summaryrefslogtreecommitdiffstats
path: root/netwerk/dns/nsIDNService.cpp
blob: 2932a28444a5924a1a19d940868f548b49f74c7c (plain)
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
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* 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 "MainThreadUtils.h"
#include "mozilla/Preferences.h"
#include "nsIDNService.h"
#include "nsReadableUtils.h"
#include "nsCRT.h"
#include "nsServiceManagerUtils.h"
#include "nsUnicharUtils.h"
#include "nsUnicodeProperties.h"
#include "nsUnicodeScriptCodes.h"
#include "harfbuzz/hb.h"
#include "punycode.h"
#include "mozilla/ArrayUtils.h"
#include "mozilla/TextUtils.h"
#include "mozilla/Utf8.h"

// Currently we use the non-transitional processing option -- see
// http://unicode.org/reports/tr46/
// To switch to transitional processing, change the value of this flag
// and kTransitionalProcessing in netwerk/test/unit/test_idna2008.js to true
// (revert bug 1218179).
const bool kIDNA2008_TransitionalProcessing = false;

#include "ICUUtils.h"
#include "unicode/uscript.h"

using namespace mozilla;
using namespace mozilla::unicode;
using namespace mozilla::net;
using mozilla::Preferences;

//-----------------------------------------------------------------------------
// RFC 1034 - 3.1. Name space specifications and terminology
static const uint32_t kMaxDNSNodeLen = 63;
// RFC 3490 - 5.   ACE prefix
static const char kACEPrefix[] = "xn--";
#define kACEPrefixLen 4

//-----------------------------------------------------------------------------

#define NS_NET_PREF_EXTRAALLOWED "network.IDN.extra_allowed_chars"
#define NS_NET_PREF_EXTRABLOCKED "network.IDN.extra_blocked_chars"
#define NS_NET_PREF_SHOWPUNYCODE "network.IDN_show_punycode"
#define NS_NET_PREF_IDNWHITELIST "network.IDN.whitelist."
#define NS_NET_PREF_IDNUSEWHITELIST "network.IDN.use_whitelist"
#define NS_NET_PREF_IDNRESTRICTION "network.IDN.restriction_profile"

static inline bool isOnlySafeChars(const nsString& in,
                                   const nsTArray<BlocklistRange>& aBlocklist) {
  if (aBlocklist.IsEmpty()) {
    return true;
  }
  const char16_t* cur = in.BeginReading();
  const char16_t* end = in.EndReading();

  for (; cur < end; ++cur) {
    if (CharInBlocklist(*cur, aBlocklist)) {
      return false;
    }
  }
  return true;
}

//-----------------------------------------------------------------------------
// nsIDNService
//-----------------------------------------------------------------------------

/* Implementation file */
NS_IMPL_ISUPPORTS(nsIDNService, nsIIDNService, nsISupportsWeakReference)

static const char* gCallbackPrefs[] = {
    NS_NET_PREF_EXTRAALLOWED,    NS_NET_PREF_EXTRABLOCKED,
    NS_NET_PREF_SHOWPUNYCODE,    NS_NET_PREF_IDNRESTRICTION,
    NS_NET_PREF_IDNUSEWHITELIST, nullptr,
};

nsresult nsIDNService::Init() {
  MOZ_ASSERT(NS_IsMainThread());
  MutexAutoLock lock(mLock);

  nsCOMPtr<nsIPrefService> prefs(do_GetService(NS_PREFSERVICE_CONTRACTID));
  if (prefs) {
    prefs->GetBranch(NS_NET_PREF_IDNWHITELIST,
                     getter_AddRefs(mIDNWhitelistPrefBranch));
  }

  Preferences::RegisterPrefixCallbacks(PrefChanged, gCallbackPrefs, this);
  prefsChanged(nullptr);
  InitializeBlocklist(mIDNBlocklist);

  return NS_OK;
}

void nsIDNService::prefsChanged(const char* pref) {
  MOZ_ASSERT(NS_IsMainThread());
  mLock.AssertCurrentThreadOwns();

  if (pref && nsLiteralCString(NS_NET_PREF_EXTRAALLOWED).Equals(pref)) {
    InitializeBlocklist(mIDNBlocklist);
  }
  if (pref && nsLiteralCString(NS_NET_PREF_EXTRABLOCKED).Equals(pref)) {
    InitializeBlocklist(mIDNBlocklist);
  }
  if (!pref || nsLiteralCString(NS_NET_PREF_SHOWPUNYCODE).Equals(pref)) {
    bool val;
    if (NS_SUCCEEDED(Preferences::GetBool(NS_NET_PREF_SHOWPUNYCODE, &val))) {
      mShowPunycode = val;
    }
  }
  if (!pref || nsLiteralCString(NS_NET_PREF_IDNUSEWHITELIST).Equals(pref)) {
    bool val;
    if (NS_SUCCEEDED(Preferences::GetBool(NS_NET_PREF_IDNUSEWHITELIST, &val))) {
      mIDNUseWhitelist = val;
    }
  }
  if (!pref || nsLiteralCString(NS_NET_PREF_IDNRESTRICTION).Equals(pref)) {
    nsAutoCString profile;
    if (NS_FAILED(
            Preferences::GetCString(NS_NET_PREF_IDNRESTRICTION, profile))) {
      profile.Truncate();
    }
    if (profile.EqualsLiteral("moderate")) {
      mRestrictionProfile = eModeratelyRestrictiveProfile;
    } else if (profile.EqualsLiteral("high")) {
      mRestrictionProfile = eHighlyRestrictiveProfile;
    } else {
      mRestrictionProfile = eASCIIOnlyProfile;
    }
  }
}

nsIDNService::nsIDNService()
    : mLock("DNService pref value lock"),
      mShowPunycode(false),
      mRestrictionProfile(static_cast<restrictionProfile>(0)),
      mIDNUseWhitelist(false) {
  MOZ_ASSERT(NS_IsMainThread());

  uint32_t IDNAOptions = UIDNA_CHECK_BIDI | UIDNA_CHECK_CONTEXTJ;
  if (!kIDNA2008_TransitionalProcessing) {
    IDNAOptions |= UIDNA_NONTRANSITIONAL_TO_UNICODE;
  }
  UErrorCode errorCode = U_ZERO_ERROR;
  mIDNA = uidna_openUTS46(IDNAOptions, &errorCode);
}

nsIDNService::~nsIDNService() {
  MOZ_ASSERT(NS_IsMainThread());

  Preferences::UnregisterPrefixCallbacks(PrefChanged, gCallbackPrefs, this);

  uidna_close(mIDNA);
}

nsresult nsIDNService::IDNA2008ToUnicode(const nsACString& input,
                                         nsAString& output) {
  NS_ConvertUTF8toUTF16 inputStr(input);
  UIDNAInfo info = UIDNA_INFO_INITIALIZER;
  UErrorCode errorCode = U_ZERO_ERROR;
  int32_t inLen = inputStr.Length();
  int32_t outMaxLen = kMaxDNSNodeLen + 1;
  UChar outputBuffer[kMaxDNSNodeLen + 1];

  int32_t outLen =
      uidna_labelToUnicode(mIDNA, (const UChar*)inputStr.get(), inLen,
                           outputBuffer, outMaxLen, &info, &errorCode);
  if (info.errors != 0) {
    return NS_ERROR_MALFORMED_URI;
  }

  if (U_SUCCESS(errorCode)) {
    ICUUtils::AssignUCharArrayToString(outputBuffer, outLen, output);
  }

  nsresult rv = ICUUtils::UErrorToNsResult(errorCode);
  if (rv == NS_ERROR_FAILURE) {
    rv = NS_ERROR_MALFORMED_URI;
  }
  return rv;
}

nsresult nsIDNService::IDNA2008StringPrep(const nsAString& input,
                                          nsAString& output,
                                          stringPrepFlag flag) {
  UIDNAInfo info = UIDNA_INFO_INITIALIZER;
  UErrorCode errorCode = U_ZERO_ERROR;
  int32_t inLen = input.Length();
  int32_t outMaxLen = kMaxDNSNodeLen + 1;
  UChar outputBuffer[kMaxDNSNodeLen + 1];

  int32_t outLen =
      uidna_labelToUnicode(mIDNA, (const UChar*)PromiseFlatString(input).get(),
                           inLen, outputBuffer, outMaxLen, &info, &errorCode);
  nsresult rv = ICUUtils::UErrorToNsResult(errorCode);
  if (rv == NS_ERROR_FAILURE) {
    rv = NS_ERROR_MALFORMED_URI;
  }
  NS_ENSURE_SUCCESS(rv, rv);

  // Output the result of nameToUnicode even if there were errors.
  // But in the case of invalid punycode, the uidna_labelToUnicode result
  // appears to get an appended U+FFFD REPLACEMENT CHARACTER, which will
  // confuse our subsequent processing, so we drop that.
  // (https://bugzilla.mozilla.org/show_bug.cgi?id=1399540#c9)
  if ((info.errors & UIDNA_ERROR_PUNYCODE) && outLen > 0 &&
      outputBuffer[outLen - 1] == 0xfffd) {
    --outLen;
  }
  ICUUtils::AssignUCharArrayToString(outputBuffer, outLen, output);

  if (flag == eStringPrepIgnoreErrors) {
    return NS_OK;
  }

  if (info.errors != 0) {
    if (flag == eStringPrepForDNS) {
      output.Truncate();
    }
    rv = NS_ERROR_MALFORMED_URI;
  }

  return rv;
}

NS_IMETHODIMP nsIDNService::ConvertUTF8toACE(const nsACString& input,
                                             nsACString& ace) {
  return UTF8toACE(input, ace, eStringPrepForDNS);
}

nsresult nsIDNService::UTF8toACE(const nsACString& input, nsACString& ace,
                                 stringPrepFlag flag) {
  nsresult rv;
  NS_ConvertUTF8toUTF16 ustr(input);

  // map ideographic period to ASCII period etc.
  normalizeFullStops(ustr);

  uint32_t len, offset;
  len = 0;
  offset = 0;
  nsAutoCString encodedBuf;

  nsAString::const_iterator start, end;
  ustr.BeginReading(start);
  ustr.EndReading(end);
  ace.Truncate();

  // encode nodes if non ASCII
  while (start != end) {
    len++;
    if (*start++ == (char16_t)'.') {
      rv = stringPrepAndACE(Substring(ustr, offset, len - 1), encodedBuf, flag);
      NS_ENSURE_SUCCESS(rv, rv);

      ace.Append(encodedBuf);
      ace.Append('.');
      offset += len;
      len = 0;
    }
  }

  // encode the last node if non ASCII
  if (len) {
    rv = stringPrepAndACE(Substring(ustr, offset, len), encodedBuf, flag);
    NS_ENSURE_SUCCESS(rv, rv);

    ace.Append(encodedBuf);
  }

  return NS_OK;
}

NS_IMETHODIMP nsIDNService::ConvertACEtoUTF8(const nsACString& input,
                                             nsACString& _retval) {
  return ACEtoUTF8(input, _retval, eStringPrepForDNS);
}

nsresult nsIDNService::ACEtoUTF8(const nsACString& input, nsACString& _retval,
                                 stringPrepFlag flag) {
  // RFC 3490 - 4.2 ToUnicode
  // ToUnicode never fails.  If any step fails, then the original input
  // sequence is returned immediately in that step.
  //
  // Note that this refers to the decoding of a single label.
  // ACEtoUTF8 may be called with a sequence of labels separated by dots;
  // this test applies individually to each label.

  uint32_t len = 0, offset = 0;
  nsAutoCString decodedBuf;

  nsACString::const_iterator start, end;
  input.BeginReading(start);
  input.EndReading(end);
  _retval.Truncate();

  // loop and decode nodes
  while (start != end) {
    len++;
    if (*start++ == '.') {
      nsDependentCSubstring origLabel(input, offset, len - 1);
      if (NS_FAILED(decodeACE(origLabel, decodedBuf, flag))) {
        // If decoding failed, use the original input sequence
        // for this label.
        _retval.Append(origLabel);
      } else {
        _retval.Append(decodedBuf);
      }

      _retval.Append('.');
      offset += len;
      len = 0;
    }
  }
  // decode the last node
  if (len) {
    nsDependentCSubstring origLabel(input, offset, len);
    if (NS_FAILED(decodeACE(origLabel, decodedBuf, flag))) {
      _retval.Append(origLabel);
    } else {
      _retval.Append(decodedBuf);
    }
  }

  return NS_OK;
}

NS_IMETHODIMP nsIDNService::IsACE(const nsACString& input, bool* _retval) {
  const char* data = input.BeginReading();
  uint32_t dataLen = input.Length();

  // look for the ACE prefix in the input string.  it may occur
  // at the beginning of any segment in the domain name.  for
  // example: "www.xn--ENCODED.com"

  const char* p = PL_strncasestr(data, kACEPrefix, dataLen);

  *_retval = p && (p == data || *(p - 1) == '.');
  return NS_OK;
}

NS_IMETHODIMP nsIDNService::Normalize(const nsACString& input,
                                      nsACString& output) {
  // protect against bogus input
  NS_ENSURE_TRUE(IsUtf8(input), NS_ERROR_UNEXPECTED);

  NS_ConvertUTF8toUTF16 inUTF16(input);
  normalizeFullStops(inUTF16);

  // pass the domain name to stringprep label by label
  nsAutoString outUTF16, outLabel;

  uint32_t len = 0, offset = 0;
  nsresult rv;
  nsAString::const_iterator start, end;
  inUTF16.BeginReading(start);
  inUTF16.EndReading(end);

  while (start != end) {
    len++;
    if (*start++ == char16_t('.')) {
      rv = stringPrep(Substring(inUTF16, offset, len - 1), outLabel,
                      eStringPrepIgnoreErrors);
      NS_ENSURE_SUCCESS(rv, rv);

      outUTF16.Append(outLabel);
      outUTF16.Append(char16_t('.'));
      offset += len;
      len = 0;
    }
  }
  if (len) {
    rv = stringPrep(Substring(inUTF16, offset, len), outLabel,
                    eStringPrepIgnoreErrors);
    NS_ENSURE_SUCCESS(rv, rv);

    outUTF16.Append(outLabel);
  }

  CopyUTF16toUTF8(outUTF16, output);
  return NS_OK;
}

namespace {

class MOZ_STACK_CLASS MutexSettableAutoUnlock final {
  Mutex* mMutex;

 public:
  MutexSettableAutoUnlock() : mMutex(nullptr) {}

  void Acquire(mozilla::Mutex& aMutex) {
    MOZ_ASSERT(!mMutex);
    mMutex = &aMutex;
    mMutex->Lock();
  }

  ~MutexSettableAutoUnlock() {
    if (mMutex) {
      mMutex->Unlock();
    }
  }
};

}  // anonymous namespace

NS_IMETHODIMP nsIDNService::ConvertToDisplayIDN(const nsACString& input,
                                                bool* _isASCII,
                                                nsACString& _retval) {
  MutexSettableAutoUnlock lock;
  if (!NS_IsMainThread()) {
    lock.Acquire(mLock);
  }

  // If host is ACE, then convert to UTF-8 if the host is in the IDN whitelist.
  // Else, if host is already UTF-8, then make sure it is normalized per IDN.

  nsresult rv = NS_OK;

  // Even if the hostname is not ASCII, individual labels may still be ACE, so
  // test IsACE before testing IsASCII
  bool isACE;
  IsACE(input, &isACE);

  if (IsAscii(input)) {
    // first, canonicalize the host to lowercase, for whitelist lookup
    _retval = input;
    ToLowerCase(_retval);

    if (isACE && !mShowPunycode) {
      // ACEtoUTF8() can't fail, but might return the original ACE string
      nsAutoCString temp(_retval);
      // If the domain is in the whitelist, return the host in UTF-8.
      // Otherwise convert from ACE to UTF8 only those labels which are
      // considered safe for display
      ACEtoUTF8(
          temp, _retval,
          isInWhitelist(temp) ? eStringPrepIgnoreErrors : eStringPrepForUI);
      *_isASCII = IsAscii(_retval);
    } else {
      *_isASCII = true;
    }
  } else {
    // We have to normalize the hostname before testing against the domain
    // whitelist (see bug 315411), and to ensure the entire string gets
    // normalized.
    //
    // Normalization and the tests for safe display below, assume that the
    // input is Unicode, so first convert any ACE labels to UTF8
    if (isACE) {
      nsAutoCString temp;
      ACEtoUTF8(input, temp, eStringPrepIgnoreErrors);
      rv = Normalize(temp, _retval);
    } else {
      rv = Normalize(input, _retval);
    }
    if (NS_FAILED(rv)) {
      return rv;
    }

    if (mShowPunycode &&
        NS_SUCCEEDED(UTF8toACE(_retval, _retval, eStringPrepIgnoreErrors))) {
      *_isASCII = true;
      return NS_OK;
    }

    // normalization could result in an ASCII-only hostname. alternatively, if
    // the host is converted to ACE by the normalizer, then the host may contain
    // unsafe characters, so leave it ACE encoded. see bug 283016, bug 301694,
    // and bug 309311.
    *_isASCII = IsAscii(_retval);
    if (!*_isASCII && !isInWhitelist(_retval)) {
      // UTF8toACE with eStringPrepForUI may return a domain name where
      // some labels are in UTF-8 and some are in ACE, depending on
      // whether they are considered safe for display
      rv = UTF8toACE(_retval, _retval, eStringPrepForUI);
      *_isASCII = IsAscii(_retval);
      return rv;
    }
  }

  return NS_OK;
}

//-----------------------------------------------------------------------------

static nsresult utf16ToUcs4(const nsAString& in, uint32_t* out,
                            uint32_t outBufLen, uint32_t* outLen) {
  uint32_t i = 0;
  nsAString::const_iterator start, end;
  in.BeginReading(start);
  in.EndReading(end);

  while (start != end) {
    char16_t curChar;

    curChar = *start++;

    if (start != end && NS_IS_SURROGATE_PAIR(curChar, *start)) {
      out[i] = SURROGATE_TO_UCS4(curChar, *start);
      ++start;
    } else {
      out[i] = curChar;
    }

    i++;
    if (i >= outBufLen) {
      return NS_ERROR_MALFORMED_URI;
    }
  }
  out[i] = (uint32_t)'\0';
  *outLen = i;
  return NS_OK;
}

static nsresult punycode(const nsAString& in, nsACString& out) {
  uint32_t ucs4Buf[kMaxDNSNodeLen + 1];
  uint32_t ucs4Len = 0u;
  nsresult rv = utf16ToUcs4(in, ucs4Buf, kMaxDNSNodeLen, &ucs4Len);
  NS_ENSURE_SUCCESS(rv, rv);

  // need maximum 20 bits to encode 16 bit Unicode character
  // (include null terminator)
  const uint32_t kEncodedBufSize = kMaxDNSNodeLen * 20 / 8 + 1 + 1;
  char encodedBuf[kEncodedBufSize];
  punycode_uint encodedLength = kEncodedBufSize;

  enum punycode_status status =
      punycode_encode(ucs4Len, ucs4Buf, nullptr, &encodedLength, encodedBuf);

  if (punycode_success != status || encodedLength >= kEncodedBufSize) {
    return NS_ERROR_MALFORMED_URI;
  }

  encodedBuf[encodedLength] = '\0';
  out.Assign(nsDependentCString(kACEPrefix) + nsDependentCString(encodedBuf));

  return rv;
}

// RFC 3454
//
// 1) Map -- For each character in the input, check if it has a mapping
// and, if so, replace it with its mapping. This is described in section 3.
//
// 2) Normalize -- Possibly normalize the result of step 1 using Unicode
// normalization. This is described in section 4.
//
// 3) Prohibit -- Check for any characters that are not allowed in the
// output. If any are found, return an error. This is described in section
// 5.
//
// 4) Check bidi -- Possibly check for right-to-left characters, and if any
// are found, make sure that the whole string satisfies the requirements
// for bidirectional strings. If the string does not satisfy the requirements
// for bidirectional strings, return an error. This is described in section 6.
//
// 5) Check unassigned code points -- If allowUnassigned is false, check for
// any unassigned Unicode points and if any are found return an error.
// This is described in section 7.
//
nsresult nsIDNService::stringPrep(const nsAString& in, nsAString& out,
                                  stringPrepFlag flag) {
  return IDNA2008StringPrep(in, out, flag);
}

nsresult nsIDNService::stringPrepAndACE(const nsAString& in, nsACString& out,
                                        stringPrepFlag flag) {
  nsresult rv = NS_OK;

  out.Truncate();

  if (in.Length() > kMaxDNSNodeLen) {
    NS_WARNING("IDN node too large");
    return NS_ERROR_MALFORMED_URI;
  }

  if (IsAscii(in)) {
    LossyCopyUTF16toASCII(in, out);
    return NS_OK;
  }

  nsAutoString strPrep;
  rv = stringPrep(in, strPrep, flag);
  if (flag == eStringPrepForDNS) {
    NS_ENSURE_SUCCESS(rv, rv);
  }

  if (IsAscii(strPrep)) {
    LossyCopyUTF16toASCII(strPrep, out);
    return NS_OK;
  }

  if (flag == eStringPrepForUI && NS_SUCCEEDED(rv) && isLabelSafe(in)) {
    CopyUTF16toUTF8(strPrep, out);
    return NS_OK;
  }

  rv = punycode(strPrep, out);
  // Check that the encoded output isn't larger than the maximum length
  // of a DNS node per RFC 1034.
  // This test isn't necessary in the code paths above where the input
  // is ASCII (since the output will be the same length as the input) or
  // where we convert to UTF-8 (since the output is only used for
  // display in the UI and not passed to DNS and can legitimately be
  // longer than the limit).
  if (out.Length() > kMaxDNSNodeLen) {
    NS_WARNING("IDN node too large");
    return NS_ERROR_MALFORMED_URI;
  }

  return rv;
}

// RFC 3490
// 1) Whenever dots are used as label separators, the following characters
//    MUST be recognized as dots: U+002E (full stop), U+3002 (ideographic full
//    stop), U+FF0E (fullwidth full stop), U+FF61 (halfwidth ideographic full
//    stop).

void nsIDNService::normalizeFullStops(nsAString& s) {
  nsAString::const_iterator start, end;
  s.BeginReading(start);
  s.EndReading(end);
  int32_t index = 0;

  while (start != end) {
    switch (*start) {
      case 0x3002:
      case 0xFF0E:
      case 0xFF61:
        s.ReplaceLiteral(index, 1, u".");
        break;
      default:
        break;
    }
    start++;
    index++;
  }
}

nsresult nsIDNService::decodeACE(const nsACString& in, nsACString& out,
                                 stringPrepFlag flag) {
  bool isAce;
  IsACE(in, &isAce);
  if (!isAce) {
    out.Assign(in);
    return NS_OK;
  }

  nsAutoString utf16;
  nsresult result = IDNA2008ToUnicode(in, utf16);
  NS_ENSURE_SUCCESS(result, result);

  if (flag != eStringPrepForUI || isLabelSafe(utf16)) {
    CopyUTF16toUTF8(utf16, out);
  } else {
    out.Assign(in);
    return NS_OK;
  }

  // Validation: encode back to ACE and compare the strings
  nsAutoCString ace;
  nsresult rv = UTF8toACE(out, ace, flag);
  NS_ENSURE_SUCCESS(rv, rv);

  if (flag == eStringPrepForDNS &&
      !ace.Equals(in, nsCaseInsensitiveCStringComparator)) {
    return NS_ERROR_MALFORMED_URI;
  }

  return NS_OK;
}

bool nsIDNService::isInWhitelist(const nsACString& host) {
  if (!NS_IsMainThread()) {
    mLock.AssertCurrentThreadOwns();
  }

  if (mIDNUseWhitelist && mIDNWhitelistPrefBranch) {
    nsAutoCString tld(host);
    // make sure the host is ACE for lookup and check that there are no
    // unassigned codepoints
    if (!IsAscii(tld) && NS_FAILED(UTF8toACE(tld, tld, eStringPrepForDNS))) {
      return false;
    }

    // truncate trailing dots first
    tld.Trim(".");
    int32_t pos = tld.RFind(".");
    if (pos == kNotFound) {
      return false;
    }

    tld.Cut(0, pos + 1);

    bool safe;
    if (NS_SUCCEEDED(mIDNWhitelistPrefBranch->GetBoolPref(tld.get(), &safe))) {
      return safe;
    }
  }

  return false;
}

bool nsIDNService::isLabelSafe(const nsAString& label) {
  if (!NS_IsMainThread()) {
    mLock.AssertCurrentThreadOwns();
  }

  if (!isOnlySafeChars(PromiseFlatString(label), mIDNBlocklist)) {
    return false;
  }

  // We should never get here if the label is ASCII
  NS_ASSERTION(!IsAscii(label), "ASCII label in IDN checking");
  if (mRestrictionProfile == eASCIIOnlyProfile) {
    return false;
  }

  nsAString::const_iterator current, end;
  label.BeginReading(current);
  label.EndReading(end);

  Script lastScript = Script::INVALID;
  uint32_t previousChar = 0;
  uint32_t baseChar = 0;  // last non-diacritic seen (base char for marks)
  uint32_t savedNumberingSystem = 0;
// Simplified/Traditional Chinese check temporarily disabled -- bug 857481
#if 0
  HanVariantType savedHanVariant = HVT_NotHan;
#endif

  int32_t savedScript = -1;

  while (current != end) {
    uint32_t ch = *current++;

    if (current != end && NS_IS_SURROGATE_PAIR(ch, *current)) {
      ch = SURROGATE_TO_UCS4(ch, *current++);
    }

    IdentifierType idType = GetIdentifierType(ch);
    if (idType == IDTYPE_RESTRICTED) {
      return false;
    }
    MOZ_ASSERT(idType == IDTYPE_ALLOWED);

    // Check for mixed script
    Script script = GetScriptCode(ch);
    if (script != Script::COMMON && script != Script::INHERITED &&
        script != lastScript) {
      if (illegalScriptCombo(script, savedScript)) {
        return false;
      }
    }

    // Check for mixed numbering systems
    auto genCat = GetGeneralCategory(ch);
    if (genCat == HB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER) {
      uint32_t zeroCharacter = ch - GetNumericValue(ch);
      if (savedNumberingSystem == 0) {
        // If we encounter a decimal number, save the zero character from that
        // numbering system.
        savedNumberingSystem = zeroCharacter;
      } else if (zeroCharacter != savedNumberingSystem) {
        return false;
      }
    }

    if (genCat == HB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK) {
      // Check for consecutive non-spacing marks.
      if (previousChar != 0 && previousChar == ch) {
        return false;
      }
      // Check for marks whose expected script doesn't match the base script.
      if (lastScript != Script::INVALID) {
        const size_t kMaxScripts = 32;  // more than ample for current values
                                        // of ScriptExtensions property
        UScriptCode scripts[kMaxScripts];
        UErrorCode errorCode = U_ZERO_ERROR;
        int nScripts =
            uscript_getScriptExtensions(ch, scripts, kMaxScripts, &errorCode);
        MOZ_ASSERT(U_SUCCESS(errorCode), "uscript_getScriptExtensions failed");
        if (U_FAILURE(errorCode)) {
          return false;
        }
        // nScripts will always be >= 1, because even for undefined characters
        // uscript_getScriptExtensions will return Script::INVALID.
        // If the mark just has script=COMMON or INHERITED, we can't check any
        // more carefully, but if it has specific scriptExtension codes, then
        // assume those are the only valid scripts to use it with.
        if (nScripts > 1 || (Script(scripts[0]) != Script::COMMON &&
                             Script(scripts[0]) != Script::INHERITED)) {
          while (--nScripts >= 0) {
            if (Script(scripts[nScripts]) == lastScript) {
              break;
            }
          }
          if (nScripts == -1) {
            return false;
          }
        }
      }
      // Check for diacritics on dotless-i, which would be indistinguishable
      // from normal accented letter i.
      if (baseChar == 0x0131 &&
          ((ch >= 0x0300 && ch <= 0x0314) || ch == 0x031a)) {
        return false;
      }
    } else {
      baseChar = ch;
    }

    if (script != Script::COMMON && script != Script::INHERITED) {
      lastScript = script;
    }

    // Simplified/Traditional Chinese check temporarily disabled -- bug 857481
#if 0

    // Check for both simplified-only and traditional-only Chinese characters
    HanVariantType hanVariant = GetHanVariant(ch);
    if (hanVariant == HVT_SimplifiedOnly || hanVariant == HVT_TraditionalOnly) {
      if (savedHanVariant == HVT_NotHan) {
        savedHanVariant = hanVariant;
      } else if (hanVariant != savedHanVariant)  {
        return false;
      }
    }
#endif

    previousChar = ch;
  }
  return true;
}

// Scripts that we care about in illegalScriptCombo
static const Script scriptTable[] = {
    Script::BOPOMOFO, Script::CYRILLIC, Script::GREEK,    Script::HANGUL,
    Script::HAN,      Script::HIRAGANA, Script::KATAKANA, Script::LATIN};

#define BOPO 0
#define CYRL 1
#define GREK 2
#define HANG 3
#define HANI 4
#define HIRA 5
#define KATA 6
#define LATN 7
#define OTHR 8
#define JPAN 9   // Latin + Han + Hiragana + Katakana
#define CHNA 10  // Latin + Han + Bopomofo
#define KORE 11  // Latin + Han + Hangul
#define HNLT 12  // Latin + Han (could be any of the above combinations)
#define FAIL 13

static inline int32_t findScriptIndex(Script aScript) {
  int32_t tableLength = mozilla::ArrayLength(scriptTable);
  for (int32_t index = 0; index < tableLength; ++index) {
    if (aScript == scriptTable[index]) {
      return index;
    }
  }
  return OTHR;
}

static const int32_t scriptComboTable[13][9] = {
    /* thisScript: BOPO  CYRL  GREK  HANG  HANI  HIRA  KATA  LATN  OTHR
     * savedScript */
    /* BOPO */ {BOPO, FAIL, FAIL, FAIL, CHNA, FAIL, FAIL, CHNA, FAIL},
    /* CYRL */ {FAIL, CYRL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL},
    /* GREK */ {FAIL, FAIL, GREK, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL},
    /* HANG */ {FAIL, FAIL, FAIL, HANG, KORE, FAIL, FAIL, KORE, FAIL},
    /* HANI */ {CHNA, FAIL, FAIL, KORE, HANI, JPAN, JPAN, HNLT, FAIL},
    /* HIRA */ {FAIL, FAIL, FAIL, FAIL, JPAN, HIRA, JPAN, JPAN, FAIL},
    /* KATA */ {FAIL, FAIL, FAIL, FAIL, JPAN, JPAN, KATA, JPAN, FAIL},
    /* LATN */ {CHNA, FAIL, FAIL, KORE, HNLT, JPAN, JPAN, LATN, OTHR},
    /* OTHR */ {FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, OTHR, FAIL},
    /* JPAN */ {FAIL, FAIL, FAIL, FAIL, JPAN, JPAN, JPAN, JPAN, FAIL},
    /* CHNA */ {CHNA, FAIL, FAIL, FAIL, CHNA, FAIL, FAIL, CHNA, FAIL},
    /* KORE */ {FAIL, FAIL, FAIL, KORE, KORE, FAIL, FAIL, KORE, FAIL},
    /* HNLT */ {CHNA, FAIL, FAIL, KORE, HNLT, JPAN, JPAN, HNLT, FAIL}};

bool nsIDNService::illegalScriptCombo(Script script, int32_t& savedScript) {
  if (!NS_IsMainThread()) {
    mLock.AssertCurrentThreadOwns();
  }

  if (savedScript == -1) {
    savedScript = findScriptIndex(script);
    return false;
  }

  savedScript = scriptComboTable[savedScript][findScriptIndex(script)];
  /*
   * Special case combinations that depend on which profile is in use
   * In the Highly Restrictive profile Latin is not allowed with any
   *  other script
   *
   * In the Moderately Restrictive profile Latin mixed with any other
   *  single script is allowed.
   */
  return ((savedScript == OTHR &&
           mRestrictionProfile == eHighlyRestrictiveProfile) ||
          savedScript == FAIL);
}

#undef BOPO
#undef CYRL
#undef GREK
#undef HANG
#undef HANI
#undef HIRA
#undef KATA
#undef LATN
#undef OTHR
#undef JPAN
#undef CHNA
#undef KORE
#undef HNLT
#undef FAIL