DetectUTFBom

Program.cs

//
// Finds and displays the filenames of all UTF8 files that contain a byte order mark
// in a specified directory tree.
//
// based on information from the following URL
//
// http://stackoverflow.com/questions/4520184/how-to-detect-the-character-encoding-of-a-text-file 
//

using System;
using System.IO;
using System.Linq;

namespace DetectUTFBom
{
    class Program
    {
        static int Main(string[] args)
        {
            if (args.Length == 0)
            {
                Console.WriteLine("Usage: DetectUTFBOM <directory>");
                return 1;
            }

            var directoryToScan = args[0];
            if (!Directory.Exists(directoryToScan))
            {
                Console.WriteLine("Directory does not exist.");
                return 2;
            }

            var allFiles = Directory.GetFiles(directoryToScan,
                                              "*.*",
                                              SearchOption.AllDirectories);

            var filesWithBom = allFiles.Where(FileHasByteOrderMark);
    
            foreach(var filename in filesWithBom)
                Console.WriteLine(filename);

            Console.WriteLine();
            Console.WriteLine("{0} file(s) found,", filesWithBom.Count());
            
            return 0;
        }

        private static bool FileHasByteOrderMark(string filename)
        {
            using (var s = File.Open(filename, FileMode.Open, FileAccess.Read, FileShare.Read))
            {
                // read the first three bytes. that should contain the byte order mark
                // which is the following sequence of bytes EF BB BF
                var bom = new byte[3];
                s.Read(bom, 0, 3);
                if (bom[0] == 0xEF && bom[1] == 0xBB && bom[2] == 0xBF)
                    return true; // found bom
                s.Read(bom, 0, 1);
            }
            return false;
        } // FileHasByteOrderMark

    }
}