C#获取文本文件的编码,自动区分GB2312和UTF8
2014-10-22 15:03
337 查看
以下是获取文件编码的一个类
using System;
using System.IO;
using System.Text;
/// <summary>
/// FileEncoding 的摘要说明
/// </summary>
namespace FileEncoding
{
/// <summary>
/// 获取文件的编码格式
/// </summary>
public class EncodingType
{
/// <summary>
/// 给定文件的路径,读取文件的二进制数据,判断文件的编码类型
/// </summary>
/// <param name="FILE_NAME">文件路径</param>
/// <returns>文件的编码类型</returns>
public static System.Text.Encoding GetType(string FILE_NAME)
{
FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
Encoding r = GetType(fs);
fs.Close();
return r;
}
/// <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 static System.Text.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, System.Text.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 static 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 < data.Length; i++)
{
curByte = data[i];
if (charByteCounter == 1)
{
if (curByte >= 0x80)
{
//判断当前
while (((curByte <<= 1) & 0x80) != 0)
{
charByteCounter++;
}
//标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
if (charByteCounter == 1 || charByteCounter > 6)
{
return false;
}
}
}
else
{
//若是UTF-8 此时第一位必须为1
if ((curByte & 0xC0) != 0x80)
{
return false;
}
charByteCounter--;
}
}
if (charByteCounter > 1)
{
throw new Exception("非预期的byte格式");
}
return true;
}
}
}
以下是使用示例
#region 打开按钮
/// <summary>
/// 打开按钮
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void txtMenuOpen_Click(object sender, EventArgs e)
{
string fName;
OpenFileDialog openFileDialog = new OpenFileDialog();
openFileDialog.InitialDirectory = "";//注意这里写路径时要用c:而不是c:
openFileDialog.Filter = "文本文档|*.txt";
openFileDialog.RestoreDirectory = true;
openFileDialog.FilterIndex = 1;
if (openFileDialog.ShowDialog() == DialogResult.OK)
{
fName = openFileDialog.FileName;
txtBox.Text = System.IO.File.ReadAllText(fName,
FileEncoding.EncodingType.GetType(fName));
}
}
#endregion
转载:http://blog.163.com/da7_1@126/blog/static/1040726782013111339269/
using System;
using System.IO;
using System.Text;
/// <summary>
/// FileEncoding 的摘要说明
/// </summary>
namespace FileEncoding
{
/// <summary>
/// 获取文件的编码格式
/// </summary>
public class EncodingType
{
/// <summary>
/// 给定文件的路径,读取文件的二进制数据,判断文件的编码类型
/// </summary>
/// <param name="FILE_NAME">文件路径</param>
/// <returns>文件的编码类型</returns>
public static System.Text.Encoding GetType(string FILE_NAME)
{
FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
Encoding r = GetType(fs);
fs.Close();
return r;
}
/// <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 static System.Text.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, System.Text.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 static 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 < data.Length; i++)
{
curByte = data[i];
if (charByteCounter == 1)
{
if (curByte >= 0x80)
{
//判断当前
while (((curByte <<= 1) & 0x80) != 0)
{
charByteCounter++;
}
//标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
if (charByteCounter == 1 || charByteCounter > 6)
{
return false;
}
}
}
else
{
//若是UTF-8 此时第一位必须为1
if ((curByte & 0xC0) != 0x80)
{
return false;
}
charByteCounter--;
}
}
if (charByteCounter > 1)
{
throw new Exception("非预期的byte格式");
}
return true;
}
}
}
以下是使用示例
#region 打开按钮
/// <summary>
/// 打开按钮
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void txtMenuOpen_Click(object sender, EventArgs e)
{
string fName;
OpenFileDialog openFileDialog = new OpenFileDialog();
openFileDialog.InitialDirectory = "";//注意这里写路径时要用c:而不是c:
openFileDialog.Filter = "文本文档|*.txt";
openFileDialog.RestoreDirectory = true;
openFileDialog.FilterIndex = 1;
if (openFileDialog.ShowDialog() == DialogResult.OK)
{
fName = openFileDialog.FileName;
txtBox.Text = System.IO.File.ReadAllText(fName,
FileEncoding.EncodingType.GetType(fName));
}
}
#endregion
转载:http://blog.163.com/da7_1@126/blog/static/1040726782013111339269/
相关文章推荐
- C#获取文本文件的编码,自动区分GB2312和UTF8
- C# 获取文本文件的编码,自动区分GB2312和UTF8
- C# 获取文本文件的编码,自动区分GB2312和UTF8
- C#实现获取文本文件的编码的一个类(区分GB2312和UTF8)
- C#实现获取文本文件的编码的一个类(区分GB2312和UTF8)-来自转载收集
- 自动检测文本文件编码是否为GB2312(简体中文),并转换为UTF8编码,附一个GB2312全区对应的utf8编码码表
- VC之网页获取(能区分GB2312与UTF8)
- VC之网页获取(能区分GB2312与UTF8)
- c# 获取网页源码,自动判断编码格式新方法!(转)
- PHP自动判断字符串是gb2312还是utf8编码
- C#获取网页源码并且自动判断网页字符集编码
- Atitit.检测文本文件的编码 自动获取文件的中文编码
- C#获取网页源码,自动判断网页字符集编码
- 【编码】_C#中编码名称(Name)与页面标识(CodePage)的关系_编码gb2312的获取
- c# 获取网页源码,自动判断编码格式新方法
- C#中获取汉字的GB2312编码
- C#获取网页源码,自动判断网页字符集编码[转]
- 黄聪:PHP自动判断字符串是gb2312还是utf8编码
- C#判断文本文件编码是ANSI还是无BOM的UTF8
- Atitit.检测文本文件的编码 自动获取文件的中文编码