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
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
|
/* Copyright Joyent, Inc. and other Node contributors.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include "http_parser.h"
#include <assert.h>
#include <stddef.h>
#include <ctype.h>
#include <string.h>
#include <limits.h>
static uint32_t max_header_size = HTTP_MAX_HEADER_SIZE;
#ifndef ULLONG_MAX
# define ULLONG_MAX ((uint64_t) -1) /* 2^64-1 */
#endif
#ifndef MIN
# define MIN(a,b) ((a) < (b) ? (a) : (b))
#endif
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0]))
#endif
#ifndef BIT_AT
# define BIT_AT(a, i) \
(!!((unsigned int) (a)[(unsigned int) (i) >> 3] & \
(1 << ((unsigned int) (i) & 7))))
#endif
#ifndef ELEM_AT
# define ELEM_AT(a, i, v) ((unsigned int) (i) < ARRAY_SIZE(a) ? (a)[(i)] : (v))
#endif
#define SET_ERRNO(e) \
do { \
parser->nread = nread; \
parser->http_errno = (e); \
} while(0)
#define CURRENT_STATE() p_state
#define UPDATE_STATE(V) p_state = (enum state) (V);
#define RETURN(V) \
do { \
parser->nread = nread; \
parser->state = CURRENT_STATE(); \
return (V); \
} while (0);
#define REEXECUTE() \
goto reexecute; \
#ifdef __GNUC__
# define LIKELY(X) __builtin_expect(!!(X), 1)
# define UNLIKELY(X) __builtin_expect(!!(X), 0)
#else
# define LIKELY(X) (X)
# define UNLIKELY(X) (X)
#endif
/* Run the notify callback FOR, returning ER if it fails */
#define CALLBACK_NOTIFY_(FOR, ER) \
do { \
assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \
\
if (LIKELY(settings->on_##FOR)) { \
parser->state = CURRENT_STATE(); \
if (UNLIKELY(0 != settings->on_##FOR(parser))) { \
SET_ERRNO(HPE_CB_##FOR); \
} \
UPDATE_STATE(parser->state); \
\
/* We either errored above or got paused; get out */ \
if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \
return (ER); \
} \
} \
} while (0)
/* Run the notify callback FOR and consume the current byte */
#define CALLBACK_NOTIFY(FOR) CALLBACK_NOTIFY_(FOR, p - data + 1)
/* Run the notify callback FOR and don't consume the current byte */
#define CALLBACK_NOTIFY_NOADVANCE(FOR) CALLBACK_NOTIFY_(FOR, p - data)
/* Run data callback FOR with LEN bytes, returning ER if it fails */
#define CALLBACK_DATA_(FOR, LEN, ER) \
do { \
assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \
\
if (FOR##_mark) { \
if (LIKELY(settings->on_##FOR)) { \
parser->state = CURRENT_STATE(); \
if (UNLIKELY(0 != \
settings->on_##FOR(parser, FOR##_mark, (LEN)))) { \
SET_ERRNO(HPE_CB_##FOR); \
} \
UPDATE_STATE(parser->state); \
\
/* We either errored above or got paused; get out */ \
if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \
return (ER); \
} \
} \
FOR##_mark = NULL; \
} \
} while (0)
/* Run the data callback FOR and consume the current byte */
#define CALLBACK_DATA(FOR) \
CALLBACK_DATA_(FOR, p - FOR##_mark, p - data + 1)
/* Run the data callback FOR and don't consume the current byte */
#define CALLBACK_DATA_NOADVANCE(FOR) \
CALLBACK_DATA_(FOR, p - FOR##_mark, p - data)
/* Set the mark FOR; non-destructive if mark is already set */
#define MARK(FOR) \
do { \
if (!FOR##_mark) { \
FOR##_mark = p; \
} \
} while (0)
/* Don't allow the total size of the HTTP headers (including the status
* line) to exceed max_header_size. This check is here to protect
* embedders against denial-of-service attacks where the attacker feeds
* us a never-ending header that the embedder keeps buffering.
*
* This check is arguably the responsibility of embedders but we're doing
* it on the embedder's behalf because most won't bother and this way we
* make the web a little safer. max_header_size is still far bigger
* than any reasonable request or response so this should never affect
* day-to-day operation.
*/
#define COUNT_HEADER_SIZE(V) \
do { \
nread += (uint32_t)(V); \
if (UNLIKELY(nread > max_header_size)) { \
SET_ERRNO(HPE_HEADER_OVERFLOW); \
goto error; \
} \
} while (0)
#define PROXY_CONNECTION "proxy-connection"
#define CONNECTION "connection"
#define CONTENT_LENGTH "content-length"
#define TRANSFER_ENCODING "transfer-encoding"
#define UPGRADE "upgrade"
#define CHUNKED "chunked"
#define KEEP_ALIVE "keep-alive"
#define CLOSE "close"
static const char *method_strings[] =
{
#define XX(num, name, string) #string,
HTTP_METHOD_MAP(XX)
#undef XX
};
/* Tokens as defined by rfc 2616. Also lowercases them.
* token = 1*<any CHAR except CTLs or separators>
* separators = "(" | ")" | "<" | ">" | "@"
* | "," | ";" | ":" | "\" | <">
* | "/" | "[" | "]" | "?" | "="
* | "{" | "}" | SP | HT
*/
static const char tokens[256] = {
/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */
0, 0, 0, 0, 0, 0, 0, 0,
/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */
0, 0, 0, 0, 0, 0, 0, 0,
/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */
0, 0, 0, 0, 0, 0, 0, 0,
/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */
0, 0, 0, 0, 0, 0, 0, 0,
/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */
' ', '!', 0, '#', '$', '%', '&', '\'',
/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */
0, 0, '*', '+', 0, '-', '.', 0,
/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */
'0', '1', '2', '3', '4', '5', '6', '7',
/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */
'8', '9', 0, 0, 0, 0, 0, 0,
/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */
0, 'a', 'b', 'c', 'd', 'e', 'f', 'g',
/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */
'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */
'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */
'x', 'y', 'z', 0, 0, 0, '^', '_',
/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */
'`', 'a', 'b', 'c', 'd', 'e', 'f', 'g',
/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */
'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */
'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */
'x', 'y', 'z', 0, '|', 0, '~', 0 };
static const int8_t unhex[256] =
{-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,-1,-1,-1,-1,-1,-1
,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1
,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1
,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
};
#if HTTP_PARSER_STRICT
# define T(v) 0
#else
# define T(v) v
#endif
static const uint8_t normal_url_char[32] = {
/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,
/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */
0 | T(2) | 0 | 0 | T(16) | 0 | 0 | 0,
/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,
/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,
/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */
0 | 2 | 4 | 0 | 16 | 32 | 64 | 128,
/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 0,
/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */
1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, };
#undef T
enum state
{ s_dead = 1 /* important that this is > 0 */
, s_start_req_or_res
, s_res_or_resp_H
, s_start_res
, s_res_H
, s_res_HT
, s_res_HTT
, s_res_HTTP
, s_res_http_major
, s_res_http_dot
, s_res_http_minor
, s_res_http_end
, s_res_first_status_code
, s_res_status_code
, s_res_status_start
, s_res_status
, s_res_line_almost_done
, s_start_req
, s_req_method
, s_req_spaces_before_url
, s_req_schema
, s_req_schema_slash
, s_req_schema_slash_slash
, s_req_server_start
, s_req_server
, s_req_server_with_at
, s_req_path
, s_req_query_string_start
, s_req_query_string
, s_req_fragment_start
, s_req_fragment
, s_req_http_start
, s_req_http_H
, s_req_http_HT
, s_req_http_HTT
, s_req_http_HTTP
, s_req_http_I
, s_req_http_IC
, s_req_http_major
, s_req_http_dot
, s_req_http_minor
, s_req_http_end
, s_req_line_almost_done
, s_header_field_start
, s_header_field
, s_header_value_discard_ws
, s_header_value_discard_ws_almost_done
, s_header_value_discard_lws
, s_header_value_start
, s_header_value
, s_header_value_lws
, s_header_almost_done
, s_chunk_size_start
, s_chunk_size
, s_chunk_parameters
, s_chunk_size_almost_done
, s_headers_almost_done
, s_headers_done
/* Important: 's_headers_done' must be the last 'header' state. All
* states beyond this must be 'body' states. It is used for overflow
* checking. See the PARSING_HEADER() macro.
*/
, s_chunk_data
, s_chunk_data_almost_done
, s_chunk_data_done
, s_body_identity
, s_body_identity_eof
, s_message_done
};
#define PARSING_HEADER(state) (state <= s_headers_done)
enum header_states
{ h_general = 0
, h_C
, h_CO
, h_CON
, h_matching_connection
, h_matching_proxy_connection
, h_matching_content_length
, h_matching_transfer_encoding
, h_matching_upgrade
, h_connection
, h_content_length
, h_content_length_num
, h_content_length_ws
, h_transfer_encoding
, h_upgrade
, h_matching_transfer_encoding_token_start
, h_matching_transfer_encoding_chunked
, h_matching_transfer_encoding_token
, h_matching_connection_token_start
, h_matching_connection_keep_alive
, h_matching_connection_close
, h_matching_connection_upgrade
, h_matching_connection_token
, h_transfer_encoding_chunked
, h_connection_keep_alive
, h_connection_close
, h_connection_upgrade
};
enum http_host_state
{
s_http_host_dead = 1
, s_http_userinfo_start
, s_http_userinfo
, s_http_host_start
, s_http_host_v6_start
, s_http_host
, s_http_host_v6
, s_http_host_v6_end
, s_http_host_v6_zone_start
, s_http_host_v6_zone
, s_http_host_port_start
, s_http_host_port
};
/* Macros for character classes; depends on strict-mode */
#define CR '\r'
#define LF '\n'
#define LOWER(c) (unsigned char)(c | 0x20)
#define IS_ALPHA(c) (LOWER(c) >= 'a' && LOWER(c) <= 'z')
#define IS_NUM(c) ((c) >= '0' && (c) <= '9')
#define IS_ALPHANUM(c) (IS_ALPHA(c) || IS_NUM(c))
#define IS_HEX(c) (IS_NUM(c) || (LOWER(c) >= 'a' && LOWER(c) <= 'f'))
#define IS_MARK(c) ((c) == '-' || (c) == '_' || (c) == '.' || \
(c) == '!' || (c) == '~' || (c) == '*' || (c) == '\'' || (c) == '(' || \
(c) == ')')
#define IS_USERINFO_CHAR(c) (IS_ALPHANUM(c) || IS_MARK(c) || (c) == '%' || \
(c) == ';' || (c) == ':' || (c) == '&' || (c) == '=' || (c) == '+' || \
(c) == '$' || (c) == ',')
#define STRICT_TOKEN(c) ((c == ' ') ? 0 : tokens[(unsigned char)c])
#if HTTP_PARSER_STRICT
#define TOKEN(c) STRICT_TOKEN(c)
#define IS_URL_CHAR(c) (BIT_AT(normal_url_char, (unsigned char)c))
#define IS_HOST_CHAR(c) (IS_ALPHANUM(c) || (c) == '.' || (c) == '-')
#else
#define TOKEN(c) tokens[(unsigned char)c]
#define IS_URL_CHAR(c) \
(BIT_AT(normal_url_char, (unsigned char)c) || ((c) & 0x80))
#define IS_HOST_CHAR(c) \
(IS_ALPHANUM(c) || (c) == '.' || (c) == '-' || (c) == '_')
#endif
/**
* Verify that a char is a valid visible (printable) US-ASCII
* character or %x80-FF
**/
#define IS_HEADER_CHAR(ch) \
(ch == CR || ch == LF || ch == 9 || ((unsigned char)ch > 31 && ch != 127))
#define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res)
#if HTTP_PARSER_STRICT
# define STRICT_CHECK(cond) \
do { \
if (cond) { \
SET_ERRNO(HPE_STRICT); \
goto error; \
} \
} while (0)
# define NEW_MESSAGE() (http_should_keep_alive(parser) ? start_state : s_dead)
#else
# define STRICT_CHECK(cond)
# define NEW_MESSAGE() start_state
#endif
/* Map errno values to strings for human-readable output */
#define HTTP_STRERROR_GEN(n, s) { "HPE_" #n, s },
static struct {
const char *name;
const char *description;
} http_strerror_tab[] = {
HTTP_ERRNO_MAP(HTTP_STRERROR_GEN)
};
#undef HTTP_STRERROR_GEN
int http_message_needs_eof(const http_parser *parser);
/* Our URL parser.
*
* This is designed to be shared by http_parser_execute() for URL validation,
* hence it has a state transition + byte-for-byte interface. In addition, it
* is meant to be embedded in http_parser_parse_url(), which does the dirty
* work of turning state transitions URL components for its API.
*
* This function should only be invoked with non-space characters. It is
* assumed that the caller cares about (and can detect) the transition between
* URL and non-URL states by looking for these.
*/
static enum state
parse_url_char(enum state s, const char ch)
{
if (ch == ' ' || ch == '\r' || ch == '\n') {
return s_dead;
}
#if HTTP_PARSER_STRICT
if (ch == '\t' || ch == '\f') {
return s_dead;
}
#endif
switch (s) {
case s_req_spaces_before_url:
/* Proxied requests are followed by scheme of an absolute URI (alpha).
* All methods except CONNECT are followed by '/' or '*'.
*/
if (ch == '/' || ch == '*') {
return s_req_path;
}
if (IS_ALPHA(ch)) {
return s_req_schema;
}
break;
case s_req_schema:
if (IS_ALPHA(ch)) {
return s;
}
if (ch == ':') {
return s_req_schema_slash;
}
break;
case s_req_schema_slash:
if (ch == '/') {
return s_req_schema_slash_slash;
}
break;
case s_req_schema_slash_slash:
if (ch == '/') {
return s_req_server_start;
}
break;
case s_req_server_with_at:
if (ch == '@') {
return s_dead;
}
/* fall through */
case s_req_server_start:
case s_req_server:
if (ch == '/') {
return s_req_path;
}
if (ch == '?') {
return s_req_query_string_start;
}
if (ch == '@') {
return s_req_server_with_at;
}
if (IS_USERINFO_CHAR(ch) || ch == '[' || ch == ']') {
return s_req_server;
}
break;
case s_req_path:
if (IS_URL_CHAR(ch)) {
return s;
}
switch (ch) {
case '?':
return s_req_query_string_start;
case '#':
return s_req_fragment_start;
}
break;
case s_req_query_string_start:
case s_req_query_string:
if (IS_URL_CHAR(ch)) {
return s_req_query_string;
}
switch (ch) {
case '?':
/* allow extra '?' in query string */
return s_req_query_string;
case '#':
return s_req_fragment_start;
}
break;
case s_req_fragment_start:
if (IS_URL_CHAR(ch)) {
return s_req_fragment;
}
switch (ch) {
case '?':
return s_req_fragment;
case '#':
return s;
}
break;
case s_req_fragment:
if (IS_URL_CHAR(ch)) {
return s;
}
switch (ch) {
case '?':
case '#':
return s;
}
break;
default:
break;
}
/* We should never fall out of the switch above unless there's an error */
return s_dead;
}
size_t http_parser_execute (http_parser *parser,
const http_parser_settings *settings,
const char *data,
size_t len)
{
char c, ch;
int8_t unhex_val;
const char *p = data;
const char *header_field_mark = 0;
const char *header_value_mark = 0;
const char *url_mark = 0;
const char *body_mark = 0;
const char *status_mark = 0;
enum state p_state = (enum state) parser->state;
const unsigned int lenient = parser->lenient_http_headers;
uint32_t nread = parser->nread;
/* We're in an error state. Don't bother doing anything. */
if (HTTP_PARSER_ERRNO(parser) != HPE_OK) {
return 0;
}
if (len == 0) {
switch (CURRENT_STATE()) {
case s_body_identity_eof:
/* Use of CALLBACK_NOTIFY() here would erroneously return 1 byte read if
* we got paused.
*/
CALLBACK_NOTIFY_NOADVANCE(message_complete);
return 0;
case s_dead:
case s_start_req_or_res:
case s_start_res:
case s_start_req:
return 0;
default:
SET_ERRNO(HPE_INVALID_EOF_STATE);
return 1;
}
}
if (CURRENT_STATE() == s_header_field)
header_field_mark = data;
if (CURRENT_STATE() == s_header_value)
header_value_mark = data;
switch (CURRENT_STATE()) {
case s_req_path:
case s_req_schema:
case s_req_schema_slash:
case s_req_schema_slash_slash:
case s_req_server_start:
case s_req_server:
case s_req_server_with_at:
case s_req_query_string_start:
case s_req_query_string:
case s_req_fragment_start:
case s_req_fragment:
url_mark = data;
break;
case s_res_status:
status_mark = data;
break;
default:
break;
}
for (p=data; p != data + len; p++) {
ch = *p;
if (PARSING_HEADER(CURRENT_STATE()))
COUNT_HEADER_SIZE(1);
reexecute:
switch (CURRENT_STATE()) {
case s_dead:
/* this state is used after a 'Connection: close' message
* the parser will error out if it reads another message
*/
if (LIKELY(ch == CR || ch == LF))
break;
SET_ERRNO(HPE_CLOSED_CONNECTION);
goto error;
case s_start_req_or_res:
{
if (ch == CR || ch == LF)
break;
parser->flags = 0;
parser->extra_flags = 0;
parser->content_length = ULLONG_MAX;
if (ch == 'H') {
UPDATE_STATE(s_res_or_resp_H);
CALLBACK_NOTIFY(message_begin);
} else {
parser->type = HTTP_REQUEST;
UPDATE_STATE(s_start_req);
REEXECUTE();
}
break;
}
case s_res_or_resp_H:
if (ch == 'T') {
parser->type = HTTP_RESPONSE;
UPDATE_STATE(s_res_HT);
} else {
if (UNLIKELY(ch != 'E')) {
SET_ERRNO(HPE_INVALID_CONSTANT);
goto error;
}
parser->type = HTTP_REQUEST;
parser->method = HTTP_HEAD;
parser->index = 2;
UPDATE_STATE(s_req_method);
}
break;
case s_start_res:
{
if (ch == CR || ch == LF)
break;
parser->flags = 0;
parser->extra_flags = 0;
parser->content_length = ULLONG_MAX;
if (ch == 'H') {
UPDATE_STATE(s_res_H);
} else {
SET_ERRNO(HPE_INVALID_CONSTANT);
goto error;
}
CALLBACK_NOTIFY(message_begin);
break;
}
case s_res_H:
STRICT_CHECK(ch != 'T');
UPDATE_STATE(s_res_HT);
break;
case s_res_HT:
STRICT_CHECK(ch != 'T');
UPDATE_STATE(s_res_HTT);
break;
case s_res_HTT:
STRICT_CHECK(ch != 'P');
UPDATE_STATE(s_res_HTTP);
break;
case s_res_HTTP:
STRICT_CHECK(ch != '/');
UPDATE_STATE(s_res_http_major);
break;
case s_res_http_major:
if (UNLIKELY(!IS_NUM(ch))) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
parser->http_major = ch - '0';
UPDATE_STATE(s_res_http_dot);
break;
case s_res_http_dot:
{
if (UNLIKELY(ch != '.')) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
UPDATE_STATE(s_res_http_minor);
break;
}
case s_res_http_minor:
if (UNLIKELY(!IS_NUM(ch))) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
parser->http_minor = ch - '0';
UPDATE_STATE(s_res_http_end);
break;
case s_res_http_end:
{
if (UNLIKELY(ch != ' ')) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
UPDATE_STATE(s_res_first_status_code);
break;
}
case s_res_first_status_code:
{
if (!IS_NUM(ch)) {
if (ch == ' ') {
break;
}
SET_ERRNO(HPE_INVALID_STATUS);
goto error;
}
parser->status_code = ch - '0';
UPDATE_STATE(s_res_status_code);
break;
}
case s_res_status_code:
{
if (!IS_NUM(ch)) {
switch (ch) {
case ' ':
UPDATE_STATE(s_res_status_start);
break;
case CR:
case LF:
UPDATE_STATE(s_res_status_start);
REEXECUTE();
break;
default:
SET_ERRNO(HPE_INVALID_STATUS);
goto error;
}
break;
}
parser->status_code *= 10;
parser->status_code += ch - '0';
if (UNLIKELY(parser->status_code > 999)) {
SET_ERRNO(HPE_INVALID_STATUS);
goto error;
}
break;
}
case s_res_status_start:
{
MARK(status);
UPDATE_STATE(s_res_status);
parser->index = 0;
if (ch == CR || ch == LF)
REEXECUTE();
break;
}
case s_res_status:
if (ch == CR) {
UPDATE_STATE(s_res_line_almost_done);
CALLBACK_DATA(status);
break;
}
if (ch == LF) {
UPDATE_STATE(s_header_field_start);
CALLBACK_DATA(status);
break;
}
break;
case s_res_line_almost_done:
STRICT_CHECK(ch != LF);
UPDATE_STATE(s_header_field_start);
break;
case s_start_req:
{
if (ch == CR || ch == LF)
break;
parser->flags = 0;
parser->extra_flags = 0;
parser->content_length = ULLONG_MAX;
if (UNLIKELY(!IS_ALPHA(ch))) {
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
parser->method = (enum http_method) 0;
parser->index = 1;
switch (ch) {
case 'A': parser->method = HTTP_ACL; break;
case 'B': parser->method = HTTP_BIND; break;
case 'C': parser->method = HTTP_CONNECT; /* or COPY, CHECKOUT */ break;
case 'D': parser->method = HTTP_DELETE; break;
case 'G': parser->method = HTTP_GET; break;
case 'H': parser->method = HTTP_HEAD; break;
case 'L': parser->method = HTTP_LOCK; /* or LINK */ break;
case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE, M-SEARCH, MKCALENDAR */ break;
case 'N': parser->method = HTTP_NOTIFY; break;
case 'O': parser->method = HTTP_OPTIONS; break;
case 'P': parser->method = HTTP_POST;
/* or PROPFIND|PROPPATCH|PUT|PATCH|PURGE */
break;
case 'R': parser->method = HTTP_REPORT; /* or REBIND */ break;
case 'S': parser->method = HTTP_SUBSCRIBE; /* or SEARCH, SOURCE */ break;
case 'T': parser->method = HTTP_TRACE; break;
case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE, UNBIND, UNLINK */ break;
default:
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
UPDATE_STATE(s_req_method);
CALLBACK_NOTIFY(message_begin);
break;
}
case s_req_method:
{
const char *matcher;
if (UNLIKELY(ch == '\0')) {
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
matcher = method_strings[parser->method];
if (ch == ' ' && matcher[parser->index] == '\0') {
UPDATE_STATE(s_req_spaces_before_url);
} else if (ch == matcher[parser->index]) {
; /* nada */
} else if ((ch >= 'A' && ch <= 'Z') || ch == '-') {
switch (parser->method << 16 | parser->index << 8 | ch) {
#define XX(meth, pos, ch, new_meth) \
case (HTTP_##meth << 16 | pos << 8 | ch): \
parser->method = HTTP_##new_meth; break;
XX(POST, 1, 'U', PUT)
XX(POST, 1, 'A', PATCH)
XX(POST, 1, 'R', PROPFIND)
XX(PUT, 2, 'R', PURGE)
XX(CONNECT, 1, 'H', CHECKOUT)
XX(CONNECT, 2, 'P', COPY)
XX(MKCOL, 1, 'O', MOVE)
XX(MKCOL, 1, 'E', MERGE)
XX(MKCOL, 1, '-', MSEARCH)
XX(MKCOL, 2, 'A', MKACTIVITY)
XX(MKCOL, 3, 'A', MKCALENDAR)
XX(SUBSCRIBE, 1, 'E', SEARCH)
XX(SUBSCRIBE, 1, 'O', SOURCE)
XX(REPORT, 2, 'B', REBIND)
XX(PROPFIND, 4, 'P', PROPPATCH)
XX(LOCK, 1, 'I', LINK)
XX(UNLOCK, 2, 'S', UNSUBSCRIBE)
XX(UNLOCK, 2, 'B', UNBIND)
XX(UNLOCK, 3, 'I', UNLINK)
#undef XX
default:
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
} else {
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
++parser->index;
break;
}
case s_req_spaces_before_url:
{
if (ch == ' ') break;
MARK(url);
if (parser->method == HTTP_CONNECT) {
UPDATE_STATE(s_req_server_start);
}
UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch));
if (UNLIKELY(CURRENT_STATE() == s_dead)) {
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
break;
}
case s_req_schema:
case s_req_schema_slash:
case s_req_schema_slash_slash:
case s_req_server_start:
{
switch (ch) {
/* No whitespace allowed here */
case ' ':
case CR:
case LF:
SET_ERRNO(HPE_INVALID_URL);
goto error;
default:
UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch));
if (UNLIKELY(CURRENT_STATE() == s_dead)) {
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
}
break;
}
case s_req_server:
case s_req_server_with_at:
case s_req_path:
case s_req_query_string_start:
case s_req_query_string:
case s_req_fragment_start:
case s_req_fragment:
{
switch (ch) {
case ' ':
UPDATE_STATE(s_req_http_start);
CALLBACK_DATA(url);
break;
case CR:
case LF:
parser->http_major = 0;
parser->http_minor = 9;
UPDATE_STATE((ch == CR) ?
s_req_line_almost_done :
s_header_field_start);
CALLBACK_DATA(url);
break;
default:
UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch));
if (UNLIKELY(CURRENT_STATE() == s_dead)) {
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
}
break;
}
case s_req_http_start:
switch (ch) {
case ' ':
break;
case 'H':
UPDATE_STATE(s_req_http_H);
break;
case 'I':
if (parser->method == HTTP_SOURCE) {
UPDATE_STATE(s_req_http_I);
break;
}
/* fall through */
default:
SET_ERRNO(HPE_INVALID_CONSTANT);
goto error;
}
break;
case s_req_http_H:
STRICT_CHECK(ch != 'T');
UPDATE_STATE(s_req_http_HT);
break;
case s_req_http_HT:
STRICT_CHECK(ch != 'T');
UPDATE_STATE(s_req_http_HTT);
break;
case s_req_http_HTT:
STRICT_CHECK(ch != 'P');
UPDATE_STATE(s_req_http_HTTP);
break;
case s_req_http_I:
STRICT_CHECK(ch != 'C');
UPDATE_STATE(s_req_http_IC);
break;
case s_req_http_IC:
STRICT_CHECK(ch != 'E');
UPDATE_STATE(s_req_http_HTTP); /* Treat "ICE" as "HTTP". */
break;
case s_req_http_HTTP:
STRICT_CHECK(ch != '/');
UPDATE_STATE(s_req_http_major);
break;
case s_req_http_major:
if (UNLIKELY(!IS_NUM(ch))) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
parser->http_major = ch - '0';
UPDATE_STATE(s_req_http_dot);
break;
case s_req_http_dot:
{
if (UNLIKELY(ch != '.')) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
UPDATE_STATE(s_req_http_minor);
break;
}
case s_req_http_minor:
if (UNLIKELY(!IS_NUM(ch))) {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
parser->http_minor = ch - '0';
UPDATE_STATE(s_req_http_end);
break;
case s_req_http_end:
{
if (ch == CR) {
UPDATE_STATE(s_req_line_almost_done);
break;
}
if (ch == LF) {
UPDATE_STATE(s_header_field_start);
break;
}
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
break;
}
/* end of request line */
case s_req_line_almost_done:
{
if (UNLIKELY(ch != LF)) {
SET_ERRNO(HPE_LF_EXPECTED);
goto error;
}
UPDATE_STATE(s_header_field_start);
break;
}
case s_header_field_start:
{
if (ch == CR) {
UPDATE_STATE(s_headers_almost_done);
break;
}
if (ch == LF) {
/* they might be just sending \n instead of \r\n so this would be
* the second \n to denote the end of headers*/
UPDATE_STATE(s_headers_almost_done);
REEXECUTE();
}
c = TOKEN(ch);
if (UNLIKELY(!c)) {
SET_ERRNO(HPE_INVALID_HEADER_TOKEN);
goto error;
}
MARK(header_field);
parser->index = 0;
UPDATE_STATE(s_header_field);
switch (c) {
case 'c':
parser->header_state = h_C;
break;
case 'p':
parser->header_state = h_matching_proxy_connection;
break;
case 't':
parser->header_state = h_matching_transfer_encoding;
break;
case 'u':
parser->header_state = h_matching_upgrade;
break;
default:
parser->header_state = h_general;
break;
}
break;
}
case s_header_field:
{
const char* start = p;
for (; p != data + len; p++) {
ch = *p;
c = TOKEN(ch);
if (!c)
break;
switch (parser->header_state) {
case h_general: {
size_t left = data + len - p;
const char* pe = p + MIN(left, max_header_size);
while (p+1 < pe && TOKEN(p[1])) {
p++;
}
break;
}
case h_C:
parser->index++;
parser->header_state = (c == 'o' ? h_CO : h_general);
break;
case h_CO:
parser->index++;
parser->header_state = (c == 'n' ? h_CON : h_general);
break;
case h_CON:
parser->index++;
switch (c) {
case 'n':
parser->header_state = h_matching_connection;
break;
case 't':
parser->header_state = h_matching_content_length;
break;
default:
parser->header_state = h_general;
break;
}
break;
/* connection */
case h_matching_connection:
parser->index++;
if (parser->index > sizeof(CONNECTION)-1
|| c != CONNECTION[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(CONNECTION)-2) {
parser->header_state = h_connection;
}
break;
/* proxy-connection */
case h_matching_proxy_connection:
parser->index++;
if (parser->index > sizeof(PROXY_CONNECTION)-1
|| c != PROXY_CONNECTION[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(PROXY_CONNECTION)-2) {
parser->header_state = h_connection;
}
break;
/* content-length */
case h_matching_content_length:
parser->index++;
if (parser->index > sizeof(CONTENT_LENGTH)-1
|| c != CONTENT_LENGTH[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(CONTENT_LENGTH)-2) {
parser->header_state = h_content_length;
}
break;
/* transfer-encoding */
case h_matching_transfer_encoding:
parser->index++;
if (parser->index > sizeof(TRANSFER_ENCODING)-1
|| c != TRANSFER_ENCODING[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(TRANSFER_ENCODING)-2) {
parser->header_state = h_transfer_encoding;
parser->extra_flags |= F_TRANSFER_ENCODING >> 8;
}
break;
/* upgrade */
case h_matching_upgrade:
parser->index++;
if (parser->index > sizeof(UPGRADE)-1
|| c != UPGRADE[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(UPGRADE)-2) {
parser->header_state = h_upgrade;
}
break;
case h_connection:
case h_content_length:
case h_transfer_encoding:
case h_upgrade:
if (ch != ' ') parser->header_state = h_general;
break;
default:
assert(0 && "Unknown header_state");
break;
}
}
if (p == data + len) {
--p;
COUNT_HEADER_SIZE(p - start);
break;
}
COUNT_HEADER_SIZE(p - start);
if (ch == ':') {
UPDATE_STATE(s_header_value_discard_ws);
CALLBACK_DATA(header_field);
break;
}
SET_ERRNO(HPE_INVALID_HEADER_TOKEN);
goto error;
}
case s_header_value_discard_ws:
if (ch == ' ' || ch == '\t') break;
if (ch == CR) {
UPDATE_STATE(s_header_value_discard_ws_almost_done);
break;
}
if (ch == LF) {
UPDATE_STATE(s_header_value_discard_lws);
break;
}
/* fall through */
case s_header_value_start:
{
MARK(header_value);
UPDATE_STATE(s_header_value);
parser->index = 0;
c = LOWER(ch);
switch (parser->header_state) {
case h_upgrade:
parser->flags |= F_UPGRADE;
parser->header_state = h_general;
break;
case h_transfer_encoding:
/* looking for 'Transfer-Encoding: chunked' */
if ('c' == c) {
parser->header_state = h_matching_transfer_encoding_chunked;
} else {
parser->header_state = h_matching_transfer_encoding_token;
}
break;
/* Multi-value `Transfer-Encoding` header */
case h_matching_transfer_encoding_token_start:
break;
case h_content_length:
if (UNLIKELY(!IS_NUM(ch))) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
goto error;
}
if (parser->flags & F_CONTENTLENGTH) {
SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH);
goto error;
}
parser->flags |= F_CONTENTLENGTH;
parser->content_length = ch - '0';
parser->header_state = h_content_length_num;
break;
/* when obsolete line folding is encountered for content length
* continue to the s_header_value state */
case h_content_length_ws:
break;
case h_connection:
/* looking for 'Connection: keep-alive' */
if (c == 'k') {
parser->header_state = h_matching_connection_keep_alive;
/* looking for 'Connection: close' */
} else if (c == 'c') {
parser->header_state = h_matching_connection_close;
} else if (c == 'u') {
parser->header_state = h_matching_connection_upgrade;
} else {
parser->header_state = h_matching_connection_token;
}
break;
/* Multi-value `Connection` header */
case h_matching_connection_token_start:
break;
default:
parser->header_state = h_general;
break;
}
break;
}
case s_header_value:
{
const char* start = p;
enum header_states h_state = (enum header_states) parser->header_state;
for (; p != data + len; p++) {
ch = *p;
if (ch == CR) {
UPDATE_STATE(s_header_almost_done);
parser->header_state = h_state;
CALLBACK_DATA(header_value);
break;
}
if (ch == LF) {
UPDATE_STATE(s_header_almost_done);
COUNT_HEADER_SIZE(p - start);
parser->header_state = h_state;
CALLBACK_DATA_NOADVANCE(header_value);
REEXECUTE();
}
if (!lenient && !IS_HEADER_CHAR(ch)) {
SET_ERRNO(HPE_INVALID_HEADER_TOKEN);
goto error;
}
c = LOWER(ch);
switch (h_state) {
case h_general:
{
size_t left = data + len - p;
const char* pe = p + MIN(left, max_header_size);
for (; p != pe; p++) {
ch = *p;
if (ch == CR || ch == LF) {
--p;
break;
}
if (!lenient && !IS_HEADER_CHAR(ch)) {
SET_ERRNO(HPE_INVALID_HEADER_TOKEN);
goto error;
}
}
if (p == data + len)
--p;
break;
}
case h_connection:
case h_transfer_encoding:
assert(0 && "Shouldn't get here.");
break;
case h_content_length:
if (ch == ' ') break;
h_state = h_content_length_num;
/* fall through */
case h_content_length_num:
{
uint64_t t;
if (ch == ' ') {
h_state = h_content_length_ws;
break;
}
if (UNLIKELY(!IS_NUM(ch))) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
parser->header_state = h_state;
goto error;
}
t = parser->content_length;
t *= 10;
t += ch - '0';
/* Overflow? Test against a conservative limit for simplicity. */
if (UNLIKELY((ULLONG_MAX - 10) / 10 < parser->content_length)) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
parser->header_state = h_state;
goto error;
}
parser->content_length = t;
break;
}
case h_content_length_ws:
if (ch == ' ') break;
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
parser->header_state = h_state;
goto error;
/* Transfer-Encoding: chunked */
case h_matching_transfer_encoding_token_start:
/* looking for 'Transfer-Encoding: chunked' */
if ('c' == c) {
h_state = h_matching_transfer_encoding_chunked;
} else if (STRICT_TOKEN(c)) {
/* TODO(indutny): similar code below does this, but why?
* At the very least it seems to be inconsistent given that
* h_matching_transfer_encoding_token does not check for
* `STRICT_TOKEN`
*/
h_state = h_matching_transfer_encoding_token;
} else if (c == ' ' || c == '\t') {
/* Skip lws */
} else {
h_state = h_general;
}
break;
case h_matching_transfer_encoding_chunked:
parser->index++;
if (parser->index > sizeof(CHUNKED)-1
|| c != CHUNKED[parser->index]) {
h_state = h_matching_transfer_encoding_token;
} else if (parser->index == sizeof(CHUNKED)-2) {
h_state = h_transfer_encoding_chunked;
}
break;
case h_matching_transfer_encoding_token:
if (ch == ',') {
h_state = h_matching_transfer_encoding_token_start;
parser->index = 0;
}
break;
case h_matching_connection_token_start:
/* looking for 'Connection: keep-alive' */
if (c == 'k') {
h_state = h_matching_connection_keep_alive;
/* looking for 'Connection: close' */
} else if (c == 'c') {
h_state = h_matching_connection_close;
} else if (c == 'u') {
h_state = h_matching_connection_upgrade;
} else if (STRICT_TOKEN(c)) {
h_state = h_matching_connection_token;
} else if (c == ' ' || c == '\t') {
/* Skip lws */
} else {
h_state = h_general;
}
break;
/* looking for 'Connection: keep-alive' */
case h_matching_connection_keep_alive:
parser->index++;
if (parser->index > sizeof(KEEP_ALIVE)-1
|| c != KEEP_ALIVE[parser->index]) {
h_state = h_matching_connection_token;
} else if (parser->index == sizeof(KEEP_ALIVE)-2) {
h_state = h_connection_keep_alive;
}
break;
/* looking for 'Connection: close' */
case h_matching_connection_close:
parser->index++;
if (parser->index > sizeof(CLOSE)-1 || c != CLOSE[parser->index]) {
h_state = h_matching_connection_token;
} else if (parser->index == sizeof(CLOSE)-2) {
h_state = h_connection_close;
}
break;
/* looking for 'Connection: upgrade' */
case h_matching_connection_upgrade:
parser->index++;
if (parser->index > sizeof(UPGRADE) - 1 ||
c != UPGRADE[parser->index]) {
h_state = h_matching_connection_token;
} else if (parser->index == sizeof(UPGRADE)-2) {
h_state = h_connection_upgrade;
}
break;
case h_matching_connection_token:
if (ch == ',') {
h_state = h_matching_connection_token_start;
parser->index = 0;
}
break;
case h_transfer_encoding_chunked:
if (ch != ' ') h_state = h_matching_transfer_encoding_token;
break;
case h_connection_keep_alive:
case h_connection_close:
case h_connection_upgrade:
if (ch == ',') {
if (h_state == h_connection_keep_alive) {
parser->flags |= F_CONNECTION_KEEP_ALIVE;
} else if (h_state == h_connection_close) {
parser->flags |= F_CONNECTION_CLOSE;
} else if (h_state == h_connection_upgrade) {
parser->flags |= F_CONNECTION_UPGRADE;
}
h_state = h_matching_connection_token_start;
parser->index = 0;
} else if (ch != ' ') {
h_state = h_matching_connection_token;
}
break;
default:
UPDATE_STATE(s_header_value);
h_state = h_general;
break;
}
}
parser->header_state = h_state;
if (p == data + len)
--p;
COUNT_HEADER_SIZE(p - start);
break;
}
case s_header_almost_done:
{
if (UNLIKELY(ch != LF)) {
SET_ERRNO(HPE_LF_EXPECTED);
goto error;
}
UPDATE_STATE(s_header_value_lws);
break;
}
case s_header_value_lws:
{
if (ch == ' ' || ch == '\t') {
if (parser->header_state == h_content_length_num) {
/* treat obsolete line folding as space */
parser->header_state = h_content_length_ws;
}
UPDATE_STATE(s_header_value_start);
REEXECUTE();
}
/* finished the header */
switch (parser->header_state) {
case h_connection_keep_alive:
parser->flags |= F_CONNECTION_KEEP_ALIVE;
break;
case h_connection_close:
parser->flags |= F_CONNECTION_CLOSE;
break;
case h_transfer_encoding_chunked:
parser->flags |= F_CHUNKED;
break;
case h_connection_upgrade:
parser->flags |= F_CONNECTION_UPGRADE;
break;
default:
break;
}
UPDATE_STATE(s_header_field_start);
REEXECUTE();
}
case s_header_value_discard_ws_almost_done:
{
STRICT_CHECK(ch != LF);
UPDATE_STATE(s_header_value_discard_lws);
break;
}
case s_header_value_discard_lws:
{
if (ch == ' ' || ch == '\t') {
UPDATE_STATE(s_header_value_discard_ws);
break;
} else {
switch (parser->header_state) {
case h_connection_keep_alive:
parser->flags |= F_CONNECTION_KEEP_ALIVE;
break;
case h_connection_close:
parser->flags |= F_CONNECTION_CLOSE;
break;
case h_connection_upgrade:
parser->flags |= F_CONNECTION_UPGRADE;
break;
case h_transfer_encoding_chunked:
parser->flags |= F_CHUNKED;
break;
case h_content_length:
/* do not allow empty content length */
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
goto error;
break;
default:
break;
}
/* header value was empty */
MARK(header_value);
UPDATE_STATE(s_header_field_start);
CALLBACK_DATA_NOADVANCE(header_value);
REEXECUTE();
}
}
case s_headers_almost_done:
{
STRICT_CHECK(ch != LF);
if (parser->flags & F_TRAILING) {
/* End of a chunked request */
UPDATE_STATE(s_message_done);
CALLBACK_NOTIFY_NOADVANCE(chunk_complete);
REEXECUTE();
}
/* Cannot us transfer-encoding and a content-length header together
per the HTTP specification. (RFC 7230 Section 3.3.3) */
if ((parser->extra_flags & (F_TRANSFER_ENCODING >> 8)) &&
(parser->flags & F_CONTENTLENGTH)) {
/* Allow it for lenient parsing as long as `Transfer-Encoding` is
* not `chunked`
*/
if (!lenient || (parser->flags & F_CHUNKED)) {
SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH);
goto error;
}
}
UPDATE_STATE(s_headers_done);
/* Set this here so that on_headers_complete() callbacks can see it */
if ((parser->flags & F_UPGRADE) &&
(parser->flags & F_CONNECTION_UPGRADE)) {
/* For responses, "Upgrade: foo" and "Connection: upgrade" are
* mandatory only when it is a 101 Switching Protocols response,
* otherwise it is purely informational, to announce support.
*/
parser->upgrade =
(parser->type == HTTP_REQUEST || parser->status_code == 101);
} else {
parser->upgrade = (parser->method == HTTP_CONNECT);
}
/* Here we call the headers_complete callback. This is somewhat
* different than other callbacks because if the user returns 1, we
* will interpret that as saying that this message has no body. This
* is needed for the annoying case of recieving a response to a HEAD
* request.
*
* We'd like to use CALLBACK_NOTIFY_NOADVANCE() here but we cannot, so
* we have to simulate it by handling a change in errno below.
*/
if (settings->on_headers_complete) {
switch (settings->on_headers_complete(parser)) {
case 0:
break;
case 2:
parser->upgrade = 1;
/* fall through */
case 1:
parser->flags |= F_SKIPBODY;
break;
default:
SET_ERRNO(HPE_CB_headers_complete);
RETURN(p - data); /* Error */
}
}
if (HTTP_PARSER_ERRNO(parser) != HPE_OK) {
RETURN(p - data);
}
REEXECUTE();
}
case s_headers_done:
{
int hasBody;
STRICT_CHECK(ch != LF);
parser->nread = 0;
nread = 0;
hasBody = parser->flags & F_CHUNKED ||
(parser->content_length > 0 && parser->content_length != ULLONG_MAX);
if (parser->upgrade && (parser->method == HTTP_CONNECT ||
(parser->flags & F_SKIPBODY) || !hasBody)) {
/* Exit, the rest of the message is in a different protocol. */
UPDATE_STATE(NEW_MESSAGE());
CALLBACK_NOTIFY(message_complete);
RETURN((p - data) + 1);
}
if (parser->flags & F_SKIPBODY) {
UPDATE_STATE(NEW_MESSAGE());
CALLBACK_NOTIFY(message_complete);
} else if (parser->flags & F_CHUNKED) {
/* chunked encoding - ignore Content-Length header,
* prepare for a chunk */
UPDATE_STATE(s_chunk_size_start);
} else if (parser->extra_flags & (F_TRANSFER_ENCODING >> 8)) {
if (parser->type == HTTP_REQUEST && !lenient) {
/* RFC 7230 3.3.3 */
/* If a Transfer-Encoding header field
* is present in a request and the chunked transfer coding is not
* the final encoding, the message body length cannot be determined
* reliably; the server MUST respond with the 400 (Bad Request)
* status code and then close the connection.
*/
SET_ERRNO(HPE_INVALID_TRANSFER_ENCODING);
RETURN(p - data); /* Error */
} else {
/* RFC 7230 3.3.3 */
/* If a Transfer-Encoding header field is present in a response and
* the chunked transfer coding is not the final encoding, the
* message body length is determined by reading the connection until
* it is closed by the server.
*/
UPDATE_STATE(s_body_identity_eof);
}
} else {
if (parser->content_length == 0) {
/* Content-Length header given but zero: Content-Length: 0\r\n */
UPDATE_STATE(NEW_MESSAGE());
CALLBACK_NOTIFY(message_complete);
} else if (parser->content_length != ULLONG_MAX) {
/* Content-Length header given and non-zero */
UPDATE_STATE(s_body_identity);
} else {
if (!http_message_needs_eof(parser)) {
/* Assume content-length 0 - read the next */
UPDATE_STATE(NEW_MESSAGE());
CALLBACK_NOTIFY(message_complete);
} else {
/* Read body until EOF */
UPDATE_STATE(s_body_identity_eof);
}
}
}
break;
}
case s_body_identity:
{
uint64_t to_read = MIN(parser->content_length,
(uint64_t) ((data + len) - p));
assert(parser->content_length != 0
&& parser->content_length != ULLONG_MAX);
/* The difference between advancing content_length and p is because
* the latter will automaticaly advance on the next loop iteration.
* Further, if content_length ends up at 0, we want to see the last
* byte again for our message complete callback.
*/
MARK(body);
parser->content_length -= to_read;
p += to_read - 1;
if (parser->content_length == 0) {
UPDATE_STATE(s_message_done);
/* Mimic CALLBACK_DATA_NOADVANCE() but with one extra byte.
*
* The alternative to doing this is to wait for the next byte to
* trigger the data callback, just as in every other case. The
* problem with this is that this makes it difficult for the test
* harness to distinguish between complete-on-EOF and
* complete-on-length. It's not clear that this distinction is
* important for applications, but let's keep it for now.
*/
CALLBACK_DATA_(body, p - body_mark + 1, p - data);
REEXECUTE();
}
break;
}
/* read until EOF */
case s_body_identity_eof:
MARK(body);
p = data + len - 1;
break;
case s_message_done:
UPDATE_STATE(NEW_MESSAGE());
CALLBACK_NOTIFY(message_complete);
if (parser->upgrade) {
/* Exit, the rest of the message is in a different protocol. */
RETURN((p - data) + 1);
}
break;
case s_chunk_size_start:
{
assert(nread == 1);
assert(parser->flags & F_CHUNKED);
unhex_val = unhex[(unsigned char)ch];
if (UNLIKELY(unhex_val == -1)) {
SET_ERRNO(HPE_INVALID_CHUNK_SIZE);
goto error;
}
parser->content_length = unhex_val;
UPDATE_STATE(s_chunk_size);
break;
}
case s_chunk_size:
{
uint64_t t;
assert(parser->flags & F_CHUNKED);
if (ch == CR) {
UPDATE_STATE(s_chunk_size_almost_done);
break;
}
unhex_val = unhex[(unsigned char)ch];
if (unhex_val == -1) {
if (ch == ';' || ch == ' ') {
UPDATE_STATE(s_chunk_parameters);
break;
}
SET_ERRNO(HPE_INVALID_CHUNK_SIZE);
goto error;
}
t = parser->content_length;
t *= 16;
t += unhex_val;
/* Overflow? Test against a conservative limit for simplicity. */
if (UNLIKELY((ULLONG_MAX - 16) / 16 < parser->content_length)) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
goto error;
}
parser->content_length = t;
break;
}
case s_chunk_parameters:
{
assert(parser->flags & F_CHUNKED);
/* just ignore this shit. TODO check for overflow */
if (ch == CR) {
UPDATE_STATE(s_chunk_size_almost_done);
break;
}
break;
}
case s_chunk_size_almost_done:
{
assert(parser->flags & F_CHUNKED);
STRICT_CHECK(ch != LF);
parser->nread = 0;
nread = 0;
if (parser->content_length == 0) {
parser->flags |= F_TRAILING;
UPDATE_STATE(s_header_field_start);
} else {
UPDATE_STATE(s_chunk_data);
}
CALLBACK_NOTIFY(chunk_header);
break;
}
case s_chunk_data:
{
uint64_t to_read = MIN(parser->content_length,
(uint64_t) ((data + len) - p));
assert(parser->flags & F_CHUNKED);
assert(parser->content_length != 0
&& parser->content_length != ULLONG_MAX);
/* See the explanation in s_body_identity for why the content
* length and data pointers are managed this way.
*/
MARK(body);
parser->content_length -= to_read;
p += to_read - 1;
if (parser->content_length == 0) {
UPDATE_STATE(s_chunk_data_almost_done);
}
break;
}
case s_chunk_data_almost_done:
assert(parser->flags & F_CHUNKED);
assert(parser->content_length == 0);
STRICT_CHECK(ch != CR);
UPDATE_STATE(s_chunk_data_done);
CALLBACK_DATA(body);
break;
case s_chunk_data_done:
assert(parser->flags & F_CHUNKED);
STRICT_CHECK(ch != LF);
parser->nread = 0;
nread = 0;
UPDATE_STATE(s_chunk_size_start);
CALLBACK_NOTIFY(chunk_complete);
break;
default:
assert(0 && "unhandled state");
SET_ERRNO(HPE_INVALID_INTERNAL_STATE);
goto error;
}
}
/* Run callbacks for any marks that we have leftover after we ran out of
* bytes. There should be at most one of these set, so it's OK to invoke
* them in series (unset marks will not result in callbacks).
*
* We use the NOADVANCE() variety of callbacks here because 'p' has already
* overflowed 'data' and this allows us to correct for the off-by-one that
* we'd otherwise have (since CALLBACK_DATA() is meant to be run with a 'p'
* value that's in-bounds).
*/
assert(((header_field_mark ? 1 : 0) +
(header_value_mark ? 1 : 0) +
(url_mark ? 1 : 0) +
(body_mark ? 1 : 0) +
(status_mark ? 1 : 0)) <= 1);
CALLBACK_DATA_NOADVANCE(header_field);
CALLBACK_DATA_NOADVANCE(header_value);
CALLBACK_DATA_NOADVANCE(url);
CALLBACK_DATA_NOADVANCE(body);
CALLBACK_DATA_NOADVANCE(status);
RETURN(len);
error:
if (HTTP_PARSER_ERRNO(parser) == HPE_OK) {
SET_ERRNO(HPE_UNKNOWN);
}
RETURN(p - data);
}
/* Does the parser need to see an EOF to find the end of the message? */
int
http_message_needs_eof (const http_parser *parser)
{
if (parser->type == HTTP_REQUEST) {
return 0;
}
/* See RFC 2616 section 4.4 */
if (parser->status_code / 100 == 1 || /* 1xx e.g. Continue */
parser->status_code == 204 || /* No Content */
parser->status_code == 304 || /* Not Modified */
parser->flags & F_SKIPBODY) { /* response to a HEAD request */
return 0;
}
/* RFC 7230 3.3.3, see `s_headers_almost_done` */
if ((parser->extra_flags & (F_TRANSFER_ENCODING >> 8)) &&
(parser->flags & F_CHUNKED) == 0) {
return 1;
}
if ((parser->flags & F_CHUNKED) || parser->content_length != ULLONG_MAX) {
return 0;
}
return 1;
}
int
http_should_keep_alive (const http_parser *parser)
{
if (parser->http_major > 0 && parser->http_minor > 0) {
/* HTTP/1.1 */
if (parser->flags & F_CONNECTION_CLOSE) {
return 0;
}
} else {
/* HTTP/1.0 or earlier */
if (!(parser->flags & F_CONNECTION_KEEP_ALIVE)) {
return 0;
}
}
return !http_message_needs_eof(parser);
}
const char *
http_method_str (enum http_method m)
{
return ELEM_AT(method_strings, m, "<unknown>");
}
const char *
http_status_str (enum http_status s)
{
switch (s) {
#define XX(num, name, string) case HTTP_STATUS_##name: return #string;
HTTP_STATUS_MAP(XX)
#undef XX
default: return "<unknown>";
}
}
void
http_parser_init (http_parser *parser, enum http_parser_type t)
{
void *data = parser->data; /* preserve application data */
memset(parser, 0, sizeof(*parser));
parser->data = data;
parser->type = t;
parser->state = (t == HTTP_REQUEST ? s_start_req : (t == HTTP_RESPONSE ? s_start_res : s_start_req_or_res));
parser->http_errno = HPE_OK;
}
void
http_parser_settings_init(http_parser_settings *settings)
{
memset(settings, 0, sizeof(*settings));
}
const char *
http_errno_name(enum http_errno err) {
assert(((size_t) err) < ARRAY_SIZE(http_strerror_tab));
return http_strerror_tab[err].name;
}
const char *
http_errno_description(enum http_errno err) {
assert(((size_t) err) < ARRAY_SIZE(http_strerror_tab));
return http_strerror_tab[err].description;
}
static enum http_host_state
http_parse_host_char(enum http_host_state s, const char ch) {
switch(s) {
case s_http_userinfo:
case s_http_userinfo_start:
if (ch == '@') {
return s_http_host_start;
}
if (IS_USERINFO_CHAR(ch)) {
return s_http_userinfo;
}
break;
case s_http_host_start:
if (ch == '[') {
return s_http_host_v6_start;
}
if (IS_HOST_CHAR(ch)) {
return s_http_host;
}
break;
case s_http_host:
if (IS_HOST_CHAR(ch)) {
return s_http_host;
}
/* fall through */
case s_http_host_v6_end:
if (ch == ':') {
return s_http_host_port_start;
}
break;
case s_http_host_v6:
if (ch == ']') {
return s_http_host_v6_end;
}
/* fall through */
case s_http_host_v6_start:
if (IS_HEX(ch) || ch == ':' || ch == '.') {
return s_http_host_v6;
}
if (s == s_http_host_v6 && ch == '%') {
return s_http_host_v6_zone_start;
}
break;
case s_http_host_v6_zone:
if (ch == ']') {
return s_http_host_v6_end;
}
/* fall through */
case s_http_host_v6_zone_start:
/* RFC 6874 Zone ID consists of 1*( unreserved / pct-encoded) */
if (IS_ALPHANUM(ch) || ch == '%' || ch == '.' || ch == '-' || ch == '_' ||
ch == '~') {
return s_http_host_v6_zone;
}
break;
case s_http_host_port:
case s_http_host_port_start:
if (IS_NUM(ch)) {
return s_http_host_port;
}
break;
default:
break;
}
return s_http_host_dead;
}
static int
http_parse_host(const char * buf, struct http_parser_url *u, int found_at) {
enum http_host_state s;
const char *p;
size_t buflen = u->field_data[UF_HOST].off + u->field_data[UF_HOST].len;
assert(u->field_set & (1 << UF_HOST));
u->field_data[UF_HOST].len = 0;
s = found_at ? s_http_userinfo_start : s_http_host_start;
for (p = buf + u->field_data[UF_HOST].off; p < buf + buflen; p++) {
enum http_host_state new_s = http_parse_host_char(s, *p);
if (new_s == s_http_host_dead) {
return 1;
}
switch(new_s) {
case s_http_host:
if (s != s_http_host) {
u->field_data[UF_HOST].off = (uint16_t)(p - buf);
}
u->field_data[UF_HOST].len++;
break;
case s_http_host_v6:
if (s != s_http_host_v6) {
u->field_data[UF_HOST].off = (uint16_t)(p - buf);
}
u->field_data[UF_HOST].len++;
break;
case s_http_host_v6_zone_start:
case s_http_host_v6_zone:
u->field_data[UF_HOST].len++;
break;
case s_http_host_port:
if (s != s_http_host_port) {
u->field_data[UF_PORT].off = (uint16_t)(p - buf);
u->field_data[UF_PORT].len = 0;
u->field_set |= (1 << UF_PORT);
}
u->field_data[UF_PORT].len++;
break;
case s_http_userinfo:
if (s != s_http_userinfo) {
u->field_data[UF_USERINFO].off = (uint16_t)(p - buf);
u->field_data[UF_USERINFO].len = 0;
u->field_set |= (1 << UF_USERINFO);
}
u->field_data[UF_USERINFO].len++;
break;
default:
break;
}
s = new_s;
}
/* Make sure we don't end somewhere unexpected */
switch (s) {
case s_http_host_start:
case s_http_host_v6_start:
case s_http_host_v6:
case s_http_host_v6_zone_start:
case s_http_host_v6_zone:
case s_http_host_port_start:
case s_http_userinfo:
case s_http_userinfo_start:
return 1;
default:
break;
}
return 0;
}
void
http_parser_url_init(struct http_parser_url *u) {
memset(u, 0, sizeof(*u));
}
int
http_parser_parse_url(const char *buf, size_t buflen, int is_connect,
struct http_parser_url *u)
{
enum state s;
const char *p;
enum http_parser_url_fields uf, old_uf;
int found_at = 0;
if (buflen == 0) {
return 1;
}
u->port = u->field_set = 0;
s = is_connect ? s_req_server_start : s_req_spaces_before_url;
old_uf = UF_MAX;
for (p = buf; p < buf + buflen; p++) {
s = parse_url_char(s, *p);
/* Figure out the next field that we're operating on */
switch (s) {
case s_dead:
return 1;
/* Skip delimeters */
case s_req_schema_slash:
case s_req_schema_slash_slash:
case s_req_server_start:
case s_req_query_string_start:
case s_req_fragment_start:
continue;
case s_req_schema:
uf = UF_SCHEMA;
break;
case s_req_server_with_at:
found_at = 1;
/* fall through */
case s_req_server:
uf = UF_HOST;
break;
case s_req_path:
uf = UF_PATH;
break;
case s_req_query_string:
uf = UF_QUERY;
break;
case s_req_fragment:
uf = UF_FRAGMENT;
break;
default:
assert(!"Unexpected state");
return 1;
}
/* Nothing's changed; soldier on */
if (uf == old_uf) {
u->field_data[uf].len++;
continue;
}
u->field_data[uf].off = (uint16_t)(p - buf);
u->field_data[uf].len = 1;
u->field_set |= (1 << uf);
old_uf = uf;
}
/* host must be present if there is a schema */
/* parsing http:///toto will fail */
if ((u->field_set & (1 << UF_SCHEMA)) &&
(u->field_set & (1 << UF_HOST)) == 0) {
return 1;
}
if (u->field_set & (1 << UF_HOST)) {
if (http_parse_host(buf, u, found_at) != 0) {
return 1;
}
}
/* CONNECT requests can only contain "hostname:port" */
if (is_connect && u->field_set != ((1 << UF_HOST)|(1 << UF_PORT))) {
return 1;
}
if (u->field_set & (1 << UF_PORT)) {
uint16_t off;
uint16_t len;
const char* p;
const char* end;
unsigned long v;
off = u->field_data[UF_PORT].off;
len = u->field_data[UF_PORT].len;
end = buf + off + len;
/* NOTE: The characters are already validated and are in the [0-9] range */
assert(off + len <= buflen && "Port number overflow");
v = 0;
for (p = buf + off; p < end; p++) {
v *= 10;
v += *p - '0';
/* Ports have a max value of 2^16 */
if (v > 0xffff) {
return 1;
}
}
u->port = (uint16_t) v;
}
return 0;
}
void
http_parser_pause(http_parser *parser, int paused) {
/* Users should only be pausing/unpausing a parser that is not in an error
* state. In non-debug builds, there's not much that we can do about this
* other than ignore it.
*/
if (HTTP_PARSER_ERRNO(parser) == HPE_OK ||
HTTP_PARSER_ERRNO(parser) == HPE_PAUSED) {
uint32_t nread = parser->nread; /* used by the SET_ERRNO macro */
SET_ERRNO((paused) ? HPE_PAUSED : HPE_OK);
} else {
assert(0 && "Attempting to pause parser in error state");
}
}
int
http_body_is_final(const struct http_parser *parser) {
return parser->state == s_message_done;
}
unsigned long
http_parser_version(void) {
return HTTP_PARSER_VERSION_MAJOR * 0x10000 |
HTTP_PARSER_VERSION_MINOR * 0x00100 |
HTTP_PARSER_VERSION_PATCH * 0x00001;
}
void
http_parser_set_max_header_size(uint32_t size) {
max_header_size = size;
}
|