forked from Floorp-Projects/Floorp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnsMIMEHeaderParamImpl.cpp
1346 lines (1157 loc) · 40.4 KB
/
nsMIMEHeaderParamImpl.cpp
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
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set sw=4 ts=8 et tw=80 : */
/* 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 <string.h>
#include "prmem.h"
#include "prprf.h"
#include "plstr.h"
#include "plbase64.h"
#include "nsCRT.h"
#include "nsMemory.h"
#include "nsTArray.h"
#include "nsCOMPtr.h"
#include "nsEscape.h"
#include "nsIUTF8ConverterService.h"
#include "nsUConvCID.h"
#include "nsIServiceManager.h"
#include "nsMIMEHeaderParamImpl.h"
#include "nsReadableUtils.h"
#include "nsNativeCharsetUtils.h"
#include "nsError.h"
#include "nsIUnicodeDecoder.h"
#include "mozilla/dom/EncodingUtils.h"
using mozilla::dom::EncodingUtils;
// static functions declared below are moved from mailnews/mime/src/comi18n.cpp
static char *DecodeQ(const char *, uint32_t);
static bool Is7bitNonAsciiString(const char *, uint32_t);
static void CopyRawHeader(const char *, uint32_t, const char *, nsACString &);
static nsresult DecodeRFC2047Str(const char *, const char *, bool, nsACString&);
static nsresult internalDecodeParameter(const nsACString&, const char*,
const char*, bool, bool, nsACString&);
// XXX The chance of UTF-7 being used in the message header is really
// low, but in theory it's possible.
#define IS_7BIT_NON_ASCII_CHARSET(cset) \
(!nsCRT::strncasecmp((cset), "ISO-2022", 8) || \
!nsCRT::strncasecmp((cset), "HZ-GB", 5) || \
!nsCRT::strncasecmp((cset), "UTF-7", 5))
NS_IMPL_ISUPPORTS(nsMIMEHeaderParamImpl, nsIMIMEHeaderParam)
NS_IMETHODIMP
nsMIMEHeaderParamImpl::GetParameter(const nsACString& aHeaderVal,
const char *aParamName,
const nsACString& aFallbackCharset,
bool aTryLocaleCharset,
char **aLang, nsAString& aResult)
{
return DoGetParameter(aHeaderVal, aParamName, MIME_FIELD_ENCODING,
aFallbackCharset, aTryLocaleCharset, aLang, aResult);
}
NS_IMETHODIMP
nsMIMEHeaderParamImpl::GetParameterHTTP(const nsACString& aHeaderVal,
const char *aParamName,
const nsACString& aFallbackCharset,
bool aTryLocaleCharset,
char **aLang, nsAString& aResult)
{
return DoGetParameter(aHeaderVal, aParamName, HTTP_FIELD_ENCODING,
aFallbackCharset, aTryLocaleCharset, aLang, aResult);
}
// XXX : aTryLocaleCharset is not yet effective.
nsresult
nsMIMEHeaderParamImpl::DoGetParameter(const nsACString& aHeaderVal,
const char *aParamName,
ParamDecoding aDecoding,
const nsACString& aFallbackCharset,
bool aTryLocaleCharset,
char **aLang, nsAString& aResult)
{
aResult.Truncate();
nsresult rv;
// get parameter (decode RFC 2231/5987 when applicable, as specified by
// aDecoding (5987 being a subset of 2231) and return charset.)
nsXPIDLCString med;
nsXPIDLCString charset;
rv = DoParameterInternal(PromiseFlatCString(aHeaderVal).get(), aParamName,
aDecoding, getter_Copies(charset), aLang,
getter_Copies(med));
if (NS_FAILED(rv))
return rv;
// convert to UTF-8 after charset conversion and RFC 2047 decoding
// if necessary.
nsAutoCString str1;
rv = internalDecodeParameter(med, charset.get(), nullptr, false,
// was aDecoding == MIME_FIELD_ENCODING
// see bug 875615
true,
str1);
NS_ENSURE_SUCCESS(rv, rv);
if (!aFallbackCharset.IsEmpty())
{
nsAutoCString charset;
EncodingUtils::FindEncodingForLabel(aFallbackCharset, charset);
nsAutoCString str2;
nsCOMPtr<nsIUTF8ConverterService>
cvtUTF8(do_GetService(NS_UTF8CONVERTERSERVICE_CONTRACTID));
if (cvtUTF8 &&
NS_SUCCEEDED(cvtUTF8->ConvertStringToUTF8(str1,
PromiseFlatCString(aFallbackCharset).get(), false,
!charset.EqualsLiteral("UTF-8"),
1, str2))) {
CopyUTF8toUTF16(str2, aResult);
return NS_OK;
}
}
if (IsUTF8(str1)) {
CopyUTF8toUTF16(str1, aResult);
return NS_OK;
}
if (aTryLocaleCharset && !NS_IsNativeUTF8())
return NS_CopyNativeToUnicode(str1, aResult);
CopyASCIItoUTF16(str1, aResult);
return NS_OK;
}
// remove backslash-encoded sequences from quoted-strings
// modifies string in place, potentially shortening it
void RemoveQuotedStringEscapes(char *src)
{
char *dst = src;
for (char *c = src; *c; ++c)
{
if (c[0] == '\\' && c[1])
{
// skip backslash if not at end
++c;
}
*dst++ = *c;
}
*dst = 0;
}
// true is character is a hex digit
bool IsHexDigit(char aChar)
{
char c = aChar;
return (c >= 'a' && c <= 'f') ||
(c >= 'A' && c <= 'F') ||
(c >= '0' && c <= '9');
}
// validate that a C String containing %-escapes is syntactically valid
bool IsValidPercentEscaped(const char *aValue, int32_t len)
{
for (int32_t i = 0; i < len; i++) {
if (aValue[i] == '%') {
if (!IsHexDigit(aValue[i + 1]) || !IsHexDigit(aValue[i + 2])) {
return false;
}
}
}
return true;
}
// Support for continuations (RFC 2231, Section 3)
// only a sane number supported
#define MAX_CONTINUATIONS 999
// part of a continuation
class Continuation {
public:
Continuation(const char *aValue, uint32_t aLength,
bool aNeedsPercentDecoding, bool aWasQuotedString) {
value = aValue;
length = aLength;
needsPercentDecoding = aNeedsPercentDecoding;
wasQuotedString = aWasQuotedString;
}
Continuation() {
// empty constructor needed for nsTArray
value = 0L;
length = 0;
needsPercentDecoding = false;
wasQuotedString = false;
}
~Continuation() {}
const char *value;
uint32_t length;
bool needsPercentDecoding;
bool wasQuotedString;
};
// combine segments into a single string, returning the allocated string
// (or nullptr) while emptying the list
char *combineContinuations(nsTArray<Continuation>& aArray)
{
// Sanity check
if (aArray.Length() == 0)
return nullptr;
// Get an upper bound for the length
uint32_t length = 0;
for (uint32_t i = 0; i < aArray.Length(); i++) {
length += aArray[i].length;
}
// Allocate
char *result = (char *) moz_xmalloc(length + 1);
// Concatenate
if (result) {
*result = '\0';
for (uint32_t i = 0; i < aArray.Length(); i++) {
Continuation cont = aArray[i];
if (! cont.value) break;
char *c = result + strlen(result);
strncat(result, cont.value, cont.length);
if (cont.needsPercentDecoding) {
nsUnescape(c);
}
if (cont.wasQuotedString) {
RemoveQuotedStringEscapes(c);
}
}
// return null if empty value
if (*result == '\0') {
free(result);
result = nullptr;
}
} else {
// Handle OOM
NS_WARNING("Out of memory\n");
}
return result;
}
// add a continuation, return false on error if segment already has been seen
bool addContinuation(nsTArray<Continuation>& aArray, uint32_t aIndex,
const char *aValue, uint32_t aLength,
bool aNeedsPercentDecoding, bool aWasQuotedString)
{
if (aIndex < aArray.Length() && aArray[aIndex].value) {
NS_WARNING("duplicate RC2231 continuation segment #\n");
return false;
}
if (aIndex > MAX_CONTINUATIONS) {
NS_WARNING("RC2231 continuation segment # exceeds limit\n");
return false;
}
if (aNeedsPercentDecoding && aWasQuotedString) {
NS_WARNING("RC2231 continuation segment can't use percent encoding and quoted string form at the same time\n");
return false;
}
Continuation cont(aValue, aLength, aNeedsPercentDecoding, aWasQuotedString);
if (aArray.Length() <= aIndex) {
aArray.SetLength(aIndex + 1);
}
aArray[aIndex] = cont;
return true;
}
// parse a segment number; return -1 on error
int32_t parseSegmentNumber(const char *aValue, int32_t aLen)
{
if (aLen < 1) {
NS_WARNING("segment number missing\n");
return -1;
}
if (aLen > 1 && aValue[0] == '0') {
NS_WARNING("leading '0' not allowed in segment number\n");
return -1;
}
int32_t segmentNumber = 0;
for (int32_t i = 0; i < aLen; i++) {
if (! (aValue[i] >= '0' && aValue[i] <= '9')) {
NS_WARNING("invalid characters in segment number\n");
return -1;
}
segmentNumber *= 10;
segmentNumber += aValue[i] - '0';
if (segmentNumber > MAX_CONTINUATIONS) {
NS_WARNING("Segment number exceeds sane size\n");
return -1;
}
}
return segmentNumber;
}
// validate a given octet sequence for compliance with the specified
// encoding
bool IsValidOctetSequenceForCharset(nsACString& aCharset, const char *aOctets)
{
nsCOMPtr<nsIUTF8ConverterService> cvtUTF8(do_GetService
(NS_UTF8CONVERTERSERVICE_CONTRACTID));
if (!cvtUTF8) {
NS_WARNING("Can't get UTF8ConverterService\n");
return false;
}
nsAutoCString tmpRaw;
tmpRaw.Assign(aOctets);
nsAutoCString tmpDecoded;
nsresult rv = cvtUTF8->ConvertStringToUTF8(tmpRaw,
PromiseFlatCString(aCharset).get(),
false, false, 1, tmpDecoded);
if (rv != NS_OK) {
// we can't decode; charset may be unsupported, or the octet sequence
// is broken (illegal or incomplete octet sequence contained)
NS_WARNING("RFC2231/5987 parameter value does not decode according to specified charset\n");
return false;
}
return true;
}
// moved almost verbatim from mimehdrs.cpp
// char *
// MimeHeaders_get_parameter (const char *header_value, const char *parm_name,
// char **charset, char **language)
//
// The format of these header lines is
// <token> [ ';' <token> '=' <token-or-quoted-string> ]*
NS_IMETHODIMP
nsMIMEHeaderParamImpl::GetParameterInternal(const char *aHeaderValue,
const char *aParamName,
char **aCharset,
char **aLang,
char **aResult)
{
return DoParameterInternal(aHeaderValue, aParamName, MIME_FIELD_ENCODING,
aCharset, aLang, aResult);
}
nsresult
nsMIMEHeaderParamImpl::DoParameterInternal(const char *aHeaderValue,
const char *aParamName,
ParamDecoding aDecoding,
char **aCharset,
char **aLang,
char **aResult)
{
if (!aHeaderValue || !*aHeaderValue || !aResult)
return NS_ERROR_INVALID_ARG;
*aResult = nullptr;
if (aCharset) *aCharset = nullptr;
if (aLang) *aLang = nullptr;
nsAutoCString charset;
// change to (aDecoding != HTTP_FIELD_ENCODING) when we want to disable
// them for HTTP header fields later on, see bug 776324
bool acceptContinuations = true;
const char *str = aHeaderValue;
// skip leading white space.
for (; *str && nsCRT::IsAsciiSpace(*str); ++str)
;
const char *start = str;
// aParamName is empty. return the first (possibly) _unnamed_ 'parameter'
// For instance, return 'inline' in the following case:
// Content-Disposition: inline; filename=.....
if (!aParamName || !*aParamName)
{
for (; *str && *str != ';' && !nsCRT::IsAsciiSpace(*str); ++str)
;
if (str == start)
return NS_ERROR_FIRST_HEADER_FIELD_COMPONENT_EMPTY;
*aResult = (char *) nsMemory::Clone(start, (str - start) + 1);
NS_ENSURE_TRUE(*aResult, NS_ERROR_OUT_OF_MEMORY);
(*aResult)[str - start] = '\0'; // null-terminate
return NS_OK;
}
/* Skip forward to first ';' */
for (; *str && *str != ';' && *str != ','; ++str)
;
if (*str)
str++;
/* Skip over following whitespace */
for (; *str && nsCRT::IsAsciiSpace(*str); ++str)
;
// Some broken http servers just specify parameters
// like 'filename' without specifying disposition
// method. Rewind to the first non-white-space
// character.
if (!*str)
str = start;
// RFC2231 - The legitimate parm format can be:
// A. title=ThisIsTitle
// B. title*=us-ascii'en-us'This%20is%20wierd.
// C. title*0*=us-ascii'en'This%20is%20wierd.%20We
// title*1*=have%20to%20support%20this.
// title*2="Else..."
// D. title*0="Hey, what you think you are doing?"
// title*1="There is no charset and lang info."
// RFC5987: only A and B
// collect results for the different algorithms (plain filename,
// RFC5987/2231-encoded filename, + continuations) separately and decide
// which to use at the end
char *caseAResult = nullptr;
char *caseBResult = nullptr;
char *caseCDResult = nullptr;
// collect continuation segments
nsTArray<Continuation> segments;
// our copies of the charset parameter, kept separately as they might
// differ for the two formats
nsDependentCSubstring charsetB, charsetCD;
nsDependentCSubstring lang;
int32_t paramLen = strlen(aParamName);
while (*str) {
// find name/value
const char *nameStart = str;
const char *nameEnd = nullptr;
const char *valueStart = str;
const char *valueEnd = nullptr;
bool isQuotedString = false;
NS_ASSERTION(!nsCRT::IsAsciiSpace(*str), "should be after whitespace.");
// Skip forward to the end of this token.
for (; *str && !nsCRT::IsAsciiSpace(*str) && *str != '=' && *str != ';'; str++)
;
nameEnd = str;
int32_t nameLen = nameEnd - nameStart;
// Skip over whitespace, '=', and whitespace
while (nsCRT::IsAsciiSpace(*str)) ++str;
if (!*str) {
break;
}
if (*str++ != '=') {
// don't accept parameters without "="
goto increment_str;
}
while (nsCRT::IsAsciiSpace(*str)) ++str;
if (*str != '"') {
// The value is a token, not a quoted string.
valueStart = str;
for (valueEnd = str;
*valueEnd && !nsCRT::IsAsciiSpace (*valueEnd) && *valueEnd != ';';
valueEnd++)
;
str = valueEnd;
} else {
isQuotedString = true;
++str;
valueStart = str;
for (valueEnd = str; *valueEnd; ++valueEnd) {
if (*valueEnd == '\\' && *(valueEnd + 1))
++valueEnd;
else if (*valueEnd == '"')
break;
}
str = valueEnd;
// *valueEnd != null means that *valueEnd is quote character.
if (*valueEnd)
str++;
}
// See if this is the simplest case (case A above),
// a 'single' line value with no charset and lang.
// If so, copy it and return.
if (nameLen == paramLen &&
!nsCRT::strncasecmp(nameStart, aParamName, paramLen)) {
if (caseAResult) {
// we already have one caseA result, ignore subsequent ones
goto increment_str;
}
// if the parameter spans across multiple lines we have to strip out the
// line continuation -- jht 4/29/98
nsAutoCString tempStr(valueStart, valueEnd - valueStart);
tempStr.StripChars("\r\n");
char *res = ToNewCString(tempStr);
NS_ENSURE_TRUE(res, NS_ERROR_OUT_OF_MEMORY);
if (isQuotedString)
RemoveQuotedStringEscapes(res);
caseAResult = res;
// keep going, we may find a RFC 2231/5987 encoded alternative
}
// case B, C, and D
else if (nameLen > paramLen &&
!nsCRT::strncasecmp(nameStart, aParamName, paramLen) &&
*(nameStart + paramLen) == '*') {
// 1st char past '*'
const char *cp = nameStart + paramLen + 1;
// if param name ends in "*" we need do to RFC5987 "ext-value" decoding
bool needExtDecoding = *(nameEnd - 1) == '*';
bool caseB = nameLen == paramLen + 1;
bool caseCStart = (*cp == '0') && needExtDecoding;
// parse the segment number
int32_t segmentNumber = -1;
if (!caseB) {
int32_t segLen = (nameEnd - cp) - (needExtDecoding ? 1 : 0);
segmentNumber = parseSegmentNumber(cp, segLen);
if (segmentNumber == -1) {
acceptContinuations = false;
goto increment_str;
}
}
// CaseB and start of CaseC: requires charset and optional language
// in quotes (quotes required even if lang is blank)
if (caseB || (caseCStart && acceptContinuations)) {
// look for single quotation mark(')
const char *sQuote1 = PL_strchr(valueStart, 0x27);
const char *sQuote2 = sQuote1 ? PL_strchr(sQuote1 + 1, 0x27) : nullptr;
// Two single quotation marks must be present even in
// absence of charset and lang.
if (!sQuote1 || !sQuote2) {
NS_WARNING("Mandatory two single quotes are missing in header parameter\n");
}
const char *charsetStart = nullptr;
int32_t charsetLength = 0;
const char *langStart = nullptr;
int32_t langLength = 0;
const char *rawValStart = nullptr;
int32_t rawValLength = 0;
if (sQuote2 && sQuote1) {
// both delimiters present: charSet'lang'rawVal
rawValStart = sQuote2 + 1;
rawValLength = valueEnd - rawValStart;
langStart = sQuote1 + 1;
langLength = sQuote2 - langStart;
charsetStart = valueStart;
charsetLength = sQuote1 - charsetStart;
}
else if (sQuote1) {
// one delimiter; assume charset'rawVal
rawValStart = sQuote1 + 1;
rawValLength = valueEnd - rawValStart;
charsetStart = valueStart;
charsetLength = sQuote1 - valueStart;
}
else {
// no delimiter: just rawVal
rawValStart = valueStart;
rawValLength = valueEnd - valueStart;
}
if (langLength != 0) {
lang.Assign(langStart, langLength);
}
// keep the charset for later
if (caseB) {
charsetB.Assign(charsetStart, charsetLength);
} else {
// if caseCorD
charsetCD.Assign(charsetStart, charsetLength);
}
// non-empty value part
if (rawValLength > 0) {
if (!caseBResult && caseB) {
if (!IsValidPercentEscaped(rawValStart, rawValLength)) {
goto increment_str;
}
// allocate buffer for the raw value
char *tmpResult = (char *) nsMemory::Clone(rawValStart, rawValLength + 1);
if (!tmpResult) {
goto increment_str;
}
*(tmpResult + rawValLength) = 0;
nsUnescape(tmpResult);
caseBResult = tmpResult;
} else {
// caseC
bool added = addContinuation(segments, 0, rawValStart,
rawValLength, needExtDecoding,
isQuotedString);
if (!added) {
// continuation not added, stop processing them
acceptContinuations = false;
}
}
}
} // end of if-block : title*0*= or title*=
// caseD: a line of multiline param with no need for unescaping : title*[0-9]=
// or 2nd or later lines of a caseC param : title*[1-9]*=
else if (acceptContinuations && segmentNumber != -1) {
uint32_t valueLength = valueEnd - valueStart;
bool added = addContinuation(segments, segmentNumber, valueStart,
valueLength, needExtDecoding,
isQuotedString);
if (!added) {
// continuation not added, stop processing them
acceptContinuations = false;
}
} // end of if-block : title*[0-9]= or title*[1-9]*=
}
// str now points after the end of the value.
// skip over whitespace, ';', whitespace.
increment_str:
while (nsCRT::IsAsciiSpace(*str)) ++str;
if (*str == ';') {
++str;
} else {
// stop processing the header field; either we are done or the
// separator was missing
break;
}
while (nsCRT::IsAsciiSpace(*str)) ++str;
}
caseCDResult = combineContinuations(segments);
if (caseBResult && !charsetB.IsEmpty()) {
// check that the 2231/5987 result decodes properly given the
// specified character set
if (!IsValidOctetSequenceForCharset(charsetB, caseBResult))
caseBResult = nullptr;
}
if (caseCDResult && !charsetCD.IsEmpty()) {
// check that the 2231/5987 result decodes properly given the
// specified character set
if (!IsValidOctetSequenceForCharset(charsetCD, caseCDResult))
caseCDResult = nullptr;
}
if (caseBResult) {
// prefer simple 5987 format over 2231 with continuations
*aResult = caseBResult;
caseBResult = nullptr;
charset.Assign(charsetB);
}
else if (caseCDResult) {
// prefer 2231/5987 with or without continuations over plain format
*aResult = caseCDResult;
caseCDResult = nullptr;
charset.Assign(charsetCD);
}
else if (caseAResult) {
*aResult = caseAResult;
caseAResult = nullptr;
}
// free unused stuff
free(caseAResult);
free(caseBResult);
free(caseCDResult);
// if we have a result
if (*aResult) {
// then return charset and lang as well
if (aLang && !lang.IsEmpty()) {
uint32_t len = lang.Length();
*aLang = (char *) nsMemory::Clone(lang.BeginReading(), len + 1);
if (*aLang) {
*(*aLang + len) = 0;
}
}
if (aCharset && !charset.IsEmpty()) {
uint32_t len = charset.Length();
*aCharset = (char *) nsMemory::Clone(charset.BeginReading(), len + 1);
if (*aCharset) {
*(*aCharset + len) = 0;
}
}
}
return *aResult ? NS_OK : NS_ERROR_INVALID_ARG;
}
nsresult
internalDecodeRFC2047Header(const char* aHeaderVal, const char* aDefaultCharset,
bool aOverrideCharset, bool aEatContinuations,
nsACString& aResult)
{
aResult.Truncate();
if (!aHeaderVal)
return NS_ERROR_INVALID_ARG;
if (!*aHeaderVal)
return NS_OK;
// If aHeaderVal is RFC 2047 encoded or is not a UTF-8 string but
// aDefaultCharset is specified, decodes RFC 2047 encoding and converts
// to UTF-8. Otherwise, just strips away CRLF.
if (PL_strstr(aHeaderVal, "=?") ||
(aDefaultCharset && (!IsUTF8(nsDependentCString(aHeaderVal)) ||
Is7bitNonAsciiString(aHeaderVal, strlen(aHeaderVal))))) {
DecodeRFC2047Str(aHeaderVal, aDefaultCharset, aOverrideCharset, aResult);
} else if (aEatContinuations &&
(PL_strchr(aHeaderVal, '\n') || PL_strchr(aHeaderVal, '\r'))) {
aResult = aHeaderVal;
} else {
aEatContinuations = false;
aResult = aHeaderVal;
}
if (aEatContinuations) {
nsAutoCString temp(aResult);
temp.ReplaceSubstring("\n\t", " ");
temp.ReplaceSubstring("\r\t", " ");
temp.StripChars("\r\n");
aResult = temp;
}
return NS_OK;
}
NS_IMETHODIMP
nsMIMEHeaderParamImpl::DecodeRFC2047Header(const char* aHeaderVal,
const char* aDefaultCharset,
bool aOverrideCharset,
bool aEatContinuations,
nsACString& aResult)
{
return internalDecodeRFC2047Header(aHeaderVal, aDefaultCharset,
aOverrideCharset, aEatContinuations,
aResult);
}
// true if the character is allowed in a RFC 5987 value
// see RFC 5987, Section 3.2.1, "attr-char"
bool IsRFC5987AttrChar(char aChar)
{
char c = aChar;
return (c >= 'a' && c <= 'z') ||
(c >= 'A' && c <= 'Z') ||
(c >= '0' && c <= '9') ||
(c == '!' || c == '#' || c == '$' || c == '&' ||
c == '+' || c == '-' || c == '.' || c == '^' ||
c == '_' || c == '`' || c == '|' || c == '~');
}
// percent-decode a value
// returns false on failure
bool PercentDecode(nsACString& aValue)
{
char *c = (char *) moz_xmalloc(aValue.Length() + 1);
if (!c) {
return false;
}
strcpy(c, PromiseFlatCString(aValue).get());
nsUnescape(c);
aValue.Assign(c);
free(c);
return true;
}
// Decode a parameter value using the encoding defined in RFC 5987
//
// charset "'" [ language ] "'" value-chars
NS_IMETHODIMP
nsMIMEHeaderParamImpl::DecodeRFC5987Param(const nsACString& aParamVal,
nsACString& aLang,
nsAString& aResult)
{
nsAutoCString charset;
nsAutoCString language;
nsAutoCString value;
uint32_t delimiters = 0;
const char *encoded = PromiseFlatCString(aParamVal).get();
const char *c = encoded;
while (*c) {
char tc = *c++;
if (tc == '\'') {
// single quote
delimiters++;
} else if (((unsigned char)tc) >= 128) {
// fail early, not ASCII
NS_WARNING("non-US-ASCII character in RFC5987-encoded param");
return NS_ERROR_INVALID_ARG;
} else {
if (delimiters == 0) {
// valid characters are checked later implicitly
charset.Append(tc);
} else if (delimiters == 1) {
// no value checking for now
language.Append(tc);
} else if (delimiters == 2) {
if (IsRFC5987AttrChar(tc)) {
value.Append(tc);
} else if (tc == '%') {
if (!IsHexDigit(c[0]) || !IsHexDigit(c[1])) {
// we expect two more characters
NS_WARNING("broken %-escape in RFC5987-encoded param");
return NS_ERROR_INVALID_ARG;
}
value.Append(tc);
// we consume two more
value.Append(*c++);
value.Append(*c++);
} else {
// character not allowed here
NS_WARNING("invalid character in RFC5987-encoded param");
return NS_ERROR_INVALID_ARG;
}
}
}
}
if (delimiters != 2) {
NS_WARNING("missing delimiters in RFC5987-encoded param");
return NS_ERROR_INVALID_ARG;
}
// abort early for unsupported encodings
if (!charset.LowerCaseEqualsLiteral("utf-8")) {
NS_WARNING("unsupported charset in RFC5987-encoded param");
return NS_ERROR_INVALID_ARG;
}
// percent-decode
if (!PercentDecode(value)) {
return NS_ERROR_OUT_OF_MEMORY;
}
// return the encoding
aLang.Assign(language);
// finally convert octet sequence to UTF-8 and be done
nsresult rv = NS_OK;
nsCOMPtr<nsIUTF8ConverterService> cvtUTF8 =
do_GetService(NS_UTF8CONVERTERSERVICE_CONTRACTID, &rv);
NS_ENSURE_SUCCESS(rv, rv);
nsAutoCString utf8;
rv = cvtUTF8->ConvertStringToUTF8(value, charset.get(), true, false, 1, utf8);
NS_ENSURE_SUCCESS(rv, rv);
CopyUTF8toUTF16(utf8, aResult);
return NS_OK;
}
nsresult
internalDecodeParameter(const nsACString& aParamValue, const char* aCharset,
const char* aDefaultCharset, bool aOverrideCharset,
bool aDecode2047, nsACString& aResult)
{
aResult.Truncate();
// If aCharset is given, aParamValue was obtained from RFC2231/5987
// encoding and we're pretty sure that it's in aCharset.
if (aCharset && *aCharset)
{
nsCOMPtr<nsIUTF8ConverterService> cvtUTF8(do_GetService(NS_UTF8CONVERTERSERVICE_CONTRACTID));
if (cvtUTF8)
return cvtUTF8->ConvertStringToUTF8(aParamValue, aCharset,
true, true, 1, aResult);
}
const nsAFlatCString& param = PromiseFlatCString(aParamValue);
nsAutoCString unQuoted;
nsACString::const_iterator s, e;
param.BeginReading(s);
param.EndReading(e);
// strip '\' when used to quote CR, LF, '"' and '\'
for ( ; s != e; ++s) {
if ((*s == '\\')) {
if (++s == e) {
--s; // '\' is at the end. move back and append '\'.
}
else if (*s != nsCRT::CR && *s != nsCRT::LF && *s != '"' && *s != '\\') {
--s; // '\' is not foll. by CR,LF,'"','\'. move back and append '\'
}
// else : skip '\' and append the quoted character.
}
unQuoted.Append(*s);
}
aResult = unQuoted;
nsresult rv = NS_OK;
if (aDecode2047) {
nsAutoCString decoded;
// Try RFC 2047 encoding, instead.
rv = internalDecodeRFC2047Header(unQuoted.get(), aDefaultCharset,
aOverrideCharset, true, decoded);
if (NS_SUCCEEDED(rv) && !decoded.IsEmpty())
aResult = decoded;
}
return rv;
}
NS_IMETHODIMP
nsMIMEHeaderParamImpl::DecodeParameter(const nsACString& aParamValue,
const char* aCharset,
const char* aDefaultCharset,
bool aOverrideCharset,
nsACString& aResult)
{
return internalDecodeParameter(aParamValue, aCharset, aDefaultCharset,
aOverrideCharset, true, aResult);
}
#define ISHEXCHAR(c) \
((0x30 <= uint8_t(c) && uint8_t(c) <= 0x39) || \
(0x41 <= uint8_t(c) && uint8_t(c) <= 0x46) || \
(0x61 <= uint8_t(c) && uint8_t(c) <= 0x66))
// Decode Q encoding (RFC 2047).
// static
char *DecodeQ(const char *in, uint32_t length)
{
char *out, *dest = 0;
out = dest = (char *)PR_Calloc(length + 1, sizeof(char));
if (dest == nullptr)
return nullptr;
while (length > 0) {
unsigned c = 0;
switch (*in) {
case '=':
// check if |in| in the form of '=hh' where h is [0-9a-fA-F].
if (length < 3 || !ISHEXCHAR(in[1]) || !ISHEXCHAR(in[2]))
goto badsyntax;
PR_sscanf(in + 1, "%2X", &c);
*out++ = (char) c;
in += 3;
length -= 3;
break;
case '_':
*out++ = ' ';
in++;
length--;
break;
default:
if (*in & 0x80) goto badsyntax;