Skip to content

G
git2
Commit 64ac9548 by Vicent Marti
Options

Bump the builtin http-parser

parent 9a50026b
Showing with 1079 additions and 647 deletions
deps/http-parser/http_parser.c
......@@ -21,61 +21,100 @@
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include <http_parser.h>
#include "http_parser.h"
#include <assert.h>
#include <stddef.h>
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
#include <limits.h>
#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
#if HTTP_PARSER_DEBUG
#define SET_ERRNO(e) \
do { \
parser->http_errno = (e); \
parser->error_lineno = __LINE__; \
} while (0)
#else
#define SET_ERRNO(e) \
do { \
parser->http_errno = (e); \
} while(0)
#endif
#define CALLBACK2(FOR) \
/* Run the notify callback FOR, returning ER if it fails */
#define CALLBACK_NOTIFY_(FOR, ER) \
do { \
assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \
\
if (settings->on_##FOR) { \
if (0 != settings->on_##FOR(parser)) { \
SET_ERRNO(HPE_CB_##FOR); \
return (p - data); \
} \
\
/* We either errored above or got paused; get out */ \
if (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)
#define MARK(FOR) \
do { \
FOR##_mark = p; \
} while (0)
/* Run the notify callback FOR and don't consume the current byte */
#define CALLBACK_NOTIFY_NOADVANCE(FOR) CALLBACK_NOTIFY_(FOR, p - data)
#define CALLBACK(FOR) \
/* 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 (settings->on_##FOR) { \
if (0 != settings->on_##FOR(parser, \
FOR##_mark, \
p - FOR##_mark)) \
{ \
if (0 != settings->on_##FOR(parser, FOR##_mark, (LEN))) { \
SET_ERRNO(HPE_CB_##FOR); \
return (p - data); \
} \
\
/* We either errored above or got paused; get out */ \
if (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)
#define PROXY_CONNECTION "proxy-connection"
......@@ -89,30 +128,10 @@ do { \
static const char *method_strings[] =
{ "DELETE"
, "GET"
, "HEAD"
, "POST"
, "PUT"
, "CONNECT"
, "OPTIONS"
, "TRACE"
, "COPY"
, "LOCK"
, "MKCOL"
, "MOVE"
, "PROPFIND"
, "PROPPATCH"
, "UNLOCK"
, "REPORT"
, "MKACTIVITY"
, "CHECKOUT"
, "MERGE"
, "M-SEARCH"
, "NOTIFY"
, "SUBSCRIBE"
, "UNSUBSCRIBE"
, "PATCH"
{
#define XX(num, name, string) #string,
HTTP_METHOD_MAP(XX)
#undef XX
};
......@@ -133,9 +152,9 @@ static const char tokens[256] = {
/* 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 ' */
' ', '!', '"', '#', '$', '%', '&', '\'',
0, '!', 0, '#', '$', '%', '&', '\'',
/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */
0, 0, '*', '+', 0, '-', '.', '/',
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 ? */
......@@ -155,7 +174,7 @@ static const char tokens[256] = {
/* 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 };
'x', 'y', 'z', 0, '|', 0, '~', 0 };
static const int8_t unhex[256] =
......@@ -170,40 +189,48 @@ static const int8_t unhex[256] =
};
static const uint8_t normal_url_char[256] = {
#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,
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,
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,
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,
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,
/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */
0, 1, 1, 0, 1, 1, 1, 1,
0 | 2 | 4 | 0 | 16 | 32 | 64 | 128,
/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */
1, 1, 1, 1, 1, 1, 1, 1,
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, 1, 1, 1, 1, 1, 1, 1,
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */
1, 1, 1, 1, 1, 1, 1, 0,
1 | 2 | 4 | 8 | 16 | 32 | 64 | 0,
/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */
1, 1, 1, 1, 1, 1, 1, 1,
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, 1, 1, 1, 1, 1, 1, 1,
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, 1, 1, 1, 1, 1, 1, 1,
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */
1, 1, 1, 1, 1, 1, 1, 1,
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */
1, 1, 1, 1, 1, 1, 1, 1,
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, 1, 1, 1, 1, 1, 1, 1,
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, 1, 1, 1, 1, 1, 1, 1,
1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,
/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */
1, 1, 1, 1, 1, 1, 1, 0, };
1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, };
#undef T
enum state
{ s_dead = 1 /* important that this is > 0 */
......@@ -231,8 +258,9 @@ enum state
, s_req_schema
, s_req_schema_slash
, s_req_schema_slash_slash
, s_req_host
, s_req_port
, s_req_server_start
, s_req_server
, s_req_server_with_at
, s_req_path
, s_req_query_string_start
, s_req_query_string
......@@ -261,9 +289,11 @@ enum state
, s_chunk_size
, s_chunk_parameters
, s_chunk_size_almost_done
, s_headers_almost_done
/* Important: 's_headers_almost_done' must be the last 'header' state. All
, 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.
*/
......@@ -274,10 +304,12 @@ enum state
, s_body_identity
, s_body_identity_eof
, s_message_done
};
#define PARSING_HEADER(state) (state <= s_headers_almost_done)
#define PARSING_HEADER(state) (state <= s_headers_done)
enum header_states
......@@ -306,22 +338,43 @@ enum header_states
, h_connection_close
};
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_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 TOKEN(c) (tokens[(unsigned char)c])
#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) == ',')
#if HTTP_PARSER_STRICT
#define IS_URL_CHAR(c) (normal_url_char[(unsigned char) (c)])
#define TOKEN(c) (tokens[(unsigned char)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) ((c == ' ') ? ' ' : tokens[(unsigned char)c])
#define IS_URL_CHAR(c) \
(normal_url_char[(unsigned char) (c)] || ((c) & 0x80))
(BIT_AT(normal_url_char, (unsigned char)c) || ((c) & 0x80))
#define IS_HOST_CHAR(c) \
(IS_ALPHANUM(c) || (c) == '.' || (c) == '-' || (c) == '_')
#endif
......@@ -355,6 +408,166 @@ static struct {
};
#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;
}
/* FALLTHROUGH */
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,
......@@ -363,27 +576,24 @@ size_t http_parser_execute (http_parser *parser,
{
char c, ch;
int8_t unhex_val;
const char *p = data, *pe;
size_t to_read;
enum state state;
enum header_states header_state;
size_t index = parser->index;
size_t nread = parser->nread;
const char *header_field_mark, *header_value_mark, *url_mark;
const char *matcher;
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;
/* We're in an error state. Don't bother doing anything. */
if (HTTP_PARSER_ERRNO(parser) != HPE_OK) {
return 0;
}
state = (enum state) parser->state;
header_state = (enum header_states) parser->header_state;
if (len == 0) {
switch (state) {
switch (parser->state) {
case s_body_identity_eof:
CALLBACK2(message_complete);
/* 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:
......@@ -398,42 +608,49 @@ size_t http_parser_execute (http_parser *parser,
}
}
/* technically we could combine all of these (except for url_mark) into one
variable, saving stack space, but it seems more clear to have them
separated. */
header_field_mark = 0;
header_value_mark = 0;
url_mark = 0;
if (state == s_header_field)
if (parser->state == s_header_field)
header_field_mark = data;
if (state == s_header_value)
if (parser->state == s_header_value)
header_value_mark = data;
if (state == s_req_path || state == s_req_schema || state == s_req_schema_slash
|| state == s_req_schema_slash_slash || state == s_req_port
|| state == s_req_query_string_start || state == s_req_query_string
|| state == s_req_host
|| state == s_req_fragment_start || state == s_req_fragment)
switch (parser->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;
}
for (p=data, pe=data+len; p != pe; p++) {
for (p=data; p != data + len; p++) {
ch = *p;
if (PARSING_HEADER(state)) {
++nread;
if (PARSING_HEADER(parser->state)) {
++parser->nread;
/* Buffer overflow attack */
if (nread > HTTP_MAX_HEADER_SIZE) {
if (parser->nread > HTTP_MAX_HEADER_SIZE) {
SET_ERRNO(HPE_HEADER_OVERFLOW);
goto error;
}
}
switch (state) {
reexecute_byte:
switch (parser->state) {
case s_dead:
/* this state is used after a 'Connection: close' message
* the parser will error out if it reads another message
*/
if (ch == CR || ch == LF)
break;
SET_ERRNO(HPE_CLOSED_CONNECTION);
goto error;
......@@ -442,23 +659,25 @@ size_t http_parser_execute (http_parser *parser,
if (ch == CR || ch == LF)
break;
parser->flags = 0;
parser->content_length = -1;
parser->content_length = ULLONG_MAX;
CALLBACK2(message_begin);
if (ch == 'H') {
parser->state = s_res_or_resp_H;
if (ch == 'H')
state = s_res_or_resp_H;
else {
CALLBACK_NOTIFY(message_begin);
} else {
parser->type = HTTP_REQUEST;
goto start_req_method_assign;
parser->state = s_start_req;
goto reexecute_byte;
}
break;
}
case s_res_or_resp_H:
if (ch == 'T') {
parser->type = HTTP_RESPONSE;
state = s_res_HT;
parser->state = s_res_HT;
} else {
if (ch != 'E') {
SET_ERRNO(HPE_INVALID_CONSTANT);
......@@ -467,21 +686,19 @@ size_t http_parser_execute (http_parser *parser,
parser->type = HTTP_REQUEST;
parser->method = HTTP_HEAD;
index = 2;
state = s_req_method;
parser->index = 2;
parser->state = s_req_method;
}
break;
case s_start_res:
{
parser->flags = 0;
parser->content_length = -1;
CALLBACK2(message_begin);
parser->content_length = ULLONG_MAX;
switch (ch) {
case 'H':
state = s_res_H;
parser->state = s_res_H;
break;
case CR:
......@@ -492,44 +709,46 @@ size_t http_parser_execute (http_parser *parser,
SET_ERRNO(HPE_INVALID_CONSTANT);
goto error;
}
CALLBACK_NOTIFY(message_begin);
break;
}
case s_res_H:
STRICT_CHECK(ch != 'T');
state = s_res_HT;
parser->state = s_res_HT;
break;
case s_res_HT:
STRICT_CHECK(ch != 'T');
state = s_res_HTT;
parser->state = s_res_HTT;
break;
case s_res_HTT:
STRICT_CHECK(ch != 'P');
state = s_res_HTTP;
parser->state = s_res_HTTP;
break;
case s_res_HTTP:
STRICT_CHECK(ch != '/');
state = s_res_first_http_major;
parser->state = s_res_first_http_major;
break;
case s_res_first_http_major:
if (ch < '1' || ch > '9') {
if (ch < '0' || ch > '9') {
SET_ERRNO(HPE_INVALID_VERSION);
goto error;
}
parser->http_major = ch - '0';
state = s_res_http_major;
parser->state = s_res_http_major;
break;
/* major HTTP version or dot */
case s_res_http_major:
{
if (ch == '.') {
state = s_res_first_http_minor;
parser->state = s_res_first_http_minor;
break;
}
......@@ -557,14 +776,14 @@ size_t http_parser_execute (http_parser *parser,
}
parser->http_minor = ch - '0';
state = s_res_http_minor;
parser->state = s_res_http_minor;
break;
/* minor HTTP version or end of request line */
case s_res_http_minor:
{
if (ch == ' ') {
state = s_res_first_status_code;
parser->state = s_res_first_status_code;
break;
}
......@@ -595,7 +814,7 @@ size_t http_parser_execute (http_parser *parser,
goto error;
}
parser->status_code = ch - '0';
state = s_res_status_code;
parser->state = s_res_status_code;
break;
}
......@@ -604,13 +823,13 @@ size_t http_parser_execute (http_parser *parser,
if (!IS_NUM(ch)) {
switch (ch) {
case ' ':
state = s_res_status;
parser->state = s_res_status;
break;
case CR:
state = s_res_line_almost_done;
parser->state = s_res_line_almost_done;
break;
case LF:
state = s_header_field_start;
parser->state = s_header_field_start;
break;
default:
SET_ERRNO(HPE_INVALID_STATUS);
......@@ -634,19 +853,19 @@ size_t http_parser_execute (http_parser *parser,
/* the human readable status. e.g. "NOT FOUND"
* we are not humans so just ignore this */
if (ch == CR) {
state = s_res_line_almost_done;
parser->state = s_res_line_almost_done;
break;
}
if (ch == LF) {
state = s_header_field_start;
parser->state = s_header_field_start;
break;
}
break;
case s_res_line_almost_done:
STRICT_CHECK(ch != LF);
state = s_header_field_start;
parser->state = s_header_field_start;
break;
case s_start_req:
......@@ -654,18 +873,15 @@ size_t http_parser_execute (http_parser *parser,
if (ch == CR || ch == LF)
break;
parser->flags = 0;
parser->content_length = -1;
CALLBACK2(message_begin);
parser->content_length = ULLONG_MAX;
if (!IS_ALPHA(ch)) {
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
start_req_method_assign:
parser->method = (enum http_method) 0;
index = 1;
parser->index = 1;
switch (ch) {
case 'C': parser->method = HTTP_CONNECT; /* or COPY, CHECKOUT */ break;
case 'D': parser->method = HTTP_DELETE; break;
......@@ -676,341 +892,158 @@ size_t http_parser_execute (http_parser *parser,
case 'N': parser->method = HTTP_NOTIFY; break;
case 'O': parser->method = HTTP_OPTIONS; break;
case 'P': parser->method = HTTP_POST;
/* or PROPFIND or PROPPATCH or PUT or PATCH */
/* or PROPFIND|PROPPATCH|PUT|PATCH|PURGE */
break;
case 'R': parser->method = HTTP_REPORT; break;
case 'S': parser->method = HTTP_SUBSCRIBE; break;
case 'S': parser->method = HTTP_SUBSCRIBE; /* or SEARCH */ break;
case 'T': parser->method = HTTP_TRACE; break;
case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE */ break;
default:
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
state = s_req_method;
parser->state = s_req_method;
CALLBACK_NOTIFY(message_begin);
break;
}
case s_req_method:
{
const char *matcher;
if (ch == '\0') {
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
matcher = method_strings[parser->method];
if (ch == ' ' && matcher[index] == '\0') {
state = s_req_spaces_before_url;
} else if (ch == matcher[index]) {
if (ch == ' ' && matcher[parser->index] == '\0') {
parser->state = s_req_spaces_before_url;
} else if (ch == matcher[parser->index]) {
; /* nada */
} else if (parser->method == HTTP_CONNECT) {
if (index == 1 && ch == 'H') {
if (parser->index == 1 && ch == 'H') {
parser->method = HTTP_CHECKOUT;
} else if (index == 2 && ch == 'P') {
} else if (parser->index == 2 && ch == 'P') {
parser->method = HTTP_COPY;
} else {
goto error;
}
} else if (parser->method == HTTP_MKCOL) {
if (index == 1 && ch == 'O') {
if (parser->index == 1 && ch == 'O') {
parser->method = HTTP_MOVE;
} else if (index == 1 && ch == 'E') {
} else if (parser->index == 1 && ch == 'E') {
parser->method = HTTP_MERGE;
} else if (index == 1 && ch == '-') {
} else if (parser->index == 1 && ch == '-') {
parser->method = HTTP_MSEARCH;
} else if (index == 2 && ch == 'A') {
} else if (parser->index == 2 && ch == 'A') {
parser->method = HTTP_MKACTIVITY;
} else {
goto error;
}
} else if (index == 1 && parser->method == HTTP_POST) {
} else if (parser->method == HTTP_SUBSCRIBE) {
if (parser->index == 1 && ch == 'E') {
parser->method = HTTP_SEARCH;
} else {
goto error;
}
} else if (parser->index == 1 && parser->method == HTTP_POST) {
if (ch == 'R') {
parser->method = HTTP_PROPFIND; /* or HTTP_PROPPATCH */
} else if (ch == 'U') {
parser->method = HTTP_PUT;
parser->method = HTTP_PUT; /* or HTTP_PURGE */
} else if (ch == 'A') {
parser->method = HTTP_PATCH;
} else {
goto error;
}
} else if (index == 2 && parser->method == HTTP_UNLOCK && ch == 'S') {
parser->method = HTTP_UNSUBSCRIBE;
} else if (index == 4 && parser->method == HTTP_PROPFIND && ch == 'P') {
} else if (parser->index == 2) {
if (parser->method == HTTP_PUT) {
if (ch == 'R') parser->method = HTTP_PURGE;
} else if (parser->method == HTTP_UNLOCK) {
if (ch == 'S') parser->method = HTTP_UNSUBSCRIBE;
}
} else if (parser->index == 4 && parser->method == HTTP_PROPFIND && ch == 'P') {
parser->method = HTTP_PROPPATCH;
} else {
SET_ERRNO(HPE_INVALID_METHOD);
goto error;
}
++index;
++parser->index;
break;
}
case s_req_spaces_before_url:
{
if (ch == ' ') break;
if (ch == '/' || ch == '*') {
MARK(url);
state = s_req_path;
break;
MARK(url);
if (parser->method == HTTP_CONNECT) {
parser->state = s_req_server_start;
}
/* Proxied requests are followed by scheme of an absolute URI (alpha).
* CONNECT is followed by a hostname, which begins with alphanum.
* All other methods are followed by '/' or '*' (handled above).
*/
if (IS_ALPHA(ch) || (parser->method == HTTP_CONNECT && IS_NUM(ch))) {
MARK(url);
state = (parser->method == HTTP_CONNECT) ? s_req_host : s_req_schema;
break;
parser->state = parse_url_char((enum state)parser->state, ch);
if (parser->state == s_dead) {
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
SET_ERRNO(HPE_INVALID_URL);
goto error;
break;
}
case s_req_schema:
{
if (IS_ALPHA(ch)) break;
if (ch == ':') {
state = s_req_schema_slash;
break;
}
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
case s_req_schema_slash:
STRICT_CHECK(ch != '/');
state = s_req_schema_slash_slash;
break;
case s_req_schema_slash_slash:
STRICT_CHECK(ch != '/');
state = s_req_host;
break;
case s_req_host:
{
if (IS_HOST_CHAR(ch)) break;
switch (ch) {
case ':':
state = s_req_port;
break;
case '/':
state = s_req_path;
break;
case ' ':
/* The request line looks like:
* "GET http://foo.bar.com HTTP/1.1"
* That is, there is no path.
*/
CALLBACK(url);
state = s_req_http_start;
break;
case '?':
state = s_req_query_string_start;
break;
default:
SET_ERRNO(HPE_INVALID_HOST);
goto error;
}
break;
}
case s_req_port:
{
if (IS_NUM(ch)) break;
switch (ch) {
case '/':
state = s_req_path;
break;
case ' ':
/* The request line looks like:
* "GET http://foo.bar.com:1234 HTTP/1.1"
* That is, there is no path.
*/
CALLBACK(url);
state = s_req_http_start;
break;
case '?':
state = s_req_query_string_start;
break;
default:
SET_ERRNO(HPE_INVALID_PORT);
goto error;
}
break;
}
case s_req_path:
case s_req_server_start:
{
if (IS_URL_CHAR(ch)) break;
switch (ch) {
/* No whitespace allowed here */
case ' ':
CALLBACK(url);
state = s_req_http_start;
break;
case CR:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_req_line_almost_done;
break;
case LF:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_header_field_start;
break;
case '?':
state = s_req_query_string_start;
break;
case '#':
state = s_req_fragment_start;
break;
default:
SET_ERRNO(HPE_INVALID_PATH);
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
break;
}
case s_req_query_string_start:
{
if (IS_URL_CHAR(ch)) {
state = s_req_query_string;
break;
}
switch (ch) {
case '?':
break; /* XXX ignore extra '?' ... is this right? */
case ' ':
CALLBACK(url);
state = s_req_http_start;
break;
case CR:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_req_line_almost_done;
break;
case LF:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_header_field_start;
break;
case '#':
state = s_req_fragment_start;
break;
default:
SET_ERRNO(HPE_INVALID_QUERY_STRING);
goto error;
parser->state = parse_url_char((enum state)parser->state, ch);
if (parser->state == s_dead) {
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
}
break;
}
case s_req_query_string:
{
if (IS_URL_CHAR(ch)) break;
switch (ch) {
case '?':
/* allow extra '?' in query string */
break;
case ' ':
CALLBACK(url);
state = s_req_http_start;
break;
case CR:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_req_line_almost_done;
break;
case LF:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_header_field_start;
break;
case '#':
state = s_req_fragment_start;
break;
default:
SET_ERRNO(HPE_INVALID_QUERY_STRING);
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:
{
if (IS_URL_CHAR(ch)) {
state = s_req_fragment;
break;
}
switch (ch) {
case ' ':
CALLBACK(url);
state = s_req_http_start;
break;
case CR:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_req_line_almost_done;
break;
case LF:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_header_field_start;
break;
case '?':
state = s_req_fragment;
break;
case '#':
break;
default:
SET_ERRNO(HPE_INVALID_FRAGMENT);
goto error;
}
break;
}
case s_req_fragment:
{
if (IS_URL_CHAR(ch)) break;
switch (ch) {
case ' ':
CALLBACK(url);
state = s_req_http_start;
parser->state = s_req_http_start;
CALLBACK_DATA(url);
break;
case CR:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_req_line_almost_done;
break;
case LF:
CALLBACK(url);
parser->http_major = 0;
parser->http_minor = 9;
state = s_header_field_start;
break;
case '?':
case '#':
parser->state = (ch == CR) ?
s_req_line_almost_done :
s_header_field_start;
CALLBACK_DATA(url);
break;
default:
SET_ERRNO(HPE_INVALID_FRAGMENT);
goto error;
parser->state = parse_url_char((enum state)parser->state, ch);
if (parser->state == s_dead) {
SET_ERRNO(HPE_INVALID_URL);
goto error;
}
}
break;
}
......@@ -1018,7 +1051,7 @@ size_t http_parser_execute (http_parser *parser,
case s_req_http_start:
switch (ch) {
case 'H':
state = s_req_http_H;
parser->state = s_req_http_H;
break;
case ' ':
break;
......@@ -1030,22 +1063,22 @@ size_t http_parser_execute (http_parser *parser,
case s_req_http_H:
STRICT_CHECK(ch != 'T');
state = s_req_http_HT;
parser->state = s_req_http_HT;
break;
case s_req_http_HT:
STRICT_CHECK(ch != 'T');
state = s_req_http_HTT;
parser->state = s_req_http_HTT;
break;
case s_req_http_HTT:
STRICT_CHECK(ch != 'P');
state = s_req_http_HTTP;
parser->state = s_req_http_HTTP;
break;
case s_req_http_HTTP:
STRICT_CHECK(ch != '/');
state = s_req_first_http_major;
parser->state = s_req_first_http_major;
break;
/* first digit of major HTTP version */
......@@ -1056,14 +1089,14 @@ size_t http_parser_execute (http_parser *parser,
}
parser->http_major = ch - '0';
state = s_req_http_major;
parser->state = s_req_http_major;
break;
/* major HTTP version or dot */
case s_req_http_major:
{
if (ch == '.') {
state = s_req_first_http_minor;
parser->state = s_req_first_http_minor;
break;
}
......@@ -1091,19 +1124,19 @@ size_t http_parser_execute (http_parser *parser,
}
parser->http_minor = ch - '0';
state = s_req_http_minor;
parser->state = s_req_http_minor;
break;
/* minor HTTP version or end of request line */
case s_req_http_minor:
{
if (ch == CR) {
state = s_req_line_almost_done;
parser->state = s_req_line_almost_done;
break;
}
if (ch == LF) {
state = s_header_field_start;
parser->state = s_header_field_start;
break;
}
......@@ -1133,23 +1166,22 @@ size_t http_parser_execute (http_parser *parser,
goto error;
}
state = s_header_field_start;
parser->state = s_header_field_start;
break;
}
case s_header_field_start:
header_field_start:
{
if (ch == CR) {
state = s_headers_almost_done;
parser->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*/
state = s_headers_almost_done;
goto headers_almost_done;
parser->state = s_headers_almost_done;
goto reexecute_byte;
}
c = TOKEN(ch);
......@@ -1161,28 +1193,28 @@ size_t http_parser_execute (http_parser *parser,
MARK(header_field);
index = 0;
state = s_header_field;
parser->index = 0;
parser->state = s_header_field;
switch (c) {
case 'c':
header_state = h_C;
parser->header_state = h_C;
break;
case 'p':
header_state = h_matching_proxy_connection;
parser->header_state = h_matching_proxy_connection;
break;
case 't':
header_state = h_matching_transfer_encoding;
parser->header_state = h_matching_transfer_encoding;
break;
case 'u':
header_state = h_matching_upgrade;
parser->header_state = h_matching_upgrade;
break;
default:
header_state = h_general;
parser->header_state = h_general;
break;
}
break;
......@@ -1193,31 +1225,31 @@ size_t http_parser_execute (http_parser *parser,
c = TOKEN(ch);
if (c) {
switch (header_state) {
switch (parser->header_state) {
case h_general:
break;
case h_C:
index++;
header_state = (c == 'o' ? h_CO : h_general);
parser->index++;
parser->header_state = (c == 'o' ? h_CO : h_general);
break;
case h_CO:
index++;
header_state = (c == 'n' ? h_CON : h_general);
parser->index++;
parser->header_state = (c == 'n' ? h_CON : h_general);
break;
case h_CON:
index++;
parser->index++;
switch (c) {
case 'n':
header_state = h_matching_connection;
parser->header_state = h_matching_connection;
break;
case 't':
header_state = h_matching_content_length;
parser->header_state = h_matching_content_length;
break;
default:
header_state = h_general;
parser->header_state = h_general;
break;
}
break;
......@@ -1225,60 +1257,60 @@ size_t http_parser_execute (http_parser *parser,
/* connection */
case h_matching_connection:
index++;
if (index > sizeof(CONNECTION)-1
|| c != CONNECTION[index]) {
header_state = h_general;
} else if (index == sizeof(CONNECTION)-2) {
header_state = h_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:
index++;
if (index > sizeof(PROXY_CONNECTION)-1
|| c != PROXY_CONNECTION[index]) {
header_state = h_general;
} else if (index == sizeof(PROXY_CONNECTION)-2) {
header_state = h_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:
index++;
if (index > sizeof(CONTENT_LENGTH)-1
|| c != CONTENT_LENGTH[index]) {
header_state = h_general;
} else if (index == sizeof(CONTENT_LENGTH)-2) {
header_state = h_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:
index++;
if (index > sizeof(TRANSFER_ENCODING)-1
|| c != TRANSFER_ENCODING[index]) {
header_state = h_general;
} else if (index == sizeof(TRANSFER_ENCODING)-2) {
header_state = h_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;
}
break;
/* upgrade */
case h_matching_upgrade:
index++;
if (index > sizeof(UPGRADE)-1
|| c != UPGRADE[index]) {
header_state = h_general;
} else if (index == sizeof(UPGRADE)-2) {
header_state = h_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;
......@@ -1286,7 +1318,7 @@ size_t http_parser_execute (http_parser *parser,
case h_content_length:
case h_transfer_encoding:
case h_upgrade:
if (ch != ' ') header_state = h_general;
if (ch != ' ') parser->header_state = h_general;
break;
default:
......@@ -1297,20 +1329,20 @@ size_t http_parser_execute (http_parser *parser,
}
if (ch == ':') {
CALLBACK(header_field);
state = s_header_value_start;
parser->state = s_header_value_start;
CALLBACK_DATA(header_field);
break;
}
if (ch == CR) {
state = s_header_almost_done;
CALLBACK(header_field);
parser->state = s_header_almost_done;
CALLBACK_DATA(header_field);
break;
}
if (ch == LF) {
CALLBACK(header_field);
state = s_header_field_start;
parser->state = s_header_field_start;
CALLBACK_DATA(header_field);
break;
}
......@@ -1324,36 +1356,36 @@ size_t http_parser_execute (http_parser *parser,
MARK(header_value);
state = s_header_value;
index = 0;
parser->state = s_header_value;
parser->index = 0;
if (ch == CR) {
CALLBACK(header_value);
header_state = h_general;
state = s_header_almost_done;
parser->header_state = h_general;
parser->state = s_header_almost_done;
CALLBACK_DATA(header_value);
break;
}
if (ch == LF) {
CALLBACK(header_value);
state = s_header_field_start;
parser->state = s_header_field_start;
CALLBACK_DATA(header_value);
break;
}
c = LOWER(ch);
switch (header_state) {
switch (parser->header_state) {
case h_upgrade:
parser->flags |= F_UPGRADE;
header_state = h_general;
parser->header_state = h_general;
break;
case h_transfer_encoding:
/* looking for 'Transfer-Encoding: chunked' */
if ('c' == c) {
header_state = h_matching_transfer_encoding_chunked;
parser->header_state = h_matching_transfer_encoding_chunked;
} else {
header_state = h_general;
parser->header_state = h_general;
}
break;
......@@ -1369,17 +1401,17 @@ size_t http_parser_execute (http_parser *parser,
case h_connection:
/* looking for 'Connection: keep-alive' */
if (c == 'k') {
header_state = h_matching_connection_keep_alive;
parser->header_state = h_matching_connection_keep_alive;
/* looking for 'Connection: close' */
} else if (c == 'c') {
header_state = h_matching_connection_close;
parser->header_state = h_matching_connection_close;
} else {
header_state = h_general;
parser->header_state = h_general;
}
break;
default:
header_state = h_general;
parser->header_state = h_general;
break;
}
break;
......@@ -1389,19 +1421,20 @@ size_t http_parser_execute (http_parser *parser,
{
if (ch == CR) {
CALLBACK(header_value);
state = s_header_almost_done;
parser->state = s_header_almost_done;
CALLBACK_DATA(header_value);
break;
}
if (ch == LF) {
CALLBACK(header_value);
goto header_almost_done;
parser->state = s_header_almost_done;
CALLBACK_DATA_NOADVANCE(header_value);
goto reexecute_byte;
}
c = LOWER(ch);
switch (header_state) {
switch (parser->header_state) {
case h_general:
break;
......@@ -1411,70 +1444,83 @@ size_t http_parser_execute (http_parser *parser,
break;
case h_content_length:
{
uint64_t t;
if (ch == ' ') break;
if (!IS_NUM(ch)) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
goto error;
}
parser->content_length *= 10;
parser->content_length += ch - '0';
t = parser->content_length;
t *= 10;
t += ch - '0';
/* Overflow? */
if (t < parser->content_length || t == ULLONG_MAX) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
goto error;
}
parser->content_length = t;
break;
}
/* Transfer-Encoding: chunked */
case h_matching_transfer_encoding_chunked:
index++;
if (index > sizeof(CHUNKED)-1
|| c != CHUNKED[index]) {
header_state = h_general;
} else if (index == sizeof(CHUNKED)-2) {
header_state = h_transfer_encoding_chunked;
parser->index++;
if (parser->index > sizeof(CHUNKED)-1
|| c != CHUNKED[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(CHUNKED)-2) {
parser->header_state = h_transfer_encoding_chunked;
}
break;
/* looking for 'Connection: keep-alive' */
case h_matching_connection_keep_alive:
index++;
if (index > sizeof(KEEP_ALIVE)-1
|| c != KEEP_ALIVE[index]) {
header_state = h_general;
} else if (index == sizeof(KEEP_ALIVE)-2) {
header_state = h_connection_keep_alive;
parser->index++;
if (parser->index > sizeof(KEEP_ALIVE)-1
|| c != KEEP_ALIVE[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(KEEP_ALIVE)-2) {
parser->header_state = h_connection_keep_alive;
}
break;
/* looking for 'Connection: close' */
case h_matching_connection_close:
index++;
if (index > sizeof(CLOSE)-1 || c != CLOSE[index]) {
header_state = h_general;
} else if (index == sizeof(CLOSE)-2) {
header_state = h_connection_close;
parser->index++;
if (parser->index > sizeof(CLOSE)-1 || c != CLOSE[parser->index]) {
parser->header_state = h_general;
} else if (parser->index == sizeof(CLOSE)-2) {
parser->header_state = h_connection_close;
}
break;
case h_transfer_encoding_chunked:
case h_connection_keep_alive:
case h_connection_close:
if (ch != ' ') header_state = h_general;
if (ch != ' ') parser->header_state = h_general;
break;
default:
state = s_header_value;
header_state = h_general;
parser->state = s_header_value;
parser->header_state = h_general;
break;
}
break;
}
case s_header_almost_done:
header_almost_done:
{
STRICT_CHECK(ch != LF);
state = s_header_value_lws;
parser->state = s_header_value_lws;
switch (header_state) {
switch (parser->header_state) {
case h_connection_keep_alive:
parser->flags |= F_CONNECTION_KEEP_ALIVE;
break;
......@@ -1487,44 +1533,47 @@ size_t http_parser_execute (http_parser *parser,
default:
break;
}
break;
}
case s_header_value_lws:
{
if (ch == ' ' || ch == '\t')
state = s_header_value_start;
parser->state = s_header_value_start;
else
{
state = s_header_field_start;
goto header_field_start;
parser->state = s_header_field_start;
goto reexecute_byte;
}
break;
}
case s_headers_almost_done:
headers_almost_done:
{
STRICT_CHECK(ch != LF);
if (parser->flags & F_TRAILING) {
/* End of a chunked request */
CALLBACK2(message_complete);
state = NEW_MESSAGE();
parser->state = NEW_MESSAGE();
CALLBACK_NOTIFY(message_complete);
break;
}
nread = 0;
parser->state = s_headers_done;
if (parser->flags & F_UPGRADE || parser->method == HTTP_CONNECT) {
parser->upgrade = 1;
}
/* Set this here so that on_headers_complete() callbacks can see it */
parser->upgrade =
(parser->flags & F_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)) {
......@@ -1536,40 +1585,54 @@ size_t http_parser_execute (http_parser *parser,
break;
default:
parser->state = state;
SET_ERRNO(HPE_CB_headers_complete);
return p - data; /* Error */
}
}
if (HTTP_PARSER_ERRNO(parser) != HPE_OK) {
return p - data;
}
goto reexecute_byte;
}
case s_headers_done:
{
STRICT_CHECK(ch != LF);
parser->nread = 0;
/* Exit, the rest of the connect is in a different protocol. */
if (parser->upgrade) {
CALLBACK2(message_complete);
parser->state = NEW_MESSAGE();
CALLBACK_NOTIFY(message_complete);
return (p - data) + 1;
}
if (parser->flags & F_SKIPBODY) {
CALLBACK2(message_complete);
state = NEW_MESSAGE();
parser->state = NEW_MESSAGE();
CALLBACK_NOTIFY(message_complete);
} else if (parser->flags & F_CHUNKED) {
/* chunked encoding - ignore Content-Length header */
state = s_chunk_size_start;
parser->state = s_chunk_size_start;
} else {
if (parser->content_length == 0) {
/* Content-Length header given but zero: Content-Length: 0\r\n */
CALLBACK2(message_complete);
state = NEW_MESSAGE();
} else if (parser->content_length > 0) {
parser->state = NEW_MESSAGE();
CALLBACK_NOTIFY(message_complete);
} else if (parser->content_length != ULLONG_MAX) {
/* Content-Length header given and non-zero */
state = s_body_identity;
parser->state = s_body_identity;
} else {
if (parser->type == HTTP_REQUEST || http_should_keep_alive(parser)) {
if (parser->type == HTTP_REQUEST ||
!http_message_needs_eof(parser)) {
/* Assume content-length 0 - read the next */
CALLBACK2(message_complete);
state = NEW_MESSAGE();
parser->state = NEW_MESSAGE();
CALLBACK_NOTIFY(message_complete);
} else {
/* Read body until EOF */
state = s_body_identity_eof;
parser->state = s_body_identity_eof;
}
}
}
......@@ -1578,30 +1641,56 @@ size_t http_parser_execute (http_parser *parser,
}
case s_body_identity:
to_read = (size_t)MIN(pe - p, parser->content_length);
if (to_read > 0) {
if (settings->on_body) settings->on_body(parser, p, to_read);
p += to_read - 1;
parser->content_length -= to_read;
if (parser->content_length == 0) {
CALLBACK2(message_complete);
state = NEW_MESSAGE();
}
{
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) {
parser->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);
goto reexecute_byte;
}
break;
}
/* read until EOF */
case s_body_identity_eof:
to_read = pe - p;
if (to_read > 0) {
if (settings->on_body) settings->on_body(parser, p, to_read);
p += to_read - 1;
}
MARK(body);
p = data + len - 1;
break;
case s_message_done:
parser->state = NEW_MESSAGE();
CALLBACK_NOTIFY(message_complete);
break;
case s_chunk_size_start:
{
assert(nread == 1);
assert(parser->nread == 1);
assert(parser->flags & F_CHUNKED);
unhex_val = unhex[(unsigned char)ch];
......@@ -1611,16 +1700,18 @@ size_t http_parser_execute (http_parser *parser,
}
parser->content_length = unhex_val;
state = s_chunk_size;
parser->state = s_chunk_size;
break;
}
case s_chunk_size:
{
uint64_t t;
assert(parser->flags & F_CHUNKED);
if (ch == CR) {
state = s_chunk_size_almost_done;
parser->state = s_chunk_size_almost_done;
break;
}
......@@ -1628,7 +1719,7 @@ size_t http_parser_execute (http_parser *parser,
if (unhex_val == -1) {
if (ch == ';' || ch == ' ') {
state = s_chunk_parameters;
parser->state = s_chunk_parameters;
break;
}
......@@ -1636,8 +1727,17 @@ size_t http_parser_execute (http_parser *parser,
goto error;
}
parser->content_length *= 16;
parser->content_length += unhex_val;
t = parser->content_length;
t *= 16;
t += unhex_val;
/* Overflow? */
if (t < parser->content_length || t == ULLONG_MAX) {
SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
goto error;
}
parser->content_length = t;
break;
}
......@@ -1646,7 +1746,7 @@ size_t http_parser_execute (http_parser *parser,
assert(parser->flags & F_CHUNKED);
/* just ignore this shit. TODO check for overflow */
if (ch == CR) {
state = s_chunk_size_almost_done;
parser->state = s_chunk_size_almost_done;
break;
}
break;
......@@ -1657,46 +1757,53 @@ size_t http_parser_execute (http_parser *parser,
assert(parser->flags & F_CHUNKED);
STRICT_CHECK(ch != LF);
nread = 0;
parser->nread = 0;
if (parser->content_length == 0) {
parser->flags |= F_TRAILING;
state = s_header_field_start;
parser->state = s_header_field_start;
} else {
state = s_chunk_data;
parser->state = s_chunk_data;
}
break;
}
case s_chunk_data:
{
assert(parser->flags & F_CHUNKED);
uint64_t to_read = MIN(parser->content_length,
(uint64_t) ((data + len) - p));
to_read = (size_t)MIN(pe - p, parser->content_length);
assert(parser->flags & F_CHUNKED);
assert(parser->content_length != 0
&& parser->content_length != ULLONG_MAX);
if (to_read > 0) {
if (settings->on_body) settings->on_body(parser, p, to_read);
p += to_read - 1;
}
/* 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 ((signed)to_read == parser->content_length) {
state = s_chunk_data_almost_done;
if (parser->content_length == 0) {
parser->state = s_chunk_data_almost_done;
}
parser->content_length -= to_read;
break;
}
case s_chunk_data_almost_done:
assert(parser->flags & F_CHUNKED);
assert(parser->content_length == 0);
STRICT_CHECK(ch != CR);
state = s_chunk_data_done;
parser->state = s_chunk_data_done;
CALLBACK_DATA(body);
break;
case s_chunk_data_done:
assert(parser->flags & F_CHUNKED);
STRICT_CHECK(ch != LF);
state = s_chunk_size_start;
parser->nread = 0;
parser->state = s_chunk_size_start;
break;
default:
......@@ -1706,14 +1813,25 @@ size_t http_parser_execute (http_parser *parser,
}
}
CALLBACK(header_field);
CALLBACK(header_value);
CALLBACK(url);
/* Run callbacks for any marks that we have leftover after we ran our 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)) <= 1);
parser->state = state;
parser->header_state = header_state;
parser->index = (unsigned char) index;
parser->nread = nread;
CALLBACK_DATA_NOADVANCE(header_field);
CALLBACK_DATA_NOADVANCE(header_value);
CALLBACK_DATA_NOADVANCE(url);
CALLBACK_DATA_NOADVANCE(body);
return len;
......@@ -1726,43 +1844,65 @@ error:
}
/* Does the parser need to see an EOF to find the end of the message? */
int
http_should_keep_alive (http_parser *parser)
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;
}
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 {
return 1;
}
} else {
/* HTTP/1.0 or earlier */
if (parser->flags & F_CONNECTION_KEEP_ALIVE) {
return 1;
} else {
if (!(parser->flags & F_CONNECTION_KEEP_ALIVE)) {
return 0;
}
}
return !http_message_needs_eof(parser);
}
const char * http_method_str (enum http_method m)
const char *
http_method_str (enum http_method m)
{
return method_strings[m];
return ELEM_AT(method_strings, m, "<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->nread = 0;
parser->upgrade = 0;
parser->flags = 0;
parser->method = 0;
parser->http_errno = 0;
parser->http_errno = HPE_OK;
}
const char *
......@@ -1776,3 +1916,259 @@ http_errno_description(enum http_errno err) {
assert(err < (sizeof(http_strerror_tab)/sizeof(http_strerror_tab[0])));
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;
}
/* FALLTHROUGH */
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;
}
/* FALLTHROUGH */
case s_http_host_v6_start:
if (IS_HEX(ch) || ch == ':') {
return s_http_host_v6;
}
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;
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 = 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 = p - buf;
}
u->field_data[UF_HOST].len++;
break;
case s_http_host_port:
if (s != s_http_host_port) {
u->field_data[UF_PORT].off = 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 = 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_port_start:
case s_http_userinfo:
case s_http_userinfo_start:
return 1;
default:
break;
}
return 0;
}
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;
u->port = u->field_set = 0;
s = is_connect ? s_req_server_start : s_req_spaces_before_url;
uf = 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;
/* FALLTROUGH */
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 = 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) | (1 << UF_HOST))) != 0) {
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)) {
/* Don't bother with endp; we've already validated the string */
unsigned long v = strtoul(buf + u->field_data[UF_PORT].off, NULL, 10);
/* 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) {
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;
}
deps/http-parser/http_parser.h
......@@ -24,16 +24,25 @@
extern "C" {
#endif
#define HTTP_PARSER_VERSION_MAJOR 1
#define HTTP_PARSER_VERSION_MAJOR 2
#define HTTP_PARSER_VERSION_MINOR 0
#ifdef _MSC_VER
/* disable silly warnings */
# pragma warning(disable: 4127 4214)
#endif
#include <sys/types.h>
#include "git2/common.h"
#if defined(_WIN32) && !defined(__MINGW32__) && (!defined(_MSC_VER) || _MSC_VER<1600)
#include <BaseTsd.h>
typedef __int8 int8_t;
typedef unsigned __int8 uint8_t;
typedef __int16 int16_t;
typedef unsigned __int16 uint16_t;
typedef __int32 int32_t;
typedef unsigned __int32 uint32_t;
typedef __int64 int64_t;
typedef unsigned __int64 uint64_t;
typedef SIZE_T size_t;
typedef SSIZE_T ssize_t;
#else
#include <stdint.h>
#endif
/* Compile with -DHTTP_PARSER_STRICT=0 to make less checks, but run
* faster
......@@ -42,21 +51,12 @@ extern "C" {
# define HTTP_PARSER_STRICT 1
#endif
/* Compile with -DHTTP_PARSER_DEBUG=1 to add extra debugging information to
* the error reporting facility.
*/
#ifndef HTTP_PARSER_DEBUG
# define HTTP_PARSER_DEBUG 0
#endif
/* Maximium header size allowed */
#define HTTP_MAX_HEADER_SIZE (80*1024)
typedef struct http_parser http_parser;
typedef struct http_parser_settings http_parser_settings;
typedef struct http_parser_result http_parser_result;
/* Callbacks should return non-zero to indicate an error. The parser will
......@@ -69,7 +69,7 @@ typedef struct http_parser_result http_parser_result;
* chunked' headers that indicate the presence of a body.
*
* http_data_cb does not return data chunks. It will be call arbitrarally
* many times for each string. E.G. you might get 10 callbacks for "on_path"
* many times for each string. E.G. you might get 10 callbacks for "on_url"
* each providing just a few characters more data.
*/
typedef int (*http_data_cb) (http_parser*, const char *at, size_t length);
......@@ -77,36 +77,44 @@ typedef int (*http_cb) (http_parser*);
/* Request Methods */
#define HTTP_METHOD_MAP(XX) \
XX(0, DELETE, DELETE) \
XX(1, GET, GET) \
XX(2, HEAD, HEAD) \
XX(3, POST, POST) \
XX(4, PUT, PUT) \
/* pathological */ \
XX(5, CONNECT, CONNECT) \
XX(6, OPTIONS, OPTIONS) \
XX(7, TRACE, TRACE) \
/* webdav */ \
XX(8, COPY, COPY) \
XX(9, LOCK, LOCK) \
XX(10, MKCOL, MKCOL) \
XX(11, MOVE, MOVE) \
XX(12, PROPFIND, PROPFIND) \
XX(13, PROPPATCH, PROPPATCH) \
XX(14, SEARCH, SEARCH) \
XX(15, UNLOCK, UNLOCK) \
/* subversion */ \
XX(16, REPORT, REPORT) \
XX(17, MKACTIVITY, MKACTIVITY) \
XX(18, CHECKOUT, CHECKOUT) \
XX(19, MERGE, MERGE) \
/* upnp */ \
XX(20, MSEARCH, M-SEARCH) \
XX(21, NOTIFY, NOTIFY) \
XX(22, SUBSCRIBE, SUBSCRIBE) \
XX(23, UNSUBSCRIBE, UNSUBSCRIBE) \
/* RFC-5789 */ \
XX(24, PATCH, PATCH) \
XX(25, PURGE, PURGE) \
enum http_method
{ HTTP_DELETE = 0
, HTTP_GET
, HTTP_HEAD
, HTTP_POST
, HTTP_PUT
/* pathological */
, HTTP_CONNECT
, HTTP_OPTIONS
, HTTP_TRACE
/* webdav */
, HTTP_COPY
, HTTP_LOCK
, HTTP_MKCOL
, HTTP_MOVE
, HTTP_PROPFIND
, HTTP_PROPPATCH
, HTTP_UNLOCK
/* subversion */
, HTTP_REPORT
, HTTP_MKACTIVITY
, HTTP_CHECKOUT
, HTTP_MERGE
/* upnp */
, HTTP_MSEARCH
, HTTP_NOTIFY
, HTTP_SUBSCRIBE
, HTTP_UNSUBSCRIBE
/* RFC-5789 */
, HTTP_PATCH
{
#define XX(num, name, string) HTTP_##name = num,
HTTP_METHOD_MAP(XX)
#undef XX
};
......@@ -134,10 +142,7 @@ enum flags
\
/* Callback-related errors */ \
XX(CB_message_begin, "the on_message_begin callback failed") \
XX(CB_path, "the on_path callback failed") \
XX(CB_query_string, "the on_query_string callback failed") \
XX(CB_url, "the on_url callback failed") \
XX(CB_fragment, "the on_fragment callback failed") \
XX(CB_header_field, "the on_header_field callback failed") \
XX(CB_header_value, "the on_header_value callback failed") \
XX(CB_headers_complete, "the on_headers_complete callback failed") \
......@@ -168,6 +173,7 @@ enum flags
XX(INVALID_CONSTANT, "invalid constant string") \
XX(INVALID_INTERNAL_STATE, "encountered unexpected internal state")\
XX(STRICT, "strict mode assertion failed") \
XX(PAUSED, "parser is paused") \
XX(UNKNOWN, "an unknown error occurred")
......@@ -182,30 +188,23 @@ enum http_errno {
/* Get an http_errno value from an http_parser */
#define HTTP_PARSER_ERRNO(p) ((enum http_errno) (p)->http_errno)
/* Get the line number that generated the current error */
#if HTTP_PARSER_DEBUG
#define HTTP_PARSER_ERRNO_LINE(p) ((p)->error_lineno)
#else
#define HTTP_PARSER_ERRNO_LINE(p) 0
#endif
struct http_parser {
/** PRIVATE **/
unsigned char type : 2;
unsigned char flags : 6; /* F_* values from 'flags' enum; semi-public */
unsigned char state;
unsigned char header_state;
unsigned char index;
unsigned char type : 2; /* enum http_parser_type */
unsigned char flags : 6; /* F_* values from 'flags' enum; semi-public */
unsigned char state; /* enum state from http_parser.c */
unsigned char header_state; /* enum header_state from http_parser.c */
unsigned char index; /* index into current matcher */
size_t nread;
int64_t content_length;
uint32_t nread; /* # bytes read in various scenarios */
uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */
/** READ-ONLY **/
unsigned short http_major;
unsigned short http_minor;
unsigned short status_code; /* responses only */
unsigned char method; /* requests only */
unsigned char method; /* requests only */
unsigned char http_errno : 7;
/* 1 = Upgrade header was present and the parser has exited because of that.
......@@ -215,10 +214,6 @@ struct http_parser {
*/
unsigned char upgrade : 1;
#if HTTP_PARSER_DEBUG
uint32_t error_lineno;
#endif
/** PUBLIC **/
void *data; /* A pointer to get hook to the "connection" or "socket" object */
};
......@@ -235,6 +230,36 @@ struct http_parser_settings {
};
enum http_parser_url_fields
{ UF_SCHEMA = 0
, UF_HOST = 1
, UF_PORT = 2
, UF_PATH = 3
, UF_QUERY = 4
, UF_FRAGMENT = 5
, UF_USERINFO = 6
, UF_MAX = 7
};
/* Result structure for http_parser_parse_url().
*
* Callers should index into field_data[] with UF_* values iff field_set
* has the relevant (1 << UF_*) bit set. As a courtesy to clients (and
* because we probably have padding left over), we convert any port to
* a uint16_t.
*/
struct http_parser_url {
uint16_t field_set; /* Bitmask of (1 << UF_*) values */
uint16_t port; /* Converted UF_PORT string */
struct {
uint16_t off; /* Offset into buffer in which field starts */
uint16_t len; /* Length of run in buffer */
} field_data[UF_MAX];
};
void http_parser_init(http_parser *parser, enum http_parser_type type);
......@@ -245,12 +270,12 @@ size_t http_parser_execute(http_parser *parser,
/* If http_should_keep_alive() in the on_headers_complete or
* on_message_complete callback returns true, then this will be should be
* on_message_complete callback returns 0, then this should be
* the last message on the connection.
* If you are the server, respond with the "Connection: close" header.
* If you are the client, close the connection.
*/
int http_should_keep_alive(http_parser *parser);
int http_should_keep_alive(const http_parser *parser);
/* Returns a string version of the HTTP method. */
const char *http_method_str(enum http_method m);
......@@ -261,6 +286,17 @@ const char *http_errno_name(enum http_errno err);
/* Return a string description of the given error */
const char *http_errno_description(enum http_errno err);
/* Parse a URL; return nonzero on failure */
int http_parser_parse_url(const char *buf, size_t buflen,
int is_connect,
struct http_parser_url *u);
/* Pause or un-pause the parser; a nonzero value pauses */
void http_parser_pause(http_parser *parser, int paused);
/* Checks if this is the final chunk of the body. */
int http_body_is_final(const http_parser *parser);
#ifdef __cplusplus
}
#endif
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment