1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
/* ***** BEGIN LICENSE BLOCK *****
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
*
* The contents of this file are subject to the Mozilla Public License Version
* 1.1 (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
* http://www.mozilla.org/MPL/
*
* Software distributed under the License is distributed on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
* for the specific language governing rights and limitations under the
* License.
*
* The Original Code is Url Classifier code
*
* The Initial Developer of the Original Code is
* Google Inc.
* Portions created by the Initial Developer are Copyright (C) 2006
* the Initial Developer. All Rights Reserved.
*
* Contributor(s):
* Tony Chang <tony@ponderer.org>
*
* Alternatively, the contents of this file may be used under the terms of
* either the GNU General Public License Version 2 or later (the "GPL"), or
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
* in which case the provisions of the GPL or the LGPL are applicable instead
* of those above. If you wish to allow use of your version of this file only
* under the terms of either the GPL or the LGPL, and not to allow others to
* use your version of this file under the terms of the MPL, indicate your
* decision by deleting the provisions above and replace them with the notice
* and other provisions required by the GPL or the LGPL. If you do not delete
* the provisions above, a recipient may use your version of this file under
* the terms of any one of the MPL, the GPL or the LGPL.
*
* ***** END LICENSE BLOCK ***** */
// XXX: This should all be moved into the dbservice class so it happens
// in the background thread.
/**
* Abstract base class for a lookup table.
* @construction
*/
function UrlClassifierTable() {
this.debugZone = "urlclassifier-table";
this.name = '';
this.needsUpdate = false;
this.enchashDecrypter_ = new PROT_EnchashDecrypter();
}
UrlClassifierTable.prototype.QueryInterface = function(iid) {
if (iid.equals(Components.interfaces.nsISupports) ||
iid.equals(Components.interfaces.nsIUrlClassifierTable))
return this;
Components.returnCode = Components.results.NS_ERROR_NO_INTERFACE;
return null;
}
/**
* Subclasses need to implment this method.
*/
UrlClassifierTable.prototype.exists = function(url, callback) {
throw Components.results.NS_ERROR_NOT_IMPLEMENTED;
}
/////////////////////////////////////////////////////////////////////
// Url table implementation
function UrlClassifierTableUrl() {
UrlClassifierTable.call(this);
}
UrlClassifierTableUrl.inherits(UrlClassifierTable);
/**
* Look up a URL in a URL table
*/
UrlClassifierTableUrl.prototype.exists = function(url, callback) {
var urlUtils = Cc["@mozilla.org/url-classifier/utils;1"]
.getService(Ci.nsIUrlClassifierUtils);
// We plan on having the server collapse multiple slashes in the path.
// Until this happens, we check both the raw url and the url with multiple
// slashes removed.
var urls = [
this.enchashDecrypter_.getCanonicalUrl(url),
this.enchashDecrypter_.getCanonicalUrl(url, true) /* collapse slashes */
];
G_Debug(this, "Looking up: " + url + " (" + urls + ")");
(new ExistsMultiQuerier(urls,
this.name,
callback)).run();
}
/////////////////////////////////////////////////////////////////////
// Domain table implementation
function UrlClassifierTableDomain() {
UrlClassifierTable.call(this);
this.debugZone = "urlclassifier-table-domain";
this.ioService_ = Cc["@mozilla.org/network/io-service;1"]
.getService(Ci.nsIIOService);
}
UrlClassifierTableDomain.inherits(UrlClassifierTable);
/**
* Look up a URL in a domain table
* We also try to lookup domain + first path component (e.g.,
* www.mozilla.org/products).
*
* @returns Boolean true if the url domain is in the table
*/
UrlClassifierTableDomain.prototype.exists = function(url, callback) {
var canonicalized = this.enchashDecrypter_.getCanonicalUrl(url);
var urlObj = this.ioService_.newURI(canonicalized, null, null);
var host = '';
try {
host = urlObj.host;
} catch (e) { }
var hostComponents = host.split(".");
// Try to get the path of the URL. Pseudo urls (like wyciwyg:) throw
// errors when trying to convert to an nsIURL so we wrap in a try/catch
// block.
var path = ""
try {
urlObj.QueryInterface(Ci.nsIURL);
path = urlObj.filePath;
} catch (e) { }
var pathComponents = path.split("/");
// We don't have a good way map from hosts to domains, so we instead try
// each possibility. Could probably optimize to start at the second dot?
var possible = [];
for (var i = 0; i < hostComponents.length - 1; i++) {
host = hostComponents.slice(i).join(".");
possible.push(host);
// The path starts with a "/", so we are interested in the second path
// component if it is available
if (pathComponents.length >= 2 && pathComponents[1].length > 0) {
host = host + "/" + pathComponents[1];
possible.push(host);
}
}
// Run the possible domains against the db.
(new ExistsMultiQuerier(possible, this.name, callback)).run();
}
/////////////////////////////////////////////////////////////////////
// Enchash table implementation
function UrlClassifierTableEnchash() {
UrlClassifierTable.call(this);
this.debugZone = "urlclassifier-table-enchash";
}
UrlClassifierTableEnchash.inherits(UrlClassifierTable);
/**
* Look up a URL in an enchashDB. We try all sub domains (up to MAX_DOTS).
*/
UrlClassifierTableEnchash.prototype.exists = function(url, callback) {
url = this.enchashDecrypter_.getCanonicalUrl(url);
var host = this.enchashDecrypter_.getCanonicalHost(url,
PROT_EnchashDecrypter.MAX_DOTS);
var possible = [];
for (var i = 0; i < PROT_EnchashDecrypter.MAX_DOTS + 1; i++) {
possible.push(host);
var index = host.indexOf(".");
if (index == -1)
break;
host = host.substring(index + 1);
}
// Run the possible domains against the db.
(new EnchashMultiQuerier(possible, this.name, callback, url)).run();
}
|
