• c# 判断文本文件的编码格式


    using System;
    using System.IO;
    using System.Text;
    
    namespace Helper
    {
        public class EncodingHelper
        {
            public static Encoding GetType(FileStream fs)
            {
                byte[] Unicode = {0xFF, 0xFE, 0x41};
                byte[] UnicodeBIG = {0xFE, 0xFF, 0x00};
                byte[] UTF8 = {0xEF, 0xBB, 0xBF}; //带BOM 
                var reVal = Encoding.Default;
    
                var r = new BinaryReader(fs, Encoding.Default);
                int i;
                int.TryParse(fs.Length.ToString(), out i);
                var 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;
            }
    
            private static bool IsUTF8Bytes(byte[] data)
            {
                var 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 (var 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;
            }
        }
    }
  • 相关阅读:
    线段树节点到底开多大
    HDU4901 The Romantic Hero DP
    VIM 配置文件可执行命令
    codeforces159D
    codeforces416B
    codeforces165C
    codeforces332B
    Node.js权威指南 (9)
    iOS-android-windowsphone等移动终端平台开发流程图
    前端面试题细节问题
  • 原文地址:https://www.cnblogs.com/congqiandehoulai/p/12725673.html
Copyright © 2020-2023  润新知