1 //* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
2 /* ***** BEGIN LICENSE BLOCK *****
3 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
4 *
5 * The contents of this file are subject to the Mozilla Public License Version
6 * 1.1 (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 * http://www.mozilla.org/MPL/
9 *
10 * Software distributed under the License is distributed on an "AS IS" basis,
11 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
12 * for the specific language governing rights and limitations under the
13 * License.
14 *
15 * The Original Code is Mozilla Effective-TLD Service
16 *
17 * The Initial Developer of the Original Code is
18 * Google Inc.
19 * Portions created by the Initial Developer are Copyright (C) 2006
20 * the Initial Developer. All Rights Reserved.
21 *
22 * Contributor(s):
23 * Pamela Greene <pamg.bugs@gmail.com> (original author)
24 * Daniel Witte <dwitte@stanford.edu>
25 *
26 * Alternatively, the contents of this file may be used under the terms of
27 * either the GNU General Public License Version 2 or later (the "GPL"), or
28 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
29 * in which case the provisions of the GPL or the LGPL are applicable instead
30 * of those above. If you wish to allow use of your version of this file only
31 * under the terms of either the GPL or the LGPL, and not to allow others to
32 * use your version of this file under the terms of the MPL, indicate your
33 * decision by deleting the provisions above and replace them with the notice
34 * and other provisions required by the GPL or the LGPL. If you do not delete
35 * the provisions above, a recipient may use your version of this file under
36 * the terms of any one of the MPL, the GPL or the LGPL.
37 *
38 * ***** END LICENSE BLOCK ***** */
39
40 #include "net/base/registry_controlled_domain.h"
41
42 #include "base/logging.h"
43 #include "base/singleton.h"
44 #include "base/string_util.h"
45 #include "googleurl/src/gurl.h"
46 #include "googleurl/src/url_parse.h"
47 #include "net/base/net_module.h"
48 #include "net/base/net_util.h"
49
50 #include "effective_tld_names.cc"
51
52 namespace net {
53
54 static const int kExceptionRule = 1;
55 static const int kWildcardRule = 2;
56
RegistryControlledDomainService()57 RegistryControlledDomainService::RegistryControlledDomainService()
58 : find_domain_function_(Perfect_Hash::FindDomain) {
59 }
60
61 // static
GetDomainAndRegistry(const GURL & gurl)62 std::string RegistryControlledDomainService::GetDomainAndRegistry(
63 const GURL& gurl) {
64 const url_parse::Component host =
65 gurl.parsed_for_possibly_invalid_spec().host;
66 if ((host.len <= 0) || gurl.HostIsIPAddress())
67 return std::string();
68 return GetDomainAndRegistryImpl(std::string(
69 gurl.possibly_invalid_spec().data() + host.begin, host.len));
70 }
71
72 // static
GetDomainAndRegistry(const std::string & host)73 std::string RegistryControlledDomainService::GetDomainAndRegistry(
74 const std::string& host) {
75 url_canon::CanonHostInfo host_info;
76 const std::string canon_host(net::CanonicalizeHost(host, &host_info));
77 if (canon_host.empty() || host_info.IsIPAddress())
78 return std::string();
79 return GetDomainAndRegistryImpl(canon_host);
80 }
81
82 // static
GetDomainAndRegistry(const std::wstring & host)83 std::string RegistryControlledDomainService::GetDomainAndRegistry(
84 const std::wstring& host) {
85 url_canon::CanonHostInfo host_info;
86 const std::string canon_host(net::CanonicalizeHost(host, &host_info));
87 if (canon_host.empty() || host_info.IsIPAddress())
88 return std::string();
89 return GetDomainAndRegistryImpl(canon_host);
90 }
91
92 // static
SameDomainOrHost(const GURL & gurl1,const GURL & gurl2)93 bool RegistryControlledDomainService::SameDomainOrHost(const GURL& gurl1,
94 const GURL& gurl2) {
95 // See if both URLs have a known domain + registry, and those values are the
96 // same.
97 const std::string domain1(GetDomainAndRegistry(gurl1));
98 const std::string domain2(GetDomainAndRegistry(gurl2));
99 if (!domain1.empty() || !domain2.empty())
100 return domain1 == domain2;
101
102 // No domains. See if the hosts are identical.
103 const url_parse::Component host1 =
104 gurl1.parsed_for_possibly_invalid_spec().host;
105 const url_parse::Component host2 =
106 gurl2.parsed_for_possibly_invalid_spec().host;
107 if ((host1.len <= 0) || (host1.len != host2.len))
108 return false;
109 return !strncmp(gurl1.possibly_invalid_spec().data() + host1.begin,
110 gurl2.possibly_invalid_spec().data() + host2.begin,
111 host1.len);
112 }
113
114 // static
GetRegistryLength(const GURL & gurl,bool allow_unknown_registries)115 size_t RegistryControlledDomainService::GetRegistryLength(
116 const GURL& gurl,
117 bool allow_unknown_registries) {
118 const url_parse::Component host =
119 gurl.parsed_for_possibly_invalid_spec().host;
120 if (host.len <= 0)
121 return std::string::npos;
122 if (gurl.HostIsIPAddress())
123 return 0;
124 return GetInstance()->GetRegistryLengthImpl(
125 std::string(gurl.possibly_invalid_spec().data() + host.begin, host.len),
126 allow_unknown_registries);
127 }
128
129 // static
GetRegistryLength(const std::string & host,bool allow_unknown_registries)130 size_t RegistryControlledDomainService::GetRegistryLength(
131 const std::string& host,
132 bool allow_unknown_registries) {
133 url_canon::CanonHostInfo host_info;
134 const std::string canon_host(net::CanonicalizeHost(host, &host_info));
135 if (canon_host.empty())
136 return std::string::npos;
137 if (host_info.IsIPAddress())
138 return 0;
139 return GetInstance()->GetRegistryLengthImpl(canon_host,
140 allow_unknown_registries);
141 }
142
143 // static
GetRegistryLength(const std::wstring & host,bool allow_unknown_registries)144 size_t RegistryControlledDomainService::GetRegistryLength(
145 const std::wstring& host,
146 bool allow_unknown_registries) {
147 url_canon::CanonHostInfo host_info;
148 const std::string canon_host(net::CanonicalizeHost(host, &host_info));
149 if (canon_host.empty())
150 return std::string::npos;
151 if (host_info.IsIPAddress())
152 return 0;
153 return GetInstance()->GetRegistryLengthImpl(canon_host,
154 allow_unknown_registries);
155 }
156
157 // static
GetDomainAndRegistryImpl(const std::string & host)158 std::string RegistryControlledDomainService::GetDomainAndRegistryImpl(
159 const std::string& host) {
160 DCHECK(!host.empty());
161
162 // Find the length of the registry for this host.
163 const size_t registry_length =
164 GetInstance()->GetRegistryLengthImpl(host, true);
165 if ((registry_length == std::string::npos) || (registry_length == 0))
166 return std::string(); // No registry.
167 // The "2" in this next line is 1 for the dot, plus a 1-char minimum preceding
168 // subcomponent length.
169 DCHECK(host.length() >= 2);
170 if (registry_length > (host.length() - 2)) {
171 NOTREACHED() <<
172 "Host does not have at least one subcomponent before registry!";
173 return std::string();
174 }
175
176 // Move past the dot preceding the registry, and search for the next previous
177 // dot. Return the host from after that dot, or the whole host when there is
178 // no dot.
179 const size_t dot = host.rfind('.', host.length() - registry_length - 2);
180 if (dot == std::string::npos)
181 return host;
182 return host.substr(dot + 1);
183 }
184
GetRegistryLengthImpl(const std::string & host,bool allow_unknown_registries)185 size_t RegistryControlledDomainService::GetRegistryLengthImpl(
186 const std::string& host,
187 bool allow_unknown_registries) {
188 DCHECK(!host.empty());
189
190 // Skip leading dots.
191 const size_t host_check_begin = host.find_first_not_of('.');
192 if (host_check_begin == std::string::npos)
193 return 0; // Host is only dots.
194
195 // A single trailing dot isn't relevant in this determination, but does need
196 // to be included in the final returned length.
197 size_t host_check_len = host.length();
198 if (host[host_check_len - 1] == '.') {
199 --host_check_len;
200 DCHECK(host_check_len > 0); // If this weren't true, the host would be ".",
201 // and we'd have already returned above.
202 if (host[host_check_len - 1] == '.')
203 return 0; // Multiple trailing dots.
204 }
205
206 // Walk up the domain tree, most specific to least specific,
207 // looking for matches at each level.
208 size_t prev_start = std::string::npos;
209 size_t curr_start = host_check_begin;
210 size_t next_dot = host.find('.', curr_start);
211 if (next_dot >= host_check_len) // Catches std::string::npos as well.
212 return 0; // This can't have a registry + domain.
213 while (1) {
214 const char* domain_str = host.data() + curr_start;
215 int domain_length = host_check_len - curr_start;
216 const DomainRule* rule = find_domain_function_(domain_str, domain_length);
217
218 // We need to compare the string after finding a match because the
219 // no-collisions of perfect hashing only refers to items in the set. Since
220 // we're searching for arbitrary domains, there could be collisions.
221 if (rule &&
222 base::strncasecmp(domain_str, rule->name, domain_length) == 0) {
223 // Exception rules override wildcard rules when the domain is an exact
224 // match, but wildcards take precedence when there's a subdomain.
225 if (rule->type == kWildcardRule && (prev_start != std::string::npos)) {
226 // If prev_start == host_check_begin, then the host is the registry
227 // itself, so return 0.
228 return (prev_start == host_check_begin) ?
229 0 : (host.length() - prev_start);
230 }
231
232 if (rule->type == kExceptionRule) {
233 if (next_dot == std::string::npos) {
234 // If we get here, we had an exception rule with no dots (e.g.
235 // "!foo"). This would only be valid if we had a corresponding
236 // wildcard rule, which would have to be "*". But we explicitly
237 // disallow that case, so this kind of rule is invalid.
238 NOTREACHED() << "Invalid exception rule";
239 return 0;
240 }
241 return host.length() - next_dot - 1;
242 }
243
244 // If curr_start == host_check_begin, then the host is the registry
245 // itself, so return 0.
246 return (curr_start == host_check_begin) ?
247 0 : (host.length() - curr_start);
248 }
249
250 if (next_dot >= host_check_len) // Catches std::string::npos as well.
251 break;
252
253 prev_start = curr_start;
254 curr_start = next_dot + 1;
255 next_dot = host.find('.', curr_start);
256 }
257
258 // No rule found in the registry. curr_start now points to the first
259 // character of the last subcomponent of the host, so if we allow unknown
260 // registries, return the length of this subcomponent.
261 return allow_unknown_registries ? (host.length() - curr_start) : 0;
262 }
263
264 static RegistryControlledDomainService* test_instance_;
265
266 // static
SetInstance(RegistryControlledDomainService * instance)267 RegistryControlledDomainService* RegistryControlledDomainService::SetInstance(
268 RegistryControlledDomainService* instance) {
269 RegistryControlledDomainService* old_instance = test_instance_;
270 test_instance_ = instance;
271 return old_instance;
272 }
273
274 // static
GetInstance()275 RegistryControlledDomainService* RegistryControlledDomainService::GetInstance()
276 {
277 if (test_instance_)
278 return test_instance_;
279
280 return Singleton<RegistryControlledDomainService>::get();
281 }
282
283 // static
UseFindDomainFunction(FindDomainPtr function)284 void RegistryControlledDomainService::UseFindDomainFunction(
285 FindDomainPtr function) {
286 RegistryControlledDomainService* instance = GetInstance();
287 instance->find_domain_function_ = function;
288 }
289
290 } // namespace net
291