如何:查询目录树中的一个或多个最大的文件 (LINQ)
更新:2007 年 11 月
此示例演示与文件大小(以字节为单位)相关的五种查询:
如何检索最大文件的大小(以字节为单位)。
如何检索最小文件的大小(以字节为单位)。
如何从指定的根文件夹下的一个或多个文件夹检索 FileInfo 对象最大或最小文件。
如何检索一个序列,如 10 个最大文件。
如何按文件大小(以字节为单位)将文件分组,并忽略小于指定大小的文件。
示例
下面的示例包含五种不同的查询,这些查询演示如何根据文件大小(以字节为单位)查询和分组文件。可以轻松地修改这些示例,以使查询基于 FileInfo 对象的某个其他属性。
Module QueryBySize
Sub Main()
' Change the drive\path if necessary
Dim root As String = "C:\Program Files\Microsoft Visual Studio 9.0"
Dim fileList = GetFiles(root)
' Return the size of the largest file
Dim maxSize = Aggregate aFile In fileList Into Max(GetFileLength(aFile))
'Dim maxSize = fileLengths.Max
Console.WriteLine("The length of the largest file under {0} is {1}", _
root, maxSize)
' Return the FileInfo object of the largest file
' by sorting and selecting from the beginning of the list
Dim filesByLengDesc = From file In fileList _
Let filelength = GetFileLength(file) _
Where filelength > 0 _
Order By filelength Descending _
Select file
Dim longestFile = filesByLengDesc.First
Console.WriteLine("The largest file under {0} is {1} with a length of {2} bytes", _
root, longestFile.FullName, longestFile.Length)
Dim smallestFile = filesByLengDesc.Last
Console.WriteLine("The smallest file under {0} is {1} with a length of {2} bytes", _
root, smallestFile.FullName, smallestFile.Length)
' Return the FileInfos for the 10 largest files
' Based on a previous query, but nothing is executed
' until the For Each statement below.
Dim tenLargest = From file In filesByLengDesc Take 10
Console.WriteLine("The 10 largest files under {0} are:", root)
For Each fi As System.IO.FileInfo In tenLargest
Console.WriteLine("{0}: {1} bytes", fi.FullName, fi.Length)
Next
' Group files according to their size,
' leaving out the ones under 200K
Dim sizeGroups = From file As System.IO.FileInfo In GetFiles(root) _
Where file.Length > 0 _
Let groupLength = file.Length / 100000 _
Group file By groupLength Into fileGroup = Group _
Where groupLength >= 2 _
Order By groupLength Descending
For Each group In sizeGroups
Console.WriteLine(group.groupLength + "00000")
For Each item As System.IO.FileInfo In group.fileGroup
Console.WriteLine(" {0}: {1}", item.Name, item.Length)
Next
Next
' Keep the console window open in debug mode
Console.WriteLine("Press any key to exit.")
Console.ReadKey()
End Sub
' This method is used to catch the possible exception
' that can be raised when accessing the FileInfo.Length property.
' In this particular case, it is safe to ignore the exception.
Function GetFileLength(ByVal fi As System.IO.FileInfo) As Long
Dim retval As Long
Try
retval = fi.Length
Catch ex As FileNotFoundException
' If a file is no longer present,
' just return zero bytes.
retval = 0
End Try
Return retval
End Function
' Function to retrieve a list of files. Note that this is a copy
' of the file information.
Function GetFiles(ByVal root As String) As System.Collections.Generic.IEnumerable(Of System.IO.FileInfo)
Return From file In My.Computer.FileSystem.GetFiles _
(root, FileIO.SearchOption.SearchAllSubDirectories, "*.*") _
Select New System.IO.FileInfo(file)
End Function
End Module
class QueryBySize
{
static void Main(string[] args)
{
QueryFilesBySize();
Console.WriteLine("Press any key to exit");
Console.ReadKey();
}
private static void QueryFilesBySize()
{
string startFolder = @"c:\program files\Microsoft Visual Studio 9.0\";
// Take a snapshot of the file system.
// fileList is an IEnumerable<System.IO.FileInfo>
var fileList = GetFiles(startFolder);
//Return the size of the largest file
long maxSize =
(from file in fileList
let len = GetFileLength(file)
select len)
.Max();
Console.WriteLine("The length of the largest file under {0} is {1}",
startFolder, maxSize);
// Return the FileInfo object for the largest file
// by sorting and selecting from beginning of list
System.IO.FileInfo longestFile =
(from file in fileList
let len = GetFileLength(file)
where len > 0
orderby len descending
select file)
.First();
Console.WriteLine("The largest file under {0} is {1} with a length of {2} bytes",
startFolder, longestFile.FullName, longestFile.Length);
//Return the FileInfo of the smallest file
System.IO.FileInfo smallestFile =
(from file in fileList
let len = GetFileLength(file)
where len > 0
orderby len ascending
select file).First();
Console.WriteLine("The smallest file under {0} is {1} with a length of {2} bytes",
startFolder, smallestFile.FullName, smallestFile.Length);
//Return the FileInfos for the 10 largest files
// queryTenLargest is an IEnumerable<System.IO.FileInfo>
var queryTenLargest =
(from file in fileList
let len = GetFileLength(file)
orderby len descending
select file).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);
}
// Group the files according to their size, leaving out
// files that are less than 200000 bytes.
var querySizeGroups =
from file in fileList
let len = GetFileLength(file)
where len > 0
group file by (len / 100000) into fileGroup
where fileGroup.Key >= 2
orderby fileGroup.Key descending
select fileGroup;
foreach (var filegroup in querySizeGroups)
{
Console.WriteLine(filegroup.Key.ToString() + "00000");
foreach (var item in filegroup)
{
Console.WriteLine("\t{0}: {1}", item.Name, item.Length);
}
}
// Keep the console window open in debug mode.
Console.WriteLine("Press any key to exit.");
Console.ReadKey();
}
// This method is used to swallow the possible exception
// that can be raised when accessing the FileInfo.Length property.
// In this particular case, it is safe to swallow the exception.
static long GetFileLength(System.IO.FileInfo fi)
{
long retval;
try
{
retval = fi.Length;
}
catch (System.IO.FileNotFoundException)
{
// If a file is no longer present,
// just add zero bytes to the total.
retval = 0;
}
return retval;
}
// This method assumes that the application has discovery
// permissions for all folders under the specified path.
static IEnumerable<System.IO.FileInfo> GetFiles(string path)
{
if (!System.IO.Directory.Exists(path))
throw new System.IO.DirectoryNotFoundException();
string[] fileNames = null;
List<System.IO.FileInfo> files = new List<System.IO.FileInfo>();
fileNames = System.IO.Directory.GetFiles(path, "*.*", System.IO.SearchOption.AllDirectories);
foreach (string name in fileNames)
{
files.Add(new System.IO.FileInfo(name));
}
return files;
}
}
若要返回一个或多个完整的 FileInfo 对象,查询必须首先检查数据源中的每个对象,然后按这些对象的 Length 属性的值排序它们。然后查询可以返回具有最大长度的单个对象或序列。使用 First 可返回列表中的第一个元素。使用 Take<TSource> 可返回前 n 个元素。指定降序排序顺序可将最小的元素放在列表的开头。
查询调用单独的方法获取文件大小(以字节为单位),以便消除在以下情况下可能引发的异常:自调用 GetFiles 创建 FileInfo 对象起的时间段内在另一个线程上删除了文件。虽然已创建了 FileInfo 对象,但仍会发生异常,因为 FileInfo 对象将尝试使用第一次访问其 Length 属性时的最新大小(以字节为单位)刷新此属性。通过将此操作放在查询外的 try-catch 块中,我们遵循了避免在查询中执行可能引起副作用的操作的规则。通常,在抑制异常时必须格外谨慎,确保没有将应用程序置于未知状态。
编译代码
创建一个面向 .NET Framework 3.5 版的 Visual Studio 项目。默认情况下,该项目具有对 System.Core.dll 的引用以及针对 System.Linq 命名空间的 using 指令 (C#) 或 Imports 语句 (Visual Basic)。
将此代码复制到您的项目。
按 F5 编译并运行程序。
按任意键退出控制台窗口。
可靠编程
若要对多种类型的文档和文件的内容执行大量查询操作,请考虑使用 Windows Desktop Search(Windows 桌面搜索)引擎。