Back to index

lightning-sunbird  0.9+nobinonly
nsUrlClassifierUtils.cpp
Go to the documentation of this file.
00001 /* ***** BEGIN LICENSE BLOCK *****
00002  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
00003  *
00004  * The contents of this file are subject to the Mozilla Public License Version
00005  * 1.1 (the "License"); you may not use this file except in compliance with
00006  * the License. You may obtain a copy of the License at
00007  * http://www.mozilla.org/MPL/
00008  *
00009  * Software distributed under the License is distributed on an "AS IS" basis,
00010  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
00011  * for the specific language governing rights and limitations under the
00012  * License.
00013  *
00014  * The Original Code is Url Classifier code
00015  *
00016  * The Initial Developer of the Original Code is
00017  * Google Inc.
00018  * Portions created by the Initial Developer are Copyright (C) 2007
00019  * the Initial Developer. All Rights Reserved.
00020  *
00021  * Contributor(s):
00022  *
00023  * Alternatively, the contents of this file may be used under the terms of
00024  * either the GNU General Public License Version 2 or later (the "GPL"), or
00025  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
00026  * in which case the provisions of the GPL or the LGPL are applicable instead
00027  * of those above. If you wish to allow use of your version of this file only
00028  * under the terms of either the GPL or the LGPL, and not to allow others to
00029  * use your version of this file under the terms of the MPL, indicate your
00030  * decision by deleting the provisions above and replace them with the notice
00031  * and other provisions required by the GPL or the LGPL. If you do not delete
00032  * the provisions above, a recipient may use your version of this file under
00033  * the terms of any one of the MPL, the GPL or the LGPL.
00034  *
00035  * ***** END LICENSE BLOCK ***** */
00036 
00037 #include "nsEscape.h"
00038 #include "nsString.h"
00039 #include "nsUrlClassifierUtils.h"
00040 
00041 static char int_to_hex_digit(PRInt32 i)
00042 {
00043   NS_ASSERTION((i >= 0) && (i <= 15), "int too big in int_to_hex_digit");
00044   return NS_STATIC_CAST(char, ((i < 10) ? (i + '0') : ((i - 10) + 'A')));
00045 }
00046 
00047 
00048 nsUrlClassifierUtils::nsUrlClassifierUtils()
00049 {
00050 }
00051 
00052 NS_IMPL_ISUPPORTS1(nsUrlClassifierUtils, nsIUrlClassifierUtils)
00053 
00054 /* ACString canonicalizeURL (in ACString url); */
00055 NS_IMETHODIMP
00056 nsUrlClassifierUtils::CanonicalizeURL(const nsACString & url, nsACString & _retval)
00057 {
00058   nsCAutoString decodedUrl(url);
00059   nsCAutoString temp;
00060   while (NS_UnescapeURL(decodedUrl.get(), decodedUrl.Length(), 0, temp)) {
00061     decodedUrl.Assign(temp);
00062     temp.Truncate();
00063   }
00064   SpecialEncode(decodedUrl, _retval);
00065   return NS_OK;
00066 }
00067 
00068 // This function will encode all "special" characters in typical url
00069 // encoding, that is %hh where h is a valid hex digit.  See the comment in
00070 // the header file for details.
00071 PRBool
00072 nsUrlClassifierUtils::SpecialEncode(const nsACString & url, nsACString & _retval)
00073 {
00074   PRBool changed = PR_FALSE;
00075   const char* curChar = url.BeginReading();
00076   const char* end = url.EndReading();
00077 
00078   while (curChar != end) {
00079     unsigned char c = NS_STATIC_CAST(unsigned char, *curChar);
00080     if (ShouldURLEscape(c)) {
00081       // We don't want to deal with 0, as it can break certain strings, just
00082       // encode as one.
00083       if (c == 0)
00084         c = 1;
00085 
00086       _retval.Append('%');
00087       _retval.Append(int_to_hex_digit(c / 16));
00088       _retval.Append(int_to_hex_digit(c % 16));
00089 
00090       changed = PR_TRUE;
00091     } else {
00092       _retval.Append(*curChar);
00093     }
00094     curChar++;
00095   }
00096   return changed;
00097 }
00098 
00099 PRBool
00100 nsUrlClassifierUtils::ShouldURLEscape(const unsigned char c) const
00101 {
00102   return c <= 32 || c == '%' || c >=127;
00103 }