summaryrefslogtreecommitdiffstats
path: root/netwerk/base/nsURLHelper.cpp
blob: 8def697dac4d973598827f4062b421dddb61c4a8 (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
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
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/* vim:set ts=4 sw=4 sts=4 et cindent: */
/* 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 "mozilla/RangedPtr.h"

#include <algorithm>
#include <iterator>

#include "nsURLHelper.h"
#include "nsIFile.h"
#include "nsIURLParser.h"
#include "nsCOMPtr.h"
#include "nsCRT.h"
#include "nsNetCID.h"
#include "mozilla/Preferences.h"
#include "prnetdb.h"
#include "mozilla/Tokenizer.h"

using namespace mozilla;

//----------------------------------------------------------------------------
// Init/Shutdown
//----------------------------------------------------------------------------

static bool gInitialized = false;
static nsIURLParser *gNoAuthURLParser = nullptr;
static nsIURLParser *gAuthURLParser = nullptr;
static nsIURLParser *gStdURLParser = nullptr;
static int32_t gMaxLength = 1048576; // Default: 1MB

static void
InitGlobals()
{
    nsCOMPtr<nsIURLParser> parser;

    parser = do_GetService(NS_NOAUTHURLPARSER_CONTRACTID);
    NS_ASSERTION(parser, "failed getting 'noauth' url parser");
    if (parser) {
        gNoAuthURLParser = parser.get();
        NS_ADDREF(gNoAuthURLParser);
    }

    parser = do_GetService(NS_AUTHURLPARSER_CONTRACTID);
    NS_ASSERTION(parser, "failed getting 'auth' url parser");
    if (parser) {
        gAuthURLParser = parser.get();
        NS_ADDREF(gAuthURLParser);
    }

    parser = do_GetService(NS_STDURLPARSER_CONTRACTID);
    NS_ASSERTION(parser, "failed getting 'std' url parser");
    if (parser) {
        gStdURLParser = parser.get();
        NS_ADDREF(gStdURLParser);
    }

    gInitialized = true;
    Preferences::AddIntVarCache(&gMaxLength,
                                "network.standard-url.max-length", 1048576);
}

void
net_ShutdownURLHelper()
{
    if (gInitialized) {
        NS_IF_RELEASE(gNoAuthURLParser);
        NS_IF_RELEASE(gAuthURLParser);
        NS_IF_RELEASE(gStdURLParser);
        gInitialized = false;
    }
}

int32_t net_GetURLMaxLength()
{
    return gMaxLength;
}

//----------------------------------------------------------------------------
// nsIURLParser getters
//----------------------------------------------------------------------------

nsIURLParser *
net_GetAuthURLParser()
{
    if (!gInitialized)
        InitGlobals();
    return gAuthURLParser;
}

nsIURLParser *
net_GetNoAuthURLParser()
{
    if (!gInitialized)
        InitGlobals();
    return gNoAuthURLParser;
}

nsIURLParser *
net_GetStdURLParser()
{
    if (!gInitialized)
        InitGlobals();
    return gStdURLParser;
}

//---------------------------------------------------------------------------
// GetFileFromURLSpec implementations
//---------------------------------------------------------------------------
nsresult
net_GetURLSpecFromDir(nsIFile *aFile, nsACString &result)
{
    nsAutoCString escPath;
    nsresult rv = net_GetURLSpecFromActualFile(aFile, escPath);
    if (NS_FAILED(rv))
        return rv;

    if (escPath.Last() != '/') {
        escPath += '/';
    }

    result = escPath;
    return NS_OK;
}

nsresult
net_GetURLSpecFromFile(nsIFile *aFile, nsACString &result)
{
    nsAutoCString escPath;
    nsresult rv = net_GetURLSpecFromActualFile(aFile, escPath);
    if (NS_FAILED(rv))
        return rv;

    // if this file references a directory, then we need to ensure that the
    // URL ends with a slash.  this is important since it affects the rules
    // for relative URL resolution when this URL is used as a base URL.
    // if the file does not exist, then we make no assumption about its type,
    // and simply leave the URL unmodified.
    if (escPath.Last() != '/') {
        bool dir;
        rv = aFile->IsDirectory(&dir);
        if (NS_SUCCEEDED(rv) && dir)
            escPath += '/';
    }

    result = escPath;
    return NS_OK;
}

//----------------------------------------------------------------------------
// file:// URL parsing
//----------------------------------------------------------------------------

nsresult
net_ParseFileURL(const nsACString &inURL,
                 nsACString &outDirectory,
                 nsACString &outFileBaseName,
                 nsACString &outFileExtension)
{
    nsresult rv;

    if (inURL.Length() > (uint32_t) gMaxLength) {
        return NS_ERROR_MALFORMED_URI;
    }

    outDirectory.Truncate();
    outFileBaseName.Truncate();
    outFileExtension.Truncate();

    const nsPromiseFlatCString &flatURL = PromiseFlatCString(inURL);
    const char *url = flatURL.get();

    nsAutoCString scheme;
    rv = net_ExtractURLScheme(flatURL, scheme);
    if (NS_FAILED(rv)) return rv;

    if (!scheme.EqualsLiteral("file")) {
        NS_ERROR("must be a file:// url");
        return NS_ERROR_UNEXPECTED;
    }

    nsIURLParser *parser = net_GetNoAuthURLParser();
    NS_ENSURE_TRUE(parser, NS_ERROR_UNEXPECTED);

    uint32_t pathPos, filepathPos, directoryPos, basenamePos, extensionPos;
    int32_t pathLen, filepathLen, directoryLen, basenameLen, extensionLen;

    // invoke the parser to extract the URL path
    rv = parser->ParseURL(url, flatURL.Length(),
                          nullptr, nullptr, // don't care about scheme
                          nullptr, nullptr, // don't care about authority
                          &pathPos, &pathLen);
    if (NS_FAILED(rv)) return rv;

    // invoke the parser to extract filepath from the path
    rv = parser->ParsePath(url + pathPos, pathLen,
                           &filepathPos, &filepathLen,
                           nullptr, nullptr,  // don't care about query
                           nullptr, nullptr); // don't care about ref
    if (NS_FAILED(rv)) return rv;

    filepathPos += pathPos;

    // invoke the parser to extract the directory and filename from filepath
    rv = parser->ParseFilePath(url + filepathPos, filepathLen,
                               &directoryPos, &directoryLen,
                               &basenamePos, &basenameLen,
                               &extensionPos, &extensionLen);
    if (NS_FAILED(rv)) return rv;

    if (directoryLen > 0)
        outDirectory = Substring(inURL, filepathPos + directoryPos, directoryLen);
    if (basenameLen > 0)
        outFileBaseName = Substring(inURL, filepathPos + basenamePos, basenameLen);
    if (extensionLen > 0)
        outFileExtension = Substring(inURL, filepathPos + extensionPos, extensionLen);
    // since we are using a no-auth url parser, there will never be a host
    // XXX not strictly true... file://localhost/foo/bar.html is a valid URL

    return NS_OK;
}

//----------------------------------------------------------------------------
// path manipulation functions
//----------------------------------------------------------------------------

// Replace all /./ with a / while resolving URLs
// But only till #? 
void 
net_CoalesceDirs(netCoalesceFlags flags, char* path)
{
    /* Stolen from the old netlib's mkparse.c.
     *
     * modifies a url of the form   /foo/../foo1  ->  /foo1
     *                       and    /foo/./foo1   ->  /foo/foo1
     *                       and    /foo/foo1/..  ->  /foo/
     */
    char *fwdPtr = path;
    char *urlPtr = path;
    char *lastslash = path;
    uint32_t traversal = 0;
    uint32_t special_ftp_len = 0;

    /* Remember if this url is a special ftp one: */
    if (flags & NET_COALESCE_DOUBLE_SLASH_IS_ROOT) 
    {
       /* some schemes (for example ftp) have the speciality that 
          the path can begin // or /%2F to mark the root of the 
          servers filesystem, a simple / only marks the root relative 
          to the user loging in. We remember the length of the marker */
        if (nsCRT::strncasecmp(path,"/%2F",4) == 0)
            special_ftp_len = 4;
        else if (nsCRT::strncmp(path,"//",2) == 0 )
            special_ftp_len = 2; 
    }

    /* find the last slash before # or ? */
    for(; (*fwdPtr != '\0') && 
            (*fwdPtr != '?') && 
            (*fwdPtr != '#'); ++fwdPtr)
    {
    }

    /* found nothing, but go back one only */
    /* if there is something to go back to */
    if (fwdPtr != path && *fwdPtr == '\0')
    {
        --fwdPtr;
    }

    /* search the slash */
    for(; (fwdPtr != path) && 
            (*fwdPtr != '/'); --fwdPtr)
    {
    }
    lastslash = fwdPtr;
    fwdPtr = path;

    /* replace all %2E or %2e with . in the path */
    /* but stop at lastchar if non null */
    for(; (*fwdPtr != '\0') && 
            (*fwdPtr != '?') && 
            (*fwdPtr != '#') &&
            (*lastslash == '\0' || fwdPtr != lastslash); ++fwdPtr)
    {
        if (*fwdPtr == '%' && *(fwdPtr+1) == '2' && 
            (*(fwdPtr+2) == 'E' || *(fwdPtr+2) == 'e'))
        {
            *urlPtr++ = '.';
            ++fwdPtr;
            ++fwdPtr;
        } 
        else 
        {
            *urlPtr++ = *fwdPtr;
        }
    }
    // Copy remaining stuff past the #?;
    for (; *fwdPtr != '\0'; ++fwdPtr)
    {
        *urlPtr++ = *fwdPtr;
    }
    *urlPtr = '\0';  // terminate the url 

    // start again, this time for real 
    fwdPtr = path;
    urlPtr = path;

    for(; (*fwdPtr != '\0') && 
            (*fwdPtr != '?') && 
            (*fwdPtr != '#'); ++fwdPtr)
    {
        if (*fwdPtr == '/' && *(fwdPtr+1) == '.' && *(fwdPtr+2) == '/' )
        {
            // remove . followed by slash
            ++fwdPtr;
        }
        else if(*fwdPtr == '/' && *(fwdPtr+1) == '.' && *(fwdPtr+2) == '.' && 
                (*(fwdPtr+3) == '/' || 
                    *(fwdPtr+3) == '\0' || // This will take care of 
                    *(fwdPtr+3) == '?' ||  // something like foo/bar/..#sometag
                    *(fwdPtr+3) == '#'))
        {
            // remove foo/.. 
            // reverse the urlPtr to the previous slash if possible
            // if url does not allow relative root then drop .. above root 
            // otherwise retain them in the path 
            if(traversal > 0 || !(flags & 
                                  NET_COALESCE_ALLOW_RELATIVE_ROOT))
            { 
                if (urlPtr != path)
                    urlPtr--; // we must be going back at least by one 
                for(;*urlPtr != '/' && urlPtr != path; urlPtr--)
                    ;  // null body 
                --traversal; // count back
                // forward the fwdPtr past the ../
                fwdPtr += 2;
                // if we have reached the beginning of the path
                // while searching for the previous / and we remember
                // that it is an url that begins with /%2F then
                // advance urlPtr again by 3 chars because /%2F already 
                // marks the root of the path
                if (urlPtr == path && special_ftp_len > 3) 
                {
                    ++urlPtr;
                    ++urlPtr;
                    ++urlPtr;
                }
                // special case if we have reached the end 
                // to preserve the last /
                if (*fwdPtr == '.' && *(fwdPtr+1) == '\0')
                    ++urlPtr;
            } 
            else 
            {
                // there are to much /.. in this path, just copy them instead.
                // forward the urlPtr past the /.. and copying it

                // However if we remember it is an url that starts with
                // /%2F and urlPtr just points at the "F" of "/%2F" then do 
                // not overwrite it with the /, just copy .. and move forward
                // urlPtr. 
                if (special_ftp_len > 3 && urlPtr == path+special_ftp_len-1)
                    ++urlPtr;
                else 
                    *urlPtr++ = *fwdPtr;
                ++fwdPtr;
                *urlPtr++ = *fwdPtr;
                ++fwdPtr;
                *urlPtr++ = *fwdPtr;
            }
        }
        else
        {
            // count the hierachie, but only if we do not have reached
            // the root of some special urls with a special root marker 
            if (*fwdPtr == '/' &&  *(fwdPtr+1) != '.' &&
               (special_ftp_len != 2 || *(fwdPtr+1) != '/'))
                traversal++;
            // copy the url incrementaly 
            *urlPtr++ = *fwdPtr;
        }
    }

    /* 
     *  Now lets remove trailing . case
     *     /foo/foo1/.   ->  /foo/foo1/
     */

    if ((urlPtr > (path+1)) && (*(urlPtr-1) == '.') && (*(urlPtr-2) == '/'))
        urlPtr--;

    // Copy remaining stuff past the #?;
    for (; *fwdPtr != '\0'; ++fwdPtr)
    {
        *urlPtr++ = *fwdPtr;
    }
    *urlPtr = '\0';  // terminate the url 
}

nsresult
net_ResolveRelativePath(const nsACString &relativePath,
                        const nsACString &basePath,
                        nsACString &result)
{
    nsAutoCString name;
    nsAutoCString path(basePath);
    bool needsDelim = false;

    if ( !path.IsEmpty() ) {
        char16_t last = path.Last();
        needsDelim = !(last == '/');
    }

    nsACString::const_iterator beg, end;
    relativePath.BeginReading(beg);
    relativePath.EndReading(end);

    bool stop = false;
    char c;
    for (; !stop; ++beg) {
        c = (beg == end) ? '\0' : *beg;
        //printf("%c [name=%s] [path=%s]\n", c, name.get(), path.get());
        switch (c) {
          case '\0':
          case '#':
          case '?':
            stop = true;
            MOZ_FALLTHROUGH;
          case '/':
            // delimiter found
            if (name.EqualsLiteral("..")) {
                // pop path
                // If we already have the delim at end, then
                //  skip over that when searching for next one to the left
                int32_t offset = path.Length() - (needsDelim ? 1 : 2);
                // First check for errors
                if (offset < 0 ) 
                    return NS_ERROR_MALFORMED_URI;
                int32_t pos = path.RFind("/", false, offset);
                if (pos >= 0)
                    path.Truncate(pos + 1);
                else
                    path.Truncate();
            }
            else if (name.IsEmpty() || name.EqualsLiteral(".")) {
                // do nothing
            }
            else {
                // append name to path
                if (needsDelim)
                    path += '/';
                path += name;
                needsDelim = true;
            }
            name.Truncate();
            break;

          default:
            // append char to name
            name += c;
        }
    }
    // append anything left on relativePath (e.g. #..., ;..., ?...)
    if (c != '\0')
        path += Substring(--beg, end);

    result = path;
    return NS_OK;
}

//----------------------------------------------------------------------------
// scheme fu
//----------------------------------------------------------------------------

static bool isAsciiAlpha(char c) {
    return nsCRT::IsAsciiAlpha(c);
}

static bool
net_IsValidSchemeChar(const char aChar)
{
    if (nsCRT::IsAsciiAlpha(aChar) || nsCRT::IsAsciiDigit(aChar) ||
        aChar == '+' || aChar == '.' || aChar == '-') {
        return true;
    }
    return false;
}

/* Extract URI-Scheme if possible */
nsresult
net_ExtractURLScheme(const nsACString &inURI,
                     nsACString& scheme)
{
    nsACString::const_iterator start, end;
    inURI.BeginReading(start);
    inURI.EndReading(end);

    // Strip C0 and space from begining
    while (start != end) {
        if ((uint8_t) *start > 0x20) {
            break;
        }
        start++;
    }

    Tokenizer p(Substring(start, end), "\r\n\t");
    p.Record();
    if (!p.CheckChar(isAsciiAlpha)) {
        // First char must be alpha
        return NS_ERROR_MALFORMED_URI;
    }

    while (p.CheckChar(net_IsValidSchemeChar) || p.CheckWhite()) {
        // Skip valid scheme characters or \r\n\t
    }

    if (!p.CheckChar(':')) {
        return NS_ERROR_MALFORMED_URI;
    }

    p.Claim(scheme);
    scheme.StripChars("\r\n\t");
    return NS_OK;
}

bool
net_IsValidScheme(const char *scheme, uint32_t schemeLen)
{
    // first char must be alpha
    if (!nsCRT::IsAsciiAlpha(*scheme))
        return false;

    // nsCStrings may have embedded nulls -- reject those too
    for (; schemeLen; ++scheme, --schemeLen) {
        if (!(nsCRT::IsAsciiAlpha(*scheme) ||
              nsCRT::IsAsciiDigit(*scheme) ||
              *scheme == '+' ||
              *scheme == '.' ||
              *scheme == '-'))
            return false;
    }

    return true;
}

bool
net_IsAbsoluteURL(const nsACString& uri)
{
    nsACString::const_iterator start, end;
    uri.BeginReading(start);
    uri.EndReading(end);

    // Strip C0 and space from begining
    while (start != end) {
        if ((uint8_t) *start > 0x20) {
            break;
        }
        start++;
    }

    Tokenizer p(Substring(start, end), "\r\n\t");

    // First char must be alpha
    if (!p.CheckChar(isAsciiAlpha)) {
        return false;
    }

    while (p.CheckChar(net_IsValidSchemeChar) || p.CheckWhite()) {
        // Skip valid scheme characters or \r\n\t
    }
    if (!p.CheckChar(':')) {
        return false;
    }
    p.SkipWhites();

    if (!p.CheckChar('/')) {
        return false;
    }
    p.SkipWhites();

    if (p.CheckChar('/')) {
        // aSpec is really absolute. Ignore aBaseURI in this case
        return true;
    }
    return false;
}

void
net_FilterURIString(const nsACString& input, nsACString& result)
{
    const char kCharsToStrip[] = "\r\n\t";

    result.Truncate();

    auto start = input.BeginReading();
    auto end = input.EndReading();

    // Trim off leading and trailing invalid chars.
    auto charFilter = [](char c) { return static_cast<uint8_t>(c) > 0x20; };
    auto newStart = std::find_if(start, end, charFilter);
    auto newEnd = std::find_if(
        std::reverse_iterator<decltype(end)>(end),
        std::reverse_iterator<decltype(newStart)>(newStart),
        charFilter).base();

    // Check if chars need to be stripped.
    auto itr = std::find_first_of(
        newStart, newEnd, std::begin(kCharsToStrip), std::end(kCharsToStrip));
    const bool needsStrip = itr != newEnd;

    // Just use the passed in string rather than creating new copies if no
    // changes are necessary.
    if (newStart == start && newEnd == end && !needsStrip) {
        result = input;
        return;
    }

    result.Assign(Substring(newStart, newEnd));
    if (needsStrip) {
        result.StripChars(kCharsToStrip);
    }
}


#if defined(XP_WIN)
bool
net_NormalizeFileURL(const nsACString &aURL, nsCString &aResultBuf)
{
    bool writing = false;

    nsACString::const_iterator beginIter, endIter;
    aURL.BeginReading(beginIter);
    aURL.EndReading(endIter);

    const char *s, *begin = beginIter.get();

    for (s = begin; s != endIter.get(); ++s)
    {
        if (*s == '\\')
        {
            writing = true;
            if (s > begin)
                aResultBuf.Append(begin, s - begin);
            aResultBuf += '/';
            begin = s + 1;
        }
    }
    if (writing && s > begin)
        aResultBuf.Append(begin, s - begin);

    return writing;
}
#endif

//----------------------------------------------------------------------------
// miscellaneous (i.e., stuff that should really be elsewhere)
//----------------------------------------------------------------------------

static inline
void ToLower(char &c)
{
    if ((unsigned)(c - 'A') <= (unsigned)('Z' - 'A'))
        c += 'a' - 'A';
}

void
net_ToLowerCase(char *str, uint32_t length)
{
    for (char *end = str + length; str < end; ++str)
        ToLower(*str);
}

void
net_ToLowerCase(char *str)
{
    for (; *str; ++str)
        ToLower(*str);
}

char *
net_FindCharInSet(const char *iter, const char *stop, const char *set)
{
    for (; iter != stop && *iter; ++iter) {
        for (const char *s = set; *s; ++s) {
            if (*iter == *s)
                return (char *) iter;
        }
    }
    return (char *) iter;
}

char *
net_FindCharNotInSet(const char *iter, const char *stop, const char *set)
{
repeat:
    for (const char *s = set; *s; ++s) {
        if (*iter == *s) {
            if (++iter == stop)
                break;
            goto repeat;
        }
    }
    return (char *) iter;
}

char *
net_RFindCharNotInSet(const char *stop, const char *iter, const char *set)
{
    --iter;
    --stop;

    if (iter == stop)
        return (char *) iter;

repeat:
    for (const char *s = set; *s; ++s) {
        if (*iter == *s) {
            if (--iter == stop)
                break;
            goto repeat;
        }
    }
    return (char *) iter;
}

#define HTTP_LWS " \t"

// Return the index of the closing quote of the string, if any
static uint32_t
net_FindStringEnd(const nsCString& flatStr,
                  uint32_t stringStart,
                  char stringDelim)
{
    NS_ASSERTION(stringStart < flatStr.Length() &&
                 flatStr.CharAt(stringStart) == stringDelim &&
                 (stringDelim == '"' || stringDelim == '\''),
                 "Invalid stringStart");

    const char set[] = { stringDelim, '\\', '\0' };
    do {
        // stringStart points to either the start quote or the last
        // escaped char (the char following a '\\')
                
        // Write to searchStart here, so that when we get back to the
        // top of the loop right outside this one we search from the
        // right place.
        uint32_t stringEnd = flatStr.FindCharInSet(set, stringStart + 1);
        if (stringEnd == uint32_t(kNotFound))
            return flatStr.Length();

        if (flatStr.CharAt(stringEnd) == '\\') {
            // Hit a backslash-escaped char.  Need to skip over it.
            stringStart = stringEnd + 1;
            if (stringStart == flatStr.Length())
                return stringStart;

            // Go back to looking for the next escape or the string end
            continue;
        }

        return stringEnd;

    } while (true);

    NS_NOTREACHED("How did we get here?");
    return flatStr.Length();
}
                  

static uint32_t
net_FindMediaDelimiter(const nsCString& flatStr,
                       uint32_t searchStart,
                       char delimiter)
{
    do {
        // searchStart points to the spot from which we should start looking
        // for the delimiter.
        const char delimStr[] = { delimiter, '"', '\0' };
        uint32_t curDelimPos = flatStr.FindCharInSet(delimStr, searchStart);
        if (curDelimPos == uint32_t(kNotFound))
            return flatStr.Length();
            
        char ch = flatStr.CharAt(curDelimPos);
        if (ch == delimiter) {
            // Found delimiter
            return curDelimPos;
        }

        // We hit the start of a quoted string.  Look for its end.
        searchStart = net_FindStringEnd(flatStr, curDelimPos, ch);
        if (searchStart == flatStr.Length())
            return searchStart;

        ++searchStart;

        // searchStart now points to the first char after the end of the
        // string, so just go back to the top of the loop and look for
        // |delimiter| again.
    } while (true);

    NS_NOTREACHED("How did we get here?");
    return flatStr.Length();
}

// aOffset should be added to aCharsetStart and aCharsetEnd if this
// function sets them.
static void
net_ParseMediaType(const nsACString &aMediaTypeStr,
                   nsACString       &aContentType,
                   nsACString       &aContentCharset,
                   int32_t          aOffset,
                   bool             *aHadCharset,
                   int32_t          *aCharsetStart,
                   int32_t          *aCharsetEnd,
                   bool             aStrict)
{
    const nsCString& flatStr = PromiseFlatCString(aMediaTypeStr);
    const char* start = flatStr.get();
    const char* end = start + flatStr.Length();

    // Trim LWS leading and trailing whitespace from type.  We include '(' in
    // the trailing trim set to catch media-type comments, which are not at all
    // standard, but may occur in rare cases.
    const char* type = net_FindCharNotInSet(start, end, HTTP_LWS);
    const char* typeEnd = net_FindCharInSet(type, end, HTTP_LWS ";(");

    const char* charset = "";
    const char* charsetEnd = charset;
    int32_t charsetParamStart = 0;
    int32_t charsetParamEnd = 0;

    uint32_t consumed = typeEnd - type;

    // Iterate over parameters
    bool typeHasCharset = false;
    uint32_t paramStart = flatStr.FindChar(';', typeEnd - start);
    if (paramStart != uint32_t(kNotFound)) {
        // We have parameters.  Iterate over them.
        uint32_t curParamStart = paramStart + 1;
        do {
            uint32_t curParamEnd =
                net_FindMediaDelimiter(flatStr, curParamStart, ';');

            const char* paramName = net_FindCharNotInSet(start + curParamStart,
                                                         start + curParamEnd,
                                                         HTTP_LWS);
            static const char charsetStr[] = "charset=";
            if (PL_strncasecmp(paramName, charsetStr,
                               sizeof(charsetStr) - 1) == 0) {
                charset = paramName + sizeof(charsetStr) - 1;
                charsetEnd = start + curParamEnd;
                typeHasCharset = true;
                charsetParamStart = curParamStart - 1;
                charsetParamEnd = curParamEnd;
            }

            consumed = curParamEnd;
            curParamStart = curParamEnd + 1;
        } while (curParamStart < flatStr.Length());
    }

    bool charsetNeedsQuotedStringUnescaping = false;
    if (typeHasCharset) {
        // Trim LWS leading and trailing whitespace from charset.  We include
        // '(' in the trailing trim set to catch media-type comments, which are
        // not at all standard, but may occur in rare cases.
        charset = net_FindCharNotInSet(charset, charsetEnd, HTTP_LWS);
        if (*charset == '"') {
            charsetNeedsQuotedStringUnescaping = true;
            charsetEnd =
                start + net_FindStringEnd(flatStr, charset - start, *charset);
            charset++;
            NS_ASSERTION(charsetEnd >= charset, "Bad charset parsing");
        } else {
            charsetEnd = net_FindCharInSet(charset, charsetEnd, HTTP_LWS ";(");
        }
    }

    // if the server sent "*/*", it is meaningless, so do not store it.
    // also, if type is the same as aContentType, then just update the
    // charset.  however, if charset is empty and aContentType hasn't
    // changed, then don't wipe-out an existing aContentCharset.  We
    // also want to reject a mime-type if it does not include a slash.
    // some servers give junk after the charset parameter, which may
    // include a comma, so this check makes us a bit more tolerant.

    if (type != typeEnd &&
        memchr(type, '/', typeEnd - type) != nullptr &&
        (aStrict ? (net_FindCharNotInSet(start + consumed, end, HTTP_LWS) == end) :
                   (strncmp(type, "*/*", typeEnd - type) != 0))) {
        // Common case here is that aContentType is empty
        bool eq = !aContentType.IsEmpty() &&
            aContentType.Equals(Substring(type, typeEnd),
                                nsCaseInsensitiveCStringComparator());
        if (!eq) {
            aContentType.Assign(type, typeEnd - type);
            ToLowerCase(aContentType);
        }

        if ((!eq && *aHadCharset) || typeHasCharset) {
            *aHadCharset = true;
            if (charsetNeedsQuotedStringUnescaping) {
                // parameters using the "quoted-string" syntax need
                // backslash-escapes to be unescaped (see RFC 2616 Section 2.2)
                aContentCharset.Truncate();
                for (const char *c = charset; c != charsetEnd; c++) {
                    if (*c == '\\' && c + 1 != charsetEnd) {
                        // eat escape
                        c++;  
                    }
                    aContentCharset.Append(*c);
                }
            }
            else {
                aContentCharset.Assign(charset, charsetEnd - charset);
            }
            if (typeHasCharset) {
                *aCharsetStart = charsetParamStart + aOffset;
                *aCharsetEnd = charsetParamEnd + aOffset;
            }
        }
        // Only set a new charset position if this is a different type
        // from the last one we had and it doesn't already have a
        // charset param.  If this is the same type, we probably want
        // to leave the charset position on its first occurrence.
        if (!eq && !typeHasCharset) {
            int32_t charsetStart = int32_t(paramStart);
            if (charsetStart == kNotFound)
                charsetStart =  flatStr.Length();

            *aCharsetEnd = *aCharsetStart = charsetStart + aOffset;
        }
    }
}

#undef HTTP_LWS

void
net_ParseContentType(const nsACString &aHeaderStr,
                     nsACString       &aContentType,
                     nsACString       &aContentCharset,
                     bool             *aHadCharset)
{
    int32_t dummy1, dummy2;
    net_ParseContentType(aHeaderStr, aContentType, aContentCharset,
                         aHadCharset, &dummy1, &dummy2);
}

void
net_ParseContentType(const nsACString &aHeaderStr,
                     nsACString       &aContentType,
                     nsACString       &aContentCharset,
                     bool             *aHadCharset,
                     int32_t          *aCharsetStart,
                     int32_t          *aCharsetEnd)
{
    //
    // Augmented BNF (from RFC 2616 section 3.7):
    //
    //   header-value = media-type *( LWS "," LWS media-type )
    //   media-type   = type "/" subtype *( LWS ";" LWS parameter )
    //   type         = token
    //   subtype      = token
    //   parameter    = attribute "=" value
    //   attribute    = token
    //   value        = token | quoted-string
    //   
    //
    // Examples:
    //
    //   text/html
    //   text/html, text/html
    //   text/html,text/html; charset=ISO-8859-1
    //   text/html,text/html; charset="ISO-8859-1"
    //   text/html;charset=ISO-8859-1, text/html
    //   text/html;charset='ISO-8859-1', text/html
    //   application/octet-stream
    //

    *aHadCharset = false;
    const nsCString& flatStr = PromiseFlatCString(aHeaderStr);
    
    // iterate over media-types.  Note that ',' characters can happen
    // inside quoted strings, so we need to watch out for that.
    uint32_t curTypeStart = 0;
    do {
        // curTypeStart points to the start of the current media-type.  We want
        // to look for its end.
        uint32_t curTypeEnd =
            net_FindMediaDelimiter(flatStr, curTypeStart, ',');
        
        // At this point curTypeEnd points to the spot where the media-type
        // starting at curTypeEnd ends.  Time to parse that!
        net_ParseMediaType(Substring(flatStr, curTypeStart,
                                     curTypeEnd - curTypeStart),
                           aContentType, aContentCharset, curTypeStart,
                           aHadCharset, aCharsetStart, aCharsetEnd, false);

        // And let's move on to the next media-type
        curTypeStart = curTypeEnd + 1;
    } while (curTypeStart < flatStr.Length());
}

void
net_ParseRequestContentType(const nsACString &aHeaderStr,
                            nsACString       &aContentType,
                            nsACString       &aContentCharset,
                            bool             *aHadCharset)
{
    //
    // Augmented BNF (from RFC 7231 section 3.1.1.1):
    //
    //   media-type   = type "/" subtype *( OWS ";" OWS parameter )
    //   type         = token
    //   subtype      = token
    //   parameter    = token "=" ( token / quoted-string )
    //
    // Examples:
    //
    //   text/html
    //   text/html; charset=ISO-8859-1
    //   text/html; charset="ISO-8859-1"
    //   application/octet-stream
    //

    aContentType.Truncate();
    aContentCharset.Truncate();
    *aHadCharset = false;
    const nsCString& flatStr = PromiseFlatCString(aHeaderStr);

    // At this point curTypeEnd points to the spot where the media-type
    // starting at curTypeEnd ends.  Time to parse that!
    nsAutoCString contentType, contentCharset;
    bool hadCharset = false;
    int32_t dummy1, dummy2;
    uint32_t typeEnd = net_FindMediaDelimiter(flatStr, 0, ',');
    if (typeEnd != flatStr.Length()) {
        // We have some stuff left at the end, so this is not a valid
        // request Content-Type header.
        return;
    }
    net_ParseMediaType(flatStr, contentType, contentCharset, 0,
                       &hadCharset, &dummy1, &dummy2, true);

    aContentType = contentType;
    aContentCharset = contentCharset;
    *aHadCharset = hadCharset;
}

bool
net_IsValidHostName(const nsCSubstring &host)
{
    const char *end = host.EndReading();
    // Use explicit whitelists to select which characters we are
    // willing to send to lower-level DNS logic. This is more
    // self-documenting, and can also be slightly faster than the
    // blacklist approach, since DNS names are the common case, and
    // the commonest characters will tend to be near the start of
    // the list.

    // Whitelist for DNS names (RFC 1035) with extra characters added 
    // for pragmatic reasons "$+_"
    // see https://bugzilla.mozilla.org/show_bug.cgi?id=355181#c2
    if (net_FindCharNotInSet(host.BeginReading(), end,
                             "abcdefghijklmnopqrstuvwxyz"
                             ".-0123456789"
                             "ABCDEFGHIJKLMNOPQRSTUVWXYZ$+_") == end)
        return true;

    // Might be a valid IPv6 link-local address containing a percent sign
    nsAutoCString strhost(host);
    PRNetAddr addr;
    return PR_StringToNetAddr(strhost.get(), &addr) == PR_SUCCESS;
}

bool
net_IsValidIPv4Addr(const char *addr, int32_t addrLen)
{
    RangedPtr<const char> p(addr, addrLen);

    int32_t octet = -1;   // means no digit yet
    int32_t dotCount = 0; // number of dots in the address

    for (; addrLen; ++p, --addrLen) {
        if (*p == '.') {
            dotCount++;
            if (octet == -1) {
                // invalid octet
                return false;
            }
            octet = -1;
        } else if (*p >= '0' && *p <='9') {
            if (octet == 0) {
                // leading 0 is not allowed
                return false;
            } else if (octet == -1) {
                octet = *p - '0';
            } else {
                octet *= 10;
                octet += *p - '0';
                if (octet > 255)
                    return false;
            }
        } else {
            // invalid character
            return false;
        }
    }

    return (dotCount == 3 && octet != -1);
}

bool
net_IsValidIPv6Addr(const char *addr, int32_t addrLen)
{
    RangedPtr<const char> p(addr, addrLen);

    int32_t digits = 0; // number of digits in current block
    int32_t colons = 0; // number of colons in a row during parsing
    int32_t blocks = 0; // number of hexadecimal blocks
    bool haveZeros = false; // true if double colon is present in the address

    for (; addrLen; ++p, --addrLen) {
        if (*p == ':') {
            if (colons == 0) {
                if (digits != 0) {
                    digits = 0;
                    blocks++;
                }
            } else if (colons == 1) {
                if (haveZeros)
                    return false; // only one occurrence is allowed
                haveZeros = true;
            } else {
                // too many colons in a row
                return false;
            }
            colons++;
        } else if ((*p >= '0' && *p <= '9') || (*p >= 'a' && *p <= 'f') ||
                   (*p >= 'A' && *p <= 'F')) {
            if (colons == 1 && blocks == 0) // starts with a single colon
                return false;
            if (digits == 4) // too many digits
                return false;
            colons = 0;
            digits++;
        } else if (*p == '.') {
            // check valid IPv4 from the beginning of the last block
            if (!net_IsValidIPv4Addr(p.get() - digits, addrLen + digits))
                return false;
            return (haveZeros && blocks < 6) || (!haveZeros && blocks == 6);
        } else {
            // invalid character
            return false;
        }
    }

    if (colons == 1) // ends with a single colon
        return false;

    if (digits) // there is a block at the end
        blocks++;

    return (haveZeros && blocks < 8) || (!haveZeros && blocks == 8);
}