LINQ和文件目录

记录的学习

 

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}";
        }
    }
}