我需要判斷一個(gè)由某個(gè)壓縮包文件解壓縮出來的文件夾里面的文件內(nèi)容，是否和壓縮包里面記錄的相同，于是就寫了這個(gè)工具

本文記錄的工具能夠?qū)崿F(xiàn)以下情況的對比：

• 文件夾里面丟失了某個(gè)在壓縮包里面記錄的文件
• 文件夾里面的文件和壓縮包里面的文件的內(nèi)容不相同
• 文件夾多出了壓縮包里面沒有的文件

我這里新建的是一個(gè) .NET 9 的 WPF 應(yīng)用，只有簡單的界面，理論上核心代碼可以應(yīng)用在任何 UI 框架上，甚至控制臺項(xiàng)目也可以

界面代碼如下，非常簡單，只有兩個(gè)輸入框，用來分別輸入壓縮包文件路徑和解壓縮的文件夾路徑，和一個(gè)按鈕

    <Grid>
        <Grid HorizontalAlignment="Center" VerticalAlignment="Center">
            <Grid.RowDefinitions>
                <RowDefinition Height="Auto"></RowDefinition>
                <RowDefinition Height="Auto"></RowDefinition>
                <RowDefinition Height="Auto"></RowDefinition>
            </Grid.RowDefinitions>
            <Grid.ColumnDefinitions>
                <ColumnDefinition Width="Auto"></ColumnDefinition>
                <ColumnDefinition MinWidth="200"></ColumnDefinition>
            </Grid.ColumnDefinitions>

            <TextBlock VerticalAlignment="Center" Text="壓縮包路徑："></TextBlock>
            <TextBox x:Name="ZipFilePathTextBox" Grid.Row="0" Grid.Column="1" VerticalAlignment="Center" Text="C:\lindexi\Work\Source.zip"></TextBox>

            <TextBlock Grid.Row="1" Grid.Column="0" Margin="0,10,0,0" VerticalAlignment="Center" Text="解壓縮文件夾："></TextBlock>
            <TextBox x:Name="UnzipFolderPathTextBox" Grid.Row="1" Grid.Column="1" Margin="0,10,0,0" VerticalAlignment="Center" Text="C:\lindexi\Work\Unzip\"></TextBox>

            <Button Grid.Row="2" Grid.Column="1" Margin="10,10,0,10" HorizontalAlignment="Right" Content="對比" Click="Button_OnClick"></Button>
        </Grid>
    </Grid>

我編寫了一個(gè) ZipComparer 類型，用這個(gè)類型可以用來對比壓縮包文件和解壓縮文件夾里面的內(nèi)容，按鈕的 Button_OnClick 代碼如下

    private async void Button_OnClick(object sender, RoutedEventArgs e)
    {
        try
        {
            var zipCompareOptions = new ZipCompareOptions(ReturnFast: true, IgnoreExtra: false);

            var result = await ZipComparer.Compare(new FileInfo(ZipFilePathTextBox.Text), new DirectoryInfo(UnzipFolderPathTextBox.Text), zipCompareOptions);

            if (result.IsSuccess)
            {
                MessageBox.Show("文件一致");
            }
            else
            {
                var stringBuilder = new StringBuilder();
                stringBuilder.AppendLine("文件不一致");
                foreach (var item in result.DifferenceList)
                {
                    stringBuilder.AppendLine(item.RelativeFilePath);
                    stringBuilder.AppendLine(item.DifferenceType.ToString());
                }
                MessageBox.Show(stringBuilder.ToString());
            }
        }
        catch
        {
            // 忽略
        }
    }

核心代碼是 ZipComparer 類，代碼如下

public static class ZipComparer
{
    public static async Task<ZipCompareResult> Compare(FileInfo zipFile, DirectoryInfo unzipFolder, ZipCompareOptions options)
    {
        HashSet<string/*RelativePath*/>? visitedFileSet = null;
        if (!options.IgnoreExtra)
        {
            visitedFileSet = [];
        }

        List<ZipCompareDifferenceFileInfo>? differenceList = null;

        await using var fileStream = zipFile.OpenRead();
        using var zipArchive = new System.IO.Compression.ZipArchive(fileStream, System.IO.Compression.ZipArchiveMode.Read, leaveOpen: true);
        foreach (var zipArchiveEntry in zipArchive.Entries)
        {
            var name = zipArchiveEntry.FullName;
            visitedFileSet?.Add(name);
            var filePath = Path.Join(unzipFolder.FullName, name);

            if (!File.Exists(filePath))
            {
                // 文件不存在
                AddDifference(new ZipCompareDifferenceFileInfo(name, ZipCompareDifferenceType.Miss));

                if (options.ReturnFast)
                {
                    break;
                }
                else
                {
                    continue;
                }
            }

            var fileInfo = new FileInfo(filePath);
            if (fileInfo.Length != zipArchiveEntry.Length)
            {
                // 文件大小不同
                AddDifference(new ZipCompareDifferenceFileInfo(name, ZipCompareDifferenceType.ContentLengthDifference));
                if (options.ReturnFast)
                {
                    break;
                }
                else
                {
                    continue;
                }
            }

            // 先不引入 Crc32 對比邏輯。要真正想用，需要引入 System.IO.Hashing 包
            //var crc32 = zipArchiveEntry.Crc32;
            //if (crc32 != 0 && Crc32.IsSupported)
            //{
            //    var fileCrc32 = await GetFileZipCrcAsync(fileInfo);
            //    if (crc32 == fileCrc32)
            //    {
            //        continue;
            //    }
            //    else
            //    {
            //        // CRC32 不同
            //        AddDifference(new ZipCompareDifferenceFileInfo(name, ZipCompareDifferenceType.ContentDifference));
            //        if (options.ReturnFast)
            //        {
            //            break;
            //        }
            //        else
            //        {
            //            continue;
            //        }
            //    }
            //}

            // 開始對比文件內(nèi)容
            await using var zipStream = zipArchiveEntry.Open();
            await using var currentFileStream = fileInfo.OpenRead();
            var success = await CompareStream(zipStream, currentFileStream);
            if (!success)
            {
                // 文件內(nèi)容不同
                AddDifference(new ZipCompareDifferenceFileInfo(name, ZipCompareDifferenceType.ContentDifference));
                if (options.ReturnFast)
                {
                    break;
                }
            }
        }

        var isDifferenceFastReturn = options.ReturnFast && differenceList is { Count: > 0 };

        if (!options.IgnoreExtra
            // 如果是快速返回，則不需要檢查額外的文件，此時(shí)已經(jīng)存在不相同的文件
            && !isDifferenceFastReturn)
        {
            // 如果不能忽略額外的文件，則需要檢查解壓縮文件夾中是否有額外的文件
            Debug.Assert(visitedFileSet != null);

            foreach (var file in unzipFolder.EnumerateFiles("*", new EnumerationOptions()
            {
                RecurseSubdirectories = true
            }))
            {
                var relativePath = Path.GetRelativePath(unzipFolder.FullName, file.FullName);
                if (!visitedFileSet.Contains(relativePath))
                {
                    // 額外的文件
                    AddDifference(new ZipCompareDifferenceFileInfo(relativePath, ZipCompareDifferenceType.Extra));
                    if (options.ReturnFast)
                    {
                        break;
                    }
                }
            }
        }

        return new ZipCompareResult
        {
            DifferenceList = differenceList,
        };

        void AddDifference(ZipCompareDifferenceFileInfo info)
        {
            differenceList ??= new List<ZipCompareDifferenceFileInfo>();
            differenceList.Add(info);
        }
    }

    //private static async ValueTask<uint> GetFileZipCrcAsync(FileInfo fileInfo)
    //{
    //    const int bufferLength = 4 * 1024;
    //    var buffer = ArrayPool<byte>.Shared.Rent(bufferLength);
    //    uint crc = 0;
    //    try
    //    {
    //        await using var fileStream = fileInfo.OpenRead();
    //        var memory = buffer.AsMemory(0, bufferLength);

    //        while (true)
    //        {
    //            var readLength = await fileStream.ReadAsync(memory);

    //            if (readLength == 0)
    //            {
    //                return crc;
    //            }

    //            for (int i = 0; i < readLength; i++)
    //            {
    //                crc = Crc32.ComputeCrc32(crc, memory.Span[i]);
    //            }
    //        }
    //    }
    //    finally
    //    {
    //        ArrayPool<byte>.Shared.Return(buffer);
    //    }
    //}

    private static async ValueTask<bool> CompareStream(Stream a, Stream b)
    {
        const int bufferLength = 4 * 1024;
        var bufferA = ArrayPool<byte>.Shared.Rent(bufferLength);
        var bufferB = ArrayPool<byte>.Shared.Rent(bufferLength);

        try
        {
            while (true)
            {
                var memoryA = bufferA.AsMemory(0, bufferLength);

                var readLength = await a.ReadAsync(memoryA);
                if (readLength == 0)
                {
                    // 讀取完畢
                    return true;
                }

                var memoryB = bufferB.AsMemory(0, readLength);
                await b.ReadExactlyAsync(memoryB);

                if (!memoryA.Span.Slice(0, readLength).SequenceEqual(memoryB.Span))
                {
                    return false;
                }
            }
        }
        finally
        {
            ArrayPool<byte>.Shared.Return(bufferA);
            ArrayPool<byte>.Shared.Return(bufferB);
        }
    }
}

/// <summary>
/// 比較的選項(xiàng)
/// </summary>
/// <param name="ReturnFast">找到第一個(gè)差異就立刻結(jié)束</param>
/// <param name="IgnoreExtra">忽略額外的文件。忽略解壓縮文件夾存在，但壓縮包不存在的文件</param>
public readonly record struct ZipCompareOptions(bool ReturnFast, bool IgnoreExtra);

public readonly record struct ZipCompareResult
{
    [MemberNotNullWhen(false, nameof(DifferenceList))]
    public bool IsSuccess => DifferenceList is null || DifferenceList.Count == 0;

    public IReadOnlyList<ZipCompareDifferenceFileInfo>? DifferenceList { get; internal init; }
}

public readonly record struct ZipCompareDifferenceFileInfo(string RelativeFilePath, ZipCompareDifferenceType DifferenceType);

public enum ZipCompareDifferenceType
{
    /// <summary>
    /// 文件不存在
    /// </summary>
    Miss,

    /// <summary>
    /// 文件大小不同
    /// </summary>
    ContentLengthDifference,

    /// <summary>
    /// 文件內(nèi)容不同
    /// </summary>
    ContentDifference,

    /// <summary>
    /// 額外的文件，即解壓縮文件夾存在，但壓縮包不存在的文件
    /// </summary>
    Extra,
}

本文代碼放在 github 和 gitee 上，可以使用如下命令行拉取代碼。我整個(gè)代碼倉庫比較龐大，使用以下命令行可以進(jìn)行部分拉取，拉取速度比較快

先創(chuàng)建一個(gè)空文件夾，接著使用命令行 cd 命令進(jìn)入此空文件夾，在命令行里面輸入以下代碼，即可獲取到本文的代碼

git init
git remote add origin https://gitee.com/lindexi/lindexi_gd.git
git pull origin 88e3c7fe8009b4ad239481404c2c4b5089f05953

以上使用的是國內(nèi)的 gitee 的源，如果 gitee 不能訪問，請?zhí)鎿Q為 github 的源。請?jiān)诿钚欣^續(xù)輸入以下代碼，將 gitee 源換成 github 源進(jìn)行拉取代碼。如果依然拉取不到代碼，可以發(fā)郵件向我要代碼

git remote remove origin
git remote add origin https://github.com/lindexi/lindexi_gd.git
git pull origin 88e3c7fe8009b4ad239481404c2c4b5089f05953

獲取代碼之后，進(jìn)入 WPFDemo/CardawnarheaCahichemga 文件夾，即可獲取到源代碼

更多技術(shù)博客，請參閱 博客導(dǎo)航