An extension method for converting a byte array to a string (reading its BOM)
July 19, 2010
Below is an extension method that adapts Rick Strahl’s code (and the comments too) to stop you having to guess or read the byte order mark of a byte array or text file each time you convert it to a string.
The commonest way of doing this is usually with
byte[] buffer = File.ReadAllBytes(@"C:\file.txt"); System.Text.Encoding.xxx.GetString(buffer)
where xxx is Ascii, Unicode, or UTF8, or Default, but the extension method you to simply do
byte[] buffer = File.ReadAllBytes(@"C:\file.txt"); string content = buffer.GetString();
Here’s the method
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| public static class Extensions | |
| { | |
| /// <summary> | |
| /// Converts a byte array to a string, using its byte order mark to convert it to the right encoding. | |
| /// Original article: http://www.west-wind.com/WebLog/posts/197245.aspx | |
| /// </summary> | |
| /// <param name="buffer">An array of bytes to convert</param> | |
| /// <returns>The byte as a string.</returns> | |
| public static string GetString(this byte[] buffer) | |
| { | |
| if (buffer == null || buffer.Length == 0) | |
| return ""; | |
| // Ansi as default | |
| Encoding encoding = Encoding.Default; | |
| /* | |
| EF BB BF UTF-8 | |
| FF FE UTF-16 little endian | |
| FE FF UTF-16 big endian | |
| FF FE 00 00 UTF-32, little endian | |
| 00 00 FE FF UTF-32, big-endian | |
| */ | |
| if (buffer[0] == 0xef && buffer[1] == 0xbb && buffer[2] == 0xbf) | |
| encoding = Encoding.UTF8; | |
| else if (buffer[0] == 0xfe && buffer[1] == 0xff) | |
| encoding = Encoding.Unicode; | |
| else if (buffer[0] == 0xfe && buffer[1] == 0xff) | |
| encoding = Encoding.BigEndianUnicode; // utf-16be | |
| else if (buffer[0] == 0 && buffer[1] == 0 && buffer[2] == 0xfe && buffer[3] == 0xff) | |
| encoding = Encoding.UTF32; | |
| else if (buffer[0] == 0x2b && buffer[1] == 0x2f && buffer[2] == 0x76) | |
| encoding = Encoding.UTF7; | |
| using (MemoryStream stream = new MemoryStream()) | |
| { | |
| stream.Write(buffer, 0, buffer.Length); | |
| stream.Seek(0, SeekOrigin.Begin); | |
| using (StreamReader reader = new StreamReader(stream, encoding)) | |
| { | |
| return reader.ReadToEnd(); | |
| } | |
| } | |
| } | |
| } |
I'm Chris Small, a software engineer working in London. This is my tech blog. Find out more about me via Github, Stackoverflow, Resume