欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  后端开发

C#读取中文文件乱码的解方法

程序员文章站 2022-05-13 07:57:18
...
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);

StreamReader 使用3个参数 最后一个自动检测utf-8,中文大部分是gb2312,如果不是utf-8,就用gb2312


系统自带utf 检测 ,见如下

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 = 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];
        }
    }
}