日期:2014-05-17 浏览次数:21219 次
本人是JAVA开发 由于开发的人多了 有的人开发环境编码格式也不同 有的是GBK 有的是UTF-8 代码中更是层出不穷
直接导致项目中中文的类乱码 写代码不能加注释的囧地 为了解决此问题编写了此软件 ?分享出来希望能帮助到其他人
部分代码如下:
?
public int[] Count=new int[3];//存储计数信息
public string SelectPath = null;//存储选择的路径
private Profile profile = new Profile();
string confitemp = "Configuration";//配置的总节点
/// <summary>
/// 判断文件编码格式是什么
/// </summary>
/// <param name="stream"></param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream)
{
Encoding targetEncoding = Encoding.Default;
if (stream != null && stream.Length >= 2)
{
//保存文件流的前4个字节
byte byte1 = 0;
byte byte2 = 0;
byte byte3 = 0;
byte byte4 = 0;
//保存当前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());
}
//根据文件流的前4个字节判断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;
}
//恢复Seek位置
stream.Seek(origPos, SeekOrigin.Begin);
}
return targetEncoding;
}
/// <summary>
/// 通过给定的文件流,判断文件的编码类型
/// </summary>
/// <param name="fs">文件流</param>
/// <returns>文件的编码类型</returns>
public Encoding GetType(FileStream fs)
{
byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };
byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //带BOM
Encoding reVal = Encoding.Default;
BinaryReader r = new BinaryReader(fs,Encoding.Default);
int i;
int.TryParse(fs.Length.ToString(), out i);
byte[] ss = r.ReadBytes(i);
if (IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
{
reVal = Encoding.UTF8;
}
else if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
{
reVal = Encoding.BigEndianUnicode;
}
else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41)
{
reVal = Encoding.Unicode;
}
r.Close();
return reVal;
}
/// <summary>
/// 判断是否是不带 BOM 的 UTF8 格式
/// </summary>
/// <param name="data"></param>
/// <returns></returns>
private bool IsUTF8Bytes(byte[] data)
{
int charByteCounter = 1; //计算当前正分析的字符应还有的字节数
byte curByte; //当前分析的字节.
for (int i = 0; i