Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Browse files

Upgrade http-parser

  • Loading branch information...
commit 299eda8a6cade1c6a2aae0e879e30ae624ae5f24 1 parent ebbaa86
ry ry authored
2  deps/http_parser/README.md
View
@@ -39,10 +39,10 @@ like this for a request parser:
settings.on_path = my_path_callback;
settings.on_header_field = my_header_field_callback;
/* ... */
- settings.data = my_socket;
http_parser *parser = malloc(sizeof(http_parser));
http_parser_init(parser, HTTP_REQUEST);
+ parser->data = my_socket;
When data is received on the socket execute the parser and check for errors.
78 deps/http_parser/http_parser.c
View
@@ -19,16 +19,6 @@
* IN THE SOFTWARE.
*/
#include <http_parser.h>
-#ifdef _WIN32
-typedef __int8 int8_t;
-typedef unsigned __int8 uint8_t;
-typedef __int16 int16_t;
-typedef unsigned __int16 uint16_t;
-typedef __int16 int32_t;
-typedef unsigned __int32 uint32_t;
-#else
-#include <stdint.h>
-#endif
#include <assert.h>
#include <stddef.h>
@@ -108,7 +98,7 @@ static const char *method_strings[] =
/* ' ', '_', '-' and all alpha-numeric ascii characters are accepted by acceptable_header.
The 'A'-'Z' are lower-cased. */
-static const unsigned char acceptable_header[256] = {
+static const char acceptable_header[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 */
@@ -143,7 +133,49 @@ static const unsigned char acceptable_header[256] = {
'x', 'y', 'z', 0, 0, 0, 0, 0 };
-static const int unhex[256] =
+/* 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 ' */
+ ' ', '!', '"', '#', '$', '%', '&', '\'',
+/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */
+ 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 };
+
+
+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
@@ -155,7 +187,7 @@ static const int unhex[256] =
};
-static const int normal_url_char[256] = {
+static const uint8_t normal_url_char[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 */
@@ -302,6 +334,7 @@ enum flags
#define CR '\r'
#define LF '\n'
#define LOWER(c) (unsigned char)(c | 0x20)
+#define TOKEN(c) tokens[(unsigned char)c]
#define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res)
@@ -600,7 +633,7 @@ size_t http_parser_execute (http_parser *parser,
if (ch == ' ' && matcher[index] == '\0') {
state = s_req_spaces_before_url;
} else if (ch == matcher[index]) {
- ; // nada
+ ; /* nada */
} else if (parser->method == HTTP_CONNECT) {
if (index == 1 && ch == 'H') {
parser->method = HTTP_CHECKOUT;
@@ -772,7 +805,7 @@ size_t http_parser_execute (http_parser *parser,
switch (ch) {
case '?':
- break; // XXX ignore extra '?' ... is this right?
+ break; /* XXX ignore extra '?' ... is this right? */
case ' ':
CALLBACK(url);
state = s_req_http_start;
@@ -802,7 +835,7 @@ size_t http_parser_execute (http_parser *parser,
switch (ch) {
case '?':
- // allow extra '?' in query string
+ /* allow extra '?' in query string */
break;
case ' ':
CALLBACK(url);
@@ -1006,9 +1039,9 @@ size_t http_parser_execute (http_parser *parser,
goto headers_almost_done;
}
- c = LOWER(ch);
+ c = TOKEN(ch);
- if (c < 'a' || 'z' < c) goto error;
+ if (!c) goto error;
MARK(header_field);
@@ -1041,7 +1074,7 @@ size_t http_parser_execute (http_parser *parser,
case s_header_field:
{
- c = acceptable_header[(unsigned char)ch];
+ c = TOKEN(ch);
if (c) {
switch (header_state) {
@@ -1377,7 +1410,7 @@ size_t http_parser_execute (http_parser *parser,
}
}
- // Exit, the rest of the connect is in a different protocol.
+ /* Exit, the rest of the connect is in a different protocol. */
if (parser->upgrade) {
CALLBACK2(message_complete);
return (p - data);
@@ -1438,7 +1471,7 @@ size_t http_parser_execute (http_parser *parser,
{
assert(parser->flags & F_CHUNKED);
- c = unhex[(int)ch];
+ c = unhex[(unsigned char)ch];
if (c == -1) goto error;
parser->content_length = c;
state = s_chunk_size;
@@ -1454,7 +1487,7 @@ size_t http_parser_execute (http_parser *parser,
break;
}
- c = unhex[(int)ch];
+ c = unhex[(unsigned char)ch];
if (c == -1) {
if (ch == ';' || ch == ' ') {
@@ -1546,6 +1579,7 @@ size_t http_parser_execute (http_parser *parser,
return len;
error:
+ parser->state = s_dead;
return (p - data);
}
13 deps/http_parser/http_parser.h
View
@@ -26,11 +26,20 @@ extern "C" {
#include <sys/types.h>
-#include <stdint.h>
-
#ifdef _WIN32
+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 unsigned int size_t;
typedef int ssize_t;
+#else
+#include <stdint.h>
#endif
/* Compile with -DHTTP_PARSER_STRICT=0 to make less checks, but run
67 deps/http_parser/test.c
View
@@ -31,7 +31,7 @@
#undef FALSE
#define FALSE 0
-#define MAX_HEADERS 10
+#define MAX_HEADERS 13
#define MAX_ELEMENT_SIZE 500
#define MIN(a,b) ((a) < (b) ? (a) : (b))
@@ -833,6 +833,71 @@ const struct message responses[] =
,.body= "<xml>hello</xml>"
}
+
+#define RES_FIELD_UNDERSCORE 10
+/* Should handle spaces in header fields */
+, {.name= "field underscore"
+ ,.type= HTTP_RESPONSE
+ ,.raw= "HTTP/1.1 200 OK\r\n"
+ "Date: Tue, 28 Sep 2010 01:14:13 GMT\r\n"
+ "Server: Apache\r\n"
+ "Cache-Control: no-cache, must-revalidate\r\n"
+ "Expires: Mon, 26 Jul 1997 05:00:00 GMT\r\n"
+ "Set-Cookie: PlaxoCS=1274804622353690521; path=/; domain=.plaxo.com\r\n"
+ "Vary: Accept-Encoding\r\n"
+ "_eep-Alive: timeout=45\r\n" /* semantic value ignored */
+ "_onnection: Keep-Alive\r\n" /* semantic value ignored */
+ "Transfer-Encoding: chunked\r\n"
+ "Content-Type: text/html\r\n"
+ "Connection: close\r\n"
+ "\r\n"
+ "0\r\n\r\n"
+ ,.should_keep_alive= FALSE
+ ,.message_complete_on_eof= FALSE
+ ,.http_major= 1
+ ,.http_minor= 1
+ ,.status_code= 200
+ ,.num_headers= 11
+ ,.headers=
+ { { "Date", "Tue, 28 Sep 2010 01:14:13 GMT" }
+ , { "Server", "Apache" }
+ , { "Cache-Control", "no-cache, must-revalidate" }
+ , { "Expires", "Mon, 26 Jul 1997 05:00:00 GMT" }
+ , { "Set-Cookie", "PlaxoCS=1274804622353690521; path=/; domain=.plaxo.com" }
+ , { "Vary", "Accept-Encoding" }
+ , { "_eep-Alive", "timeout=45" }
+ , { "_onnection", "Keep-Alive" }
+ , { "Transfer-Encoding", "chunked" }
+ , { "Content-Type", "text/html" }
+ , { "Connection", "close" }
+ }
+ ,.body= ""
+ }
+
+#define NON_ASCII_IN_STATUS_LINE 11
+/* Should handle non-ASCII in status line */
+, {.name= "non-ASCII in status line"
+ ,.type= HTTP_RESPONSE
+ ,.raw= "HTTP/1.1 500 Oriëntatieprobleem\r\n"
+ "Date: Fri, 5 Nov 2010 23:07:12 GMT+2\r\n"
+ "Content-Length: 0\r\n"
+ "Connection: close\r\n"
+ "\r\n"
+ ,.should_keep_alive= FALSE
+ ,.message_complete_on_eof= FALSE
+ ,.http_major= 1
+ ,.http_minor= 1
+ ,.status_code= 500
+ ,.num_headers= 3
+ ,.headers=
+ { { "Date", "Fri, 5 Nov 2010 23:07:12 GMT+2" }
+ , { "Content-Length", "0" }
+ , { "Connection", "close" }
+ }
+ ,.body= ""
+ }
+
+
, {.name= NULL } /* sentinel */
};
Please sign in to comment.
Something went wrong with that request. Please try again.