Query the Contents of Files

This example shows how to query over all the files in a specified directory tree, open each file, and inspect its contents. This type of technique could be used to create indexes or reverse indexes of the contents of a directory tree.

A simple string search is performed in this example.

 
class QueryContents
{
    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.
        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 fileList = dir.GetFiles("*.*", System.IO.SearchOption.AllDirectories);

        string searchTerm = @"Visual Studio";

        // Search the contents of each file.
        // A regular expression created with the RegEx class
        // could be used instead of the Contains method.
        // queryMatchingFiles is an IEnumerable.
        var queryMatchingFiles =
            from file in fileList
            where file.Extension == ".htm"
            let fileText = GetFileText(file.FullName)
            where fileText.Contains(searchTerm)
            select file.FullName;

        // Execute the query.
        Console.WriteLine("The term \"{0}\" was found in:", searchTerm);
        foreach (string filename in queryMatchingFiles)
        {
            Console.WriteLine(filename);
        }

        // Keep the console window open in debug mode.
        Console.WriteLine("Press any key to exit");
        Console.ReadKey();
    }

    // Read the contents of the file.
    static string GetFileText(string name)
    {
        string fileContents = String.Empty;

        // If the file has been deleted since we took 
        // the snapshot, ignore it and return the empty string.
        if (System.IO.File.Exists(name))
        {
            fileContents = System.IO.File.ReadAllText(name);
        }
        return fileContents;
    }
}