C#读取中文文件出现乱码的解决方法读取中文文件出现乱码的解决方法
主要介绍了C#读取中文文件出现乱码的解决方法,涉及C#中文编码的操作技巧,非常具有实用价值,需要的朋友可
以参考下
本文实例讲述了C#读取中文文件出现乱码的解决方法。分享给大家供大家参考。具体分析如下：
先来看这段代码：
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 < 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];
}
}
}
希望本文所述对大家的C#程序设计有所帮助。
评论0