C#检查目录下所有文件的编码格式并转换为UTF8格式

1、检查目录下所有文件的编码格式(递归)

2、将不是utf8的格式转换为UTF8格式


.config

  <appSettings>
    <add key="ExceptList" value=".git,.nuget,.vs,.dll,.pdb, .png,.jpg,.gif ,.log,.eot, .ttf, .woff, .swf, packages , ReferenceDLL ,.cache,.xls, .xlsx,.doc,.docx,favicon.ico,_references.js,.exe" />
    <add key="isChangeToUTF8" value="true" />
  </appSettings>


public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
            this.txt_url.Text = "G:\\WorkSpace\\messagecenter";
        }

        private static List<string> ExceptList = new List<string>();

        private static bool isChangeToUTF8 = false;

        private List<string> ResultList=new List<string>();

        static Form1()
        {
            System.Configuration.AppSettingsReader appReader = new System.Configuration.AppSettingsReader();
            string strExcept= Convert.ToString(appReader.GetValue("ExceptList", typeof(string)));
            string strIsChange = Convert.ToString(appReader.GetValue("isChangeToUTF8", typeof(string)));

            if (!string.IsNullOrEmpty(strExcept))
            {
                var tempExcept = strExcept.Split(new char[] { ',' }, StringSplitOptions.RemoveEmptyEntries);
                foreach (var temp in tempExcept)
                {
                    ExceptList.Add(temp.Trim());
                }

            }
            if (!string.IsNullOrEmpty(strIsChange) && strIsChange.ToUpper()=="TRUE")
            {
                isChangeToUTF8 = true;
            }
        }


        private void btn_start_Click(object sender, EventArgs e)
        {
            ResultList = new List<string>();
            string myPath = txt_url.Text;
            if (string.IsNullOrEmpty(myPath))
            {
                MessageBox.Show("PATH?");
                return;
            }

            List<string> pathList = new List<string>();
            try
            {
                //查找目录下的所有文件
                GetDirectory(myPath, pathList);
                foreach (var path in pathList)
                {
                    //获取文件编码格式
                    var type = EncodingType.GetType(path, ResultList);
                    if (type != Encoding.UTF8)
                    {
                        ResultList.Add($"{path},原格式{type.EncodingName}");
                        if (isChangeToUTF8)
                        {
                            //转换编码格式至UTF8
                            ChangeEncoding(path, type);
                        }
                    }
                }
            }
            catch (Exception exception)
            {
                MessageBox.Show(exception.ToString());
                return;
            }

            if (ResultList.Any())
            {
                ResultList.Insert(0,myPath);
                ResultList.Insert(1,$"共计文件{pathList.Count}个");
                ResultList.Insert(2,$"非UTF-8文件共{ResultList.Count-2}个");
                byte[] myByte = System.Text.Encoding.UTF8.GetBytes(string.Join(Environment.NewLine, ResultList.ToArray()));
                using (FileStream fsWrite = new FileStream($"D:\\result{DateTime.Now.ToString("yyyyMMddHHmmss")}.txt", FileMode.Append))
                {
                    fsWrite.Write(myByte, 0, myByte.Length);
                };
                MessageBox.Show("D:\\result.txt");
            }
            else
            {
                ResultList.Insert(0, myPath);
                ResultList.Insert(1, $"共计文件{pathList.Count}个");
                ResultList.Insert(2, $"非UTF-8文件共{ResultList.Count - 2}个");
                byte[] myByte = System.Text.Encoding.UTF8.GetBytes(string.Join(Environment.NewLine, ResultList.ToArray()));
                using (FileStream fsWrite = new FileStream($"D:\\success{DateTime.Now.ToString("yyyyMMddHHmmss")}.txt", FileMode.Append))
                {
                    fsWrite.Write(myByte, 0, myByte.Length);
                };
                MessageBox.Show("finish!");
            }
        }


        private void GetDirectory(string path, List<string> list)
        {
            DirectoryInfo folder = new DirectoryInfo(path);
            GetFile(path,list);
            foreach (var directory in folder.GetDirectories())
            {
                if (!ExceptList.Contains(directory.Name))
                {
                    string childPath = $"{path}\\{directory.Name}";
                    GetDirectory(childPath, list);
                }
                
            }
        }
        private void GetFile(string path, List<string> list)
        {
            DirectoryInfo folder = new DirectoryInfo(path);
            foreach (FileInfo file in folder.GetFiles())
            {
                if (!ExceptList.Any(e => file.Name.EndsWith(e))) 
                {
                    list.Add($"{path}\\{file.Name}");
                }
                
            }
        }


        private void ChangeEncoding(string filename , System.Text.Encoding encoding)
        {
            System.IO.FileStream fs = new System.IO.FileStream(filename, System.IO.FileMode.Open, System.IO.FileAccess.Read);
            byte[] flieByte = new byte[fs.Length];
            fs.Read(flieByte, 0, flieByte.Length);
            fs.Close();

            StreamWriter docWriter;
            System.Text.Encoding ec = System.Text.Encoding.GetEncoding("UTF-8");
            docWriter = new StreamWriter(filename, false, ec);
            docWriter.Write(encoding.GetString(flieByte));
            docWriter.Close();
        }

    }


 /// <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 ,List<string> ResultList)
        {
            FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
            Encoding r = GetType(fs, FILE_NAME, ResultList);
            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, string FILE_NAME , List<string> ResultList)
        {
            //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, FILE_NAME, ResultList) || (ss.Length > 3 && ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
            {
                reVal = Encoding.UTF8;
            }
            else if (ss.Length > 3 && ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
            {
                reVal = Encoding.BigEndianUnicode;
            }
            else if (ss.Length>3 && 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, string FILE_NAME, List<string> ResultList)
        {
            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)
            {
                ResultList.Add($"{FILE_NAME},异常:非预期的byte格式,无法判断是否是UTF8(不带BOM)格式,已跳过");
                //throw new Exception("非预期的byte格式");
            }
            return true;
        }

    }


  • 3
    点赞
  • 15
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值