DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (2b8364cfdb04)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#include "chromium/safebrowsing.pb.h"
#include "nsEscape.h"
#include "nsString.h"
#include "nsIURI.h"
#include "nsIURIMutator.h"
#include "nsIURL.h"
#include "nsUrlClassifierUtils.h"
#include "nsTArray.h"
#include "nsReadableUtils.h"
#include "plbase64.h"
#include "nsPrintfCString.h"
#include "mozilla/ClearOnShutdown.h"
#include "mozilla/Sprintf.h"
#include "mozilla/StaticPtr.h"
#include "mozilla/Mutex.h"
#include "nsIRedirectHistoryEntry.h"
#include "nsIHttpChannelInternal.h"
#include "mozIThirdPartyUtil.h"
#include "nsIDocShell.h"
#include "mozilla/TextUtils.h"
#include "mozilla/Preferences.h"
#include "mozilla/Services.h"
#include "mozilla/Telemetry.h"
#include "nsNetUtil.h"
#include "nsIHttpChannel.h"
#include "nsIObserverService.h"
#include "nsIPrefBranch.h"
#include "nsIPrefService.h"
#include "nsMemory.h"
#include "nsPIDOMWindow.h"
#include "nsServiceManagerUtils.h"
#include "nsThreadManager.h"
#include "Classifier.h"
#include "Entries.h"
#include "prprf.h"
#include "prtime.h"

#define DEFAULT_PROTOCOL_VERSION "2.2"

using namespace mozilla;
using namespace mozilla::safebrowsing;

static mozilla::StaticRefPtr<nsUrlClassifierUtils> gUrlClassifierUtils;

static char int_to_hex_digit(int32_t i) {
  NS_ASSERTION((i >= 0) && (i <= 15), "int too big in int_to_hex_digit");
  return static_cast<char>(((i < 10) ? (i + '0') : ((i - 10) + 'A')));
}

static bool IsDecimal(const nsACString& num) {
  for (uint32_t i = 0; i < num.Length(); i++) {
    if (!mozilla::IsAsciiDigit(num[i])) {
      return false;
    }
  }

  return true;
}

static bool IsHex(const nsACString& num) {
  if (num.Length() < 3) {
    return false;
  }

  if (num[0] != '0' || !(num[1] == 'x' || num[1] == 'X')) {
    return false;
  }

  for (uint32_t i = 2; i < num.Length(); i++) {
    if (!mozilla::IsAsciiHexDigit(num[i])) {
      return false;
    }
  }

  return true;
}

static bool IsOctal(const nsACString& num) {
  if (num.Length() < 2) {
    return false;
  }

  if (num[0] != '0') {
    return false;
  }

  for (uint32_t i = 1; i < num.Length(); i++) {
    if (!mozilla::IsAsciiDigit(num[i]) || num[i] == '8' || num[i] == '9') {
      return false;
    }
  }

  return true;
}

/////////////////////////////////////////////////////////////////
// SafeBrowsing V4 related utits.

namespace mozilla {
namespace safebrowsing {

static PlatformType GetPlatformType() {
#if defined(ANDROID)
  return ANDROID_PLATFORM;
#elif defined(XP_MACOSX)
  return OSX_PLATFORM;
#elif defined(XP_LINUX)
  return LINUX_PLATFORM;
#elif defined(XP_WIN)
  return WINDOWS_PLATFORM;
#else
  // Default to Linux for other platforms (see bug 1362501).
  return LINUX_PLATFORM;
#endif
}

typedef FetchThreatListUpdatesRequest_ListUpdateRequest ListUpdateRequest;
typedef FetchThreatListUpdatesRequest_ListUpdateRequest_Constraints Constraints;

static void InitListUpdateRequest(ThreatType aThreatType,
                                  const nsCString& aStateBase64,
                                  ListUpdateRequest* aListUpdateRequest) {
  aListUpdateRequest->set_threat_type(aThreatType);
  PlatformType platform = GetPlatformType();
#if defined(ANDROID)
  // Temporary hack to fix bug 1441345.
  if ((aThreatType == SOCIAL_ENGINEERING_PUBLIC) ||
      (aThreatType == SOCIAL_ENGINEERING)) {
    platform = LINUX_PLATFORM;
  }
#endif
  aListUpdateRequest->set_platform_type(platform);
  aListUpdateRequest->set_threat_entry_type(URL);

  Constraints* contraints = new Constraints();
  contraints->add_supported_compressions(RICE);
  aListUpdateRequest->set_allocated_constraints(contraints);

  // Only set non-empty state.
  if (!aStateBase64.IsEmpty()) {
    nsCString stateBinary;
    nsresult rv = Base64Decode(aStateBase64, stateBinary);
    if (NS_SUCCEEDED(rv)) {
      aListUpdateRequest->set_state(stateBinary.get(), stateBinary.Length());
    }
  }
}

static ClientInfo* CreateClientInfo() {
  ClientInfo* c = new ClientInfo();

  nsCOMPtr<nsIPrefBranch> prefBranch = do_GetService(NS_PREFSERVICE_CONTRACTID);

  nsAutoCString clientId;
  nsresult rv = prefBranch->GetCharPref("browser.safebrowsing.id", clientId);

  if (NS_FAILED(rv)) {
    clientId = "Firefox";  // Use "Firefox" as fallback.
  }

  c->set_client_id(clientId.get());

  return c;
}

static bool IsAllowedOnCurrentPlatform(uint32_t aThreatType) {
  PlatformType platform = GetPlatformType();

  switch (aThreatType) {
    case POTENTIALLY_HARMFUL_APPLICATION:
      // Bug 1388582 - Google server would respond 404 error if the request
      // contains PHA on non-mobile platform.
      return ANDROID_PLATFORM == platform;
    case MALICIOUS_BINARY:
    case CSD_DOWNLOAD_WHITELIST:
      // Bug 1392204 - 'goog-downloadwhite-proto' and 'goog-badbinurl-proto'
      // are not available on android.
      return ANDROID_PLATFORM != platform;
  }
  // We allow every threat type not listed in the switch cases.
  return true;
}

}  // end of namespace safebrowsing.
}  // end of namespace mozilla.

// static
already_AddRefed<nsUrlClassifierUtils>
nsUrlClassifierUtils::GetXPCOMSingleton() {
  if (gUrlClassifierUtils) {
    return do_AddRef(gUrlClassifierUtils);
  }

  RefPtr<nsUrlClassifierUtils> utils = new nsUrlClassifierUtils();
  if (NS_WARN_IF(NS_FAILED(utils->Init()))) {
    return nullptr;
  }

  // Note: This is cleared in the nsUrlClassifierUtils destructor.
  gUrlClassifierUtils = utils.get();
  ClearOnShutdown(&gUrlClassifierUtils);
  return utils.forget();
}

// static
nsUrlClassifierUtils* nsUrlClassifierUtils::GetInstance() {
  if (!gUrlClassifierUtils) {
    RefPtr<nsUrlClassifierUtils> utils = GetXPCOMSingleton();
  }

  return gUrlClassifierUtils;
}

nsUrlClassifierUtils::nsUrlClassifierUtils()
    : mProviderDictLock("nsUrlClassifierUtils.mProviderDictLock") {}

nsUrlClassifierUtils::~nsUrlClassifierUtils() {
  if (gUrlClassifierUtils) {
    MOZ_ASSERT(gUrlClassifierUtils == this);
    gUrlClassifierUtils = nullptr;
  }
}

nsresult nsUrlClassifierUtils::Init() {
  // nsIUrlClassifierUtils is a thread-safe service so it's
  // allowed to use on non-main threads. However, building
  // the provider dictionary must be on the main thread.
  // We forcefully load nsUrlClassifierUtils in
  // nsUrlClassifierDBService::Init() to ensure we must
  // now be on the main thread.
  nsresult rv = ReadProvidersFromPrefs(mProviderDict);
  NS_ENSURE_SUCCESS(rv, rv);

  // Add an observer for shutdown
  nsCOMPtr<nsIObserverService> observerService =
      mozilla::services::GetObserverService();
  if (!observerService) return NS_ERROR_FAILURE;

  observerService->AddObserver(this, "xpcom-shutdown-threads", false);
  mozilla::Preferences::AddStrongObserver(this, "browser.safebrowsing");

  return NS_OK;
}

NS_IMPL_ISUPPORTS(nsUrlClassifierUtils, nsIUrlClassifierUtils, nsIObserver)

/////////////////////////////////////////////////////////////////////////////
// nsIUrlClassifierUtils

NS_IMETHODIMP
nsUrlClassifierUtils::GetKeyForURI(nsIURI* uri, nsACString& _retval) {
  nsCOMPtr<nsIURI> innerURI = NS_GetInnermostURI(uri);
  if (!innerURI) innerURI = uri;

  nsAutoCString host;
  innerURI->GetAsciiHost(host);

  if (host.IsEmpty()) {
    return NS_ERROR_MALFORMED_URI;
  }

  nsresult rv = CanonicalizeHostname(host, _retval);
  NS_ENSURE_SUCCESS(rv, rv);

  nsAutoCString path;
  rv = innerURI->GetPathQueryRef(path);
  NS_ENSURE_SUCCESS(rv, rv);

  // strip out anchors
  int32_t ref = path.FindChar('#');
  if (ref != kNotFound) path.SetLength(ref);

  nsAutoCString temp;
  rv = CanonicalizePath(path, temp);
  NS_ENSURE_SUCCESS(rv, rv);

  _retval.Append(temp);

  return NS_OK;
}

// We use "goog-*-proto" as the list name for v4, where "proto" indicates
// it's updated (as well as hash completion) via protobuf.
//
// In the mozilla official build, we are allowed to use the
// private phishing list (goog-phish-proto). See Bug 1288840.
static const struct {
  const char* mListName;
  uint32_t mThreatType;
} THREAT_TYPE_CONV_TABLE[] = {
    {"goog-malware-proto", MALWARE_THREAT},                   // 1
    {"googpub-phish-proto", SOCIAL_ENGINEERING_PUBLIC},       // 2
    {"goog-unwanted-proto", UNWANTED_SOFTWARE},               // 3
    {"goog-harmful-proto", POTENTIALLY_HARMFUL_APPLICATION},  // 4
    {"goog-phish-proto", SOCIAL_ENGINEERING},                 // 5

    // For application reputation
    {"goog-badbinurl-proto", MALICIOUS_BINARY},            // 7
    {"goog-downloadwhite-proto", CSD_DOWNLOAD_WHITELIST},  // 9

    // For login reputation
    {"goog-passwordwhite-proto", CSD_WHITELIST},  // 8

    // For testing purpose.
    {"moztest-phish-proto", SOCIAL_ENGINEERING_PUBLIC},  // 2
    {"test-phish-proto", SOCIAL_ENGINEERING_PUBLIC},     // 2
    {"moztest-unwanted-proto", UNWANTED_SOFTWARE},       // 3
    {"test-unwanted-proto", UNWANTED_SOFTWARE},          // 3
    {"moztest-passwordwhite-proto", CSD_WHITELIST},      // 8
    {"test-passwordwhite-proto", CSD_WHITELIST},         // 8
};

NS_IMETHODIMP
nsUrlClassifierUtils::ConvertThreatTypeToListNames(uint32_t aThreatType,
                                                   nsACString& aListNames) {
  for (uint32_t i = 0; i < ArrayLength(THREAT_TYPE_CONV_TABLE); i++) {
    if (aThreatType == THREAT_TYPE_CONV_TABLE[i].mThreatType) {
      if (!aListNames.IsEmpty()) {
        aListNames.AppendLiteral(",");
      }
      aListNames += THREAT_TYPE_CONV_TABLE[i].mListName;
    }
  }

  return aListNames.IsEmpty() ? NS_ERROR_FAILURE : NS_OK;
}

NS_IMETHODIMP
nsUrlClassifierUtils::ConvertListNameToThreatType(const nsACString& aListName,
                                                  uint32_t* aThreatType) {
  for (uint32_t i = 0; i < ArrayLength(THREAT_TYPE_CONV_TABLE); i++) {
    if (aListName.EqualsASCII(THREAT_TYPE_CONV_TABLE[i].mListName)) {
      *aThreatType = THREAT_TYPE_CONV_TABLE[i].mThreatType;
      return NS_OK;
    }
  }

  return NS_ERROR_FAILURE;
}

NS_IMETHODIMP
nsUrlClassifierUtils::GetProvider(const nsACString& aTableName,
                                  nsACString& aProvider) {
  MutexAutoLock lock(mProviderDictLock);
  nsCString* provider = nullptr;

  if (IsTestTable(aTableName)) {
    aProvider = NS_LITERAL_CSTRING(TESTING_TABLE_PROVIDER_NAME);
  } else if (mProviderDict.Get(aTableName, &provider)) {
    aProvider = provider ? *provider : EmptyCString();
  } else {
    aProvider = EmptyCString();
  }
  return NS_OK;
}

NS_IMETHODIMP
nsUrlClassifierUtils::GetTelemetryProvider(const nsACString& aTableName,
                                           nsACString& aProvider) {
  GetProvider(aTableName, aProvider);
  // Whitelist known providers to avoid reporting on private ones.
  // An empty provider is treated as "other"
  if (!NS_LITERAL_CSTRING("mozilla").Equals(aProvider) &&
      !NS_LITERAL_CSTRING("google").Equals(aProvider) &&
      !NS_LITERAL_CSTRING("google4").Equals(aProvider) &&
      !NS_LITERAL_CSTRING("baidu").Equals(aProvider) &&
      !NS_LITERAL_CSTRING("mozcn").Equals(aProvider) &&
      !NS_LITERAL_CSTRING("yandex").Equals(aProvider) &&
      !NS_LITERAL_CSTRING(TESTING_TABLE_PROVIDER_NAME).Equals(aProvider)) {
    aProvider.AssignLiteral("other");
  }

  return NS_OK;
}

NS_IMETHODIMP
nsUrlClassifierUtils::GetProtocolVersion(const nsACString& aProvider,
                                         nsACString& aVersion) {
  nsCOMPtr<nsIPrefBranch> prefBranch = do_GetService(NS_PREFSERVICE_CONTRACTID);
  if (prefBranch) {
    nsPrintfCString prefName("browser.safebrowsing.provider.%s.pver",
                             nsCString(aProvider).get());
    nsAutoCString version;
    nsresult rv = prefBranch->GetCharPref(prefName.get(), version);

    aVersion = NS_SUCCEEDED(rv) ? version.get() : DEFAULT_PROTOCOL_VERSION;
  } else {
    aVersion = DEFAULT_PROTOCOL_VERSION;
  }

  return NS_OK;
}

NS_IMETHODIMP
nsUrlClassifierUtils::MakeUpdateRequestV4(
    const nsTArray<nsCString>& aListNames,
    const nsTArray<nsCString>& aStatesBase64, nsACString& aRequest) {
  using namespace mozilla::safebrowsing;

  if (aListNames.Length() != aStatesBase64.Length()) {
    return NS_ERROR_INVALID_ARG;
  }

  FetchThreatListUpdatesRequest r;
  r.set_allocated_client(CreateClientInfo());

  for (uint32_t i = 0; i < aListNames.Length(); i++) {
    uint32_t threatType;
    nsresult rv = ConvertListNameToThreatType(aListNames[i], &threatType);
    if (NS_FAILED(rv)) {
      continue;  // Unknown list name.
    }
    if (!IsAllowedOnCurrentPlatform(threatType)) {
      NS_WARNING(
          nsPrintfCString(
              "Threat type %d (%s) is unsupported on current platform: %d",
              threatType, aListNames[i].get(), GetPlatformType())
              .get());
      continue;  // Some threat types are not available on some platforms.
    }
    auto lur = r.mutable_list_update_requests()->Add();
    InitListUpdateRequest(static_cast<ThreatType>(threatType), aStatesBase64[i],
                          lur);
  }

  // Then serialize.
  std::string s;
  r.SerializeToString(&s);

  nsCString out;
  nsresult rv = Base64URLEncode(s.size(), (const uint8_t*)s.c_str(),
                                Base64URLEncodePaddingPolicy::Include, out);
  NS_ENSURE_SUCCESS(rv, rv);

  aRequest = out;

  return NS_OK;
}

NS_IMETHODIMP
nsUrlClassifierUtils::MakeFindFullHashRequestV4(
    const nsTArray<nsCString>& aListNames,
    const nsTArray<nsCString>& aListStatesBase64,
    const nsTArray<nsCString>& aPrefixesBase64, nsACString& aRequest) {
  if (aListNames.Length() != aListStatesBase64.Length()) {
    return NS_ERROR_INVALID_ARG;
  }

  FindFullHashesRequest r;
  r.set_allocated_client(CreateClientInfo());

  nsresult rv;

  //-------------------------------------------------------------------
  // Set up FindFullHashesRequest.threat_info.
  auto threatInfo = r.mutable_threat_info();

  PlatformType platform = GetPlatformType();

  // 1) Set threat types.
  for (uint32_t i = 0; i < aListNames.Length(); i++) {
    // Add threat types.
    uint32_t threatType;
    rv = ConvertListNameToThreatType(aListNames[i], &threatType);
    NS_ENSURE_SUCCESS(rv, rv);
    if (!IsAllowedOnCurrentPlatform(threatType)) {
      NS_WARNING(
          nsPrintfCString(
              "Threat type %d (%s) is unsupported on current platform: %d",
              threatType, aListNames[i].get(), GetPlatformType())
              .get());
      continue;
    }
    threatInfo->add_threat_types((ThreatType)threatType);

#if defined(ANDROID)
    // Temporary hack to fix bug 1441345.
    if (((ThreatType)threatType == SOCIAL_ENGINEERING_PUBLIC) ||
        ((ThreatType)threatType == SOCIAL_ENGINEERING)) {
      platform = LINUX_PLATFORM;
    }
#endif

    // Add client states for index 'i' only when the threat type is available
    // on current platform.
    nsCString stateBinary;
    rv = Base64Decode(aListStatesBase64[i], stateBinary);
    NS_ENSURE_SUCCESS(rv, rv);
    r.add_client_states(stateBinary.get(), stateBinary.Length());
  }

  // 2) Set platform type.
  threatInfo->add_platform_types(platform);

  // 3) Set threat entry type.
  threatInfo->add_threat_entry_types(URL);

  // 4) Set threat entries.
  for (const nsCString& prefix : aPrefixesBase64) {
    nsCString prefixBinary;
    rv = Base64Decode(prefix, prefixBinary);
    threatInfo->add_threat_entries()->set_hash(prefixBinary.get(),
                                               prefixBinary.Length());
  }
  //-------------------------------------------------------------------

  // Then serialize.
  std::string s;
  r.SerializeToString(&s);

  nsCString out;
  rv = Base64URLEncode(s.size(), (const uint8_t*)s.c_str(),
                       Base64URLEncodePaddingPolicy::Include, out);
  NS_ENSURE_SUCCESS(rv, rv);

  aRequest = out;

  return NS_OK;
}

// Remove ref, query, userpass, anypart which may contain sensitive data
static nsresult GetSpecWithoutSensitiveData(nsIURI* aUri, nsACString& aSpec) {
  if (NS_WARN_IF(!aUri)) {
    return NS_ERROR_INVALID_ARG;
  }

  nsresult rv;
  nsCOMPtr<nsIURL> url(do_QueryInterface(aUri));
  if (url) {
    nsCOMPtr<nsIURI> clone;
    rv = NS_MutateURI(url)
             .SetQuery(EmptyCString())
             .SetRef(EmptyCString())
             .SetUserPass(EmptyCString())
             .Finalize(clone);
    NS_ENSURE_SUCCESS(rv, rv);
    rv = clone->GetAsciiSpec(aSpec);
    NS_ENSURE_SUCCESS(rv, rv);
  }
  return NS_OK;
}

static nsresult AddThreatSourceFromChannel(ThreatHit& aHit,
                                           nsIChannel* aChannel,
                                           ThreatHit_ThreatSourceType aType) {
  if (NS_WARN_IF(!aChannel)) {
    return NS_ERROR_INVALID_ARG;
  }

  nsresult rv;

  auto matchingSource = aHit.add_resources();
  matchingSource->set_type(aType);

  nsCOMPtr<nsIURI> uri;
  rv = NS_GetFinalChannelURI(aChannel, getter_AddRefs(uri));
  NS_ENSURE_SUCCESS(rv, rv);

  nsCString spec;
  rv = GetSpecWithoutSensitiveData(uri, spec);
  NS_ENSURE_SUCCESS(rv, rv);
  matchingSource->set_url(spec.get());

  nsCOMPtr<nsIHttpChannel> httpChannel = do_QueryInterface(aChannel);
  if (httpChannel) {
    nsCOMPtr<nsIReferrerInfo> referrerInfo = httpChannel->GetReferrerInfo();
    if (referrerInfo) {
      nsAutoCString referrerSpec;
      nsCOMPtr<nsIURI> referrer = referrerInfo->GetComputedReferrer();
      if (referrer) {
        rv = GetSpecWithoutSensitiveData(referrer, referrerSpec);
        NS_ENSURE_SUCCESS(rv, rv);
        matchingSource->set_referrer(referrerSpec.get());
      }
    }
  }

  nsCOMPtr<nsIHttpChannelInternal> httpChannelInternal =
      do_QueryInterface(aChannel);
  if (httpChannelInternal) {
    nsCString remoteIp;
    rv = httpChannelInternal->GetRemoteAddress(remoteIp);
    if (NS_SUCCEEDED(rv) && !remoteIp.IsEmpty()) {
      matchingSource->set_remote_ip(remoteIp.get());
    }
  }
  return NS_OK;
}
static nsresult AddThreatSourceFromRedirectEntry(
    ThreatHit& aHit, nsIRedirectHistoryEntry* aRedirectEntry,
    ThreatHit_ThreatSourceType aType) {
  if (NS_WARN_IF(!aRedirectEntry)) {
    return NS_ERROR_INVALID_ARG;
  }

  nsresult rv;

  nsCOMPtr<nsIPrincipal> principal;
  rv = aRedirectEntry->GetPrincipal(getter_AddRefs(principal));
  NS_ENSURE_SUCCESS(rv, rv);

  nsCOMPtr<nsIURI> uri;
  rv = principal->GetURI(getter_AddRefs(uri));
  NS_ENSURE_SUCCESS(rv, rv);

  nsCString spec;
  rv = GetSpecWithoutSensitiveData(uri, spec);
  NS_ENSURE_SUCCESS(rv, rv);
  auto source = aHit.add_resources();
  source->set_url(spec.get());
  source->set_type(aType);

  nsCOMPtr<nsIURI> referrer;
  rv = aRedirectEntry->GetReferrerURI(getter_AddRefs(referrer));
  if (NS_SUCCEEDED(rv) && referrer) {
    nsCString referrerSpec;
    rv = GetSpecWithoutSensitiveData(referrer, referrerSpec);
    NS_ENSURE_SUCCESS(rv, rv);
    source->set_referrer(referrerSpec.get());
  }

  nsCString remoteIp;
  rv = aRedirectEntry->GetRemoteAddress(remoteIp);
  if (NS_SUCCEEDED(rv) && !remoteIp.IsEmpty()) {
    source->set_remote_ip(remoteIp.get());
  }
  return NS_OK;
}

// Add top level tab url and redirect threatsources to threatHit message
static nsresult AddTabThreatSources(ThreatHit& aHit, nsIChannel* aChannel) {
  if (NS_WARN_IF(!aChannel)) {
    return NS_ERROR_INVALID_ARG;
  }

  nsresult rv;
  nsCOMPtr<mozIDOMWindowProxy> win;
  nsCOMPtr<mozIThirdPartyUtil> thirdPartyUtil =
      do_GetService(THIRDPARTYUTIL_CONTRACTID, &rv);
  NS_ENSURE_SUCCESS(rv, rv);

  rv = thirdPartyUtil->GetTopWindowForChannel(aChannel, nullptr,
                                              getter_AddRefs(win));
  NS_ENSURE_SUCCESS(rv, rv);

  auto* pwin = nsPIDOMWindowOuter::From(win);
  nsCOMPtr<nsIDocShell> docShell = pwin->GetDocShell();
  if (!docShell) {
    return NS_OK;
  }

  nsCOMPtr<nsIChannel> topChannel;
  docShell->GetCurrentDocumentChannel(getter_AddRefs(topChannel));
  if (!topChannel) {
    return NS_OK;
  }

  nsCOMPtr<nsIURI> uri;
  rv = aChannel->GetURI(getter_AddRefs(uri));
  NS_ENSURE_SUCCESS(rv, rv);

  nsCOMPtr<nsIURI> topUri;
  rv = topChannel->GetURI(getter_AddRefs(topUri));
  NS_ENSURE_SUCCESS(rv, rv);

  bool isTopUri = false;
  rv = topUri->Equals(uri, &isTopUri);
  if (NS_SUCCEEDED(rv) && !isTopUri) {
    nsCOMPtr<nsILoadInfo> loadInfo = aChannel->LoadInfo();
    if (loadInfo->RedirectChain().Length()) {
      AddThreatSourceFromRedirectEntry(aHit, loadInfo->RedirectChain()[0],
                                       ThreatHit_ThreatSourceType_TAB_RESOURCE);
    }
  }

  // Set top level tab_url threat source
  rv = AddThreatSourceFromChannel(aHit, topChannel,
                                  ThreatHit_ThreatSourceType_TAB_URL);
  Unused << NS_WARN_IF(NS_FAILED(rv));

  // Set tab_redirect threat sources if there's any
  nsCOMPtr<nsILoadInfo> topLoadInfo = topChannel->LoadInfo();
  nsIRedirectHistoryEntry* redirectEntry;
  size_t length = topLoadInfo->RedirectChain().Length();
  for (size_t i = 0; i < length; i++) {
    redirectEntry = topLoadInfo->RedirectChain()[i];
    AddThreatSourceFromRedirectEntry(aHit, redirectEntry,
                                     ThreatHit_ThreatSourceType_TAB_REDIRECT);
  }

  return NS_OK;
}

NS_IMETHODIMP
nsUrlClassifierUtils::MakeThreatHitReport(nsIChannel* aChannel,
                                          const nsACString& aListName,
                                          const nsACString& aHashBase64,
                                          nsACString& aRequest) {
  if (NS_WARN_IF(aListName.IsEmpty()) || NS_WARN_IF(aHashBase64.IsEmpty()) ||
      NS_WARN_IF(!aChannel)) {
    return NS_ERROR_INVALID_ARG;
  }

  ThreatHit hit;
  nsresult rv;

  uint32_t threatType;
  rv = ConvertListNameToThreatType(aListName, &threatType);
  NS_ENSURE_SUCCESS(rv, rv);
  hit.set_threat_type(static_cast<ThreatType>(threatType));

  hit.set_platform_type(GetPlatformType());

  nsCString hash;
  rv = Base64Decode(aHashBase64, hash);
  if (NS_FAILED(rv) || hash.Length() != COMPLETE_SIZE) {
    return NS_ERROR_FAILURE;
  }

  auto threatEntry = hit.mutable_entry();
  threatEntry->set_hash(hash.get(), hash.Length());

  // Set matching source
  rv = AddThreatSourceFromChannel(hit, aChannel,
                                  ThreatHit_ThreatSourceType_MATCHING_URL);
  Unused << NS_WARN_IF(NS_FAILED(rv));
  // Set tab url, tab resource url and redirect sources
  rv = AddTabThreatSources(hit, aChannel);
  Unused << NS_WARN_IF(NS_FAILED(rv));

  hit.set_allocated_client_info(CreateClientInfo());

  std::string s;
  hit.SerializeToString(&s);

  nsCString out;
  rv = Base64URLEncode(s.size(), reinterpret_cast<const uint8_t*>(s.c_str()),
                       Base64URLEncodePaddingPolicy::Include, out);
  NS_ENSURE_SUCCESS(rv, rv);

  aRequest = out;

  return NS_OK;
}

static uint32_t DurationToMs(const Duration& aDuration) {
  // Seconds precision is good enough. Ignore nanoseconds like Chrome does.
  return aDuration.seconds() * 1000;
}

NS_IMETHODIMP
nsUrlClassifierUtils::ParseFindFullHashResponseV4(
    const nsACString& aResponse,
    nsIUrlClassifierParseFindFullHashCallback* aCallback) {
  enum CompletionErrorType {
    SUCCESS = 0,
    PARSING_FAILURE = 1,
    UNKNOWN_THREAT_TYPE = 2,
  };

  FindFullHashesResponse r;
  if (!r.ParseFromArray(aResponse.BeginReading(), aResponse.Length())) {
    NS_WARNING("Invalid response");
    Telemetry::Accumulate(Telemetry::URLCLASSIFIER_COMPLETION_ERROR,
                          PARSING_FAILURE);
    return NS_ERROR_FAILURE;
  }

  bool hasUnknownThreatType = false;

  for (auto& m : r.matches()) {
    nsCString tableNames;
    nsresult rv = ConvertThreatTypeToListNames(m.threat_type(), tableNames);
    if (NS_FAILED(rv)) {
      hasUnknownThreatType = true;
      continue;  // Ignore un-convertable threat type.
    }
    auto& hash = m.threat().hash();
    auto cacheDurationSec = m.cache_duration().seconds();
    aCallback->OnCompleteHashFound(
        nsDependentCString(hash.c_str(), hash.length()), tableNames,
        cacheDurationSec);
  }

  auto minWaitDuration = DurationToMs(r.minimum_wait_duration());
  auto negCacheDurationSec = r.negative_cache_duration().seconds();

  aCallback->OnResponseParsed(minWaitDuration, negCacheDurationSec);

  Telemetry::Accumulate(Telemetry::URLCLASSIFIER_COMPLETION_ERROR,
                        hasUnknownThreatType ? UNKNOWN_THREAT_TYPE : SUCCESS);
  return NS_OK;
}

//////////////////////////////////////////////////////////
// nsIObserver

NS_IMETHODIMP
nsUrlClassifierUtils::Observe(nsISupports* aSubject, const char* aTopic,
                              const char16_t* aData) {
  if (0 == strcmp(aTopic, NS_PREFBRANCH_PREFCHANGE_TOPIC_ID)) {
    MutexAutoLock lock(mProviderDictLock);
    return ReadProvidersFromPrefs(mProviderDict);
  }

  if (0 == strcmp(aTopic, "xpcom-shutdown-threads")) {
    nsCOMPtr<nsIPrefBranch> prefs = do_GetService(NS_PREFSERVICE_CONTRACTID);
    NS_ENSURE_TRUE(prefs, NS_ERROR_FAILURE);
    return prefs->RemoveObserver("browser.safebrowsing", this);
  }

  return NS_ERROR_UNEXPECTED;
}

/////////////////////////////////////////////////////////////////////////////
// non-interface methods

nsresult nsUrlClassifierUtils::ReadProvidersFromPrefs(ProviderDictType& aDict) {
  MOZ_ASSERT(NS_IsMainThread(),
             "ReadProvidersFromPrefs must be on main thread");

  nsCOMPtr<nsIPrefService> prefs = do_GetService(NS_PREFSERVICE_CONTRACTID);
  NS_ENSURE_TRUE(prefs, NS_ERROR_FAILURE);
  nsCOMPtr<nsIPrefBranch> prefBranch;
  nsresult rv = prefs->GetBranch("browser.safebrowsing.provider.",
                                 getter_AddRefs(prefBranch));
  NS_ENSURE_SUCCESS(rv, rv);

  // We've got a pref branch for "browser.safebrowsing.provider.".
  // Enumerate all children prefs and parse providers.
  nsTArray<nsCString> childArray;
  rv = prefBranch->GetChildList("", childArray);
  NS_ENSURE_SUCCESS(rv, rv);

  // Collect providers from childArray.
  nsTHashtable<nsCStringHashKey> providers;
  for (auto& child : childArray) {
    auto dotPos = child.FindChar('.');
    if (dotPos < 0) {
      continue;
    }

    nsDependentCSubstring provider = Substring(child, 0, dotPos);

    providers.PutEntry(provider);
  }

  // Now we have all providers. Check which one owns |aTableName|.
  // e.g. The owning lists of provider "google" is defined in
  // "browser.safebrowsing.provider.google.lists".
  for (auto itr = providers.Iter(); !itr.Done(); itr.Next()) {
    auto entry = itr.Get();
    nsCString provider(entry->GetKey());
    nsPrintfCString owninListsPref("%s.lists", provider.get());

    nsAutoCString owningLists;
    nsresult rv = prefBranch->GetCharPref(owninListsPref.get(), owningLists);
    if (NS_FAILED(rv)) {
      continue;
    }

    // We've got the owning lists (represented as string) of |provider|.
    // Build the dictionary for the owning list and the current provider.
    nsTArray<nsCString> tables;
    Classifier::SplitTables(owningLists, tables);
    for (auto tableName : tables) {
      aDict.Put(tableName, new nsCString(provider));
    }
  }

  return NS_OK;
}

nsresult nsUrlClassifierUtils::CanonicalizeHostname(const nsACString& hostname,
                                                    nsACString& _retval) {
  nsAutoCString unescaped;
  if (!NS_UnescapeURL(PromiseFlatCString(hostname).get(),
                      PromiseFlatCString(hostname).Length(), 0, unescaped)) {
    unescaped.Assign(hostname);
  }

  nsAutoCString cleaned;
  CleanupHostname(unescaped, cleaned);

  nsAutoCString temp;
  ParseIPAddress(cleaned, temp);
  if (!temp.IsEmpty()) {
    cleaned.Assign(temp);
  }

  ToLowerCase(cleaned);
  SpecialEncode(cleaned, false, _retval);

  return NS_OK;
}

nsresult nsUrlClassifierUtils::CanonicalizePath(const nsACString& path,
                                                nsACString& _retval) {
  _retval.Truncate();

  nsAutoCString decodedPath(path);
  nsAutoCString temp;
  while (NS_UnescapeURL(decodedPath.get(), decodedPath.Length(), 0, temp)) {
    decodedPath.Assign(temp);
    temp.Truncate();
  }

  SpecialEncode(decodedPath, true, _retval);
  // XXX: lowercase the path?

  return NS_OK;
}

void nsUrlClassifierUtils::CleanupHostname(const nsACString& hostname,
                                           nsACString& _retval) {
  _retval.Truncate();

  const char* curChar = hostname.BeginReading();
  const char* end = hostname.EndReading();
  char lastChar = '\0';
  while (curChar != end) {
    unsigned char c = static_cast<unsigned char>(*curChar);
    if (c == '.' && (lastChar == '\0' || lastChar == '.')) {
      // skip
    } else {
      _retval.Append(*curChar);
    }
    lastChar = c;
    ++curChar;
  }

  // cut off trailing dots
  while (_retval.Length() > 0 && _retval[_retval.Length() - 1] == '.') {
    _retval.SetLength(_retval.Length() - 1);
  }
}

void nsUrlClassifierUtils::ParseIPAddress(const nsACString& host,
                                          nsACString& _retval) {
  _retval.Truncate();
  nsACString::const_iterator iter, end;
  host.BeginReading(iter);
  host.EndReading(end);

  if (host.Length() <= 15) {
    // The Windows resolver allows a 4-part dotted decimal IP address to
    // have a space followed by any old rubbish, so long as the total length
    // of the string doesn't get above 15 characters. So, "10.192.95.89 xy"
    // is resolved to 10.192.95.89.
    // If the string length is greater than 15 characters, e.g.
    // "10.192.95.89 xy.wildcard.example.com", it will be resolved through
    // DNS.

    if (FindCharInReadable(' ', iter, end)) {
      end = iter;
    }
  }

  for (host.BeginReading(iter); iter != end; iter++) {
    if (!(mozilla::IsAsciiHexDigit(*iter) || *iter == 'x' || *iter == 'X' ||
          *iter == '.')) {
      // not an IP
      return;
    }
  }

  host.BeginReading(iter);
  nsTArray<nsCString> parts;
  ParseString(PromiseFlatCString(Substring(iter, end)), '.', parts);
  if (parts.Length() > 4) {
    return;
  }

  // If any potentially-octal numbers (start with 0 but not hex) have
  // non-octal digits, no part of the ip can be in octal
  // XXX: this came from the old javascript implementation, is it really
  // supposed to be like this?
  bool allowOctal = true;
  uint32_t i;

  for (i = 0; i < parts.Length(); i++) {
    const nsCString& part = parts[i];
    if (part[0] == '0') {
      for (uint32_t j = 1; j < part.Length(); j++) {
        if (part[j] == 'x') {
          break;
        }
        if (part[j] == '8' || part[j] == '9') {
          allowOctal = false;
          break;
        }
      }
    }
  }

  for (i = 0; i < parts.Length(); i++) {
    nsAutoCString canonical;

    if (i == parts.Length() - 1) {
      CanonicalNum(parts[i], 5 - parts.Length(), allowOctal, canonical);
    } else {
      CanonicalNum(parts[i], 1, allowOctal, canonical);
    }

    if (canonical.IsEmpty()) {
      _retval.Truncate();
      return;
    }

    if (_retval.IsEmpty()) {
      _retval.Assign(canonical);
    } else {
      _retval.Append('.');
      _retval.Append(canonical);
    }
  }
}

void nsUrlClassifierUtils::CanonicalNum(const nsACString& num, uint32_t bytes,
                                        bool allowOctal, nsACString& _retval) {
  _retval.Truncate();

  if (num.Length() < 1) {
    return;
  }

  uint32_t val;
  if (allowOctal && IsOctal(num)) {
    if (PR_sscanf(PromiseFlatCString(num).get(), "%o", &val) != 1) {
      return;
    }
  } else if (IsDecimal(num)) {
    if (PR_sscanf(PromiseFlatCString(num).get(), "%u", &val) != 1) {
      return;
    }
  } else if (IsHex(num)) {
    if (PR_sscanf(PromiseFlatCString(num).get(),
                  num[1] == 'X' ? "0X%x" : "0x%x", &val) != 1) {
      return;
    }
  } else {
    return;
  }

  while (bytes--) {
    char buf[20];
    SprintfLiteral(buf, "%u", val & 0xff);
    if (_retval.IsEmpty()) {
      _retval.Assign(buf);
    } else {
      _retval = nsDependentCString(buf) + NS_LITERAL_CSTRING(".") + _retval;
    }
    val >>= 8;
  }
}

// This function will encode all "special" characters in typical url
// encoding, that is %hh where h is a valid hex digit.  It will also fold
// any duplicated slashes.
bool nsUrlClassifierUtils::SpecialEncode(const nsACString& url,
                                         bool foldSlashes,
                                         nsACString& _retval) {
  bool changed = false;
  const char* curChar = url.BeginReading();
  const char* end = url.EndReading();

  unsigned char lastChar = '\0';
  while (curChar != end) {
    unsigned char c = static_cast<unsigned char>(*curChar);
    if (ShouldURLEscape(c)) {
      _retval.Append('%');
      _retval.Append(int_to_hex_digit(c / 16));
      _retval.Append(int_to_hex_digit(c % 16));

      changed = true;
    } else if (foldSlashes && (c == '/' && lastChar == '/')) {
      // skip
    } else {
      _retval.Append(*curChar);
    }
    lastChar = c;
    curChar++;
  }
  return changed;
}

bool nsUrlClassifierUtils::ShouldURLEscape(const unsigned char c) const {
  return c <= 32 || c == '%' || c >= 127;
}

// moztest- tables are built-in created in LookupCache, they contain hardcoded
// url entries in it. moztest tables don't support updates.
// static
bool nsUrlClassifierUtils::IsMozTestTable(const nsACString& aTableName) {
  return StringBeginsWith(aTableName, NS_LITERAL_CSTRING("moztest-"));
}

// test- tables are used by testcases and can add custom test entries
// through update API.
// static
bool nsUrlClassifierUtils::IsTestTable(const nsACString& aTableName) {
  return IsMozTestTable(aTableName) ||
         StringBeginsWith(aTableName, NS_LITERAL_CSTRING("test"));
}