| OLD | NEW |
|---|
| (Empty) |
| 1 // Copyright (c) 2012 The Chromium Authors. All rights reserved. | |
| 2 // Use of this source code is governed by a BSD-style license that can be | |
| 3 // found in the LICENSE file. | |
| 4 | |
| 5 // NB: Modelled after Mozilla's code (originally written by Pamela Greene, | |
| 6 // later modified by others), but almost entirely rewritten for Chrome. | |
| 7 // (netwerk/dns/src/nsEffectiveTLDService.cpp) | |
| 8 /* ***** BEGIN LICENSE BLOCK ***** | |
| 9 * Version: MPL 1.1/GPL 2.0/LGPL 2.1 | |
| 10 * | |
| 11 * The contents of this file are subject to the Mozilla Public License Version | |
| 12 * 1.1 (the "License"); you may not use this file except in compliance with | |
| 13 * the License. You may obtain a copy of the License at | |
| 14 * http://www.mozilla.org/MPL/ | |
| 15 * | |
| 16 * Software distributed under the License is distributed on an "AS IS" basis, | |
| 17 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License | |
| 18 * for the specific language governing rights and limitations under the | |
| 19 * License. | |
| 20 * | |
| 21 * The Original Code is Mozilla Effective-TLD Service | |
| 22 * | |
| 23 * The Initial Developer of the Original Code is | |
| 24 * Google Inc. | |
| 25 * Portions created by the Initial Developer are Copyright (C) 2006 | |
| 26 * the Initial Developer. All Rights Reserved. | |
| 27 * | |
| 28 * Contributor(s): | |
| 29 * Pamela Greene <pamg.bugs@gmail.com> (original author) | |
| 30 * Daniel Witte <dwitte@stanford.edu> | |
| 31 * | |
| 32 * Alternatively, the contents of this file may be used under the terms of | |
| 33 * either the GNU General Public License Version 2 or later (the "GPL"), or | |
| 34 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"), | |
| 35 * in which case the provisions of the GPL or the LGPL are applicable instead | |
| 36 * of those above. If you wish to allow use of your version of this file only | |
| 37 * under the terms of either the GPL or the LGPL, and not to allow others to | |
| 38 * use your version of this file under the terms of the MPL, indicate your | |
| 39 * decision by deleting the provisions above and replace them with the notice | |
| 40 * and other provisions required by the GPL or the LGPL. If you do not delete | |
| 41 * the provisions above, a recipient may use your version of this file under | |
| 42 * the terms of any one of the MPL, the GPL or the LGPL. | |
| 43 * | |
| 44 * ***** END LICENSE BLOCK ***** */ | |
| 45 | |
| 46 #include "net/base/registry_controlled_domain.h" | |
| 47 | |
| 48 #include "base/logging.h" | |
| 49 #include "base/string_util.h" | |
| 50 #include "base/utf_string_conversions.h" | |
| 51 #include "googleurl/src/gurl.h" | |
| 52 #include "googleurl/src/url_parse.h" | |
| 53 #include "net/base/net_module.h" | |
| 54 #include "net/base/net_util.h" | |
| 55 | |
| 56 #include "effective_tld_names.cc" | |
| 57 | |
| 58 namespace net { | |
| 59 | |
| 60 namespace { | |
| 61 | |
| 62 const int kExceptionRule = 1; | |
| 63 const int kWildcardRule = 2; | |
| 64 | |
| 65 } // namespace | |
| 66 | |
| 67 RegistryControlledDomainService::FindDomainPtr | |
| 68 RegistryControlledDomainService::find_domain_function_ = | |
| 69 Perfect_Hash::FindDomain; | |
| 70 | |
| 71 // static | |
| 72 std::string RegistryControlledDomainService::GetDomainAndRegistry( | |
| 73 const GURL& gurl) { | |
| 74 const url_parse::Component host = | |
| 75 gurl.parsed_for_possibly_invalid_spec().host; | |
| 76 if ((host.len <= 0) || gurl.HostIsIPAddress()) | |
| 77 return std::string(); | |
| 78 return GetDomainAndRegistryImpl(std::string( | |
| 79 gurl.possibly_invalid_spec().data() + host.begin, host.len)); | |
| 80 } | |
| 81 | |
| 82 // static | |
| 83 std::string RegistryControlledDomainService::GetDomainAndRegistry( | |
| 84 const std::string& host) { | |
| 85 url_canon::CanonHostInfo host_info; | |
| 86 const std::string canon_host(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 | |
| 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 | |
| 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 GetRegistryLengthImpl( | |
| 125 std::string(gurl.possibly_invalid_spec().data() + host.begin, host.len), | |
| 126 allow_unknown_registries); | |
| 127 } | |
| 128 | |
| 129 // static | |
| 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(CanonicalizeHost(host, &host_info)); | |
| 135 if (canon_host.empty()) | |
| 136 return std::string::npos; | |
| 137 if (host_info.IsIPAddress()) | |
| 138 return 0; | |
| 139 return GetRegistryLengthImpl(canon_host, allow_unknown_registries); | |
| 140 } | |
| 141 | |
| 142 // static | |
| 143 void RegistryControlledDomainService::UseFindDomainFunction( | |
| 144 FindDomainPtr function) { | |
| 145 find_domain_function_ = function ? function : Perfect_Hash::FindDomain; | |
| 146 } | |
| 147 | |
| 148 // static | |
| 149 std::string RegistryControlledDomainService::GetDomainAndRegistryImpl( | |
| 150 const std::string& host) { | |
| 151 DCHECK(!host.empty()); | |
| 152 | |
| 153 // Find the length of the registry for this host. | |
| 154 const size_t registry_length = GetRegistryLengthImpl(host, true); | |
| 155 if ((registry_length == std::string::npos) || (registry_length == 0)) | |
| 156 return std::string(); // No registry. | |
| 157 // The "2" in this next line is 1 for the dot, plus a 1-char minimum preceding | |
| 158 // subcomponent length. | |
| 159 DCHECK(host.length() >= 2); | |
| 160 if (registry_length > (host.length() - 2)) { | |
| 161 NOTREACHED() << | |
| 162 "Host does not have at least one subcomponent before registry!"; | |
| 163 return std::string(); | |
| 164 } | |
| 165 | |
| 166 // Move past the dot preceding the registry, and search for the next previous | |
| 167 // dot. Return the host from after that dot, or the whole host when there is | |
| 168 // no dot. | |
| 169 const size_t dot = host.rfind('.', host.length() - registry_length - 2); | |
| 170 if (dot == std::string::npos) | |
| 171 return host; | |
| 172 return host.substr(dot + 1); | |
| 173 } | |
| 174 | |
| 175 size_t RegistryControlledDomainService::GetRegistryLengthImpl( | |
| 176 const std::string& host, | |
| 177 bool allow_unknown_registries) { | |
| 178 DCHECK(!host.empty()); | |
| 179 | |
| 180 // Skip leading dots. | |
| 181 const size_t host_check_begin = host.find_first_not_of('.'); | |
| 182 if (host_check_begin == std::string::npos) | |
| 183 return 0; // Host is only dots. | |
| 184 | |
| 185 // A single trailing dot isn't relevant in this determination, but does need | |
| 186 // to be included in the final returned length. | |
| 187 size_t host_check_len = host.length(); | |
| 188 if (host[host_check_len - 1] == '.') { | |
| 189 --host_check_len; | |
| 190 DCHECK(host_check_len > 0); // If this weren't true, the host would be ".", | |
| 191 // and we'd have already returned above. | |
| 192 if (host[host_check_len - 1] == '.') | |
| 193 return 0; // Multiple trailing dots. | |
| 194 } | |
| 195 | |
| 196 // Walk up the domain tree, most specific to least specific, | |
| 197 // looking for matches at each level. | |
| 198 size_t prev_start = std::string::npos; | |
| 199 size_t curr_start = host_check_begin; | |
| 200 size_t next_dot = host.find('.', curr_start); | |
| 201 if (next_dot >= host_check_len) // Catches std::string::npos as well. | |
| 202 return 0; // This can't have a registry + domain. | |
| 203 while (1) { | |
| 204 const char* domain_str = host.data() + curr_start; | |
| 205 int domain_length = host_check_len - curr_start; | |
| 206 const DomainRule* rule = find_domain_function_(domain_str, domain_length); | |
| 207 | |
| 208 // We need to compare the string after finding a match because the | |
| 209 // no-collisions of perfect hashing only refers to items in the set. Since | |
| 210 // we're searching for arbitrary domains, there could be collisions. | |
| 211 if (rule && | |
| 212 base::strncasecmp(domain_str, rule->name, domain_length) == 0) { | |
| 213 // Exception rules override wildcard rules when the domain is an exact | |
| 214 // match, but wildcards take precedence when there's a subdomain. | |
| 215 if (rule->type == kWildcardRule && (prev_start != std::string::npos)) { | |
| 216 // If prev_start == host_check_begin, then the host is the registry | |
| 217 // itself, so return 0. | |
| 218 return (prev_start == host_check_begin) ? | |
| 219 0 : (host.length() - prev_start); | |
| 220 } | |
| 221 | |
| 222 if (rule->type == kExceptionRule) { | |
| 223 if (next_dot == std::string::npos) { | |
| 224 // If we get here, we had an exception rule with no dots (e.g. | |
| 225 // "!foo"). This would only be valid if we had a corresponding | |
| 226 // wildcard rule, which would have to be "*". But we explicitly | |
| 227 // disallow that case, so this kind of rule is invalid. | |
| 228 NOTREACHED() << "Invalid exception rule"; | |
| 229 return 0; | |
| 230 } | |
| 231 return host.length() - next_dot - 1; | |
| 232 } | |
| 233 | |
| 234 // If curr_start == host_check_begin, then the host is the registry | |
| 235 // itself, so return 0. | |
| 236 return (curr_start == host_check_begin) ? | |
| 237 0 : (host.length() - curr_start); | |
| 238 } | |
| 239 | |
| 240 if (next_dot >= host_check_len) // Catches std::string::npos as well. | |
| 241 break; | |
| 242 | |
| 243 prev_start = curr_start; | |
| 244 curr_start = next_dot + 1; | |
| 245 next_dot = host.find('.', curr_start); | |
| 246 } | |
| 247 | |
| 248 // No rule found in the registry. curr_start now points to the first | |
| 249 // character of the last subcomponent of the host, so if we allow unknown | |
| 250 // registries, return the length of this subcomponent. | |
| 251 return allow_unknown_registries ? (host.length() - curr_start) : 0; | |
| 252 } | |
| 253 | |
| 254 } // namespace net | |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 10796033:
Move files related to registry-controlled domains into a new net/base/registry_controlled_domains/ … (Closed)
Base URL: svn://svn.chromium.org/chrome/trunk/src/