[C#-Util]-讀寫檔案漢字亂碼

     當我們用System.IO.StreamReader讀取包含漢字的txt檔案時，經常會讀出亂碼（StreamWriater寫文字檔也有類似的問題），原因很簡單，就是檔案的編碼（encoding）和StreamReader/Writer的encoding不對應。
    為瞭解決這個問題，我寫了一個類，來取得一個文字檔的encoding，這樣我們就可以建立對應的StreamReader和StreamWriter來讀寫，保證不會出現亂碼現象。其實原理很簡單，文字編輯器（比如XP內建的記事本）在產生文字檔時，如果編碼格式和系統預設的編碼（中文系統下預設為GB2312）不一致時，會在txt檔案開頭部分添加特定的“編碼位元組序標識（Encoding Bit Order Madk，簡寫為BOM）”，類似PE格式的"MZ"檔案頭。這樣它在讀取時就可以根據這個BOM來確定該文字檔產生時所使用的Encoding。這個BOM我們用記事本等程式開啟預設是看不到的，但是用stream按位元組讀取時是可以讀到的。我的這個TxtFileEncoding類就是根據這個BOM“檔案頭”來確定txt檔案產生時用到的編碼的。

using System;using System.IO;using System.Text;namespace XXX.XXX.XXX.Common{    public class EncodingHelper    {        /// <summary>        /// GetEncoding        /// </summary>        /// <param name="fileName"></param>        /// <returns></returns>        public static Encoding GetEncoding(string fileName)        {            return GetEncoding(fileName, Encoding.Default);        }        /// <summary>        /// GetEncoding        /// </summary>        /// <param name="stream"></param>        /// <returns></returns>        public static Encoding GetEncoding(FileStream stream)        {            return GetEncoding(stream, Encoding.Default);        }        /// <summary>        /// GetEncoding        /// </summary>        /// <param name="fileName"></param>        /// <param name="defaultEncoding"></param>        /// <returns></returns>        public static Encoding GetEncoding(string fileName, Encoding defaultEncoding)        {            var fs = new FileStream(fileName, FileMode.Open);            var targetEncoding = GetEncoding(fs, defaultEncoding);            fs.Close();            return targetEncoding;        }        /// <summary>        /// GetEncoding        /// </summary>        /// <param name="stream"></param>        /// <param name="defaultEncoding"></param>        /// <returns></returns>        public static Encoding GetEncoding(FileStream stream, Encoding defaultEncoding)        {            var targetEncoding = defaultEncoding;            if (stream != null && stream.Length >= 2)            {                //儲存檔案流的前4個位元組                byte byte1 = 0;                byte byte2 = 0;                byte byte3 = 0;                byte byte4 = 0;                //儲存當前Seek位置                long origPos = stream.Seek(0, SeekOrigin.Begin);                stream.Seek(0, SeekOrigin.Begin);                int nByte = stream.ReadByte();                byte1 = Convert.ToByte(nByte);                byte2 = Convert.ToByte(stream.ReadByte());                if (stream.Length >= 3)                {                    byte3 = Convert.ToByte(stream.ReadByte());                }                if (stream.Length >= 4)                {                    byte4 = Convert.ToByte(stream.ReadByte());                }                //根據檔案流的前4個位元組判斷Encoding                //Unicode {0xFF, 0xFE};                //BE-Unicode {0xFE, 0xFF};                //UTF8 = {0xEF, 0xBB, 0xBF};                if (byte1 == 0xFE && byte2 == 0xFF)//UnicodeBe                {                    targetEncoding = Encoding.BigEndianUnicode;                }                if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode                {                    targetEncoding = Encoding.Unicode;                }                if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)//UTF8                {                    targetEncoding = Encoding.UTF8;                }                //恢複Seek位置                       stream.Seek(origPos, SeekOrigin.Begin);            }            return targetEncoding;        }        /// <summary>        /// GetEncoding        /// </summary>        /// <param name="bytes"></param>        /// <param name="defaultEncoding"></param>        /// <returns></returns>        private static Encoding GetEncoding(byte[] bytes, Encoding defaultEncoding)        {            var targetEncoding = defaultEncoding;            byte byte1 = 0;            byte byte2 = 0;            byte byte3 = 0;            if (bytes.Length >= 1)            {                byte1 = bytes[0];            }            if (bytes.Length >= 2)            {                byte2 = bytes[1];            }            if (bytes.Length >= 3)            {                byte3 = bytes[2];            }            if (byte1 == 0xFE && byte2 == 0xFF)            {                targetEncoding = Encoding.BigEndianUnicode;            }            if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)            {                targetEncoding = Encoding.Unicode;            }            if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)            {                targetEncoding = Encoding.UTF8;            }            return targetEncoding;        }    }}