C # Gets the encoding of a text file that automatically distinguishes between GB2312 and UTF8

C # Gets the encoding of a text file that automatically distinguishes between GB2312 and UTF8

The following is a class that gets the file encoding

usingSystem;usingSystem.IO;usingSystem.Text;/// <summary> ///Summary description of fileencoding/// </summary> namespacefileencoding {/// <summary> ///get the encoded format of a file/// </summary>  Public classEncodingtype {/// <summary> ///The path of the given file, reading the binary data of the file, judging the file encoding type/// </summary> /// <param name= "file_name" >file path</param> /// <returns>the encoding type of the file</returns>  Public StaticSystem.Text.Encoding GetType (stringfile_name) {FileStream FS=NewFileStream (file_name, FileMode.Open, FileAccess.Read); Encoding R=GetType (FS); fs. Close (); returnR;} /// <summary> ///determine the encoding type of a file by a given file stream/// </summary> /// <param name= "FS" >file Stream</param> /// <returns>the encoding type of the file</returns>  Public StaticSystem.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};//with BOMEncoding ReVal =Encoding.default; BinaryReader R=NewBinaryReader (FS, System.Text.Encoding.Default);inti;int. TryParse (fs. Length.tostring (), outi); 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 (); returnReVal;} /// <summary> ///determine if the UTF8 format is not with the BOM/// </summary> /// <param name= "Data" ></param> /// <returns></returns> Private Static BOOLIsutf8bytes (byte[] data) { intCharbytecounter =1;//calculates the number of bytes that are currently being parsed by the word Fu ChingbyteCurbyte;//the currently parsed bytes. for(inti =0; I < data. Length; i++) {Curbyte=Data[i];if(Charbytecounter = =1) { if(Curbyte >=0x80) { //judging the current while(((Curbyte <<=1) &0x80) !=0) {Charbytecounter++; } //If the first mark is not 0, it starts at least 2 1 such as: 110XXXXX ... 1111110Xif(Charbytecounter = =1|| Charbytecounter >6) { return false; } } } Else { //if UTF-8, the first bit must be 1 .if((Curbyte &0xC0) !=0x80) { return false; } Charbytecounter--; } } if(Charbytecounter >1) { Throw NewException ("non-expected byte format"); } return true; } } } 

The following are examples of using

#regionOpen button/// <summary> ///Open Button/// </summary> /// <param name= "Sender" ></param> /// <param name= "E" ></param> Private voidTxtmenuopen_click (Objectsender, EventArgs e) { stringFName; OpenFileDialog OpenFileDialog=NewOpenFileDialog (); Openfiledialog.initialdirectory= "";//Note that this path is written in C: instead of C:Openfiledialog.filter = "Text Document |*. txt "; Openfiledialog.restoredirectory=true; Openfiledialog.filterindex=1; if(Openfiledialog.showdialog () = =DialogResult.OK) {fName=openfiledialog.filename; Txtbox.text=System.IO.File.ReadAllText (FName, FileEncoding.EncodingType.GetType (FName));} } #endregion

C # Gets the encoding of a text file that automatically distinguishes between GB2312 and UTF8