在客户电脑上,我们拿到数据文档需要在项目中打开,但是有时候打开文档,会出先乱码,可能是因为文档编码格式和代码打开时设定的编码格式不一致,导致有些字符编码没能正确显示,这个时候就需要先判断文档类型,然后再指定类型读取文档内容。
判断文档编码格式代码方法如下:
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;
}
}
}
测试的时候通过控制台应用程序展示,代码如下:
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using CustomCommon;
namespace FileEncodingConsole
{
class Program
{
[STAThreadAttribute]
static void Main(string[] args)
{
string fName;
OpenFileDialog openFileDialog = new OpenFileDialog();
openFileDialog.InitialDirectory = "";
//openFileDialog.Filter = "文本文档|*.txt";
openFileDialog.RestoreDirectory = true;
openFileDialog.FilterIndex = 1;
if (openFileDialog.ShowDialog() == DialogResult.OK)
{
fName = openFileDialog.FileName;
Console.WriteLine("转换前:");
Console.WriteLine(System.IO.File.ReadAllText(fName));
Console.WriteLine("------------------------------------------------------------------------------");
Console.WriteLine("转换后:");
var txt = System.IO.File.ReadAllText(fName,
FileEncoding.EncodingType.GetType(fName));
Console.WriteLine(txt);
}
Console.ReadLine();
}
}
}
其实在我们读取文档时,很有可能一些数学符号、希腊字母或者部分的汉字展示出现乱码,用他们指定编码格式去读取,可以大大的降低乱码的可能性,嗯……代码记录