如何：将 LINQ 查询与正则表达式合并在一起
更新：2007 年 11 月
此示例演示如何使用 Regex 类创建正则表达式以便在文本字符串中进行更复杂的匹配。使用 LINQ 查询可以方便地对您要用正则表达式搜索的文件进行准确筛选，以及对结果进行加工。
示例
Class LinqRegExVB
Shared Sub Main()
' Root folder to query, along with all subfolders.
' Modify this path as necessary.
Dim startFolder As String = "C:\program files\Microsoft Visual Studio 9.0\"
' Take a snapshot of the file system.
Dim fileList As IEnumerable(Of System.IO.FileInfo) = GetFiles(startFolder)
' Create a regular expression to find all things "Visual".
Dim searchTerm As System.Text.RegularExpressions.Regex = _
New System.Text.RegularExpressions.Regex("Visual (Basic|C#|C\+\+|J#|SourceSafe|Studio)")
' Search the contents of each .htm file.
' Remove the where clause to find even more matches!
' This query produces a list of files where a match
' was found, and a list of the matches in that file.
' Note: Explicit typing of "Match" in select clause.
' This is required because MatchCollection is not a
' generic IEnumerable collection.
Dim queryMatchingFiles = From afile In fileList _
Where afile.Extension = ".htm" _
Let fileText = System.IO.File.ReadAllText(afile.FullName) _
Let matches = searchTerm.Matches(fileText) _
Where (searchTerm.Matches(fileText).Count > 0) _
Select Name = afile.FullName, _
Matches = From match As System.Text.RegularExpressions.Match In matches _
Select match.Value
' Execute the query.
Console.WriteLine("The term " & searchTerm.ToString() & " was found in:")
For Each fileMatches In queryMatchingFiles
' Trim the path a bit, then write
' the file name in which a match was found.
Dim s = fileMatches.Name.Substring(startFolder.Length - 1)
Console.WriteLine(s)
' For this file, write out all the matching strings
For Each match In fileMatches.Matches
Console.WriteLine(" " + match)
Next
Next
' Keep the console window open in debug mode
Console.WriteLine("Press any key to exit")
Console.ReadKey()
End Sub
' Function to retrieve a list of files. Note that this is a copy
' of the file information.
Shared Function GetFiles(ByVal root As String) As 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 Class
class QueryWithRegEx
{
public static void Main()
{
// Modify this path as necessary.
string startFolder = @"c:\program files\Microsoft Visual Studio 9.0\";
// Take a snapshot of the file system.
IEnumerable<System.IO.FileInfo> fileList = GetFiles(startFolder);
// Create the regular expression to find all things "Visual".
System.Text.RegularExpressions.Regex searchTerm =
new System.Text.RegularExpressions.Regex(@"Visual (Basic|C#|C\+\+|J#|SourceSafe|Studio)");
// Search the contents of each .htm file.
// Remove the where clause to find even more matches!
// This query produces a list of files where a match
// was found, and a list of the matches in that file.
// Note: Explicit typing of "Match" in select clause.
// This is required because MatchCollection is not a
// generic IEnumerable collection.
var queryMatchingFiles =
from file in fileList
where file.Extension == ".htm"
let fileText = System.IO.File.ReadAllText(file.FullName)
let matches = searchTerm.Matches(fileText)
where searchTerm.Matches(fileText).Count > 0
select new
{
name = file.FullName,
matches = from System.Text.RegularExpressions.Match match in matches
select match.Value
};
// Execute the query.
Console.WriteLine("The term \"{0}\" was found in:", searchTerm.ToString());
foreach (var v in queryMatchingFiles)
{
// Trim the path a bit, then write
// the file name in which a match was found.
string s = v.name.Substring(startFolder.Length - 1);
Console.WriteLine(s);
// For this file, write out all the matching strings
foreach (var v2 in v.matches)
{
Console.WriteLine(" " + v2);
}
}
// Keep the console window open in debug mode
Console.WriteLine("Press any key to exit");
Console.ReadKey();
}
// 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;
}
}
请注意，您还可以查询由 RegEx 搜索返回的 MatchCollection 对象。在此示例中，结果中仅生成每个匹配项的值。但也可使用 LINQ 对该集合执行各种筛选、排序和分组操作。由于 MatchCollection 是非泛型 IEnumerable 集合，因此必须显式声明查询中的范围变量的类型。
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 的引用和针对 System.Linq 命名空间的 using 指令 (C#) 或 Imports 语句 (Visual Basic)。在 C# 项目中，添加针对 System.IO 命名空间的 using 指令。
将这段代码复制到项目中。
按 F5 编译并运行程序。
按任意键退出控制台窗口。