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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545
|
// Copyright 2013 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "net/base/url_util.h"
#include "build/build_config.h"
#if BUILDFLAG(IS_POSIX)
#include <netinet/in.h>
#elif BUILDFLAG(IS_WIN)
#include <ws2tcpip.h>
#endif
#include "base/check_op.h"
#include "base/containers/fixed_flat_set.h"
#include "base/strings/escape.h"
#include "base/strings/strcat.h"
#include "base/strings/string_piece.h"
#include "base/strings/string_util.h"
#include "base/strings/stringprintf.h"
#include "base/strings/utf_string_conversions.h"
#include "net/base/ip_address.h"
#include "net/base/registry_controlled_domains/registry_controlled_domain.h"
#include "third_party/abseil-cpp/absl/types/optional.h"
#include "url/gurl.h"
#include "url/scheme_host_port.h"
#include "url/url_canon.h"
#include "url/url_canon_internal.h"
#include "url/url_canon_ip.h"
#include "url/url_constants.h"
#include "url/url_util.h"
namespace net {
namespace {
bool IsHostCharAlphanumeric(char c) {
// We can just check lowercase because uppercase characters have already been
// normalized.
return ((c >= 'a') && (c <= 'z')) || ((c >= '0') && (c <= '9'));
}
bool IsNormalizedLocalhostTLD(base::StringPiece host) {
return base::EndsWith(host, ".localhost",
base::CompareCase::INSENSITIVE_ASCII);
}
// Helper function used by GetIdentityFromURL. If |escaped_text| can be "safely
// unescaped" to a valid UTF-8 string, return that string, as UTF-16. Otherwise,
// convert it as-is to UTF-16. "Safely unescaped" is defined as having no
// escaped character between '0x00' and '0x1F', inclusive.
std::u16string UnescapeIdentityString(base::StringPiece escaped_text) {
std::string unescaped_text;
if (base::UnescapeBinaryURLComponentSafe(
escaped_text, false /* fail_on_path_separators */, &unescaped_text)) {
std::u16string result;
if (base::UTF8ToUTF16(unescaped_text.data(), unescaped_text.length(),
&result)) {
return result;
}
}
return base::UTF8ToUTF16(escaped_text);
}
} // namespace
GURL AppendQueryParameter(const GURL& url,
base::StringPiece name,
base::StringPiece value) {
std::string query(url.query());
if (!query.empty())
query += "&";
query += (base::EscapeQueryParamValue(name, true) + "=" +
base::EscapeQueryParamValue(value, true));
GURL::Replacements replacements;
replacements.SetQueryStr(query);
return url.ReplaceComponents(replacements);
}
GURL AppendOrReplaceQueryParameter(const GURL& url,
base::StringPiece name,
absl::optional<base::StringPiece> value) {
bool replaced = false;
std::string param_name = base::EscapeQueryParamValue(name, true);
bool should_keep_param = value.has_value();
std::string param_value;
if (should_keep_param)
param_value = base::EscapeQueryParamValue(value.value(), true);
const base::StringPiece input = url.query_piece();
url::Component cursor(0, input.size());
std::string output;
url::Component key_range, value_range;
while (url::ExtractQueryKeyValue(input.data(), &cursor, &key_range,
&value_range)) {
const base::StringPiece key = input.substr(key_range.begin, key_range.len);
std::string key_value_pair;
// Check |replaced| as only the first pair should be replaced.
if (!replaced && key == param_name) {
replaced = true;
if (!should_keep_param)
continue;
key_value_pair = param_name + "=" + param_value;
} else {
key_value_pair = std::string(
input.substr(key_range.begin, value_range.end() - key_range.begin));
}
if (!output.empty())
output += "&";
output += key_value_pair;
}
if (!replaced && should_keep_param) {
if (!output.empty())
output += "&";
output += (param_name + "=" + param_value);
}
GURL::Replacements replacements;
replacements.SetQueryStr(output);
return url.ReplaceComponents(replacements);
}
GURL AppendOrReplaceRef(const GURL& url, const base::StringPiece& ref) {
GURL::Replacements replacements;
replacements.SetRefStr(ref);
return url.ReplaceComponents(replacements);
}
QueryIterator::QueryIterator(const GURL& url)
: url_(url), at_end_(!url.is_valid()) {
if (!at_end_) {
query_ = url.parsed_for_possibly_invalid_spec().query;
Advance();
}
}
QueryIterator::~QueryIterator() = default;
base::StringPiece QueryIterator::GetKey() const {
DCHECK(!at_end_);
if (key_.is_nonempty())
return base::StringPiece(url_->spec()).substr(key_.begin, key_.len);
return base::StringPiece();
}
base::StringPiece QueryIterator::GetValue() const {
DCHECK(!at_end_);
if (value_.is_nonempty())
return base::StringPiece(url_->spec()).substr(value_.begin, value_.len);
return base::StringPiece();
}
const std::string& QueryIterator::GetUnescapedValue() {
DCHECK(!at_end_);
if (value_.is_nonempty() && unescaped_value_.empty()) {
unescaped_value_ = base::UnescapeURLComponent(
GetValue(),
base::UnescapeRule::SPACES | base::UnescapeRule::PATH_SEPARATORS |
base::UnescapeRule::URL_SPECIAL_CHARS_EXCEPT_PATH_SEPARATORS |
base::UnescapeRule::REPLACE_PLUS_WITH_SPACE);
}
return unescaped_value_;
}
bool QueryIterator::IsAtEnd() const {
return at_end_;
}
void QueryIterator::Advance() {
DCHECK(!at_end_);
key_.reset();
value_.reset();
unescaped_value_.clear();
at_end_ =
!url::ExtractQueryKeyValue(url_->spec().c_str(), &query_, &key_, &value_);
}
bool GetValueForKeyInQuery(const GURL& url,
base::StringPiece search_key,
std::string* out_value) {
for (QueryIterator it(url); !it.IsAtEnd(); it.Advance()) {
if (it.GetKey() == search_key) {
*out_value = it.GetUnescapedValue();
return true;
}
}
return false;
}
bool ParseHostAndPort(base::StringPiece input, std::string* host, int* port) {
if (input.empty())
return false;
url::Component auth_component(0, input.size());
url::Component username_component;
url::Component password_component;
url::Component hostname_component;
url::Component port_component;
// `input` is not NUL-terminated, so `input.data()` must be accompanied by a
// length. In these calls, `url::Component` provides an offset and length.
url::ParseAuthority(input.data(), auth_component, &username_component,
&password_component, &hostname_component,
&port_component);
// There shouldn't be a username/password.
if (username_component.is_valid() || password_component.is_valid())
return false;
if (hostname_component.is_empty())
return false; // Failed parsing.
int parsed_port_number = -1;
if (port_component.is_nonempty()) {
parsed_port_number = url::ParsePort(input.data(), port_component);
// If parsing failed, port_number will be either PORT_INVALID or
// PORT_UNSPECIFIED, both of which are negative.
if (parsed_port_number < 0)
return false; // Failed parsing the port number.
}
if (port_component.len == 0)
return false; // Reject inputs like "foo:"
unsigned char tmp_ipv6_addr[16];
// If the hostname starts with a bracket, it is either an IPv6 literal or
// invalid. If it is an IPv6 literal then strip the brackets.
if (hostname_component.len > 0 && input[hostname_component.begin] == '[') {
if (input[hostname_component.end() - 1] == ']' &&
url::IPv6AddressToNumber(input.data(), hostname_component,
tmp_ipv6_addr)) {
// Strip the brackets.
hostname_component.begin++;
hostname_component.len -= 2;
} else {
return false;
}
}
// Pass results back to caller.
*host = std::string(
input.substr(hostname_component.begin, hostname_component.len));
*port = parsed_port_number;
return true; // Success.
}
std::string GetHostAndPort(const GURL& url) {
// For IPv6 literals, GURL::host() already includes the brackets so it is
// safe to just append a colon.
return base::StringPrintf("%s:%d", url.host().c_str(),
url.EffectiveIntPort());
}
std::string GetHostAndOptionalPort(const GURL& url) {
// For IPv6 literals, GURL::host() already includes the brackets
// so it is safe to just append a colon.
if (url.has_port())
return base::StringPrintf("%s:%s", url.host().c_str(), url.port().c_str());
return url.host();
}
NET_EXPORT std::string GetHostAndOptionalPort(
const url::SchemeHostPort& scheme_host_port) {
int default_port = url::DefaultPortForScheme(
scheme_host_port.scheme().data(),
static_cast<int>(scheme_host_port.scheme().length()));
if (default_port != scheme_host_port.port()) {
return base::StringPrintf("%s:%i", scheme_host_port.host().c_str(),
scheme_host_port.port());
}
return scheme_host_port.host();
}
std::string TrimEndingDot(base::StringPiece host) {
base::StringPiece host_trimmed = host;
size_t len = host_trimmed.length();
if (len > 1 && host_trimmed[len - 1] == '.') {
host_trimmed.remove_suffix(1);
}
return std::string(host_trimmed);
}
std::string GetHostOrSpecFromURL(const GURL& url) {
return url.has_host() ? TrimEndingDot(url.host_piece()) : url.spec();
}
std::string GetSuperdomain(base::StringPiece domain) {
size_t dot_pos = domain.find('.');
if (dot_pos == std::string::npos)
return "";
return std::string(domain.substr(dot_pos + 1));
}
bool IsSubdomainOf(base::StringPiece subdomain, base::StringPiece superdomain) {
// Subdomain must be identical or have strictly more labels than the
// superdomain.
if (subdomain.length() <= superdomain.length())
return subdomain == superdomain;
// Superdomain must be suffix of subdomain, and the last character not
// included in the matching substring must be a dot.
if (!base::EndsWith(subdomain, superdomain))
return false;
subdomain.remove_suffix(superdomain.length());
return subdomain.back() == '.';
}
std::string CanonicalizeHost(base::StringPiece host,
url::CanonHostInfo* host_info) {
// Try to canonicalize the host.
const url::Component raw_host_component(0, static_cast<int>(host.length()));
std::string canon_host;
url::StdStringCanonOutput canon_host_output(&canon_host);
// A url::StdStringCanonOutput starts off with a zero length buffer. The
// first time through Grow() immediately resizes it to 32 bytes, incurring
// a malloc. With libcxx a 22 byte or smaller request can be accommodated
// within the std::string itself (i.e. no malloc occurs). Start the buffer
// off at the max size to avoid a malloc on short strings.
// NOTE: To ensure the final size is correctly reflected, it's necessary
// to call Complete() which will adjust the size to the actual bytes written.
// This is handled below for success cases, while failure cases discard all
// the output.
const int kCxxMaxStringBufferSizeWithoutMalloc = 22;
canon_host_output.Resize(kCxxMaxStringBufferSizeWithoutMalloc);
url::CanonicalizeHostVerbose(host.data(), raw_host_component,
&canon_host_output, host_info);
if (host_info->out_host.is_nonempty() &&
host_info->family != url::CanonHostInfo::BROKEN) {
// Success! Assert that there's no extra garbage.
canon_host_output.Complete();
DCHECK_EQ(host_info->out_host.len, static_cast<int>(canon_host.length()));
} else {
// Empty host, or canonicalization failed. We'll return empty.
canon_host.clear();
}
return canon_host;
}
bool IsCanonicalizedHostCompliant(base::StringPiece host) {
if (host.empty() || host.size() > 254 ||
(host.back() != '.' && host.size() == 254)) {
return false;
}
bool in_component = false;
bool most_recent_component_started_alphanumeric = false;
size_t label_size = 0;
for (char c : host) {
++label_size;
if (!in_component) {
most_recent_component_started_alphanumeric = IsHostCharAlphanumeric(c);
if (!most_recent_component_started_alphanumeric && (c != '-') &&
(c != '_')) {
return false;
}
in_component = true;
} else if (c == '.') {
in_component = false;
if (label_size > 64 || label_size == 1) {
// Label should not be empty or longer than 63 characters (+1 for '.'
// character included in `label_size`).
return false;
} else {
label_size = 0;
}
} else if (!IsHostCharAlphanumeric(c) && (c != '-') && (c != '_')) {
return false;
}
}
// Check for too-long label when not ended with final '.'.
if (label_size > 63)
return false;
return most_recent_component_started_alphanumeric;
}
bool IsHostnameNonUnique(base::StringPiece hostname) {
// CanonicalizeHost requires surrounding brackets to parse an IPv6 address.
const std::string host_or_ip = hostname.find(':') != std::string::npos
? base::StrCat({"[", hostname, "]"})
: std::string(hostname);
url::CanonHostInfo host_info;
std::string canonical_name = CanonicalizeHost(host_or_ip, &host_info);
// If canonicalization fails, then the input is truly malformed. However,
// to avoid mis-reporting bad inputs as "non-unique", treat them as unique.
if (canonical_name.empty())
return false;
// If |hostname| is an IP address, check to see if it's in an IANA-reserved
// range reserved for non-publicly routable networks.
if (host_info.IsIPAddress()) {
IPAddress host_addr;
if (!host_addr.AssignFromIPLiteral(hostname.substr(
host_info.out_host.begin, host_info.out_host.len))) {
return false;
}
switch (host_info.family) {
case url::CanonHostInfo::IPV4:
case url::CanonHostInfo::IPV6:
return !host_addr.IsPubliclyRoutable();
case url::CanonHostInfo::NEUTRAL:
case url::CanonHostInfo::BROKEN:
return false;
}
}
// Check for a registry controlled portion of |hostname|, ignoring private
// registries, as they already chain to ICANN-administered registries,
// and explicitly ignoring unknown registries.
//
// Note: This means that as new gTLDs are introduced on the Internet, they
// will be treated as non-unique until the registry controlled domain list
// is updated. However, because gTLDs are expected to provide significant
// advance notice to deprecate older versions of this code, this an
// acceptable tradeoff.
return !registry_controlled_domains::HostHasRegistryControlledDomain(
canonical_name, registry_controlled_domains::EXCLUDE_UNKNOWN_REGISTRIES,
registry_controlled_domains::EXCLUDE_PRIVATE_REGISTRIES);
}
bool IsLocalhost(const GURL& url) {
return HostStringIsLocalhost(url.HostNoBracketsPiece());
}
bool HostStringIsLocalhost(base::StringPiece host) {
IPAddress ip_address;
if (ip_address.AssignFromIPLiteral(host))
return ip_address.IsLoopback();
return IsLocalHostname(host);
}
GURL SimplifyUrlForRequest(const GURL& url) {
DCHECK(url.is_valid());
// Fast path to avoid re-canonicalization via ReplaceComponents.
if (!url.has_username() && !url.has_password() && !url.has_ref())
return url;
GURL::Replacements replacements;
replacements.ClearUsername();
replacements.ClearPassword();
replacements.ClearRef();
return url.ReplaceComponents(replacements);
}
GURL ChangeWebSocketSchemeToHttpScheme(const GURL& url) {
DCHECK(url.SchemeIsWSOrWSS());
GURL::Replacements replace_scheme;
replace_scheme.SetSchemeStr(url.SchemeIs(url::kWssScheme) ? url::kHttpsScheme
: url::kHttpScheme);
return url.ReplaceComponents(replace_scheme);
}
bool IsStandardSchemeWithNetworkHost(base::StringPiece scheme) {
// file scheme is special. Windows file share origins can have network hosts.
if (scheme == url::kFileScheme)
return true;
url::SchemeType scheme_type;
if (!url::GetStandardSchemeType(
scheme.data(), url::Component(0, scheme.length()), &scheme_type)) {
return false;
}
return scheme_type == url::SCHEME_WITH_HOST_PORT_AND_USER_INFORMATION ||
scheme_type == url::SCHEME_WITH_HOST_AND_PORT;
}
void GetIdentityFromURL(const GURL& url,
std::u16string* username,
std::u16string* password) {
*username = UnescapeIdentityString(url.username());
*password = UnescapeIdentityString(url.password());
}
bool HasGoogleHost(const GURL& url) {
return IsGoogleHost(url.host_piece());
}
bool IsGoogleHost(base::StringPiece host) {
static const char* kGoogleHostSuffixes[] = {
".google.com",
".youtube.com",
".gmail.com",
".doubleclick.net",
".gstatic.com",
".googlevideo.com",
".googleusercontent.com",
".googlesyndication.com",
".google-analytics.com",
".googleadservices.com",
".googleapis.com",
".ytimg.com",
};
for (const char* suffix : kGoogleHostSuffixes) {
// Here it's possible to get away with faster case-sensitive comparisons
// because the list above is all lowercase, and a GURL's host name will
// always be canonicalized to lowercase as well.
if (base::EndsWith(host, suffix))
return true;
}
return false;
}
bool IsGoogleHostWithAlpnH3(base::StringPiece host) {
return base::EqualsCaseInsensitiveASCII(host, "google.com") ||
base::EqualsCaseInsensitiveASCII(host, "www.google.com");
}
bool IsLocalHostname(base::StringPiece host) {
// Remove any trailing '.'.
if (!host.empty() && *host.rbegin() == '.')
host.remove_suffix(1);
return base::EqualsCaseInsensitiveASCII(host, "localhost") ||
IsNormalizedLocalhostTLD(host);
}
std::string UnescapePercentEncodedUrl(base::StringPiece input) {
std::string result(input);
// Replace any 0x2B (+) with 0x20 (SP).
for (char& c : result) {
if (c == '+') {
c = ' ';
}
}
// Run UTF-8 decoding without BOM on the percent-decoding.
url::RawCanonOutputT<char16_t> canon_output;
url::DecodeURLEscapeSequences(result, url::DecodeURLMode::kUTF8,
&canon_output);
return base::UTF16ToUTF8(canon_output.view());
}
} // namespace net
|