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
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
|
// Copyright (c) 2011 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
// The rules for header parsing were borrowed from Firefox:
// http://lxr.mozilla.org/seamonkey/source/netwerk/protocol/http/src/nsHttpResponseHead.cpp
// The rules for parsing content-types were also borrowed from Firefox:
// http://lxr.mozilla.org/mozilla/source/netwerk/base/src/nsURLHelper.cpp#834
#include "net/http/http_response_headers.h"
#include <algorithm>
#include "base/logging.h"
#include "base/metrics/histogram.h"
#include "base/pickle.h"
#include "base/string_number_conversions.h"
#include "base/string_piece.h"
#include "base/string_util.h"
#include "base/time.h"
#include "net/base/escape.h"
#include "net/http/http_util.h"
using base::StringPiece;
using base::Time;
using base::TimeDelta;
namespace net {
//-----------------------------------------------------------------------------
namespace {
// These headers are RFC 2616 hop-by-hop headers;
// not to be stored by caches.
const char* const kHopByHopResponseHeaders[] = {
"connection",
"proxy-connection",
"keep-alive",
"trailer",
"transfer-encoding",
"upgrade"
};
// These headers are challenge response headers;
// not to be stored by caches.
const char* const kChallengeResponseHeaders[] = {
"www-authenticate",
"proxy-authenticate"
};
// These headers are cookie setting headers;
// not to be stored by caches or disclosed otherwise.
const char* const kCookieResponseHeaders[] = {
"set-cookie",
"set-cookie2"
};
// These response headers are not copied from a 304/206 response to the cached
// response headers. This list is based on Mozilla's nsHttpResponseHead.cpp.
const char* const kNonUpdatedHeaders[] = {
"connection",
"proxy-connection",
"keep-alive",
"www-authenticate",
"proxy-authenticate",
"trailer",
"transfer-encoding",
"upgrade",
// these should never change:
"content-location",
"content-md5",
"etag",
// assume cache-control: no-transform
"content-encoding",
"content-range",
"content-type",
// some broken microsoft servers send 'content-length: 0' with 304s
"content-length"
};
bool ShouldUpdateHeader(const std::string::const_iterator& name_begin,
const std::string::const_iterator& name_end) {
for (size_t i = 0; i < arraysize(kNonUpdatedHeaders); ++i) {
if (LowerCaseEqualsASCII(name_begin, name_end, kNonUpdatedHeaders[i]))
return false;
}
return true;
}
// Functions for histogram initialization. The code 0 is put in the
// response map to track response codes that are invalid.
// TODO(gavinp): Greatly prune the collected codes once we learn which
// ones are not sent in practice, to reduce upload size & memory use.
enum {
HISTOGRAM_MIN_HTTP_RESPONSE_CODE = 100,
HISTOGRAM_MAX_HTTP_RESPONSE_CODE = 599,
};
std::vector<int> GetAllHttpResponseCodes() {
std::vector<int> codes;
codes.reserve(
HISTOGRAM_MAX_HTTP_RESPONSE_CODE - HISTOGRAM_MIN_HTTP_RESPONSE_CODE + 2);
codes.push_back(0);
for (int i = HISTOGRAM_MIN_HTTP_RESPONSE_CODE;
i <= HISTOGRAM_MAX_HTTP_RESPONSE_CODE; ++i)
codes.push_back(i);
return codes;
}
int MapHttpResponseCode(int code) {
if (HISTOGRAM_MIN_HTTP_RESPONSE_CODE <= code &&
code <= HISTOGRAM_MAX_HTTP_RESPONSE_CODE)
return code;
return 0;
}
void CheckDoesNotHaveEmbededNulls(const std::string& str) {
// Care needs to be taken when adding values to the raw headers string to
// make sure it does not contain embeded NULLs. Any embeded '\0' may be
// understood as line terminators and change how header lines get tokenized.
CHECK(str.find('\0') == std::string::npos);
}
} // namespace
struct HttpResponseHeaders::ParsedHeader {
// A header "continuation" contains only a subsequent value for the
// preceding header. (Header values are comma separated.)
bool is_continuation() const { return name_begin == name_end; }
std::string::const_iterator name_begin;
std::string::const_iterator name_end;
std::string::const_iterator value_begin;
std::string::const_iterator value_end;
};
//-----------------------------------------------------------------------------
HttpResponseHeaders::HttpResponseHeaders(const std::string& raw_input)
: response_code_(-1) {
Parse(raw_input);
// The most important thing to do with this histogram is find out
// the existence of unusual HTTP response codes. As it happens
// right now, there aren't double-constructions of response headers
// using this constructor, so our counts should also be accurate,
// without instantiating the histogram in two places. It is also
// important that this histogram not collect data in the other
// constructor, which rebuilds an histogram from a pickle, since
// that would actually create a double call between the original
// HttpResponseHeader that was serialized, and initialization of the
// new object from that pickle.
UMA_HISTOGRAM_CUSTOM_ENUMERATION("Net.HttpResponseCode",
MapHttpResponseCode(response_code_),
// Note the third argument is only
// evaluated once, see macro
// definition for details.
GetAllHttpResponseCodes());
}
HttpResponseHeaders::HttpResponseHeaders(const Pickle& pickle, void** iter)
: response_code_(-1) {
std::string raw_input;
if (pickle.ReadString(iter, &raw_input))
Parse(raw_input);
}
void HttpResponseHeaders::Persist(Pickle* pickle, PersistOptions options) {
if (options == PERSIST_RAW) {
pickle->WriteString(raw_headers_);
return; // Done.
}
HeaderSet filter_headers;
// Construct set of headers to filter out based on options.
if ((options & PERSIST_SANS_NON_CACHEABLE) == PERSIST_SANS_NON_CACHEABLE)
AddNonCacheableHeaders(&filter_headers);
if ((options & PERSIST_SANS_COOKIES) == PERSIST_SANS_COOKIES)
AddCookieHeaders(&filter_headers);
if ((options & PERSIST_SANS_CHALLENGES) == PERSIST_SANS_CHALLENGES)
AddChallengeHeaders(&filter_headers);
if ((options & PERSIST_SANS_HOP_BY_HOP) == PERSIST_SANS_HOP_BY_HOP)
AddHopByHopHeaders(&filter_headers);
if ((options & PERSIST_SANS_RANGES) == PERSIST_SANS_RANGES)
AddHopContentRangeHeaders(&filter_headers);
std::string blob;
blob.reserve(raw_headers_.size());
// This copies the status line w/ terminator null.
// Note raw_headers_ has embedded nulls instead of \n,
// so this just copies the first header line.
blob.assign(raw_headers_.c_str(), strlen(raw_headers_.c_str()) + 1);
for (size_t i = 0; i < parsed_.size(); ++i) {
DCHECK(!parsed_[i].is_continuation());
// Locate the start of the next header.
size_t k = i;
while (++k < parsed_.size() && parsed_[k].is_continuation()) {}
--k;
std::string header_name(parsed_[i].name_begin, parsed_[i].name_end);
StringToLowerASCII(&header_name);
if (filter_headers.find(header_name) == filter_headers.end()) {
// Make sure there is a null after the value.
blob.append(parsed_[i].name_begin, parsed_[k].value_end);
blob.push_back('\0');
}
i = k;
}
blob.push_back('\0');
pickle->WriteString(blob);
}
void HttpResponseHeaders::Update(const HttpResponseHeaders& new_headers) {
DCHECK(new_headers.response_code() == 304 ||
new_headers.response_code() == 206);
// Copy up to the null byte. This just copies the status line.
std::string new_raw_headers(raw_headers_.c_str());
new_raw_headers.push_back('\0');
HeaderSet updated_headers;
// NOTE: we write the new headers then the old headers for convenience. The
// order should not matter.
// Figure out which headers we want to take from new_headers:
for (size_t i = 0; i < new_headers.parsed_.size(); ++i) {
const HeaderList& new_parsed = new_headers.parsed_;
DCHECK(!new_parsed[i].is_continuation());
// Locate the start of the next header.
size_t k = i;
while (++k < new_parsed.size() && new_parsed[k].is_continuation()) {}
--k;
const std::string::const_iterator& name_begin = new_parsed[i].name_begin;
const std::string::const_iterator& name_end = new_parsed[i].name_end;
if (ShouldUpdateHeader(name_begin, name_end)) {
std::string name(name_begin, name_end);
StringToLowerASCII(&name);
updated_headers.insert(name);
// Preserve this header line in the merged result, making sure there is
// a null after the value.
new_raw_headers.append(name_begin, new_parsed[k].value_end);
new_raw_headers.push_back('\0');
}
i = k;
}
// Now, build the new raw headers.
MergeWithHeaders(new_raw_headers, updated_headers);
}
void HttpResponseHeaders::MergeWithHeaders(const std::string& raw_headers,
const HeaderSet& headers_to_remove) {
std::string new_raw_headers(raw_headers);
for (size_t i = 0; i < parsed_.size(); ++i) {
DCHECK(!parsed_[i].is_continuation());
// Locate the start of the next header.
size_t k = i;
while (++k < parsed_.size() && parsed_[k].is_continuation()) {}
--k;
std::string name(parsed_[i].name_begin, parsed_[i].name_end);
StringToLowerASCII(&name);
if (headers_to_remove.find(name) == headers_to_remove.end()) {
// It's ok to preserve this header in the final result.
new_raw_headers.append(parsed_[i].name_begin, parsed_[k].value_end);
new_raw_headers.push_back('\0');
}
i = k;
}
new_raw_headers.push_back('\0');
// Make this object hold the new data.
raw_headers_.clear();
parsed_.clear();
Parse(new_raw_headers);
}
void HttpResponseHeaders::MergeWithHeadersWithValue(
const std::string& raw_headers,
const std::string& header_to_remove_name,
const std::string& header_to_remove_value) {
std::string header_to_remove_name_lowercase(header_to_remove_name);
StringToLowerASCII(&header_to_remove_name_lowercase);
std::string new_raw_headers(raw_headers);
for (size_t i = 0; i < parsed_.size(); ++i) {
DCHECK(!parsed_[i].is_continuation());
// Locate the start of the next header.
size_t k = i;
while (++k < parsed_.size() && parsed_[k].is_continuation()) {}
--k;
std::string name(parsed_[i].name_begin, parsed_[i].name_end);
StringToLowerASCII(&name);
std::string value(parsed_[i].value_begin, parsed_[i].value_end);
if (name != header_to_remove_name_lowercase ||
value != header_to_remove_value) {
// It's ok to preserve this header in the final result.
new_raw_headers.append(parsed_[i].name_begin, parsed_[k].value_end);
new_raw_headers.push_back('\0');
}
i = k;
}
new_raw_headers.push_back('\0');
// Make this object hold the new data.
raw_headers_.clear();
parsed_.clear();
Parse(new_raw_headers);
}
void HttpResponseHeaders::RemoveHeader(const std::string& name) {
// Copy up to the null byte. This just copies the status line.
std::string new_raw_headers(raw_headers_.c_str());
new_raw_headers.push_back('\0');
std::string lowercase_name(name);
StringToLowerASCII(&lowercase_name);
HeaderSet to_remove;
to_remove.insert(lowercase_name);
MergeWithHeaders(new_raw_headers, to_remove);
}
void HttpResponseHeaders::RemoveHeaderWithValue(const std::string& name,
const std::string& value) {
// Copy up to the null byte. This just copies the status line.
std::string new_raw_headers(raw_headers_.c_str());
new_raw_headers.push_back('\0');
MergeWithHeadersWithValue(new_raw_headers, name, value);
}
void HttpResponseHeaders::AddHeader(const std::string& header) {
CheckDoesNotHaveEmbededNulls(header);
DCHECK_EQ('\0', raw_headers_[raw_headers_.size() - 2]);
DCHECK_EQ('\0', raw_headers_[raw_headers_.size() - 1]);
// Don't copy the last null.
std::string new_raw_headers(raw_headers_, 0, raw_headers_.size() - 1);
new_raw_headers.append(header);
new_raw_headers.push_back('\0');
new_raw_headers.push_back('\0');
// Make this object hold the new data.
raw_headers_.clear();
parsed_.clear();
Parse(new_raw_headers);
}
void HttpResponseHeaders::ReplaceStatusLine(const std::string& new_status) {
CheckDoesNotHaveEmbededNulls(new_status);
// Copy up to the null byte. This just copies the status line.
std::string new_raw_headers(new_status);
new_raw_headers.push_back('\0');
HeaderSet empty_to_remove;
MergeWithHeaders(new_raw_headers, empty_to_remove);
}
void HttpResponseHeaders::Parse(const std::string& raw_input) {
raw_headers_.reserve(raw_input.size());
// ParseStatusLine adds a normalized status line to raw_headers_
std::string::const_iterator line_begin = raw_input.begin();
std::string::const_iterator line_end =
std::find(line_begin, raw_input.end(), '\0');
// has_headers = true, if there is any data following the status line.
// Used by ParseStatusLine() to decide if a HTTP/0.9 is really a HTTP/1.0.
bool has_headers = (line_end != raw_input.end() &&
(line_end + 1) != raw_input.end() &&
*(line_end + 1) != '\0');
ParseStatusLine(line_begin, line_end, has_headers);
raw_headers_.push_back('\0'); // Terminate status line with a null.
if (line_end == raw_input.end()) {
raw_headers_.push_back('\0'); // Ensure the headers end with a double null.
DCHECK_EQ('\0', raw_headers_[raw_headers_.size() - 2]);
DCHECK_EQ('\0', raw_headers_[raw_headers_.size() - 1]);
return;
}
// Including a terminating null byte.
size_t status_line_len = raw_headers_.size();
// Now, we add the rest of the raw headers to raw_headers_, and begin parsing
// it (to populate our parsed_ vector).
raw_headers_.append(line_end + 1, raw_input.end());
// Ensure the headers end with a double null.
while (raw_headers_.size() < 2 ||
raw_headers_[raw_headers_.size() - 2] != '\0' ||
raw_headers_[raw_headers_.size() - 1] != '\0') {
raw_headers_.push_back('\0');
}
// Adjust to point at the null byte following the status line
line_end = raw_headers_.begin() + status_line_len - 1;
HttpUtil::HeadersIterator headers(line_end + 1, raw_headers_.end(),
std::string(1, '\0'));
while (headers.GetNext()) {
AddHeader(headers.name_begin(),
headers.name_end(),
headers.values_begin(),
headers.values_end());
}
DCHECK_EQ('\0', raw_headers_[raw_headers_.size() - 2]);
DCHECK_EQ('\0', raw_headers_[raw_headers_.size() - 1]);
}
// Append all of our headers to the final output string.
void HttpResponseHeaders::GetNormalizedHeaders(std::string* output) const {
// copy up to the null byte. this just copies the status line.
output->assign(raw_headers_.c_str());
// headers may appear multiple times (not necessarily in succession) in the
// header data, so we build a map from header name to generated header lines.
// to preserve the order of the original headers, the actual values are kept
// in a separate list. finally, the list of headers is flattened to form
// the normalized block of headers.
//
// NOTE: We take special care to preserve the whitespace around any commas
// that may occur in the original response headers. Because our consumer may
// be a web app, we cannot be certain of the semantics of commas despite the
// fact that RFC 2616 says that they should be regarded as value separators.
//
typedef base::hash_map<std::string, size_t> HeadersMap;
HeadersMap headers_map;
HeadersMap::iterator iter = headers_map.end();
std::vector<std::string> headers;
for (size_t i = 0; i < parsed_.size(); ++i) {
DCHECK(!parsed_[i].is_continuation());
std::string name(parsed_[i].name_begin, parsed_[i].name_end);
std::string lower_name = StringToLowerASCII(name);
iter = headers_map.find(lower_name);
if (iter == headers_map.end()) {
iter = headers_map.insert(
HeadersMap::value_type(lower_name, headers.size())).first;
headers.push_back(name + ": ");
} else {
headers[iter->second].append(", ");
}
std::string::const_iterator value_begin = parsed_[i].value_begin;
std::string::const_iterator value_end = parsed_[i].value_end;
while (++i < parsed_.size() && parsed_[i].is_continuation())
value_end = parsed_[i].value_end;
--i;
headers[iter->second].append(value_begin, value_end);
}
for (size_t i = 0; i < headers.size(); ++i) {
output->push_back('\n');
output->append(headers[i]);
}
output->push_back('\n');
}
bool HttpResponseHeaders::GetNormalizedHeader(const std::string& name,
std::string* value) const {
// If you hit this assertion, please use EnumerateHeader instead!
DCHECK(!HttpUtil::IsNonCoalescingHeader(name));
value->clear();
bool found = false;
size_t i = 0;
while (i < parsed_.size()) {
i = FindHeader(i, name);
if (i == std::string::npos)
break;
found = true;
if (!value->empty())
value->append(", ");
std::string::const_iterator value_begin = parsed_[i].value_begin;
std::string::const_iterator value_end = parsed_[i].value_end;
while (++i < parsed_.size() && parsed_[i].is_continuation())
value_end = parsed_[i].value_end;
value->append(value_begin, value_end);
}
return found;
}
std::string HttpResponseHeaders::GetStatusLine() const {
// copy up to the null byte.
return std::string(raw_headers_.c_str());
}
std::string HttpResponseHeaders::GetStatusText() const {
// GetStatusLine() is already normalized, so it has the format:
// <http_version> SP <response_code> SP <status_text>
std::string status_text = GetStatusLine();
std::string::const_iterator begin = status_text.begin();
std::string::const_iterator end = status_text.end();
for (int i = 0; i < 2; ++i)
begin = std::find(begin, end, ' ') + 1;
return std::string(begin, end);
}
bool HttpResponseHeaders::EnumerateHeaderLines(void** iter,
std::string* name,
std::string* value) const {
size_t i = reinterpret_cast<size_t>(*iter);
if (i == parsed_.size())
return false;
DCHECK(!parsed_[i].is_continuation());
name->assign(parsed_[i].name_begin, parsed_[i].name_end);
std::string::const_iterator value_begin = parsed_[i].value_begin;
std::string::const_iterator value_end = parsed_[i].value_end;
while (++i < parsed_.size() && parsed_[i].is_continuation())
value_end = parsed_[i].value_end;
value->assign(value_begin, value_end);
*iter = reinterpret_cast<void*>(i);
return true;
}
bool HttpResponseHeaders::EnumerateHeader(void** iter, const std::string& name,
std::string* value) const {
size_t i;
if (!iter || !*iter) {
i = FindHeader(0, name);
} else {
i = reinterpret_cast<size_t>(*iter);
if (i >= parsed_.size()) {
i = std::string::npos;
} else if (!parsed_[i].is_continuation()) {
i = FindHeader(i, name);
}
}
if (i == std::string::npos) {
value->clear();
return false;
}
if (iter)
*iter = reinterpret_cast<void*>(i + 1);
value->assign(parsed_[i].value_begin, parsed_[i].value_end);
return true;
}
bool HttpResponseHeaders::HasHeaderValue(const std::string& name,
const std::string& value) const {
// The value has to be an exact match. This is important since
// 'cache-control: no-cache' != 'cache-control: no-cache="foo"'
void* iter = NULL;
std::string temp;
while (EnumerateHeader(&iter, name, &temp)) {
if (value.size() == temp.size() &&
std::equal(temp.begin(), temp.end(), value.begin(),
base::CaseInsensitiveCompare<char>()))
return true;
}
return false;
}
bool HttpResponseHeaders::HasHeader(const std::string& name) const {
return FindHeader(0, name) != std::string::npos;
}
HttpResponseHeaders::HttpResponseHeaders() : response_code_(-1) {
}
HttpResponseHeaders::~HttpResponseHeaders() {
}
// Note: this implementation implicitly assumes that line_end points at a valid
// sentinel character (such as '\0').
// static
HttpVersion HttpResponseHeaders::ParseVersion(
std::string::const_iterator line_begin,
std::string::const_iterator line_end) {
std::string::const_iterator p = line_begin;
// RFC2616 sec 3.1: HTTP-Version = "HTTP" "/" 1*DIGIT "." 1*DIGIT
// TODO: (1*DIGIT apparently means one or more digits, but we only handle 1).
// TODO: handle leading zeros, which is allowed by the rfc1616 sec 3.1.
if ((line_end - p < 4) || !LowerCaseEqualsASCII(p, p + 4, "http")) {
DVLOG(1) << "missing status line";
return HttpVersion();
}
p += 4;
if (p >= line_end || *p != '/') {
DVLOG(1) << "missing version";
return HttpVersion();
}
std::string::const_iterator dot = std::find(p, line_end, '.');
if (dot == line_end) {
DVLOG(1) << "malformed version";
return HttpVersion();
}
++p; // from / to first digit.
++dot; // from . to second digit.
if (!(*p >= '0' && *p <= '9' && *dot >= '0' && *dot <= '9')) {
DVLOG(1) << "malformed version number";
return HttpVersion();
}
uint16 major = *p - '0';
uint16 minor = *dot - '0';
return HttpVersion(major, minor);
}
// Note: this implementation implicitly assumes that line_end points at a valid
// sentinel character (such as '\0').
void HttpResponseHeaders::ParseStatusLine(
std::string::const_iterator line_begin,
std::string::const_iterator line_end,
bool has_headers) {
// Extract the version number
parsed_http_version_ = ParseVersion(line_begin, line_end);
// Clamp the version number to one of: {0.9, 1.0, 1.1}
if (parsed_http_version_ == HttpVersion(0, 9) && !has_headers) {
http_version_ = HttpVersion(0, 9);
raw_headers_ = "HTTP/0.9";
} else if (parsed_http_version_ >= HttpVersion(1, 1)) {
http_version_ = HttpVersion(1, 1);
raw_headers_ = "HTTP/1.1";
} else {
// Treat everything else like HTTP 1.0
http_version_ = HttpVersion(1, 0);
raw_headers_ = "HTTP/1.0";
}
if (parsed_http_version_ != http_version_) {
DVLOG(1) << "assuming HTTP/" << http_version_.major_value() << "."
<< http_version_.minor_value();
}
// TODO(eroman): this doesn't make sense if ParseVersion failed.
std::string::const_iterator p = std::find(line_begin, line_end, ' ');
if (p == line_end) {
DVLOG(1) << "missing response status; assuming 200 OK";
raw_headers_.append(" 200 OK");
response_code_ = 200;
return;
}
// Skip whitespace.
while (*p == ' ')
++p;
std::string::const_iterator code = p;
while (*p >= '0' && *p <= '9')
++p;
if (p == code) {
DVLOG(1) << "missing response status number; assuming 200";
raw_headers_.append(" 200 OK");
response_code_ = 200;
return;
}
raw_headers_.push_back(' ');
raw_headers_.append(code, p);
raw_headers_.push_back(' ');
base::StringToInt(StringPiece(code, p), &response_code_);
// Skip whitespace.
while (*p == ' ')
++p;
// Trim trailing whitespace.
while (line_end > p && line_end[-1] == ' ')
--line_end;
if (p == line_end) {
DVLOG(1) << "missing response status text; assuming OK";
// Not super critical what we put here. Just use "OK"
// even if it isn't descriptive of response_code_.
raw_headers_.append("OK");
} else {
raw_headers_.append(p, line_end);
}
}
size_t HttpResponseHeaders::FindHeader(size_t from,
const std::string& search) const {
for (size_t i = from; i < parsed_.size(); ++i) {
if (parsed_[i].is_continuation())
continue;
const std::string::const_iterator& name_begin = parsed_[i].name_begin;
const std::string::const_iterator& name_end = parsed_[i].name_end;
if (static_cast<size_t>(name_end - name_begin) == search.size() &&
std::equal(name_begin, name_end, search.begin(),
base::CaseInsensitiveCompare<char>()))
return i;
}
return std::string::npos;
}
void HttpResponseHeaders::AddHeader(std::string::const_iterator name_begin,
std::string::const_iterator name_end,
std::string::const_iterator values_begin,
std::string::const_iterator values_end) {
// If the header can be coalesced, then we should split it up.
if (values_begin == values_end ||
HttpUtil::IsNonCoalescingHeader(name_begin, name_end)) {
AddToParsed(name_begin, name_end, values_begin, values_end);
} else {
HttpUtil::ValuesIterator it(values_begin, values_end, ',');
while (it.GetNext()) {
AddToParsed(name_begin, name_end, it.value_begin(), it.value_end());
// clobber these so that subsequent values are treated as continuations
name_begin = name_end = raw_headers_.end();
}
}
}
void HttpResponseHeaders::AddToParsed(std::string::const_iterator name_begin,
std::string::const_iterator name_end,
std::string::const_iterator value_begin,
std::string::const_iterator value_end) {
ParsedHeader header;
header.name_begin = name_begin;
header.name_end = name_end;
header.value_begin = value_begin;
header.value_end = value_end;
parsed_.push_back(header);
}
void HttpResponseHeaders::AddNonCacheableHeaders(HeaderSet* result) const {
// Add server specified transients. Any 'cache-control: no-cache="foo,bar"'
// headers present in the response specify additional headers that we should
// not store in the cache.
const std::string kCacheControl = "cache-control";
const std::string kPrefix = "no-cache=\"";
std::string value;
void* iter = NULL;
while (EnumerateHeader(&iter, kCacheControl, &value)) {
if (value.size() > kPrefix.size() &&
value.compare(0, kPrefix.size(), kPrefix) == 0) {
// if it doesn't end with a quote, then treat as malformed
if (value[value.size()-1] != '\"')
continue;
// trim off leading and trailing bits
size_t len = value.size() - kPrefix.size() - 1;
TrimString(value.substr(kPrefix.size(), len), HTTP_LWS, &value);
size_t begin_pos = 0;
for (;;) {
// find the end of this header name
size_t comma_pos = value.find(',', begin_pos);
if (comma_pos == std::string::npos)
comma_pos = value.size();
size_t end = comma_pos;
while (end > begin_pos && strchr(HTTP_LWS, value[end - 1]))
end--;
// assuming the header is not emtpy, lowercase and insert into set
if (end > begin_pos) {
std::string name = value.substr(begin_pos, end - begin_pos);
StringToLowerASCII(&name);
result->insert(name);
}
// repeat
begin_pos = comma_pos + 1;
while (begin_pos < value.size() && strchr(HTTP_LWS, value[begin_pos]))
begin_pos++;
if (begin_pos >= value.size())
break;
}
}
}
}
void HttpResponseHeaders::AddHopByHopHeaders(HeaderSet* result) {
for (size_t i = 0; i < arraysize(kHopByHopResponseHeaders); ++i)
result->insert(std::string(kHopByHopResponseHeaders[i]));
}
void HttpResponseHeaders::AddCookieHeaders(HeaderSet* result) {
for (size_t i = 0; i < arraysize(kCookieResponseHeaders); ++i)
result->insert(std::string(kCookieResponseHeaders[i]));
}
void HttpResponseHeaders::AddChallengeHeaders(HeaderSet* result) {
for (size_t i = 0; i < arraysize(kChallengeResponseHeaders); ++i)
result->insert(std::string(kChallengeResponseHeaders[i]));
}
void HttpResponseHeaders::AddHopContentRangeHeaders(HeaderSet* result) {
result->insert("content-range");
}
void HttpResponseHeaders::GetMimeTypeAndCharset(std::string* mime_type,
std::string* charset) const {
mime_type->clear();
charset->clear();
std::string name = "content-type";
std::string value;
bool had_charset = false;
void* iter = NULL;
while (EnumerateHeader(&iter, name, &value))
HttpUtil::ParseContentType(value, mime_type, charset, &had_charset);
}
bool HttpResponseHeaders::GetMimeType(std::string* mime_type) const {
std::string unused;
GetMimeTypeAndCharset(mime_type, &unused);
return !mime_type->empty();
}
bool HttpResponseHeaders::GetCharset(std::string* charset) const {
std::string unused;
GetMimeTypeAndCharset(&unused, charset);
return !charset->empty();
}
bool HttpResponseHeaders::IsRedirect(std::string* location) const {
if (!IsRedirectResponseCode(response_code_))
return false;
// If we lack a Location header, then we can't treat this as a redirect.
// We assume that the first non-empty location value is the target URL that
// we want to follow. TODO(darin): Is this consistent with other browsers?
size_t i = std::string::npos;
do {
i = FindHeader(++i, "location");
if (i == std::string::npos)
return false;
// If the location value is empty, then it doesn't count.
} while (parsed_[i].value_begin == parsed_[i].value_end);
if (location) {
// Escape any non-ASCII characters to preserve them. The server should
// only be returning ASCII here, but for compat we need to do this.
*location = EscapeNonASCII(
std::string(parsed_[i].value_begin, parsed_[i].value_end));
}
return true;
}
// static
bool HttpResponseHeaders::IsRedirectResponseCode(int response_code) {
// Users probably want to see 300 (multiple choice) pages, so we don't count
// them as redirects that need to be followed.
return (response_code == 301 ||
response_code == 302 ||
response_code == 303 ||
response_code == 307);
}
// From RFC 2616 section 13.2.4:
//
// The calculation to determine if a response has expired is quite simple:
//
// response_is_fresh = (freshness_lifetime > current_age)
//
// Of course, there are other factors that can force a response to always be
// validated or re-fetched.
//
bool HttpResponseHeaders::RequiresValidation(const Time& request_time,
const Time& response_time,
const Time& current_time) const {
TimeDelta lifetime =
GetFreshnessLifetime(response_time);
if (lifetime == TimeDelta())
return true;
return lifetime <= GetCurrentAge(request_time, response_time, current_time);
}
// From RFC 2616 section 13.2.4:
//
// The max-age directive takes priority over Expires, so if max-age is present
// in a response, the calculation is simply:
//
// freshness_lifetime = max_age_value
//
// Otherwise, if Expires is present in the response, the calculation is:
//
// freshness_lifetime = expires_value - date_value
//
// Note that neither of these calculations is vulnerable to clock skew, since
// all of the information comes from the origin server.
//
// Also, if the response does have a Last-Modified time, the heuristic
// expiration value SHOULD be no more than some fraction of the interval since
// that time. A typical setting of this fraction might be 10%:
//
// freshness_lifetime = (date_value - last_modified_value) * 0.10
//
TimeDelta HttpResponseHeaders::GetFreshnessLifetime(
const Time& response_time) const {
// Check for headers that force a response to never be fresh. For backwards
// compat, we treat "Pragma: no-cache" as a synonym for "Cache-Control:
// no-cache" even though RFC 2616 does not specify it.
if (HasHeaderValue("cache-control", "no-cache") ||
HasHeaderValue("cache-control", "no-store") ||
HasHeaderValue("pragma", "no-cache") ||
HasHeaderValue("vary", "*")) // see RFC 2616 section 13.6
return TimeDelta(); // not fresh
// NOTE: "Cache-Control: max-age" overrides Expires, so we only check the
// Expires header after checking for max-age in GetFreshnessLifetime. This
// is important since "Expires: <date in the past>" means not fresh, but
// it should not trump a max-age value.
TimeDelta max_age_value;
if (GetMaxAgeValue(&max_age_value))
return max_age_value;
// If there is no Date header, then assume that the server response was
// generated at the time when we received the response.
Time date_value;
if (!GetDateValue(&date_value))
date_value = response_time;
Time expires_value;
if (GetExpiresValue(&expires_value)) {
// The expires value can be a date in the past!
if (expires_value > date_value)
return expires_value - date_value;
return TimeDelta(); // not fresh
}
// From RFC 2616 section 13.4:
//
// A response received with a status code of 200, 203, 206, 300, 301 or 410
// MAY be stored by a cache and used in reply to a subsequent request,
// subject to the expiration mechanism, unless a cache-control directive
// prohibits caching.
// ...
// A response received with any other status code (e.g. status codes 302
// and 307) MUST NOT be returned in a reply to a subsequent request unless
// there are cache-control directives or another header(s) that explicitly
// allow it.
//
// From RFC 2616 section 14.9.4:
//
// When the must-revalidate directive is present in a response received by
// a cache, that cache MUST NOT use the entry after it becomes stale to
// respond to a subsequent request without first revalidating it with the
// origin server. (I.e., the cache MUST do an end-to-end revalidation every
// time, if, based solely on the origin server's Expires or max-age value,
// the cached response is stale.)
//
if ((response_code_ == 200 || response_code_ == 203 ||
response_code_ == 206) &&
!HasHeaderValue("cache-control", "must-revalidate")) {
// TODO(darin): Implement a smarter heuristic.
Time last_modified_value;
if (GetLastModifiedValue(&last_modified_value)) {
// The last-modified value can be a date in the past!
if (last_modified_value <= date_value)
return (date_value - last_modified_value) / 10;
}
}
// These responses are implicitly fresh (unless otherwise overruled):
if (response_code_ == 300 || response_code_ == 301 || response_code_ == 410)
return TimeDelta::FromMicroseconds(kint64max);
return TimeDelta(); // not fresh
}
// From RFC 2616 section 13.2.3:
//
// Summary of age calculation algorithm, when a cache receives a response:
//
// /*
// * age_value
// * is the value of Age: header received by the cache with
// * this response.
// * date_value
// * is the value of the origin server's Date: header
// * request_time
// * is the (local) time when the cache made the request
// * that resulted in this cached response
// * response_time
// * is the (local) time when the cache received the
// * response
// * now
// * is the current (local) time
// */
// apparent_age = max(0, response_time - date_value);
// corrected_received_age = max(apparent_age, age_value);
// response_delay = response_time - request_time;
// corrected_initial_age = corrected_received_age + response_delay;
// resident_time = now - response_time;
// current_age = corrected_initial_age + resident_time;
//
TimeDelta HttpResponseHeaders::GetCurrentAge(const Time& request_time,
const Time& response_time,
const Time& current_time) const {
// If there is no Date header, then assume that the server response was
// generated at the time when we received the response.
Time date_value;
if (!GetDateValue(&date_value))
date_value = response_time;
// If there is no Age header, then assume age is zero. GetAgeValue does not
// modify its out param if the value does not exist.
TimeDelta age_value;
GetAgeValue(&age_value);
TimeDelta apparent_age = std::max(TimeDelta(), response_time - date_value);
TimeDelta corrected_received_age = std::max(apparent_age, age_value);
TimeDelta response_delay = response_time - request_time;
TimeDelta corrected_initial_age = corrected_received_age + response_delay;
TimeDelta resident_time = current_time - response_time;
TimeDelta current_age = corrected_initial_age + resident_time;
return current_age;
}
bool HttpResponseHeaders::GetMaxAgeValue(TimeDelta* result) const {
std::string name = "cache-control";
std::string value;
const char kMaxAgePrefix[] = "max-age=";
const size_t kMaxAgePrefixLen = arraysize(kMaxAgePrefix) - 1;
void* iter = NULL;
while (EnumerateHeader(&iter, name, &value)) {
if (value.size() > kMaxAgePrefixLen) {
if (LowerCaseEqualsASCII(value.begin(),
value.begin() + kMaxAgePrefixLen,
kMaxAgePrefix)) {
int64 seconds;
base::StringToInt64(StringPiece(value.begin() + kMaxAgePrefixLen,
value.end()),
&seconds);
*result = TimeDelta::FromSeconds(seconds);
return true;
}
}
}
return false;
}
bool HttpResponseHeaders::GetAgeValue(TimeDelta* result) const {
std::string value;
if (!EnumerateHeader(NULL, "Age", &value))
return false;
int64 seconds;
base::StringToInt64(value, &seconds);
*result = TimeDelta::FromSeconds(seconds);
return true;
}
bool HttpResponseHeaders::GetDateValue(Time* result) const {
return GetTimeValuedHeader("Date", result);
}
bool HttpResponseHeaders::GetLastModifiedValue(Time* result) const {
return GetTimeValuedHeader("Last-Modified", result);
}
bool HttpResponseHeaders::GetExpiresValue(Time* result) const {
return GetTimeValuedHeader("Expires", result);
}
bool HttpResponseHeaders::GetTimeValuedHeader(const std::string& name,
Time* result) const {
std::string value;
if (!EnumerateHeader(NULL, name, &value))
return false;
return Time::FromString(value.c_str(), result);
}
bool HttpResponseHeaders::IsKeepAlive() const {
if (http_version_ < HttpVersion(1, 0))
return false;
// NOTE: It is perhaps risky to assume that a Proxy-Connection header is
// meaningful when we don't know that this response was from a proxy, but
// Mozilla also does this, so we'll do the same.
std::string connection_val;
if (!EnumerateHeader(NULL, "connection", &connection_val))
EnumerateHeader(NULL, "proxy-connection", &connection_val);
bool keep_alive;
if (http_version_ == HttpVersion(1, 0)) {
// HTTP/1.0 responses default to NOT keep-alive
keep_alive = LowerCaseEqualsASCII(connection_val, "keep-alive");
} else {
// HTTP/1.1 responses default to keep-alive
keep_alive = !LowerCaseEqualsASCII(connection_val, "close");
}
return keep_alive;
}
bool HttpResponseHeaders::HasStrongValidators() const {
if (GetHttpVersion() < HttpVersion(1, 1))
return false;
std::string etag_value;
EnumerateHeader(NULL, "etag", &etag_value);
if (!etag_value.empty()) {
size_t slash = etag_value.find('/');
if (slash == std::string::npos || slash == 0)
return true;
std::string::const_iterator i = etag_value.begin();
std::string::const_iterator j = etag_value.begin() + slash;
HttpUtil::TrimLWS(&i, &j);
if (!LowerCaseEqualsASCII(i, j, "w"))
return true;
}
Time last_modified;
if (!GetLastModifiedValue(&last_modified))
return false;
Time date;
if (!GetDateValue(&date))
return false;
return ((date - last_modified).InSeconds() >= 60);
}
// From RFC 2616:
// Content-Length = "Content-Length" ":" 1*DIGIT
int64 HttpResponseHeaders::GetContentLength() const {
void* iter = NULL;
std::string content_length_val;
if (!EnumerateHeader(&iter, "content-length", &content_length_val))
return -1;
if (content_length_val.empty())
return -1;
if (content_length_val[0] == '+')
return -1;
int64 result;
bool ok = base::StringToInt64(content_length_val, &result);
if (!ok || result < 0)
return -1;
return result;
}
// From RFC 2616 14.16:
// content-range-spec =
// bytes-unit SP byte-range-resp-spec "/" ( instance-length | "*" )
// byte-range-resp-spec = (first-byte-pos "-" last-byte-pos) | "*"
// instance-length = 1*DIGIT
// bytes-unit = "bytes"
bool HttpResponseHeaders::GetContentRange(int64* first_byte_position,
int64* last_byte_position,
int64* instance_length) const {
void* iter = NULL;
std::string content_range_spec;
*first_byte_position = *last_byte_position = *instance_length = -1;
if (!EnumerateHeader(&iter, "content-range", &content_range_spec))
return false;
// If the header value is empty, we have an invalid header.
if (content_range_spec.empty())
return false;
size_t space_position = content_range_spec.find(' ');
if (space_position == std::string::npos)
return false;
// Invalid header if it doesn't contain "bytes-unit".
std::string::const_iterator content_range_spec_begin =
content_range_spec.begin();
std::string::const_iterator content_range_spec_end =
content_range_spec.begin() + space_position;
HttpUtil::TrimLWS(&content_range_spec_begin, &content_range_spec_end);
if (!LowerCaseEqualsASCII(content_range_spec_begin,
content_range_spec_end,
"bytes")) {
return false;
}
size_t slash_position = content_range_spec.find('/', space_position + 1);
if (slash_position == std::string::npos)
return false;
// Obtain the part behind the space and before slash.
std::string::const_iterator byte_range_resp_spec_begin =
content_range_spec.begin() + space_position + 1;
std::string::const_iterator byte_range_resp_spec_end =
content_range_spec.begin() + slash_position;
HttpUtil::TrimLWS(&byte_range_resp_spec_begin, &byte_range_resp_spec_end);
// Parse the byte-range-resp-spec part.
std::string byte_range_resp_spec(byte_range_resp_spec_begin,
byte_range_resp_spec_end);
// If byte-range-resp-spec != "*".
if (!LowerCaseEqualsASCII(byte_range_resp_spec, "*")) {
size_t minus_position = byte_range_resp_spec.find('-');
if (minus_position != std::string::npos) {
// Obtain first-byte-pos.
std::string::const_iterator first_byte_pos_begin =
byte_range_resp_spec.begin();
std::string::const_iterator first_byte_pos_end =
byte_range_resp_spec.begin() + minus_position;
HttpUtil::TrimLWS(&first_byte_pos_begin, &first_byte_pos_end);
bool ok = base::StringToInt64(StringPiece(first_byte_pos_begin,
first_byte_pos_end),
first_byte_position);
// Obtain last-byte-pos.
std::string::const_iterator last_byte_pos_begin =
byte_range_resp_spec.begin() + minus_position + 1;
std::string::const_iterator last_byte_pos_end =
byte_range_resp_spec.end();
HttpUtil::TrimLWS(&last_byte_pos_begin, &last_byte_pos_end);
ok &= base::StringToInt64(StringPiece(last_byte_pos_begin,
last_byte_pos_end),
last_byte_position);
if (!ok) {
*first_byte_position = *last_byte_position = -1;
return false;
}
if (*first_byte_position < 0 || *last_byte_position < 0 ||
*first_byte_position > *last_byte_position)
return false;
} else {
return false;
}
}
// Parse the instance-length part.
// If instance-length == "*".
std::string::const_iterator instance_length_begin =
content_range_spec.begin() + slash_position + 1;
std::string::const_iterator instance_length_end =
content_range_spec.end();
HttpUtil::TrimLWS(&instance_length_begin, &instance_length_end);
if (LowerCaseEqualsASCII(instance_length_begin, instance_length_end, "*")) {
return false;
} else if (!base::StringToInt64(StringPiece(instance_length_begin,
instance_length_end),
instance_length)) {
*instance_length = -1;
return false;
}
// We have all the values; let's verify that they make sense for a 206
// response.
if (*first_byte_position < 0 || *last_byte_position < 0 ||
*instance_length < 0 || *instance_length - 1 < *last_byte_position)
return false;
return true;
}
bool HttpResponseHeaders::IsChunkEncoded() const {
// Ignore spurious chunked responses from HTTP/1.0 servers and proxies.
return GetHttpVersion() >= HttpVersion(1, 1) &&
HasHeaderValue("Transfer-Encoding", "chunked");
}
} // namespace net
|