使用C＃压缩/解压缩字符串

Question

我是.net的新手。我在C＃中做压缩和解压缩字符串。有一个XML，我正在转换为字符串，之后我正在进行压缩和解压缩。我的代码中没有编译错误，除非我解压缩我的代码并返回我的字符串，它只返回XML的一半。

以下是我的代码，请在我错的地方纠正我。

代码：

class Program
{
    public static string Zip(string value)
    {
        //Transform string into byte[]  
        byte[] byteArray = new byte[value.Length];
        int indexBA = 0;
        foreach (char item in value.ToCharArray())
        {
            byteArray[indexBA++] = (byte)item;
        }

        //Prepare for compress
        System.IO.MemoryStream ms = new System.IO.MemoryStream();
        System.IO.Compression.GZipStream sw = new System.IO.Compression.GZipStream(ms, System.IO.Compression.CompressionMode.Compress);

        //Compress
        sw.Write(byteArray, 0, byteArray.Length);
        //Close, DO NOT FLUSH cause bytes will go missing...
        sw.Close();

        //Transform byte[] zip data to string
        byteArray = ms.ToArray();
        System.Text.StringBuilder sB = new System.Text.StringBuilder(byteArray.Length);
        foreach (byte item in byteArray)
        {
            sB.Append((char)item);
        }
        ms.Close();
        sw.Dispose();
        ms.Dispose();
        return sB.ToString();
    }

    public static string UnZip(string value)
    {
        //Transform string into byte[]
        byte[] byteArray = new byte[value.Length];
        int indexBA = 0;
        foreach (char item in value.ToCharArray())
        {
            byteArray[indexBA++] = (byte)item;
        }

        //Prepare for decompress
        System.IO.MemoryStream ms = new System.IO.MemoryStream(byteArray);
        System.IO.Compression.GZipStream sr = new System.IO.Compression.GZipStream(ms,
            System.IO.Compression.CompressionMode.Decompress);

        //Reset variable to collect uncompressed result
        byteArray = new byte[byteArray.Length];

        //Decompress
        int rByte = sr.Read(byteArray, 0, byteArray.Length);

        //Transform byte[] unzip data to string
        System.Text.StringBuilder sB = new System.Text.StringBuilder(rByte);
        //Read the number of bytes GZipStream red and do not a for each bytes in
        //resultByteArray;
        for (int i = 0; i < rByte; i++)
        {
            sB.Append((char)byteArray[i]);
        }
        sr.Close();
        ms.Close();
        sr.Dispose();
        ms.Dispose();
        return sB.ToString();
    }

    static void Main(string[] args)
    {
        XDocument doc = XDocument.Load(@"D:\RSP.xml");
        string val = doc.ToString(SaveOptions.DisableFormatting);
        val = Zip(val);
        val = UnZip(val);
    }
} 

我的XML大小为63KB。

Answer 1

压缩/解压缩字符串的代码

public static void CopyTo(Stream src, Stream dest) {
    byte[] bytes = new byte[4096];

    int cnt;

    while ((cnt = src.Read(bytes, 0, bytes.Length)) != 0) {
        dest.Write(bytes, 0, cnt);
    }
}

public static byte[] Zip(string str) {
    var bytes = Encoding.UTF8.GetBytes(str);

    using (var msi = new MemoryStream(bytes))
    using (var mso = new MemoryStream()) {
        using (var gs = new GZipStream(mso, CompressionMode.Compress)) {
            //msi.CopyTo(gs);
            CopyTo(msi, gs);
        }

        return mso.ToArray();
    }
}

public static string Unzip(byte[] bytes) {
    using (var msi = new MemoryStream(bytes))
    using (var mso = new MemoryStream()) {
        using (var gs = new GZipStream(msi, CompressionMode.Decompress)) {
            //gs.CopyTo(mso);
            CopyTo(gs, mso);
        }

        return Encoding.UTF8.GetString(mso.ToArray());
    }
}

static void Main(string[] args) {
    byte[] r1 = Zip("StringStringStringStringStringStringStringStringStringStringStringStringStringString");
    string r2 = Unzip(r1);
}

请记住，Zip会返回byte[]，而Unzip会返回string。如果你想要一个来自Zip的字符串，你可以对它进行Base64编码（例如使用Convert.ToBase64String(r1)）（Zip的结果是非常二进制的！这不是你可以打印到的屏幕或直接在XML中写入）

建议的版本适用于.NET 2.0，因为.NET 4.0使用MemoryStream.CopyTo。

重要事项：压缩内容无法写入输出流，直到GZipStream知道它具有所有输入（即，有效压缩它需要所有数据） 。在检查输出流之前，您需要确保Dispose()的{​​{1}}（例如GZipStream）。这是通过上面的mso.ToArray()块完成的。请注意，using() { }是最里面的块，内容在其外部访问。在尝试访问数据之前解压缩GZipStream的{​​{1}}也是如此。

Answer 2

根据 this snippet  我使用此代码，它工作正常：

using System;
using System.IO;
using System.IO.Compression;
using System.Text;

namespace CompressString
{
    internal static class StringCompressor
    {
        /// <summary>
        /// Compresses the string.
        /// </summary>
        /// <param name="text">The text.</param>
        /// <returns></returns>
        public static string CompressString(string text)
        {
            byte[] buffer = Encoding.UTF8.GetBytes(text);
            var memoryStream = new MemoryStream();
            using (var gZipStream = new GZipStream(memoryStream, CompressionMode.Compress, true))
            {
                gZipStream.Write(buffer, 0, buffer.Length);
            }

            memoryStream.Position = 0;

            var compressedData = new byte[memoryStream.Length];
            memoryStream.Read(compressedData, 0, compressedData.Length);

            var gZipBuffer = new byte[compressedData.Length + 4];
            Buffer.BlockCopy(compressedData, 0, gZipBuffer, 4, compressedData.Length);
            Buffer.BlockCopy(BitConverter.GetBytes(buffer.Length), 0, gZipBuffer, 0, 4);
            return Convert.ToBase64String(gZipBuffer);
        }

        /// <summary>
        /// Decompresses the string.
        /// </summary>
        /// <param name="compressedText">The compressed text.</param>
        /// <returns></returns>
        public static string DecompressString(string compressedText)
        {
            byte[] gZipBuffer = Convert.FromBase64String(compressedText);
            using (var memoryStream = new MemoryStream())
            {
                int dataLength = BitConverter.ToInt32(gZipBuffer, 0);
                memoryStream.Write(gZipBuffer, 4, gZipBuffer.Length - 4);

                var buffer = new byte[dataLength];

                memoryStream.Position = 0;
                using (var gZipStream = new GZipStream(memoryStream, CompressionMode.Decompress))
                {
                    gZipStream.Read(buffer, 0, buffer.Length);
                }

                return Encoding.UTF8.GetString(buffer);
            }
        }
    }
}

Answer 3

随着.NET 4.0（及更高版本）与Stream.CopyTo（）方法的出现，我想我会发布一个更新的方法。

我还认为以下版本作为用于将常规字符串压缩为Base64编码字符串的自包含类的明显示例非常有用，反之亦然：

public static class StringCompression
{
    /// <summary>
    /// Compresses a string and returns a deflate compressed, Base64 encoded string.
    /// </summary>
    /// <param name="uncompressedString">String to compress</param>
    public static string Compress(string uncompressedString)
    {
        byte[] compressedBytes;

        using (var uncompressedStream = new MemoryStream(Encoding.UTF8.GetBytes(uncompressedString)))
        {
            using (var compressedStream = new MemoryStream())
            { 
                // setting the leaveOpen parameter to true to ensure that compressedStream will not be closed when compressorStream is disposed
                // this allows compressorStream to close and flush its buffers to compressedStream and guarantees that compressedStream.ToArray() can be called afterward
                // although MSDN documentation states that ToArray() can be called on a closed MemoryStream, I don't want to rely on that very odd behavior should it ever change
                using (var compressorStream = new DeflateStream(compressedStream, CompressionLevel.Fastest, true))
                {
                    uncompressedStream.CopyTo(compressorStream);
                }

                // call compressedStream.ToArray() after the enclosing DeflateStream has closed and flushed its buffer to compressedStream
                compressedBytes = compressedStream.ToArray();
            }
        }

        return Convert.ToBase64String(compressedBytes);
    }

    /// <summary>
    /// Decompresses a deflate compressed, Base64 encoded string and returns an uncompressed string.
    /// </summary>
    /// <param name="compressedString">String to decompress.</param>
    public static string Decompress(string compressedString)
    {
        byte[] decompressedBytes;

        var compressedStream = new MemoryStream(Convert.FromBase64String(compressedString));

        using (var decompressorStream = new DeflateStream(compressedStream, CompressionMode.Decompress))
        {
            using (var decompressedStream = new MemoryStream())
            {
                decompressorStream.CopyTo(decompressedStream);

                decompressedBytes = decompressedStream.ToArray();
            }
        }

        return Encoding.UTF8.GetString(decompressedBytes);
    }

这是使用扩展方法技术扩展String类以添加字符串压缩和解压缩的另一种方法。您可以将下面的课程放到现有项目中，然后使用：

var uncompressedString = "Hello World!";
var compressedString = uncompressedString.Compress();

和

var decompressedString = compressedString.Decompress();

即便：

public static class Extensions
{
    /// <summary>
    /// Compresses a string and returns a deflate compressed, Base64 encoded string.
    /// </summary>
    /// <param name="uncompressedString">String to compress</param>
    public static string Compress(this string uncompressedString)
    {
        byte[] compressedBytes;

        using (var uncompressedStream = new MemoryStream(Encoding.UTF8.GetBytes(uncompressedString)))
        {
            using (var compressedStream = new MemoryStream())
            { 
                // setting the leaveOpen parameter to true to ensure that compressedStream will not be closed when compressorStream is disposed
                // this allows compressorStream to close and flush its buffers to compressedStream and guarantees that compressedStream.ToArray() can be called afterward
                // although MSDN documentation states that ToArray() can be called on a closed MemoryStream, I don't want to rely on that very odd behavior should it ever change
                using (var compressorStream = new DeflateStream(compressedStream, CompressionLevel.Fastest, true))
                {
                    uncompressedStream.CopyTo(compressorStream);
                }

                // call compressedStream.ToArray() after the enclosing DeflateStream has closed and flushed its buffer to compressedStream
                compressedBytes = compressedStream.ToArray();
            }
        }

        return Convert.ToBase64String(compressedBytes);
    }

    /// <summary>
    /// Decompresses a deflate compressed, Base64 encoded string and returns an uncompressed string.
    /// </summary>
    /// <param name="compressedString">String to decompress.</param>
    public static string Decompress(this string compressedString)
    {
        byte[] decompressedBytes;

        var compressedStream = new MemoryStream(Convert.FromBase64String(compressedString));

        using (var decompressorStream = new DeflateStream(compressedStream, CompressionMode.Decompress))
        {
            using (var decompressedStream = new MemoryStream())
            {
                decompressorStream.CopyTo(decompressedStream);

                decompressedBytes = decompressedStream.ToArray();
            }
        }

        return Encoding.UTF8.GetString(decompressedBytes);
    }

Answer 4

对于那些仍然 GZip标头中的幻数不正确的人。确保传入GZip流。错误 如果您的字符串是使用 php 压缩的，那么您需要执行以下操作：

       public static string decodeDecompress(string originalReceivedSrc) {
        byte[] bytes = Convert.FromBase64String(originalReceivedSrc);

        using (var mem = new MemoryStream()) {
            //the trick is here
            mem.Write(new byte[] { 0x1f, 0x8b, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00 }, 0, 8);
            mem.Write(bytes, 0, bytes.Length);

            mem.Position = 0;

            using (var gzip = new GZipStream(mem, CompressionMode.Decompress))
            using (var reader = new StreamReader(gzip)) {
                return reader.ReadToEnd();
                }
            }
        }

Answer 5

这是使用async / await和IEnumerables的.NET 4.5及更新版本的更新版本：

public static class CompressionExtensions
{
    public static async Task<IEnumerable<byte>> Zip(this object obj)
    {
        byte[] bytes = obj.Serialize();

        using (MemoryStream msi = new MemoryStream(bytes))
        using (MemoryStream mso = new MemoryStream())
        {
            using (var gs = new GZipStream(mso, CompressionMode.Compress))
                await msi.CopyToAsync(gs);

            return mso.ToArray().AsEnumerable();
        }
    }

    public static async Task<object> Unzip(this byte[] bytes)
    {
        using (MemoryStream msi = new MemoryStream(bytes))
        using (MemoryStream mso = new MemoryStream())
        {
            using (var gs = new GZipStream(msi, CompressionMode.Decompress))
            {
                //gs.CopyTo(mso);
                await gs.CopyToAsync(mso);
            }

            return mso.ToArray().Deserialize();
        }
    }
}

public static class SerializerExtensions
{
    /// <summary>
    /// Writes the given object instance to a binary file.
    /// <para>Object type (and all child types) must be decorated with the [Serializable] attribute.</para>
    /// <para>To prevent a variable from being serialized, decorate it with the [NonSerialized] attribute; cannot be applied to properties.</para>
    /// </summary>
    /// <typeparam name="T">The type of object being written to the XML file.</typeparam>
    /// <param name="filePath">The file path to write the object instance to.</param>
    /// <param name="objectToWrite">The object instance to write to the XML file.</param>
    /// <param name="append">If false the file will be overwritten if it already exists. If true the contents will be appended to the file.</param>
    public static byte[] Serialize<T>(this T objectToWrite)
    {
        using (MemoryStream stream = new MemoryStream())
        {
            BinaryFormatter binaryFormatter = new BinaryFormatter();
            binaryFormatter.Serialize(stream, objectToWrite);

            return stream.GetBuffer();
        }
    }

    /// <summary>
    /// Reads an object instance from a binary file.
    /// </summary>
    /// <typeparam name="T">The type of object to read from the XML.</typeparam>
    /// <param name="filePath">The file path to read the object instance from.</param>
    /// <returns>Returns a new instance of the object read from the binary file.</returns>
    public static async Task<T> _Deserialize<T>(this byte[] arr)
    {
        using (MemoryStream stream = new MemoryStream())
        {
            BinaryFormatter binaryFormatter = new BinaryFormatter();
            await stream.WriteAsync(arr, 0, arr.Length);
            stream.Position = 0;

            return (T)binaryFormatter.Deserialize(stream);
        }
    }

    public static async Task<object> Deserialize(this byte[] arr)
    {
        object obj = await arr._Deserialize<object>();
        return obj;
    }
}

通过这个，您可以序列化BinaryFormatter支持的所有内容，而不仅仅是字符串。

Answer 6

我最喜欢@fubo的答案，但我认为这要优雅得多。

此方法更加兼容，因为它不会手动预先存储长度。

我还公开了扩展，以支持对字符串到字符串，字节[]到字节[]以及流到流的压缩。

public static class ZipExtensions
{
    public static string CompressToBase64(this string data)
    {
        return Convert.ToBase64String(Encoding.UTF8.GetBytes(data).Compress());
    }

    public static string DecompressFromBase64(this string data)
    {
        return Encoding.UTF8.GetString(Convert.FromBase64String(data).Decompress());
    }
    
    public static byte[] Compress(this byte[] data)
    {
        using (var sourceStream = new MemoryStream(data))
        using (var destinationStream = new MemoryStream())
        {
            sourceStream.CompressTo(destinationStream);
            return destinationStream.ToArray();
        }
    }

    public static byte[] Decompress(this byte[] data)
    {
        using (var sourceStream = new MemoryStream(data))
        using (var destinationStream = new MemoryStream())
        {
            sourceStream.DecompressTo(destinationStream);
            return destinationStream.ToArray();
        }
    }
    
    public static void CompressTo(this Stream stream, Stream outputStream)
    {
        using (var gZipStream = new GZipStream(outputStream, CompressionMode.Compress))
        {
            stream.CopyTo(gZipStream);
            gZipStream.Flush();
        }
    }

    public static void DecompressTo(this Stream stream, Stream outputStream)
    {
        using (var gZipStream = new GZipStream(stream, CompressionMode.Decompress))
        {
            gZipStream.CopyTo(outputStream);
        }
    }
}

Answer 7

我们可以通过使用StreamReader和StreamWriter来减少代码复杂性，而不是手动将字符串转换为字节数组。您只需要三个流：

    public static byte[] Zip(string uncompressed)
    {
        byte[] ret;
        using (var outputMemory = new MemoryStream())
        {
            using (var gz = new GZipStream(outputMemory, CompressionLevel.Optimal))
            {
                using (var sw = new StreamWriter(gz, Encoding.UTF8))
                {
                    sw.Write(uncompressed);
                }
            }
            ret = outputMemory.ToArray();
        }
        return ret;
    }

    public static string Unzip(byte[] compressed)
    {
        string ret = null;
        using (var inputMemory = new MemoryStream(compressed))
        {
            using (var gz = new GZipStream(inputMemory, CompressionMode.Decompress))
            {
                using (var sr = new StreamReader(gz, Encoding.UTF8))
                {
                    ret = sr.ReadToEnd();
                }
            }
        }
        return ret;
    }