/// <summary>
/// 获取源文件的编码格式
/// </summary>
/// <param name="path"></param>
/// <returns></returns>
private static MyEncodingType GetEncode(string path)
{
MyEncodingType type = MyEncodingType.ANSI_Default;
// 获取源文本的编码方式
using (FileStream fs = new FileStream(path, FileMode.Open, FileAccess.Read))
{
BinaryReader reader = new BinaryReader(fs); //这里选择任何一种编码都没关系，都是根据实际文本编码读取二进制
byte[] bytes = reader.ReadBytes((int)fs.Length);
if (IsASCII(bytes))
{
type = MyEncodingType.ASCII_UTF8withoutBom; // 将ACSII 都看作UTF8 或 ASCII 都可以
}
else if (IsUtf8WithoutBom(bytes))
{
if (IsUtf8WithBom(bytes))
{
type = MyEncodingType.Utf8withBom;
}
else
{
type = MyEncodingType.Utf8withoutBom;
}
}
else if (IsUtf16Big(bytes))
{
type = MyEncodingType.Utf16Big;
}
else if (IsUtf16Little(bytes))
{
type = MyEncodingType.Utf16Little;
}
else
{
Console.WriteLine("当前编码方式：代码页：" + Encoding.Default.CodePage);
type = MyEncodingType.ANSI_Default;
}
}
return(type);
}
/// <summary>
/// 转化文本的编码
/// 获取了中间的string字符串
/// </summary>
/// <param name="path"></param>
/// <param name="targetEncoding"></param>
private static void SwitchEncoding(string path, Encoding targetEncoding)
{
// 获取编码
MyEncodingType myEncodingType = GetEncode(path);
// 获取源文本
string sourceStr = String.Empty;
using (FileStream fs = new FileStream(path, FileMode.Open, FileAccess.Read))
{
// 获取原文本
using (BinaryReader rd = new BinaryReader(fs, Encoding.UTF8)) // 这里的编码并没有什么作用，只是为了第三个参数，读取后不关闭文件流
{
// 获取解码器
Decoder de = null;
switch (myEncodingType)
{
case MyEncodingType.ASCII_UTF8withoutBom: // 源文本全为英文，也采用UTF8来解码
de = new UTF8Encoding(false).GetDecoder();
break;
case MyEncodingType.ANSI_Default:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
de = Encoding.Default.GetDecoder();
break;
case MyEncodingType.Utf8withBom:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
de = new UTF8Encoding(true).GetDecoder();
rd.ReadBytes(3);
break;
case MyEncodingType.Utf8withoutBom:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
de = new UTF8Encoding(false).GetDecoder();
break;
case MyEncodingType.Utf16Big:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
de = Encoding.BigEndianUnicode.GetDecoder();
rd.ReadBytes(2);
break;
case MyEncodingType.Utf16Little:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
de = Encoding.Unicode.GetDecoder();
rd.ReadBytes(2);
break;
default:
break;
}
byte[] readBytes = rd.ReadBytes((int)rd.BaseStream.Length); // 此时 rd.BaseStream.Length 大于剩下的 byte数组数量，但是没关系，只会读取剩下所有的
char[] chars = new char[de.GetCharCount(readBytes, 0, readBytes.Length)];
de.GetChars(readBytes, 0, readBytes.Length, chars, 0);
sourceStr = new string(chars);
}
}
//使用新的编码写入文本
using (FileStream fs = new FileStream(path, FileMode.Create, FileAccess.Write))
{
using (BinaryWriter writer = new BinaryWriter(fs, targetEncoding))
{
// 转换成目标编码的字节数组
byte[] targetBytes = targetEncoding.GetBytes(sourceStr);
byte[] preamble = targetEncoding.GetPreamble();
//若有BOM头，则添上Bom头
if (preamble.Length > 0)
{
byte[] finBytes = new byte[targetBytes.Length + preamble.Length];
Buffer.BlockCopy(preamble, 0, finBytes, 0, preamble.Length);
Buffer.BlockCopy(targetBytes, 0, finBytes, preamble.Length, targetBytes.Length);
targetBytes = finBytes;
}
writer.Write(targetBytes);
}
}
}
/// <summary>
/// 转化文本的编码
/// 不需要中间的string字符串
/// </summary>
/// <param name="path"></param>
/// <param name="targetEncoding"></param>
private static void ConvertEncoding(string path, Encoding targetEncoding)
{
// 获取编码
MyEncodingType myEncodingType = GetEncode(path);
Encoding srcEncoding = null;
byte[] tarBytes;
using (FileStream fs = new FileStream(path, FileMode.Open, FileAccess.Read))
{
// 获取原文本
using (BinaryReader rd = new BinaryReader(fs, Encoding.Default)) // 这里的编码并没有什么作用，只是为了第三个参数，读取后不关闭文件流
{
switch (myEncodingType)
{
case MyEncodingType.ASCII_UTF8withoutBom:
srcEncoding = new UTF8Encoding(false);
break;
case MyEncodingType.ANSI_Default:
srcEncoding = Encoding.Default;
break;
case MyEncodingType.Utf8withBom:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
srcEncoding = Encoding.UTF8;
rd.ReadBytes(3);
break;
case MyEncodingType.Utf8withoutBom:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
srcEncoding = new UTF8Encoding(false);
break;
case MyEncodingType.Utf16Big:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
srcEncoding = Encoding.BigEndianUnicode;
rd.ReadBytes(2);
break;
case MyEncodingType.Utf16Little:
if (targetEncoding == Encoding.ASCII)
{
throw new Exception("当前编码，无法转为ASCII码");
}
srcEncoding = Encoding.Unicode;
rd.ReadBytes(2);
break;
}
byte[] srcBytes = rd.ReadBytes((int)rd.BaseStream.Length);
tarBytes = Encoding.Convert(srcEncoding, targetEncoding, srcBytes);
}
}
//使用新的编码写入文本
using (FileStream fs = new FileStream(path, FileMode.Create, FileAccess.Write))
{
using (BinaryWriter writer = new BinaryWriter(fs, targetEncoding))
{
// 转换成目标编码的字节数组
byte[] preamble = targetEncoding.GetPreamble();
//若有BOM头，则添上Bom头
if (preamble.Length > 0)
{
byte[] finBytes = new byte[tarBytes.Length + preamble.Length];
Buffer.BlockCopy(preamble, 0, finBytes, 0, preamble.Length);
Buffer.BlockCopy(tarBytes, 0, finBytes, preamble.Length, tarBytes.Length);
tarBytes = finBytes;
}
writer.Write(tarBytes);
}
}
}