Compare commits

..

2 Commits

Author SHA1 Message Date
Ryan Dahl ff762c2c9b improve execute2 doc
14 years ago
Ryan Dahl c95a547959 event stream
14 years ago

26
.gitignore vendored

@ -1,30 +1,4 @@
/out/
core
tags
*.o
test
test_g
test_fast
bench
url_parser
parsertrace
parsertrace_g
*.mk
*.Makefile
*.so.*
*.exe.*
*.exe
*.a
# Visual Studio uglies
*.suo
*.sln
*.vcxproj
*.vcxproj.filters
*.vcxproj.user
*.opensdf
*.ncrunchsolution*
*.sdf
*.vsp
*.psess

@ -1,8 +0,0 @@
# update AUTHORS with:
# git log --all --reverse --format='%aN <%aE>' | perl -ne 'BEGIN{print "# Authors ordered by first contribution.\n"} print unless $h{$_}; $h{$_} = 1' > AUTHORS
Ryan Dahl <ry@tinyclouds.org>
Salman Haq <salman.haq@asti-usa.com>
Simon Zimmermann <simonz05@gmail.com>
Thomas LE ROUX <thomas@november-eleven.fr> LE ROUX Thomas <thomas@procheo.fr>
Thomas LE ROUX <thomas@november-eleven.fr> Thomas LE ROUX <thomas@procheo.fr>
Fedor Indutny <fedor@indutny.com>

@ -1,13 +0,0 @@
language: c
compiler:
- clang
- gcc
script:
- "make"
notifications:
email: false
irc:
- "irc.freenode.net#node-ci"

@ -1,68 +0,0 @@
# Authors ordered by first contribution.
Ryan Dahl <ry@tinyclouds.org>
Jeremy Hinegardner <jeremy@hinegardner.org>
Sergey Shepelev <temotor@gmail.com>
Joe Damato <ice799@gmail.com>
tomika <tomika_nospam@freemail.hu>
Phoenix Sol <phoenix@burninglabs.com>
Cliff Frey <cliff@meraki.com>
Ewen Cheslack-Postava <ewencp@cs.stanford.edu>
Santiago Gala <sgala@apache.org>
Tim Becker <tim.becker@syngenio.de>
Jeff Terrace <jterrace@gmail.com>
Ben Noordhuis <info@bnoordhuis.nl>
Nathan Rajlich <nathan@tootallnate.net>
Mark Nottingham <mnot@mnot.net>
Aman Gupta <aman@tmm1.net>
Tim Becker <tim.becker@kuriositaet.de>
Sean Cunningham <sean.cunningham@mandiant.com>
Peter Griess <pg@std.in>
Salman Haq <salman.haq@asti-usa.com>
Cliff Frey <clifffrey@gmail.com>
Jon Kolb <jon@b0g.us>
Fouad Mardini <f.mardini@gmail.com>
Paul Querna <pquerna@apache.org>
Felix Geisendörfer <felix@debuggable.com>
koichik <koichik@improvement.jp>
Andre Caron <andre.l.caron@gmail.com>
Ivo Raisr <ivosh@ivosh.net>
James McLaughlin <jamie@lacewing-project.org>
David Gwynne <loki@animata.net>
Thomas LE ROUX <thomas@november-eleven.fr>
Randy Rizun <rrizun@ortivawireless.com>
Andre Louis Caron <andre.louis.caron@usherbrooke.ca>
Simon Zimmermann <simonz05@gmail.com>
Erik Dubbelboer <erik@dubbelboer.com>
Martell Malone <martellmalone@gmail.com>
Bertrand Paquet <bpaquet@octo.com>
BogDan Vatra <bogdan@kde.org>
Peter Faiman <peter@thepicard.org>
Corey Richardson <corey@octayn.net>
Tóth Tamás <tomika_nospam@freemail.hu>
Cam Swords <cam.swords@gmail.com>
Chris Dickinson <christopher.s.dickinson@gmail.com>
Uli Köhler <ukoehler@btronik.de>
Charlie Somerville <charlie@charliesomerville.com>
Patrik Stutz <patrik.stutz@gmail.com>
Fedor Indutny <fedor.indutny@gmail.com>
runner <runner.mei@gmail.com>
Alexis Campailla <alexis@janeasystems.com>
David Wragg <david@wragg.org>
Vinnie Falco <vinnie.falco@gmail.com>
Alex Butum <alexbutum@linux.com>
Rex Feng <rexfeng@gmail.com>
Alex Kocharin <alex@kocharin.ru>
Mark Koopman <markmontymark@yahoo.com>
Helge Heß <me@helgehess.eu>
Alexis La Goutte <alexis.lagoutte@gmail.com>
George Miroshnykov <george.miroshnykov@gmail.com>
Maciej Małecki <me@mmalecki.com>
Marc O'Morain <github.com@marcomorain.com>
Jeff Pinner <jpinner@twitter.com>
Timothy J Fontaine <tjfontaine@gmail.com>
Akagi201 <akagi201@gmail.com>
Romain Giraud <giraud.romain@gmail.com>
Jay Satiro <raysatiro@yahoo.com>
Arne Steen <Arne.Steen@gmx.de>
Kjell Schubert <kjell.schubert@gmail.com>
Olivier Mengué <dolmen@cpan.org>

@ -0,0 +1,4 @@
Contributors must agree to the Contributor License Agreement before patches
can be accepted.
http://spreadsheets2.google.com/viewform?hl=en&formkey=dDJXOGUwbzlYaWM4cHN1MERwQS1CSnc6MQ

@ -1,4 +1,4 @@
Copyright Joyent, Inc. and other Node contributors.
Copyright 2009,2010 Ryan Dahl <ry@tinyclouds.org>
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to

@ -1,160 +1,41 @@
# Copyright Joyent, Inc. and other Node contributors. All rights reserved.
#
# 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.
PLATFORM ?= $(shell sh -c 'uname -s | tr "[A-Z]" "[a-z]"')
HELPER ?=
BINEXT ?=
SOLIBNAME = libhttp_parser
SOMAJOR = 2
SOMINOR = 9
SOREV = 4
ifeq (darwin,$(PLATFORM))
SOEXT ?= dylib
SONAME ?= $(SOLIBNAME).$(SOMAJOR).$(SOMINOR).$(SOEXT)
LIBNAME ?= $(SOLIBNAME).$(SOMAJOR).$(SOMINOR).$(SOREV).$(SOEXT)
else ifeq (wine,$(PLATFORM))
CC = winegcc
BINEXT = .exe.so
HELPER = wine
else
SOEXT ?= so
SONAME ?= $(SOLIBNAME).$(SOEXT).$(SOMAJOR).$(SOMINOR)
LIBNAME ?= $(SOLIBNAME).$(SOEXT).$(SOMAJOR).$(SOMINOR).$(SOREV)
endif
OPT_DEBUG=-O0 -g -Wall -Wextra -Werror -I.
OPT_FAST=-O3 -DHTTP_PARSER_STRICT=0 -I.
CC?=gcc
AR?=ar
CPPFLAGS ?=
LDFLAGS ?=
CPPFLAGS += -I.
CPPFLAGS_DEBUG = $(CPPFLAGS) -DHTTP_PARSER_STRICT=1
CPPFLAGS_DEBUG += $(CPPFLAGS_DEBUG_EXTRA)
CPPFLAGS_FAST = $(CPPFLAGS) -DHTTP_PARSER_STRICT=0
CPPFLAGS_FAST += $(CPPFLAGS_FAST_EXTRA)
CPPFLAGS_BENCH = $(CPPFLAGS_FAST)
CFLAGS += -Wall -Wextra -Werror
CFLAGS_DEBUG = $(CFLAGS) -O0 -g $(CFLAGS_DEBUG_EXTRA)
CFLAGS_FAST = $(CFLAGS) -O3 $(CFLAGS_FAST_EXTRA)
CFLAGS_BENCH = $(CFLAGS_FAST) -Wno-unused-parameter
CFLAGS_LIB = $(CFLAGS_FAST) -fPIC
LDFLAGS_LIB = $(LDFLAGS) -shared
INSTALL ?= install
PREFIX ?= /usr/local
LIBDIR = $(PREFIX)/lib
INCLUDEDIR = $(PREFIX)/include
ifeq (darwin,$(PLATFORM))
LDFLAGS_LIB += -Wl,-install_name,$(LIBDIR)/$(SONAME)
else
# TODO(bnoordhuis) The native SunOS linker expects -h rather than -soname...
LDFLAGS_LIB += -Wl,-soname=$(SONAME)
endif
test: test_g test_fast
$(HELPER) ./test_g$(BINEXT)
$(HELPER) ./test_fast$(BINEXT)
test: test_g
./test_g
test_g: http_parser_g.o test_g.o
$(CC) $(CFLAGS_DEBUG) $(LDFLAGS) http_parser_g.o test_g.o -o $@
$(CC) $(OPT_DEBUG) http_parser_g.o test_g.o -o $@
test_g.o: test.c http_parser.h Makefile
$(CC) $(CPPFLAGS_DEBUG) $(CFLAGS_DEBUG) -c test.c -o $@
http_parser_g.o: http_parser.c http_parser.h Makefile
$(CC) $(CPPFLAGS_DEBUG) $(CFLAGS_DEBUG) -c http_parser.c -o $@
test_fast: http_parser.o test.o http_parser.h
$(CC) $(CFLAGS_FAST) $(LDFLAGS) http_parser.o test.o -o $@
$(CC) $(OPT_DEBUG) -c test.c -o $@
test.o: test.c http_parser.h Makefile
$(CC) $(CPPFLAGS_FAST) $(CFLAGS_FAST) -c test.c -o $@
bench: http_parser.o bench.o
$(CC) $(CFLAGS_BENCH) $(LDFLAGS) http_parser.o bench.o -o $@
bench.o: bench.c http_parser.h Makefile
$(CC) $(CPPFLAGS_BENCH) $(CFLAGS_BENCH) -c bench.c -o $@
http_parser.o: http_parser.c http_parser.h Makefile
$(CC) $(CPPFLAGS_FAST) $(CFLAGS_FAST) -c http_parser.c
$(CC) $(OPT_FAST) -c test.c -o $@
test-run-timed: test_fast
while(true) do time $(HELPER) ./test_fast$(BINEXT) > /dev/null; done
http_parser_g.o: http_parser.c http_parser.h Makefile
$(CC) $(OPT_DEBUG) -c http_parser.c -o $@
test-valgrind: test_g
valgrind ./test_g
libhttp_parser.o: http_parser.c http_parser.h Makefile
$(CC) $(CPPFLAGS_FAST) $(CFLAGS_LIB) -c http_parser.c -o libhttp_parser.o
library: libhttp_parser.o
$(CC) $(LDFLAGS_LIB) -o $(LIBNAME) $<
package: http_parser.o
$(AR) rcs libhttp_parser.a http_parser.o
url_parser: http_parser.o contrib/url_parser.c
$(CC) $(CPPFLAGS_FAST) $(CFLAGS_FAST) $^ -o $@
http_parser.o: http_parser.c http_parser.h Makefile
$(CC) $(OPT_FAST) -c http_parser.c
url_parser_g: http_parser_g.o contrib/url_parser.c
$(CC) $(CPPFLAGS_DEBUG) $(CFLAGS_DEBUG) $^ -o $@
test_fast: http_parser.o test.c http_parser.h
$(CC) $(OPT_FAST) http_parser.o test.c -o $@
parsertrace: http_parser.o contrib/parsertrace.c
$(CC) $(CPPFLAGS_FAST) $(CFLAGS_FAST) $^ -o parsertrace$(BINEXT)
test-run-timed: test_fast
while(true) do time ./test_fast > /dev/null; done
parsertrace_g: http_parser_g.o contrib/parsertrace.c
$(CC) $(CPPFLAGS_DEBUG) $(CFLAGS_DEBUG) $^ -o parsertrace_g$(BINEXT)
tags: http_parser.c http_parser.h test.c
ctags $^
install: library
$(INSTALL) -D http_parser.h $(DESTDIR)$(INCLUDEDIR)/http_parser.h
$(INSTALL) -D $(LIBNAME) $(DESTDIR)$(LIBDIR)/$(LIBNAME)
ln -sf $(LIBNAME) $(DESTDIR)$(LIBDIR)/$(SONAME)
ln -sf $(LIBNAME) $(DESTDIR)$(LIBDIR)/$(SOLIBNAME).$(SOEXT)
install-strip: library
$(INSTALL) -D http_parser.h $(DESTDIR)$(INCLUDEDIR)/http_parser.h
$(INSTALL) -D -s $(LIBNAME) $(DESTDIR)$(LIBDIR)/$(LIBNAME)
ln -sf $(LIBNAME) $(DESTDIR)$(LIBDIR)/$(SONAME)
ln -sf $(LIBNAME) $(DESTDIR)$(LIBDIR)/$(SOLIBNAME).$(SOEXT)
uninstall:
rm $(DESTDIR)$(INCLUDEDIR)/http_parser.h
rm $(DESTDIR)$(LIBDIR)/$(SOLIBNAME).$(SOEXT)
rm $(DESTDIR)$(LIBDIR)/$(SONAME)
rm $(DESTDIR)$(LIBDIR)/$(LIBNAME)
clean:
rm -f *.o *.a tags test test_fast test_g \
http_parser.tar libhttp_parser.so.* \
url_parser url_parser_g parsertrace parsertrace_g \
*.exe *.exe.so
contrib/url_parser.c: http_parser.h
contrib/parsertrace.c: http_parser.h
rm -f *.o test test_fast test_g http_parser.tar tags
.PHONY: clean package test-run test-run-timed test-valgrind install install-strip uninstall
.PHONY: clean package test-run test-run-timed test-valgrind

@ -1,8 +1,6 @@
HTTP Parser
===========
[![Build Status](https://api.travis-ci.org/nodejs/http-parser.svg?branch=master)](https://travis-ci.org/nodejs/http-parser)
This is a parser for HTTP messages written in C. It parses both requests and
responses. The parser is designed to be used in performance HTTP
applications. It does not make any syscalls nor allocations, it does not
@ -26,7 +24,7 @@ The parser extracts the following information from HTTP messages:
* Response status code
* Transfer-Encoding
* HTTP version
* Request URL
* Request path, query string, fragment
* Message body
@ -36,46 +34,43 @@ Usage
One `http_parser` object is used per TCP connection. Initialize the struct
using `http_parser_init()` and set the callbacks. That might look something
like this for a request parser:
```c
http_parser_settings settings;
settings.on_url = my_url_callback;
settings.on_header_field = my_header_field_callback;
/* ... */
http_parser *parser = malloc(sizeof(http_parser));
http_parser_init(parser, HTTP_REQUEST);
parser->data = my_socket;
```
http_parser_settings settings;
settings.on_path = my_path_callback;
settings.on_header_field = my_header_field_callback;
/* ... */
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.
```c
size_t len = 80*1024, nparsed;
char buf[len];
ssize_t recved;
size_t len = 80*1024, nparsed;
char buf[len];
ssize_t recved;
recved = recv(fd, buf, len, 0);
recved = recv(fd, buf, len, 0);
if (recved < 0) {
/* Handle error. */
}
if (recved < 0) {
/* Handle error. */
}
/* Start up / continue the parser.
* Note we pass recved==0 to signal that EOF has been received.
*/
nparsed = http_parser_execute(parser, &settings, buf, recved);
/* Start up / continue the parser.
* Note we pass recved==0 to signal that EOF has been recieved.
*/
nparsed = http_parser_execute(parser, &settings, buf, recved);
if (parser->upgrade) {
/* handle new protocol */
} else if (nparsed != recved) {
/* Handle error. Usually just close the connection. */
}
```
if (parser->upgrade) {
/* handle new protocol */
} else if (nparsed != recved) {
/* Handle error. Usually just close the connection. */
}
`http_parser` needs to know where the end of the stream is. For example, sometimes
HTTP needs to know where the end of the stream is. For example, sometimes
servers send responses without Content-Length and expect the client to
consume input (for the body) until EOF. To tell `http_parser` about EOF, give
`0` as the fourth parameter to `http_parser_execute()`. Callbacks and errors
consume input (for the body) until EOF. To tell http_parser about EOF, give
`0` as the forth parameter to `http_parser_execute()`. Callbacks and errors
can still be encountered during an EOF, so one must still be prepared
to receive them.
@ -93,8 +88,8 @@ the on_body callback.
The Special Problem of Upgrade
------------------------------
`http_parser` supports upgrading the connection to a different protocol. An
increasingly common example of this is the WebSocket protocol which sends
HTTP supports upgrading the connection to a different protocol. An
increasingly common example of this is the Web Socket protocol which sends
a request like
GET /demo HTTP/1.1
@ -106,11 +101,11 @@ a request like
followed by non-HTTP data.
(See [RFC6455](https://tools.ietf.org/html/rfc6455) for more information the
WebSocket protocol.)
(See http://tools.ietf.org/html/draft-hixie-thewebsocketprotocol-75 for more
information the Web Socket protocol.)
To support this, the parser will treat this as a normal HTTP message without a
body, issuing both on_headers_complete and on_message_complete callbacks. However
body. Issuing both on_headers_complete and on_message_complete callbacks. However
http_parser_execute() will stop parsing at the end of the headers and return.
The user is expected to check if `parser->upgrade` has been set to 1 after
@ -131,84 +126,21 @@ There are two types of callbacks:
* notification `typedef int (*http_cb) (http_parser*);`
Callbacks: on_message_begin, on_headers_complete, on_message_complete.
* data `typedef int (*http_data_cb) (http_parser*, const char *at, size_t length);`
Callbacks: (requests only) on_url,
Callbacks: (requests only) on_path, on_query_string, on_uri, on_fragment,
(common) on_header_field, on_header_value, on_body;
Callbacks must return 0 on success. Returning a non-zero value indicates
error to the parser, making it exit immediately.
For cases where it is necessary to pass local information to/from a callback,
the `http_parser` object's `data` field can be used.
An example of such a case is when using threads to handle a socket connection,
parse a request, and then give a response over that socket. By instantiation
of a thread-local struct containing relevant data (e.g. accepted socket,
allocated memory for callbacks to write into, etc), a parser's callbacks are
able to communicate data between the scope of the thread and the scope of the
callback in a threadsafe manner. This allows `http_parser` to be used in
multi-threaded contexts.
Example:
```c
typedef struct {
socket_t sock;
void* buffer;
int buf_len;
} custom_data_t;
int my_url_callback(http_parser* parser, const char *at, size_t length) {
/* access to thread local custom_data_t struct.
Use this access save parsed data for later use into thread local
buffer, or communicate over socket
*/
parser->data;
...
return 0;
}
...
void http_parser_thread(socket_t sock) {
int nparsed = 0;
/* allocate memory for user data */
custom_data_t *my_data = malloc(sizeof(custom_data_t));
/* some information for use by callbacks.
* achieves thread -> callback information flow */
my_data->sock = sock;
/* instantiate a thread-local parser */
http_parser *parser = malloc(sizeof(http_parser));
http_parser_init(parser, HTTP_REQUEST); /* initialise parser */
/* this custom data reference is accessible through the reference to the
parser supplied to callback functions */
parser->data = my_data;
http_parser_settings settings; /* set up callbacks */
settings.on_url = my_url_callback;
/* execute parser */
nparsed = http_parser_execute(parser, &settings, buf, recved);
...
/* parsed information copied from callback.
can now perform action on data copied into thread-local memory from callbacks.
achieves callback -> thread information flow */
my_data->buffer;
...
}
```
In case you parse HTTP message in chunks (i.e. `read()` request line
from socket, parse, read half headers, parse, etc) your data callbacks
may be called more than once. `http_parser` guarantees that data pointer is only
may be called more than once. Http-parser guarantees that data pointer is only
valid for the lifetime of callback. You can also `read()` into a heap allocated
buffer to avoid copying memory around if this fits your application.
Reading headers may be a tricky task if you read/parse headers partially.
Basically, you need to remember whether last header callback was field or value
and apply the following logic:
and apply following logic:
(on_header_field and on_header_value shortened to on_h_*)
------------------------ ------------ --------------------------------------------
@ -232,15 +164,8 @@ and apply the following logic:
------------------------ ------------ --------------------------------------------
Parsing URLs
------------
A simplistic zero-copy URL parser is provided as `http_parser_parse_url()`.
Users of this library may wish to use it to parse URLs constructed from
consecutive `on_url` callbacks.
See examples of reading in headers:
* [partial example](http://gist.github.com/155877) in C
* [from http-parser tests](http://github.com/joyent/http-parser/blob/37a0ff8/test.c#L403) in C
* [from Node library](http://github.com/joyent/node/blob/842eaf4/src/http.js#L284) in Javascript
* [from http-parser tests](http://github.com/ry/http-parser/blob/37a0ff8928fb0d83cec0d0d8909c5a4abcd221af/test.c#L403) in C
* [from Node library](http://github.com/ry/node/blob/842eaf446d2fdcb33b296c67c911c32a0dabc747/src/http.js#L284) in Javascript

@ -1,128 +0,0 @@
/* Copyright Fedor Indutny. All rights reserved.
*
* 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 <stdint.h>
#include <stdio.h>
#include <string.h>
#include <sys/time.h>
/* 8 gb */
static const int64_t kBytes = 8LL << 30;
static const char data[] =
"POST /joyent/http-parser HTTP/1.1\r\n"
"Host: github.com\r\n"
"DNT: 1\r\n"
"Accept-Encoding: gzip, deflate, sdch\r\n"
"Accept-Language: ru-RU,ru;q=0.8,en-US;q=0.6,en;q=0.4\r\n"
"User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/39.0.2171.65 Safari/537.36\r\n"
"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,"
"image/webp,*/*;q=0.8\r\n"
"Referer: https://github.com/joyent/http-parser\r\n"
"Connection: keep-alive\r\n"
"Transfer-Encoding: chunked\r\n"
"Cache-Control: max-age=0\r\n\r\nb\r\nhello world\r\n0\r\n";
static const size_t data_len = sizeof(data) - 1;
static int on_info(http_parser* p) {
return 0;
}
static int on_data(http_parser* p, const char *at, size_t length) {
return 0;
}
static http_parser_settings settings = {
.on_message_begin = on_info,
.on_headers_complete = on_info,
.on_message_complete = on_info,
.on_header_field = on_data,
.on_header_value = on_data,
.on_url = on_data,
.on_status = on_data,
.on_body = on_data
};
int bench(int iter_count, int silent) {
struct http_parser parser;
int i;
int err;
struct timeval start;
struct timeval end;
if (!silent) {
err = gettimeofday(&start, NULL);
assert(err == 0);
}
fprintf(stderr, "req_len=%d\n", (int) data_len);
for (i = 0; i < iter_count; i++) {
size_t parsed;
http_parser_init(&parser, HTTP_REQUEST);
parsed = http_parser_execute(&parser, &settings, data, data_len);
assert(parsed == data_len);
}
if (!silent) {
double elapsed;
double bw;
double total;
err = gettimeofday(&end, NULL);
assert(err == 0);
fprintf(stdout, "Benchmark result:\n");
elapsed = (double) (end.tv_sec - start.tv_sec) +
(end.tv_usec - start.tv_usec) * 1e-6f;
total = (double) iter_count * data_len;
bw = (double) total / elapsed;
fprintf(stdout, "%.2f mb | %.2f mb/s | %.2f req/sec | %.2f s\n",
(double) total / (1024 * 1024),
bw / (1024 * 1024),
(double) iter_count / elapsed,
elapsed);
fflush(stdout);
}
return 0;
}
int main(int argc, char** argv) {
int64_t iterations;
iterations = kBytes / (int64_t) data_len;
if (argc == 2 && strcmp(argv[1], "infinite") == 0) {
for (;;)
bench(iterations, 1);
return 0;
} else {
return bench(iterations, 0);
}
}

@ -1,157 +0,0 @@
/* 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.
*/
/* Dump what the parser finds to stdout as it happen */
#include "http_parser.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int on_message_begin(http_parser* _) {
(void)_;
printf("\n***MESSAGE BEGIN***\n\n");
return 0;
}
int on_headers_complete(http_parser* _) {
(void)_;
printf("\n***HEADERS COMPLETE***\n\n");
return 0;
}
int on_message_complete(http_parser* _) {
(void)_;
printf("\n***MESSAGE COMPLETE***\n\n");
return 0;
}
int on_url(http_parser* _, const char* at, size_t length) {
(void)_;
printf("Url: %.*s\n", (int)length, at);
return 0;
}
int on_header_field(http_parser* _, const char* at, size_t length) {
(void)_;
printf("Header field: %.*s\n", (int)length, at);
return 0;
}
int on_header_value(http_parser* _, const char* at, size_t length) {
(void)_;
printf("Header value: %.*s\n", (int)length, at);
return 0;
}
int on_body(http_parser* _, const char* at, size_t length) {
(void)_;
printf("Body: %.*s\n", (int)length, at);
return 0;
}
void usage(const char* name) {
fprintf(stderr,
"Usage: %s $type $filename\n"
" type: -x, where x is one of {r,b,q}\n"
" parses file as a Response, reQuest, or Both\n",
name);
exit(EXIT_FAILURE);
}
int main(int argc, char* argv[]) {
enum http_parser_type file_type;
if (argc != 3) {
usage(argv[0]);
}
char* type = argv[1];
if (type[0] != '-') {
usage(argv[0]);
}
switch (type[1]) {
/* in the case of "-", type[1] will be NUL */
case 'r':
file_type = HTTP_RESPONSE;
break;
case 'q':
file_type = HTTP_REQUEST;
break;
case 'b':
file_type = HTTP_BOTH;
break;
default:
usage(argv[0]);
}
char* filename = argv[2];
FILE* file = fopen(filename, "r");
if (file == NULL) {
perror("fopen");
goto fail;
}
fseek(file, 0, SEEK_END);
long file_length = ftell(file);
if (file_length == -1) {
perror("ftell");
goto fail;
}
fseek(file, 0, SEEK_SET);
char* data = malloc(file_length);
if (fread(data, 1, file_length, file) != (size_t)file_length) {
fprintf(stderr, "couldn't read entire file\n");
free(data);
goto fail;
}
http_parser_settings settings;
memset(&settings, 0, sizeof(settings));
settings.on_message_begin = on_message_begin;
settings.on_url = on_url;
settings.on_header_field = on_header_field;
settings.on_header_value = on_header_value;
settings.on_headers_complete = on_headers_complete;
settings.on_body = on_body;
settings.on_message_complete = on_message_complete;
http_parser parser;
http_parser_init(&parser, file_type);
size_t nparsed = http_parser_execute(&parser, &settings, data, file_length);
free(data);
if (nparsed != (size_t)file_length) {
fprintf(stderr,
"Error: %s (%s)\n",
http_errno_description(HTTP_PARSER_ERRNO(&parser)),
http_errno_name(HTTP_PARSER_ERRNO(&parser)));
goto fail;
}
return EXIT_SUCCESS;
fail:
fclose(file);
return EXIT_FAILURE;
}

@ -1,47 +0,0 @@
#include "http_parser.h"
#include <stdio.h>
#include <string.h>
void
dump_url (const char *url, const struct http_parser_url *u)
{
unsigned int i;
printf("\tfield_set: 0x%x, port: %u\n", u->field_set, u->port);
for (i = 0; i < UF_MAX; i++) {
if ((u->field_set & (1 << i)) == 0) {
printf("\tfield_data[%u]: unset\n", i);
continue;
}
printf("\tfield_data[%u]: off: %u, len: %u, part: %.*s\n",
i,
u->field_data[i].off,
u->field_data[i].len,
u->field_data[i].len,
url + u->field_data[i].off);
}
}
int main(int argc, char ** argv) {
struct http_parser_url u;
int len, connect, result;
if (argc != 3) {
printf("Syntax : %s connect|get url\n", argv[0]);
return 1;
}
len = strlen(argv[2]);
connect = strcmp("connect", argv[1]) == 0 ? 1 : 0;
printf("Parsing %s, connect %d\n", argv[2], connect);
http_parser_url_init(&u);
result = http_parser_parse_url(argv[2], len, connect, &u);
if (result != 0) {
printf("Parse error : %d\n", result);
return result;
}
printf("Parse ok, result : \n");
dump_url(argv[2], &u);
return 0;
}

File diff suppressed because it is too large Load Diff

@ -1,111 +0,0 @@
# This file is used with the GYP meta build system.
# http://code.google.com/p/gyp/
# To build try this:
# svn co http://gyp.googlecode.com/svn/trunk gyp
# ./gyp/gyp -f make --depth=`pwd` http_parser.gyp
# ./out/Debug/test
{
'target_defaults': {
'default_configuration': 'Debug',
'configurations': {
# TODO: hoist these out and put them somewhere common, because
# RuntimeLibrary MUST MATCH across the entire project
'Debug': {
'defines': [ 'DEBUG', '_DEBUG' ],
'cflags': [ '-Wall', '-Wextra', '-O0', '-g', '-ftrapv' ],
'msvs_settings': {
'VCCLCompilerTool': {
'RuntimeLibrary': 1, # static debug
},
},
},
'Release': {
'defines': [ 'NDEBUG' ],
'cflags': [ '-Wall', '-Wextra', '-O3' ],
'msvs_settings': {
'VCCLCompilerTool': {
'RuntimeLibrary': 0, # static release
},
},
}
},
'msvs_settings': {
'VCCLCompilerTool': {
},
'VCLibrarianTool': {
},
'VCLinkerTool': {
'GenerateDebugInformation': 'true',
},
},
'conditions': [
['OS == "win"', {
'defines': [
'WIN32'
],
}]
],
},
'targets': [
{
'target_name': 'http_parser',
'type': 'static_library',
'include_dirs': [ '.' ],
'direct_dependent_settings': {
'defines': [ 'HTTP_PARSER_STRICT=0' ],
'include_dirs': [ '.' ],
},
'defines': [ 'HTTP_PARSER_STRICT=0' ],
'sources': [ './http_parser.c', ],
'conditions': [
['OS=="win"', {
'msvs_settings': {
'VCCLCompilerTool': {
# Compile as C++. http_parser.c is actually C99, but C++ is
# close enough in this case.
'CompileAs': 2,
},
},
}]
],
},
{
'target_name': 'http_parser_strict',
'type': 'static_library',
'include_dirs': [ '.' ],
'direct_dependent_settings': {
'defines': [ 'HTTP_PARSER_STRICT=1' ],
'include_dirs': [ '.' ],
},
'defines': [ 'HTTP_PARSER_STRICT=1' ],
'sources': [ './http_parser.c', ],
'conditions': [
['OS=="win"', {
'msvs_settings': {
'VCCLCompilerTool': {
# Compile as C++. http_parser.c is actually C99, but C++ is
# close enough in this case.
'CompileAs': 2,
},
},
}]
],
},
{
'target_name': 'test-nonstrict',
'type': 'executable',
'dependencies': [ 'http_parser' ],
'sources': [ 'test.c' ]
},
{
'target_name': 'test-strict',
'type': 'executable',
'dependencies': [ 'http_parser_strict' ],
'sources': [ 'test.c' ]
}
]
}

@ -1,4 +1,4 @@
/* Copyright Joyent, Inc. and other Node contributors. All rights reserved.
/* Copyright 2009,2010 Ryan Dahl <ry@tinyclouds.org>
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
@ -24,15 +24,9 @@
extern "C" {
#endif
/* Also update SONAME in the Makefile whenever you change these. */
#define HTTP_PARSER_VERSION_MAJOR 2
#define HTTP_PARSER_VERSION_MINOR 9
#define HTTP_PARSER_VERSION_PATCH 4
#include <stddef.h>
#if defined(_WIN32) && !defined(__MINGW32__) && \
(!defined(_MSC_VER) || _MSC_VER<1600) && !defined(__WINE__)
#include <BaseTsd.h>
#include <sys/types.h>
#if defined(_WIN32) && !defined(__MINGW32__)
typedef __int8 int8_t;
typedef unsigned __int8 uint8_t;
typedef __int16 int16_t;
@ -41,6 +35,9 @@ 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
@ -50,392 +47,229 @@ typedef unsigned __int64 uint64_t;
*/
#ifndef HTTP_PARSER_STRICT
# define HTTP_PARSER_STRICT 1
#else
# define HTTP_PARSER_STRICT 0
#endif
/* Maximium header size allowed. If the macro is not defined
* before including this header then the default is used. To
* change the maximum header size, define the macro in the build
* environment (e.g. -DHTTP_MAX_HEADER_SIZE=<value>). To remove
* the effective limit on the size of the header, define the macro
* to a very large number (e.g. -DHTTP_MAX_HEADER_SIZE=0x7fffffff)
*/
#ifndef HTTP_MAX_HEADER_SIZE
# define HTTP_MAX_HEADER_SIZE (80*1024)
#endif
typedef struct http_parser http_parser;
typedef struct http_parser_settings http_parser_settings;
/* Maximium header size allowed */
#define HTTP_MAX_HEADER_SIZE (80*1024)
/* Callbacks should return non-zero to indicate an error. The parser will
* then halt execution.
*
* The one exception is on_headers_complete. In a HTTP_RESPONSE parser
* returning '1' from on_headers_complete will tell the parser that it
* should not expect a body. This is used when receiving a response to a
* HEAD request which may contain 'Content-Length' or 'Transfer-Encoding:
* chunked' headers that indicate the presence of a body.
*
* Returning `2` from on_headers_complete will tell parser that it should not
* expect neither a body nor any futher responses on this connection. This is
* useful for handling responses to a CONNECT request which may not contain
* `Upgrade` or `Connection: upgrade` headers.
*
* http_data_cb does not return data chunks. It will be called arbitrarily
* 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);
typedef int (*http_cb) (http_parser*);
/* Status Codes */
#define HTTP_STATUS_MAP(XX) \
XX(100, CONTINUE, Continue) \
XX(101, SWITCHING_PROTOCOLS, Switching Protocols) \
XX(102, PROCESSING, Processing) \
XX(200, OK, OK) \
XX(201, CREATED, Created) \
XX(202, ACCEPTED, Accepted) \
XX(203, NON_AUTHORITATIVE_INFORMATION, Non-Authoritative Information) \
XX(204, NO_CONTENT, No Content) \
XX(205, RESET_CONTENT, Reset Content) \
XX(206, PARTIAL_CONTENT, Partial Content) \
XX(207, MULTI_STATUS, Multi-Status) \
XX(208, ALREADY_REPORTED, Already Reported) \
XX(226, IM_USED, IM Used) \
XX(300, MULTIPLE_CHOICES, Multiple Choices) \
XX(301, MOVED_PERMANENTLY, Moved Permanently) \
XX(302, FOUND, Found) \
XX(303, SEE_OTHER, See Other) \
XX(304, NOT_MODIFIED, Not Modified) \
XX(305, USE_PROXY, Use Proxy) \
XX(307, TEMPORARY_REDIRECT, Temporary Redirect) \
XX(308, PERMANENT_REDIRECT, Permanent Redirect) \
XX(400, BAD_REQUEST, Bad Request) \
XX(401, UNAUTHORIZED, Unauthorized) \
XX(402, PAYMENT_REQUIRED, Payment Required) \
XX(403, FORBIDDEN, Forbidden) \
XX(404, NOT_FOUND, Not Found) \
XX(405, METHOD_NOT_ALLOWED, Method Not Allowed) \
XX(406, NOT_ACCEPTABLE, Not Acceptable) \
XX(407, PROXY_AUTHENTICATION_REQUIRED, Proxy Authentication Required) \
XX(408, REQUEST_TIMEOUT, Request Timeout) \
XX(409, CONFLICT, Conflict) \
XX(410, GONE, Gone) \
XX(411, LENGTH_REQUIRED, Length Required) \
XX(412, PRECONDITION_FAILED, Precondition Failed) \
XX(413, PAYLOAD_TOO_LARGE, Payload Too Large) \
XX(414, URI_TOO_LONG, URI Too Long) \
XX(415, UNSUPPORTED_MEDIA_TYPE, Unsupported Media Type) \
XX(416, RANGE_NOT_SATISFIABLE, Range Not Satisfiable) \
XX(417, EXPECTATION_FAILED, Expectation Failed) \
XX(421, MISDIRECTED_REQUEST, Misdirected Request) \
XX(422, UNPROCESSABLE_ENTITY, Unprocessable Entity) \
XX(423, LOCKED, Locked) \
XX(424, FAILED_DEPENDENCY, Failed Dependency) \
XX(426, UPGRADE_REQUIRED, Upgrade Required) \
XX(428, PRECONDITION_REQUIRED, Precondition Required) \
XX(429, TOO_MANY_REQUESTS, Too Many Requests) \
XX(431, REQUEST_HEADER_FIELDS_TOO_LARGE, Request Header Fields Too Large) \
XX(451, UNAVAILABLE_FOR_LEGAL_REASONS, Unavailable For Legal Reasons) \
XX(500, INTERNAL_SERVER_ERROR, Internal Server Error) \
XX(501, NOT_IMPLEMENTED, Not Implemented) \
XX(502, BAD_GATEWAY, Bad Gateway) \
XX(503, SERVICE_UNAVAILABLE, Service Unavailable) \
XX(504, GATEWAY_TIMEOUT, Gateway Timeout) \
XX(505, HTTP_VERSION_NOT_SUPPORTED, HTTP Version Not Supported) \
XX(506, VARIANT_ALSO_NEGOTIATES, Variant Also Negotiates) \
XX(507, INSUFFICIENT_STORAGE, Insufficient Storage) \
XX(508, LOOP_DETECTED, Loop Detected) \
XX(510, NOT_EXTENDED, Not Extended) \
XX(511, NETWORK_AUTHENTICATION_REQUIRED, Network Authentication Required) \
enum http_status
{
#define XX(num, name, string) HTTP_STATUS_##name = num,
HTTP_STATUS_MAP(XX)
#undef XX
};
typedef struct http_parser 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) \
XX(16, BIND, BIND) \
XX(17, REBIND, REBIND) \
XX(18, UNBIND, UNBIND) \
XX(19, ACL, ACL) \
/* subversion */ \
XX(20, REPORT, REPORT) \
XX(21, MKACTIVITY, MKACTIVITY) \
XX(22, CHECKOUT, CHECKOUT) \
XX(23, MERGE, MERGE) \
/* upnp */ \
XX(24, MSEARCH, M-SEARCH) \
XX(25, NOTIFY, NOTIFY) \
XX(26, SUBSCRIBE, SUBSCRIBE) \
XX(27, UNSUBSCRIBE, UNSUBSCRIBE) \
/* RFC-5789 */ \
XX(28, PATCH, PATCH) \
XX(29, PURGE, PURGE) \
/* CalDAV */ \
XX(30, MKCALENDAR, MKCALENDAR) \
/* RFC-2068, section 19.6.1.2 */ \
XX(31, LINK, LINK) \
XX(32, UNLINK, UNLINK) \
/* icecast */ \
XX(33, SOURCE, SOURCE) \
enum http_method
{
#define XX(num, name, string) HTTP_##name = num,
HTTP_METHOD_MAP(XX)
#undef XX
{ 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
};
enum http_parser_type { HTTP_REQUEST, HTTP_RESPONSE, HTTP_BOTH };
/* Flag values for http_parser.flags field */
enum flags
{ F_CHUNKED = 1 << 0
, F_CONNECTION_KEEP_ALIVE = 1 << 1
, F_CONNECTION_CLOSE = 1 << 2
, F_CONNECTION_UPGRADE = 1 << 3
, F_TRAILING = 1 << 4
, F_UPGRADE = 1 << 5
, F_SKIPBODY = 1 << 6
, F_CONTENTLENGTH = 1 << 7
, F_TRANSFER_ENCODING = 1 << 8 /* Never set in http_parser.flags */
};
/* Map for errno-related constants
*
* The provided argument should be a macro that takes 2 arguments.
*/
#define HTTP_ERRNO_MAP(XX) \
/* No error */ \
XX(OK, "success") \
\
/* Callback-related errors */ \
XX(CB_message_begin, "the on_message_begin callback failed") \
XX(CB_url, "the on_url 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") \
XX(CB_body, "the on_body callback failed") \
XX(CB_message_complete, "the on_message_complete callback failed") \
XX(CB_status, "the on_status callback failed") \
XX(CB_chunk_header, "the on_chunk_header callback failed") \
XX(CB_chunk_complete, "the on_chunk_complete callback failed") \
\
/* Parsing-related errors */ \
XX(INVALID_EOF_STATE, "stream ended at an unexpected time") \
XX(HEADER_OVERFLOW, \
"too many header bytes seen; overflow detected") \
XX(CLOSED_CONNECTION, \
"data received after completed connection: close message") \
XX(INVALID_VERSION, "invalid HTTP version") \
XX(INVALID_STATUS, "invalid HTTP status code") \
XX(INVALID_METHOD, "invalid HTTP method") \
XX(INVALID_URL, "invalid URL") \
XX(INVALID_HOST, "invalid host") \
XX(INVALID_PORT, "invalid port") \
XX(INVALID_PATH, "invalid path") \
XX(INVALID_QUERY_STRING, "invalid query string") \
XX(INVALID_FRAGMENT, "invalid fragment") \
XX(LF_EXPECTED, "LF character expected") \
XX(INVALID_HEADER_TOKEN, "invalid character in header") \
XX(INVALID_CONTENT_LENGTH, \
"invalid character in content-length header") \
XX(UNEXPECTED_CONTENT_LENGTH, \
"unexpected content-length header") \
XX(INVALID_CHUNK_SIZE, \
"invalid character in chunk size header") \
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") \
XX(INVALID_TRANSFER_ENCODING, \
"request has invalid transfer-encoding") \
/* Define HPE_* values for each errno value above */
#define HTTP_ERRNO_GEN(n, s) HPE_##n,
enum http_errno {
HTTP_ERRNO_MAP(HTTP_ERRNO_GEN)
};
#undef HTTP_ERRNO_GEN
/* Get an http_errno value from an http_parser */
#define HTTP_PARSER_ERRNO(p) ((enum http_errno) (p)->http_errno)
struct http_parser {
/** PRIVATE **/
unsigned int type : 2; /* enum http_parser_type */
unsigned int flags : 8; /* F_* values from 'flags' enum; semi-public */
unsigned int state : 7; /* enum state from http_parser.c */
unsigned int header_state : 7; /* enum header_state from http_parser.c */
unsigned int index : 5; /* index into current matcher */
unsigned int extra_flags : 2;
unsigned int lenient_http_headers : 1;
unsigned char type : 2;
unsigned char flags : 6;
unsigned char state;
unsigned char header_state;
unsigned char index;
uint32_t nread; /* # bytes read in various scenarios */
uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */
uint32_t nread;
int64_t content_length;
/** READ-ONLY **/
unsigned short http_major;
unsigned short http_minor;
unsigned int status_code : 16; /* responses only */
unsigned int method : 8; /* requests only */
unsigned int http_errno : 7;
unsigned short status_code; /* responses only */
unsigned char method; /* requests only */
/* 1 = Upgrade header was present and the parser has exited because of that.
* 0 = No upgrade header present.
* Should be checked when http_parser_execute() returns in addition to
* error checking.
*/
unsigned int upgrade : 1;
char upgrade;
/** PUBLIC **/
void *data; /* A pointer to get hook to the "connection" or "socket" object */
};
void http_parser_init(http_parser *parser, enum http_parser_type type);
/* If http_should_keep_alive() in the on_headers_complete or
* on_message_complete callback returns true, then this will be 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);
/* Returns a string version of the HTTP method. */
const char *http_method_str(enum http_method);
/********* Parser Interface 1 *********/
/* For those who like callbacks */
/* Callbacks should return non-zero to indicate an error. The parser will
* then halt execution.
*
* The one exception is on_headers_complete. In a HTTP_RESPONSE parser
* returning '1' from on_headers_complete will tell the parser that it
* should not expect a body. This is used when receiving a response to a
* HEAD request which may contain 'Content-Length' or 'Transfer-Encoding:
* 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"
* each providing just a few characters more data.
*/
typedef int (*http_data_cb) (http_parser*, const char *at, size_t length);
typedef int (*http_cb) (http_parser*);
typedef struct http_parser_settings http_parser_settings;
struct http_parser_settings {
http_cb on_message_begin;
http_data_cb on_path;
http_data_cb on_query_string;
http_data_cb on_url;
http_data_cb on_status;
http_data_cb on_fragment;
http_data_cb on_header_field;
http_data_cb on_header_value;
http_cb on_headers_complete;
http_data_cb on_body;
http_cb on_message_complete;
/* When on_chunk_header is called, the current chunk length is stored
* in parser->content_length.
*/
http_cb on_chunk_header;
http_cb on_chunk_complete;
};
size_t http_parser_execute(http_parser *parser,
const http_parser_settings *settings,
const char *buf,
size_t buf_len);
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];
};
/* Returns the library version. Bits 16-23 contain the major version number,
* bits 8-15 the minor version number and bits 0-7 the patch level.
* Usage example:
*
* unsigned long version = http_parser_version();
* unsigned major = (version >> 16) & 255;
* unsigned minor = (version >> 8) & 255;
* unsigned patch = version & 255;
* printf("http_parser v%u.%u.%u\n", major, minor, patch);
*/
unsigned long http_parser_version(void);
void http_parser_init(http_parser *parser, enum http_parser_type type);
/* Initialize http_parser_settings members to 0
*/
void http_parser_settings_init(http_parser_settings *settings);
/********** Parser Interface 2 **********/
/** For those who don't like callbacks **/
/****************************************/
/* Executes the parser. Returns number of parsed bytes. Sets
* `parser->http_errno` on error. */
size_t http_parser_execute(http_parser *parser,
const http_parser_settings *settings,
const char *data,
size_t len);
typedef struct http_parser_data http_parser_data;
/* If http_should_keep_alive() in the on_headers_complete or
* 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(const http_parser *parser);
struct http_parser_data {
enum { HTTP_PARSER_ERROR = 0
, HTTP_NEEDS_INPUT
, HTTP_NEEDS_DATA_ELEMENTS
, HTTP_REQ_MESSAGE_START /* payload.method */
, HTTP_RES_MESSAGE_START /* payload.status */
, HTTP_VERSION /* payload.version */
, HTTP_PATH /* payload.string */
, HTTP_QUERY_STRING /* payload.string */
, HTTP_URL /* payload.string */
, HTTP_FRAGMENT /* payload.string */
, HTTP_HEADER_FIELD /* payload.string */
, HTTP_HEADER_VALUE /* payload.string */
, HTTP_HEADERS_END /* payload.flags */
, HTTP_BODY /* payload.string */
, HTTP_MESSAGE_END /* payload.string */
} type;
/* Returns a string version of the HTTP method. */
const char *http_method_str(enum http_method m);
union {
struct {
const char *p;
size_t len;
} string;
/* Returns a string version of the HTTP status code. */
const char *http_status_str(enum http_status s);
/* For HTTP_RES_MESSAGE_START */
unsigned short status_code;
/* Return a string name of the given error */
const char *http_errno_name(enum http_errno err);
/* For HTTP_REQ_MESSAGE_START */
unsigned char method;
/* Return a string description of the given error */
const char *http_errno_description(enum http_errno err);
/* For HTTP_VERSION */
struct {
unsigned short major;
unsigned short minor;
} version;
/* Initialize all http_parser_url members to 0 */
void http_parser_url_init(struct http_parser_url *u);
/* For HTTP_HEADERS_END */
unsigned char flags : 6;
/* 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);
} payload;
/* 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);
/* Returns the number of elements filled into `data`.
*
* Normally `http_parser_execute2` will parse the entire `buf` and fill
* `data` with elements. Under several conditions `http_parser_execute2` may
* drop out early.
*
* 1. A parse error was encountered. The last element of data will be
* HTTP_PARSER_ERROR. The parser cannot continue further. The
* connection to the peer should be severed.
*
* 2. The parser still to parser more of `buf` but it has run out of
* space in the user-supplied `http_parser_data` array. The last
* element of `data` will be HTTP_NEEDS_DATA_ELEMENTS. Restart
* http_parser_execute2() with a fresh array of elements starting at
* payload.string.p in the HTTP_NEEDS_DATA_ELEMENTS object.
*
* 3. The parser cannot continue until http_parser_has_body(parser, 1)
* or http_parser_has_body(parser, 0) is called. This is required for
* all HTTP responses. For the parser it is unclear from the headers if
* a response message has a body or not. For example, if the message is
* a response to a HEAD request, then it MUST NOT have a body but
* nevertheless may contain "Content-Length" or
* "Tranfer-Encoding: chunked" headers (which normally indicate the
* presence of a body to the parser).
*
* The last element of `data` will be HTTP_NEEDS_INPUT. The user must
* call http_parser_has_body() and then restart http_parser_execute2
* with a fresh array of `data` elements and starting at
* payload.string.p that HTTP_NEEDS_INPUT pointed to.
*/
int http_parser_execute2(http_parser* parser,
const char* buf,
size_t buf_len,
http_parser_data data[],
int data_len);
/* Change the maximum header size provided at compile time. */
void http_parser_set_max_header_size(uint32_t size);
void http_parser_has_body(http_parser* parser, int);
#ifdef __cplusplus
}

4079
test.c

File diff suppressed because it is too large Load Diff
Loading…
Cancel
Save