LINQ和文件目录

记录https://docs.microsoft.com/zh-cn/dotnet/csharp/programming-guide/concepts/linq/linq-and-file-directories的学习

 

查询具有指定扩展名的文件 （SearchOption.AllDirectories 指递归文件夹获取所有文件）

string startFolder = @"C:\Users\bibi\Desktop\代码\异步\ConsoleApp4\Test\";
DirectoryInfo dir = new DirectoryInfo(startFolder);
IEnumerable<FileInfo> fileList = dir.GetFiles("*.*", SearchOption.AllDirectories);

var fileQuery = from file in fileList
                where file.Extension == ".png"
                orderby file.Name
                select file;

foreach(var item in fileQuery)
{
    Console.WriteLine(item.FullName);
}

按扩展名对文件进行分组

// Take a snapshot of the file system.  
string startFolder = @"C:\Users\bibi\Desktop\代码\异步\ConsoleApp4\Test\";

// Used in WriteLine to trim output lines.  
int trimLength = startFolder.Length;

// Take a snapshot of the file system.  
System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(startFolder);

// This method assumes that the application has discovery permissions  
// for all folders under the specified path.  
IEnumerable<System.IO.FileInfo> fileList = dir.GetFiles("*.*", System.IO.SearchOption.AllDirectories);

var queryGroupByExt = from file in fileList
                      group file by file.Extension.ToLower() into fileGroup
                      orderby fileGroup.Key
                      select fileGroup;

foreach(var group in queryGroupByExt)
{
    Console.WriteLine(group.Key);
    foreach(var item in group)
    {
        Console.WriteLine($"    {item.Name}");
    }
}

求目录下的所有文件的总字节数

string startFolder = @"C:\Users\bibi\Desktop\代码\异步\ConsoleApp4\Test\";

System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(startFolder);
var totalLength = dir.GetFiles().Sum(x=>x.Length);

Console.WriteLine(totalLength+" bytes");

对接文件夹中的文件（序列求等SequenceEqual、交集Insect、差集Except）

string pathA = @"C:\Users\bibi\Desktop\代码\异步\ConsoleApp4\Test\";
string pathB = @"C:\Users\bibi\Desktop\代码\异步\ConsoleApp4\Test\TestX\";

System.IO.DirectoryInfo dir1 = new System.IO.DirectoryInfo(pathA);
System.IO.DirectoryInfo dir2 = new System.IO.DirectoryInfo(pathB);

//使用了顶层目录SearchOption.TopDirectoryOnly，不需递归目录下的文件夹寻找文件，只要第一层文件。
IEnumerable<System.IO.FileInfo> list1 = dir1.GetFiles("*.*", SearchOption.TopDirectoryOnly);
IEnumerable<System.IO.FileInfo> list2 = dir2.GetFiles("*.*", SearchOption.TopDirectoryOnly);

//使用自定义的文件默认比较器
FileCompare myFileCompare = new FileCompare();

//判断两个序列是否相等
bool isEqualOne = list1.SequenceEqual(list2, myFileCompare);
if (isEqualOne == true)
{
    Console.WriteLine("the two folders are the same");
}
else
{
    Console.WriteLine("The two folders are not the same");
}

//求交集文件
var queryCommonFiles = list1.Intersect(list2, myFileCompare);
if (queryCommonFiles.Any())
{
    Console.WriteLine("The following files are in both folders:");
    foreach (var v in queryCommonFiles)
    {
        Console.WriteLine(v.FullName); //shows which items end up in result list  
    }
}

//求差集文件 在list1却不在list2的文件
var queryList1Only = list1.Except(list2, myFileCompare);
Console.WriteLine("The following files are in list1 but not list2:");
foreach (var v in queryList1Only)
{
    Console.WriteLine(v.FullName);
}         

 查找目录中最大、最小的一个或多个文件。

using System;
using System.Collections.Generic;
using System.Data;
using System.Diagnostics.CodeAnalysis;
using System.IO;
using System.Linq;
using System.Reflection;

namespace ConsoleApp4
{
    class Program
    {
        static void Main(string[] args)
        {
            string startFolder = @"C:\Users\mycomputer\Desktop\代码\异步\ConsoleApp4\Test\TestX\";

            System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(startFolder);
           
            IEnumerable<System.IO.FileInfo> fileList = dir.GetFiles("*.*", System.IO.SearchOption.AllDirectories);

            //查找文件最大字节数
            long maxSize = fileList.Select(x => GetFileLength(x)).Max();
           
            Console.WriteLine($"The length of the largest file under {startFolder} is {maxSize}");

            //查找字节数最大的文件
            var longestFile = fileList.OrderByDescending(x => GetFileLength(x)).First();          

            Console.WriteLine("The largest file under {0} is {1} with a length of {2} bytes",
                                startFolder, longestFile.FullName, longestFile.Length);

            //查找字节数最小的文件
            var smallestFile = fileList.OrderBy(x => GetFileLength(x)).First();            

            Console.WriteLine("The smallest file under {0} is {1} with a length of {2} bytes",
                                startFolder, smallestFile.FullName, smallestFile.Length);

           //查找字节前十大的文件
            var queryTenLargest = fileList.OrderByDescending(x => GetFileLength(x)).Take(10);        

            Console.WriteLine("The 10 largest files under {0} are:", startFolder);

            foreach (var v in queryTenLargest)
            {
                Console.WriteLine("{0}: {1} bytes", v.FullName, v.Length);
            }
        }

        static long GetFileLength(System.IO.FileInfo fi)
        {
            long bytes;
            try
            {
                bytes = fi.Length;
            }
            catch (System.IO.FileNotFoundException)
            {
                //如果文件找不到 0字节处理
                bytes = 0;
            }
            return bytes;
        }
    }   
}

查询目录树中重复文件。

using System;
using System.Collections.Generic;
using System.Data;
using System.IO;
using System.Linq;

namespace ConsoleApp4
{
    class Program
    {
        static void Main(string[] args)
        {
            string startFolder = @"C:\Users\biubiu\Desktop\代码\异步\ConsoleApp4\Test\";
            DirectoryInfo dir = new DirectoryInfo(startFolder);           
            IEnumerable<System.IO.FileInfo> fileList = dir.GetFiles("*.*", System.IO.SearchOption.AllDirectories);

            //根据文件名字、最后更新时间、字节长度来判断文件重复
            var querySameGroup = from file in fileList
                                     group file.Name by new PortableKey { Name = file.Name, LastWriteTime = file.LastWriteTime, Length = file.Length } into fileGroup
                                     where fileGroup.Count() > 1
                                     select fileGroup;

            //Linq 方法调用写法 
            //var querySameGroup2 = fileList.GroupBy(file => new PortableKey
            //{
            //    LastWriteTime = file.LastWriteTime,
            //    Length = file.Length,
            //    Name = file.Name
            //}, file => file.Name).Where(fileGroup => fileGroup.Count() > 1);

            foreach(var group in querySameGroup)
            {
                Console.WriteLine(group.Key);
                foreach(var item in group)
                {
                    Console.WriteLine($"  {item}");
                }
            }        
        }       
    }

    class PortableKey
    {
        public string Name { get; set; }
        public DateTime LastWriteTime { get; set; }
        public long Length { get; set; }

        //分组跟这个相关
        public override bool Equals(object obj)
        {
            PortableKey other = (PortableKey)obj;
            return this.LastWriteTime == other.LastWriteTime &&
                this.Length == other.Length &&
                this.Name == other.Name;
        }

        public override int GetHashCode()
        {
            string str = $"{this.LastWriteTime}{this.Length}{this.Name}";
            return str.GetHashCode();
        }
        public override string ToString()
        {
            return $"{this.Name} {this.Length} {this.LastWriteTime}";
        }
    }
}