C#读取文档小工具
C#读取文件,牵扯到编码格式,这里面也有学问(System.IO),编码格式在微软官方技术文档里,我粗略看了下,也有几十种:
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
using System; using System.Collections.Generic; using System.ComponentModel; using System.Data; using System.Drawing; using System.IO; using System.Linq; using System.Text; using System.Threading.Tasks; using System.Windows.Forms; namespace winFtn6 { public partial class Form1 : Form { public Form1() { InitializeComponent(); } private void btn_tn6_Click(object sender, EventArgs e) { OpenFileDialog openFileDialog = new OpenFileDialog(); openFileDialog.InitialDirectory = "c:\\";//注意这里写路径时要用c:\\而不是c:\ openFileDialog.Filter = "文本文件|*.*|C#文件|*.cs|所有文件|*.*"; openFileDialog.RestoreDirectory = true; openFileDialog.FilterIndex = 1; if (openFileDialog.ShowDialog() == DialogResult.OK) { string fName = openFileDialog.FileName; System.Text.Encoding type = GetType(fName); //文本:GB2312, string text = File.ReadAllText(fName, System.Text.Encoding.GetEncoding("GB2312")); richTextBox1.Text = type.ToString()+"readalltext:"+ text; // richTextBox1.AppendText(""); /// } } /// <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; } } }
,Best Wish 不负年华