【算法系列】使用LINQ来检测和删除重复的文件

 

using System;  

using System.IO;  

using System.Linq;  

using System.Security.Cryptography;  

using System.Text;  

 

namespace DupeFinder  

{  

    internal class Program  

    {  

        private static void Main(string[] args)  

        {  

            Directory.GetFiles(@"d:\icons", "*.ico")  

                .Select(  

                    f => new 

                             {  

                                 FileName = f,  

                                 FileHash = Encoding.UTF8.GetString( new SHA1Managed()  

                                                                    .ComputeHash(new FileStream(f, FileAccess.Read)))  

                             })  

                .GroupBy(f => f.FileHash)  

                .Select(g => new {FileHash = g.Key, Files = g.Select(z => z.FileName).ToList()})  

                .SelectMany(f => f.Files.Skip(1))  

                .ToList()  

                .ForEach(File.Delete);  

            Console.ReadKey();  

        }  

    }  

} 

 

相当精妙地写法：）

见老外的文章：http://www.hosca.com/blog/post/2010/04/13/using-LINQ-to-detect-and-remove-duplicate-files.aspx