C＃を使用した圧縮/解凍文字列

Question

私は.netの初心者です。 C＃で文字列の圧縮と解凍を行っています。 XMLがあり、文字列に変換してから圧縮と解凍を行っていますが、コードを解凍して文字列を返し、XMLの半分のみを返す場合を除いて、コードにコンパイルエラーはありません。

以下は私のコードです。間違っている箇所を修正してください。

コード：

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);
    }
} 

XMLサイズは63 KBです。

Answer 1

文字列を圧縮/解凍するコード

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);
}

Zipはbyte[]を返し、Unzipはstringを返すことに注意してください。 Zipの文字列が必要な場合は、Base64でエンコードできます（たとえば、Convert.ToBase64String(r1)を使用して）（Zipの結果は非常にバイナリです！画面に印刷したり、XMLに直接書き込んだりすることはできません）

推奨されるバージョンは.NET 2.0用です。NET4.0ではMemoryStream.CopyToを使用します。

重要：圧縮されたコンテンツは、GZipStreamがすべての入力を持っていることがわかるまで出力ストリームに書き込むことができません（つまり、効果的に圧縮するにはすべてのデータが必要です）。出力ストリームを検査する前にGZipStreamのDispose()を確認する必要があります（例：mso.ToArray()）。これは、上記のusing() { }ブロックで行われます。 GZipStreamは最も内側のブロックであり、コンテンツはその外側からアクセスされることに注意してください。データへのアクセスを試みる前に、GZipStreamのDispose()を解凍する場合も同様です。

Answer 2

このスニペット に従って、私はこのコードを使用し、うまく機能しています：

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

Stream.CopyTo（）メソッドを使用した.NET 4.0（およびそれ以降）の登場により、更新されたアプローチを投稿すると思いました。

また、以下のバージョンは、通常の文字列をBase64エンコード文字列に圧縮するための自己完結型クラスの明確な例として有用であると思います。

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);
    }

次に、拡張メソッド手法を使用してStringクラスを拡張し、文字列の圧縮と圧縮解除を追加する別のアプローチを示します。以下のクラスを既存のプロジェクトにドロップして、このように使用できます。

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

そして

var decompressedString = compressedString.Decompress();

機知に：

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

まだGZipヘッダーのマジックナンバーが正しくありません。GZipストリームを渡していることを確認してください。エラーおよび文字列がphpを使用して圧縮されている場合次のようなことをする必要があります。

       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

これは、async/awaitおよびIEnumerablesを使用した.NET 4.5以降の更新バージョンです。

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;
    }
}

これにより、文字列だけでなく、BinaryFormatterがサポートするすべてをシリアル化できます。