在工做之餘,將寫代碼過程比較經常使用的代碼段作個記錄,下面的代碼段是關於C#讀取中文文件亂碼的解方法的代碼,應該是對小夥伴有好處。
FileStream aFile = new FileStream(SingleFile, FileMode.Open);
StreamReader sr = new StreamReader(aFile, Encoding.GetEncoding("gb2312"), true);
string FileContent = sr.ReadToEnd();
aFile.Close();
ProcessData Pd = new ProcessData();
Pd.ProceData(FileContent);複製代碼
StreamReader使用3個參數最後一個自動檢測utf-8,中文大部分是gb2312,若是不是utf-8,就用gb2312系統自帶utf檢測,見以下
private void DetectEncoding()
{
if (this.byteLen >= 2)
{
this._detectEncoding = false;
bool flag = false;
if ((this.byteBuffer[0] == 0xfe) && (this.byteBuffer[1] == 0xff))
{
this.encoding = new UnicodeEncoding(true, true);
this.CompressBuffer(2);
flag = true;
}
else if ((this.byteBuffer[0] == 0xff) && (this.byteBuffer[1] == 0xfe))
{
if (((this.byteLen < 4) || (this.byteBuffer[2] != 0)) || (this.byteBuffer[3] != 0))
{
this.encoding = new UnicodeEncoding(false, true);
this.CompressBuffer(2);
flag = true;
}
else
{
this.encoding = new UTF32Encoding(false, true);
this.CompressBuffer(4);
flag = true;
}
}
else if (((this.byteLen >= 3) && (this.byteBuffer[0] == 0xef)) && ((this.byteBuffer[1] == 0xbb) && (this.byteBuffer[2] == 0xbf)))
{
this.encoding = Encoding.UTF8;
this.CompressBuffer(3);
flag = true;
}
else if ((((this.byteLen >= 4) && (this.byteBuffer[0] == 0)) && ((this.byteBuffer[1] == 0) && (this.byteBuffer[2] == 0xfe))) && (this.byteBuffer[3] == 0xff))
{
this.encoding = new UTF32Encoding(true, true);
this.CompressBuffer(4);
flag = true;
}
else if (this.byteLen == 2)
{
this._detectEncoding = true;
}
if (flag)
{
this.decoder = this.encoding.GetDecoder();
this._maxCharsPerBuffer = this.encoding.GetMaxCharCount(this.byteBuffer.Length);
this.charBuffer = new char[this._maxCharsPerBuffer];
}
}
} 複製代碼