C#中判断文本文件编码格式的静态类

 1、定义一个判断文本文件编码格式的静态类--TextEncodingType:

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using System.IO;

namespace Demo_Menu
{
    public static class TextEncodingType
    {
        /// <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=“fileName“>文件路径</param>
        /// <returns>文件的编码类型</returns>
        public static System.Text.Encoding GetType(string fileName)
        {
            FileStream fs = new FileStream(fileName, 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;
        }
 
    }
}

2、在需要的地方调用它,如:

        private void mi_OpenFile_Click(object sender, EventArgs e)
        {
            if (openFileDialog1.ShowDialog()==DialogResult.OK)
            {
                _FileName = openFileDialog1.FileName;
                this.Text = _FileName;
                _FileEncode = TextEncodingType.GetType(_FileName);//自动获取文件的编码类型
                System.IO.StreamReader sr;
                sr = new System.IO.StreamReader(_FileName, _FileEncode);//加入了自动判断文件编码类型的功能
                textBox1.Text = sr.ReadToEnd();
                sr.Close();
                statusBar_Encode.Text = _FileEncode.EncodingName; //取得当前文件的编码名称并显示在状态栏中
                _IsSaved = true;
            }
        }

 

展开阅读全文

没有更多推荐了,返回首页