~grubng-dev/grubng/tools-urlsdb

//  

//  Copyright (C) 2009,2010 Bartek thindil Jasicki

// 

//  This file is part of Grubng

// 

//  Grubng is free software: you can redistribute it and/or modify

//  it under the terms of the GNU General Public License as published by

//  the Free Software Foundation, either version 3 of the License, or

//  (at your option) any later version.

// 

//  This program is distributed in the hope that it will be useful,

//  but WITHOUT ANY WARRANTY; without even the implied warranty of

//  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

//  GNU General Public License for more details.

// 

//  You should have received a copy of the GNU General Public License

//  along with this program.  If not, see <http://www.gnu.org/licenses/>.

// 

using System;

using System.Text;

using System.Text.RegularExpressions;

namespace urlsdb

{

	/// <summary>

	/// Class provide functions for manipulate URL's

	/// </summary>

	internal sealed class ParseURLs

	{

		System.Security.Cryptography.SHA1Managed SHhash;

		StringBuilder key;

		byte[] HashValue;

		byte[] PureHash;

		/// <summary>

		/// Standard class constructor.

		/// </summary>

		public ParseURLs()

		{

			this.SHhash = new System.Security.Cryptography.SHA1Managed();

			this.key = new StringBuilder();

		}

		/// <summary>

		/// Function manipulate URL - check it correctness, drop to lower case host.

		/// </summary>

		/// <param name="url">

		/// A <see cref="System.String"/> URL to parse.

		/// </param>

		/// <returns>

		/// A <see cref="System.String"/> parsed URL or String.Empty if URL is invalid.

		/// </returns>

		public static string ParseURL(string url)

		{

			//Remove http(s):// from URL

			int index = url.IndexOf("//");

			if (index > 0)

			{

				url = url.Remove(0, (index + 2));

			}

			//Check correctness of URL

			if (!Regex.IsMatch(url, @"^[a-z0-9]+([a-z0-9\=\-\.\?\,\'\/\\\+&%\$#_~]*)?$", RegexOptions.IgnoreCase))

			{

				return String.Empty;

			}

			//Conver to lower case host name

			index = url.IndexOf('/');

			string host, path;

			if (index > 0)

			{

				host = url.Substring(0, index);

				path = url.Substring(index);

			}

			else

			{

				host = url;

				path = "/";

			}

			host = host.ToLower();

			//Validate hostname

			if (!Regex.IsMatch(host, @"^[a-z0-9]+([a-z0-9\-\.]*)?$", RegexOptions.IgnoreCase))

			{

				return String.Empty;

			}

			//Remove PHPSESID from path

			if (path.Length > 1)

			{

				path = Regex.Replace(path, @"(&|\?|&)*PHPSESSID=\w+", String.Empty, RegexOptions.IgnoreCase);

			}

			url = host + path;

			url = System.Web.HttpUtility.UrlEncode(host + path);

			url = url.Replace("%2f", "/");

			url = url.Replace("%2c", ",");

			url = url.Replace("%3d", "=");

			url = url.Replace("%3f", "?");

			url = url.Replace("%26", "&");

			url = url.Replace("%3b", ";");

			url = url.Replace("%3a", ":");

			url = url.Replace("%40", "@");

			url = url.Replace("%23", "#");

			url = url.Replace("%7e", "~");

			url = url.Replace("%252f", "/");

			return url;

		}

		/// <summary>

		/// Function return SHA1 hash of URL

		/// </summary>

		/// <param name="url">

		/// A <see cref="System.String"/> URL to hash

		/// </param>

		/// <returns>

		/// A <see cref="System.String"/> SHA1 hash of URL

		/// </returns>

		public string GetHash(string url)

		{

			if (this.key.Length > 0)

			{

				this.key.Remove(0, key.Length);

			}

			this.PureHash = Encoding.UTF8.GetBytes(url);

			this.HashValue = SHhash.ComputeHash(this.PureHash);

			foreach(byte b in this.HashValue) 

			{

				this.key.Append(String.Format("{0:x2}", b));

			}

			return this.key.ToString();

		}

	}

}