System.out.printf("File Size: %d bytes%n", info.getSize());
            System.out.printf("Size (Human Readable): %s%n", formatFileSize(info.getSize()));
            
        } catch (IOException e) {
            System.err.println("IO Error: " + e.getMessage());
        } catch (Exception e) {
            System.err.println("Metadata extraction failed: " + e.getMessage());
            e.printStackTrace();
        }
    }
    
    // Helper method to make file sizes more readable
    private static String formatFileSize(long size) {
        if (size < 1024) return size + " bytes";
        if (size < 1024 * 1024) return String.format("%.2f KB", size / 1024.0);
        if (size < 1024 * 1024 * 1024) return String.format("%.2f MB", size / (1024.0 * 1024.0));
        return String.format("%.2f GB", size / (1024.0 * 1024.0 * 1024.0));
    }
    
    public static void main(String[] args) {
        String documentPath = "YOUR_DOCUMENT_DIRECTORY/report.xlsx";
        extractMetadataFromStream(documentPath);
    }
}

public class DocumentCatalogSystem {
    public void catalogDocument(String filePath) {
        try (Comparer comparer = new Comparer(filePath)) {
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            
            // Store in database or index for search
            DocumentRecord record = new DocumentRecord();
            record.setFileType(info.getFileType().getFileFormat());
            record.setPageCount(info.getPageCount());
            record.setFileSize(info.getSize());
            record.setFilePath(filePath);
            
            // Save to your database here
            saveDocumentRecord(record);
            
        } catch (Exception e) {
            logError("Failed to catalog document: " + filePath, e);
        }
    }
}

public class LegalDocumentValidator {
    public boolean validateSubmission(String documentPath) {
        try (Comparer comparer = new Comparer(documentPath)) {
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            
            // Check if document meets legal requirements
            boolean isValidFormat = isAcceptedFormat(info.getFileType().getFileFormat());
            boolean hasValidPageCount = info.getPageCount() > 0 && info.getPageCount() <= 50;
            boolean isValidSize = info.getSize() <= 10 * 1024 * 1024; // 10MB max
            
            return isValidFormat && hasValidPageCount && isValidSize;
            
        } catch (Exception e) {
            return false; // Invalid if we can't process it
        }
    }
    
    private boolean isAcceptedFormat(String format) {
        return Arrays.asList("PDF", "DOCX", "DOC").contains(format.toUpperCase());
    }
}

public class BatchDocumentProcessor {
    public void processDocumentDirectory(String directoryPath) {
        File directory = new File(directoryPath);
        File[] files = directory.listFiles((dir, name) -> 
            name.toLowerCase().endsWith(".pdf") || 
            name.toLowerCase().endsWith(".docx") ||
            name.toLowerCase().endsWith(".xlsx"));
        
        if (files == null) {
            System.out.println("No documents found in directory");
            return;
        }
        
        System.out.println("Processing " + files.length + " documents...");
        
        for (File file : files) {
            processDocument(file.getAbsolutePath());
        }
    }
    
    private void processDocument(String filePath) {
        try (Comparer comparer = new Comparer(filePath)) {
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            
            System.out.printf("%s: %s, %d pages, %s%n", 
                new File(filePath).getName(),
                info.getFileType().getFileFormat(),
                info.getPageCount(),
                formatFileSize(info.getSize()));
                
        } catch (Exception e) {
            System.err.println("Error processing " + filePath + ": " + e.getMessage());
        }
    }
}

public static boolean processDocumentSafely(String filePath) {
    File file = new File(filePath);
    
    if (!file.exists()) {
        System.err.println("File not found: " + filePath);
        return false;
    }
    
    if (!file.canRead()) {
        System.err.println("Cannot read file: " + filePath);
        return false;
    }
    
    try (Comparer comparer = new Comparer(filePath)) {
        // Your metadata extraction code here
        return true;
    } catch (Exception e) {
        System.err.println("Processing failed: " + e.getMessage());
        return false;
    }
}

public static boolean isSupportedFormat(String filePath) {
    String extension = filePath.substring(filePath.lastIndexOf('.') + 1).toLowerCase();
    Set<String> supportedFormats = Set.of(
        "pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx", 
        "txt", "rtf", "odt", "ods", "odp"
    );
    return supportedFormats.contains(extension);
}

public static void processLargeDocument(String filePath) {
    // Set JVM options: -Xmx2g -XX:+UseG1GC
    
    System.gc(); // Suggest garbage collection before processing
    
    try (Comparer comparer = new Comparer(filePath)) {
        IDocumentInfo info = comparer.getSource().getDocumentInfo();
        
        if (info.getSize() > 100 * 1024 * 1024) { // 100 MB
            System.out.println("Warning: Processing large file (" + 
                formatFileSize(info.getSize()) + ")");
        }
        
        // Process document
        
    } catch (OutOfMemoryError e) {
        System.err.println("File too large to process: " + filePath);
        // Consider splitting or using a streaming approach
    }
}

public class LicenseManager {
    private static boolean licenseSet = false;
    
    public static void setLicense() {
        if (!licenseSet) {
            try {
                License license = new License();
                license.setLicense("path/to/your/license.lic");
                licenseSet = true;
                System.out.println("License applied successfully");
            } catch (Exception e) {
                System.err.println("License error: " + e.getMessage());
                System.out.println("Running in evaluation mode");
            }
        }
    }
}

public class OptimizedDocumentProcessor {
    private static final int MAX_CONCURRENT_PROCESSES = Runtime.getRuntime().availableProcessors();
    private ExecutorService executorService = Executors.newFixedThreadPool(MAX_CONCURRENT_PROCESSES);
    
    public void processDocumentsConcurrently(List<String> filePaths) {
        List<Future<DocumentMetadata>> futures = new ArrayList<>();
        
        for (String filePath : filePaths) {
            Future<DocumentMetadata> future = executorService.submit(() -> {
                return extractMetadata(filePath);
            });
            futures.add(future);
        }
        
        // Collect results
        for (Future<DocumentMetadata> future : futures) {
            try {
                DocumentMetadata metadata = future.get(30, TimeUnit.SECONDS);
                processMetadata(metadata);
            } catch (TimeoutException e) {
                System.err.println("Document processing timed out");
            }
        }
    }
}

public class CachedMetadataExtractor {
    private static final Map<String, DocumentMetadata> metadataCache = new ConcurrentHashMap<>();
    
    public DocumentMetadata getDocumentMetadata(String filePath) {
        File file = new File(filePath);
        String cacheKey = filePath + "_" + file.lastModified();
        
        return metadataCache.computeIfAbsent(cacheKey, key -> {
            return extractMetadataInternal(filePath);
        });
    }
    
    private DocumentMetadata extractMetadataInternal(String filePath) {
        try (Comparer comparer = new Comparer(filePath)) {
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            return new DocumentMetadata(
                info.getFileType().getFileFormat(),
                info.getPageCount(),
                info.getSize()
            );
        } catch (Exception e) {
            throw new RuntimeException("Failed to extract metadata", e);
        }
    }
}

public class MemoryEfficientProcessor {
    public void processLargeDirectory(String directoryPath) {
        try (Stream<Path> paths = Files.walk(Paths.get(directoryPath))) {
            paths.filter(Files::isRegularFile)
                 .filter(path -> isSupportedFormat(path.toString()))
                 .forEach(path -> {
                     processDocument(path.toString());
                     System.gc(); // Suggest cleanup after each document
                 });
        } catch (IOException e) {
            System.err.println("Error accessing directory: " + e.getMessage());
        }
    }
}

public class DocumentAnalytics {
    public Map<String, Integer> getFormatDistribution(List<String> filePaths) {
        Map<String, Integer> formatCounts = new HashMap<>();
        
        for (String filePath : filePaths) {
            try (Comparer comparer = new Comparer(filePath)) {
                IDocumentInfo info = comparer.getSource().getDocumentInfo();
                String format = info.getFileType().getFileFormat();
                formatCounts.merge(format, 1, Integer::sum);
            } catch (Exception e) {
                formatCounts.merge("ERROR", 1, Integer::sum);
            }
        }
        
        return formatCounts;
    }
    
    public long getTotalDocumentSize(List<String> filePaths) {
        return filePaths.stream()
                .mapToLong(this::getDocumentSize)
                .sum();
    }
    
    private long getDocumentSize(String filePath) {
        try (Comparer comparer = new Comparer(filePath)) {
            return comparer.getSource().getDocumentInfo().getSize();
        } catch (Exception e) {
            return 0;
        }
    }
}

// Good - automatic resource management
try (Comparer comparer = new Comparer(filePath)) {
    // Your code here
} catch (Exception e) {
    // Handle errors
}

// Avoid - manual resource management (error‑prone)
Comparer comparer = new Comparer(filePath);
// If exception occurs here, resources might not be cleaned up
comparer.close();

public class RobustDocumentProcessor {
    public Optional<DocumentMetadata> extractMetadata(String filePath) {
        try (Comparer comparer = new Comparer(filePath)) {
            IDocumentInfo info = comparer.getSource().getDocumentInfo();
            return Optional.of(new DocumentMetadata(info));
        } catch (Exception e) {
            logError("Failed to process: " + filePath, e);
            return Optional.empty();
        }
    }
}

public void processDocument(String filePath) {
    Objects.requireNonNull(filePath, "File path cannot be null");
    
    if (filePath.trim().isEmpty()) {
        throw new IllegalArgumentException("File path cannot be empty");
    }
    
    if (!new File(filePath).exists()) {
        throw new IllegalArgumentException("File does not exist: " + filePath);
    }
    
    // Process the document
}

LoadOptions loadOptions = new LoadOptions();
loadOptions.setPassword("your-password");
try (Comparer comparer = new Comparer(filePath, loadOptions)) {
    // Extract metadata from password‑protected document
}

// Example with AWS S3
S3Object object = s3Client.getObject("bucket-name", "document-key");
try (InputStream stream = object.getObjectContent();
     Comparer comparer = new Comparer(stream)) {
    // Extract metadata
}