so sánh tài liệu .net – Hướng dẫn triển khai đầy đủ GroupDocs

public static class Constants
{
    public const string SOURCE_WORD = @"YOUR_DOCUMENT_DIRECTORY\source.docx";
    public const string TARGET_WORD = @"YOUR_DOCUMENT_DIRECTORY\target.docx";

    public static string GetOutputDirectoryPath()
    {
        return @"YOUR_OUTPUT_DIRECTORY";
    }

    public const string RESULT_WORD = "result.docx";
}

using (Comparer comparer = new Comparer(Constants.SOURCE_WORD))
{
    // Add the target document for comparison
    comparer.Add(Constants.TARGET_WORD);

    // Perform the comparison and save the result
    string outputFileName = Path.Combine(Constants.GetOutputDirectoryPath(), Constants.RESULT_WORD);
    comparer.Compare(outputFileName);
}

CompareOptions compareOptions = new CompareOptions()
{
    ShowDeletedContent = true,
    ShowInsertedContent = true,
    StyleChangeDetection = true
};

using (Comparer comparer = new Comparer(sourcePath))
{
    comparer.Add(targetPath);
    comparer.Compare(outputPath, compareOptions);
}

public static void CompareDocumentsByType(string sourcePath, string targetPath, string outputPath)
{
    string extension = Path.GetExtension(sourcePath).ToLower();
    
    using (Comparer comparer = new Comparer(sourcePath))
    {
        comparer.Add(targetPath);
        
        CompareOptions options = GetOptionsForFormat(extension);
        comparer.Compare(outputPath, options);
    }
}

private static CompareOptions GetOptionsForFormat(string extension)
{
    switch (extension)
    {
        case ".pdf":
            return new CompareOptions { DetectStyleChanges = false };
        case ".xlsx":
            return new CompareOptions { CalculateCoordinates = true };
        default:
            return new CompareOptions();
    }
}

// For files over 50MB, consider this approach
using (var sourceStream = File.OpenRead(sourcePath))
using (var targetStream = File.OpenRead(targetPath))
using (var comparer = new Comparer(sourceStream))
{
    comparer.Add(targetStream);
    comparer.Compare(outputStream);
}

try
{
    using (Comparer comparer = new Comparer(sourcePath))
    {
        comparer.Add(targetPath);
        comparer.Compare(outputPath);
    }
}
catch (FileNotFoundException ex)
{
    Console.WriteLine($"Document not found: {ex.FileName}");
}
catch (UnauthorizedAccessException ex)
{
    Console.WriteLine($"Access denied: {ex.Message}");
}
catch (Exception ex)
{
    Console.WriteLine($"Comparison failed: {ex.Message}");
}

// Wrong - will break on different operating systems
string path = "C:/Documents/source.docx";

// Right - works everywhere
string path = Path.Combine("C:", "Documents", "source.docx");

// For files over 50MB, consider this approach
using (var sourceStream = File.OpenRead(sourcePath))
using (var targetStream = File.OpenRead(targetPath))
using (var comparer = new Comparer(sourceStream))
{
    comparer.Add(targetStream);
    comparer.Compare(outputStream);
}

try
{
    using (Comparer comparer = new Comparer(sourcePath))
    {
        comparer.Add(targetPath);
        comparer.Compare(outputPath);
    }
}
catch (FileNotFoundException ex)
{
    Console.WriteLine($"Document not found: {ex.FileName}");
}
catch (UnauthorizedAccessException ex)
{
    Console.WriteLine($"Access denied: {ex.Message}");
}
catch (Exception ex)
{
    Console.WriteLine($"Comparison failed: {ex.Message}");
}

// Always dispose of resources properly
using (var comparer = new Comparer(sourcePath))
{
    comparer.Add(targetPath);
    comparer.Compare(outputPath);
    
    // Comparer is automatically disposed here
}

// For batch processing, clear resources between comparisons
for (int i = 0; i < documentPairs.Count; i++)
{
    using (var comparer = new Comparer(documentPairs[i].Source))
    {
        comparer.Add(documentPairs[i].Target);
        comparer.Compare(documentPairs[i].Output);
    }
    
    // Force garbage collection every 10 documents if needed
    if (i % 10 == 0)
    {
        GC.Collect();
        GC.WaitForPendingFinalizers();
    }
}

public async Task<bool> CompareDocumentsAsync(string sourcePath, string targetPath, string outputPath)
{
    return await Task.Run(() =>
    {
        try
        {
            using (var comparer = new Comparer(sourcePath))
            {
                comparer.Add(targetPath);
                comparer.Compare(outputPath);
                return true;
            }
        }
        catch
        {
            return false;
        }
    });
}

[ApiController]
[Route("api/[controller]")]
public class DocumentComparisonController : ControllerBase
{
    [HttpPost("compare")]
    public async Task<IActionResult> CompareDocuments([FromForm] IFormFile sourceFile, [FromForm] IFormFile targetFile)
    {
        if (sourceFile == null || targetFile == null)
            return BadRequest("Both source and target files are required.");

        var tempFolder = Path.GetTempPath();
        var sourcePath = Path.Combine(tempFolder, sourceFile.FileName);
        var targetPath = Path.Combine(tempFolder, targetFile.FileName);
        var outputPath = Path.Combine(tempFolder, $"comparison_{Guid.NewGuid()}.pdf");

        try
        {
            // Save uploaded files
            using (var stream = new FileStream(sourcePath, FileMode.Create))
                await sourceFile.CopyToAsync(stream);
            
            using (var stream = new FileStream(targetPath, FileMode.Create))
                await targetFile.CopyToAsync(stream);

            // Perform comparison
            using (var comparer = new Comparer(sourcePath))
            {
                comparer.Add(targetPath);
                comparer.Compare(outputPath);
            }

            // Return the result file
            var fileBytes = await System.IO.File.ReadAllBytesAsync(outputPath);
            return File(fileBytes, "application/pdf", "comparison_result.pdf");
        }
        finally
        {
            // Clean up temp files
            File.Delete(sourcePath);
            File.Delete(targetPath);
            File.Delete(outputPath);
        }
    }
}

@using GroupDocs.Comparison
@inject IJSRuntime JSRuntime

<div class="document-comparison">
    <InputFile OnChange="HandleFileSelection" multiple />
    <button @onclick="CompareDocuments" disabled="@(!CanCompare)">Compare Documents</button>
    
    @if (comparisonResult != null)
    {
        <div class="result">
            <a href="@comparisonResult" download="comparison_result.pdf">Download Result</a>
        </div>
    }
</div>

@code {
    private List<IBrowserFile> selectedFiles = new();
    private string comparisonResult;
    
    private bool CanCompare => selectedFiles.Count == 2;

    private async Task HandleFileSelection(InputFileChangeEventArgs e)
    {
        selectedFiles = e.GetMultipleFiles(2).ToList();
    }

    private async Task CompareDocuments()
    {
        if (selectedFiles.Count != 2) return;

        // Implementation similar to Web API example
        // Save files, compare, and generate result
    }
}

public class ContractReviewService
{
    public ContractComparisonResult ReviewContract(string originalContract, string revisedContract)
    {
        var outputPath = Path.Combine(Path.GetTempPath(), $"contract_review_{DateTime.Now:yyyyMMddHHmmss}.docx");
        
        var compareOptions = new CompareOptions
        {
            ShowDeletedContent = true,
            ShowInsertedContent = true,
            StyleChangeDetection = true,
            WordsSeparatorChars = new[] { ' ', '.', ',', '!', '?' }
        };

        using (var comparer = new Comparer(originalContract))
        {
            comparer.Add(revisedContract);
            comparer.Compare(outputPath, compareOptions);
        }

        return new ContractComparisonResult
        {
            OutputPath = outputPath,
            HasChanges = File.Exists(outputPath),
            ComparisonDate = DateTime.Now
        };
    }
}

public class DocumentVersionControl
{
    public void TrackDocumentChanges(string documentPath, string repositoryPath)
    {
        var versions = Directory.GetFiles(repositoryPath, "*.docx").OrderBy(f => f);
        var latestVersion = versions.LastOrDefault();

        if (latestVersion != null)
        {
            var comparisonPath = Path.Combine(repositoryPath, $"changes_{DateTime.Now:yyyyMMdd}.docx");
            
            using (var comparer = new Comparer(latestVersion))
            {
                comparer.Add(documentPath);
                comparer.Compare(comparisonPath);
            }

            // Archive the comparison for future reference
            ArchiveComparison(comparisonPath);
        }
    }

    private void ArchiveComparison(string comparisonPath)
    {
        // Implementation for archiving comparison results
        var archivePath = Path.Combine(Path.GetDirectoryName(comparisonPath), "archive", Path.GetFileName(comparisonPath));
        Directory.CreateDirectory(Path.GetDirectoryName(archivePath));
        File.Move(comparisonPath, archivePath);
    }
}

private static readonly HashSet<string> SupportedFormats = new HashSet<string>(StringComparer.OrdinalIgnoreCase)
{
    ".docx", ".doc", ".pdf", ".xlsx", ".xls", ".pptx", ".ppt", ".txt", ".rtf"
};

public static bool IsFormatSupported(string filePath)
{
    var extension = Path.GetExtension(filePath);
    return SupportedFormats.Contains(extension);
}

public static void CompareLargeDocuments(string sourcePath, string targetPath, string outputPath)
{
    var fileInfo = new FileInfo(sourcePath);
    
    if (fileInfo.Length > 50 * 1024 * 1024) // 50MB threshold
    {
        // Use streaming approach
        using (var sourceStream = File.OpenRead(sourcePath))
        using (var targetStream = File.OpenRead(targetPath))
        using (var outputStream = File.Create(outputPath))
        using (var comparer = new Comparer(sourceStream))
        {
            comparer.Add(targetStream);
            comparer.Compare(outputStream);
        }
    }
    else
    {
        // Standard approach for smaller files
        using (var comparer = new Comparer(sourcePath))
        {
            comparer.Add(targetPath);
            comparer.Compare(outputPath);
        }
    }
}

var compareOptions = new CompareOptions
{
    DetectStyleChanges = true,
    DiagramMasterSetting = new DiagramMasterSetting
    {
        UseSourceMaster = true,
        CloneSourceMaster = true
    },
    OriginalSize = new Size(600, 800),
    HeaderFootersComparison = true,
    PaperSize = PaperSize.A4
};

using (var comparer = new Comparer(sourcePath, new LoadOptions("password")))
{
    comparer.Add(targetPath, new LoadOptions("targetPassword"));
    comparer.Compare(outputPath);
}

var compareOptions = new CompareOptions
{
    InsertedItemStyle = new StyleSettings
    {
        HighlightColor = Color.Green,
        FontColor = Color.DarkGreen
    },
    DeletedItemStyle = new StyleSettings
    {
        HighlightColor = Color.Red,
        FontColor = Color.DarkRed
    }
};

var compareOptions = new CompareOptions
{
    DetectStyleChanges = false, // Ignore formatting changes
    HeaderFootersComparison = false, // Skip headers/footers
    WordsSeparatorChars = new[] { ' ', '\n', '\r', '\t' } // Define word boundaries
};

using (var sourceStream = await DownloadFromCloudAsync(sourceUrl))
using (var targetStream = await DownloadFromCloudAsync(targetUrl))
using (var comparer = new Comparer(sourceStream))
{
    comparer.Add(targetStream);
    comparer.Compare(outputStream);
}

FROM mcr.microsoft.com/dotnet/aspnet:6.0
# Install necessary fonts and libraries for document processing
RUN apt-get update && apt-get install -y libfontconfig1 libfreetype6

public async Task<ComparisonResult> CompareDocumentsWithRetry(string source, string target, int maxRetries = 3)
{
    for (int attempt = 1; attempt <= maxRetries; attempt++)
    {
        try
        {
            using (var comparer = new Comparer(source))
            {
                comparer.Add(target);
                var outputPath = GenerateOutputPath();
                comparer.Compare(outputPath);
                
                return new ComparisonResult { Success = true, OutputPath = outputPath };
            }
        }
        catch (Exception ex) when (attempt < maxRetries)
        {
            _logger.LogWarning($"Comparison attempt {attempt} failed: {ex.Message}. Retrying...");
            await Task.Delay(TimeSpan.FromSeconds(attempt * 2)); // Exponential backoff
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, $"Comparison failed after {maxRetries} attempts");
            return new ComparisonResult { Success = false, Error = ex.Message };
        }
    }
    
    return new ComparisonResult { Success = false, Error = "Max retries exceeded" };
}

Install-Package GroupDocs.Comparison -Version 25.4.0

dotnet add package GroupDocs.Comparison --version 25.4.0

using GroupDocs.Comparison;