http_parser.rb 0.5.2 → 0.7.0

data/ext/ruby_http_parser/vendor/http-parser/AUTHORS

@@ -0,0 +1,68 @@
+# 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>

data/ext/ruby_http_parser/vendor/http-parser/LICENSE-MIT

@@ -1,4 +1,4 @@
-Copyright Joyent, Inc. and other Node contributors. All rights reserved.
+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

data/ext/ruby_http_parser/vendor/http-parser/README.md

@@ -1,6 +1,8 @@
 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
@@ -24,7 +26,7 @@ The parser extracts the following information from HTTP messages:
   * Response status code
   * Transfer-Encoding
   * HTTP version
-  * Request path, query string, fragment
+  * Request URL
   * Message body
 
 
@@ -34,43 +36,46 @@ 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_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;
+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.
 
-    size_t len = 80*1024, nparsed;
-    char buf[len];
-    ssize_t recved;
+```c
+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 recieved.
-     */
-    nparsed = http_parser_execute(parser, &settings, buf, recved);
+/* 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);
 
-    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 needs to know where the end of the stream is. For example, sometimes
+`http_parser` 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 forth 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 fourth parameter to `http_parser_execute()`. Callbacks and errors
 can still be encountered during an EOF, so one must still be prepared
 to receive them.
 
@@ -88,8 +93,8 @@ the on_body callback.
 The Special Problem of Upgrade
 ------------------------------
 
-HTTP supports upgrading the connection to a different protocol. An
-increasingly common example of this is the Web Socket protocol which sends
+`http_parser` supports upgrading the connection to a different protocol. An
+increasingly common example of this is the WebSocket protocol which sends
 a request like
 
         GET /demo HTTP/1.1
@@ -101,11 +106,11 @@ a request like
 
 followed by non-HTTP data.
 
-(See http://tools.ietf.org/html/draft-hixie-thewebsocketprotocol-75 for more
-information the Web Socket protocol.)
+(See [RFC6455](https://tools.ietf.org/html/rfc6455) for more information the
+WebSocket 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
@@ -126,21 +131,84 @@ 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_path, on_query_string, on_uri, on_fragment,
+    Callbacks: (requests only) on_url,
                (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 following logic:
+and apply the following logic:
 
     (on_header_field and on_header_value shortened to on_h_*)
      ------------------------ ------------ --------------------------------------------
@@ -164,8 +232,15 @@ and apply 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/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
+* [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

data/ext/ruby_http_parser/vendor/http-parser/bench.c

@@ -0,0 +1,128 @@
+/* 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);
+  }
+}

data/ext/ruby_http_parser/vendor/http-parser/contrib/parsertrace.c

@@ -0,0 +1,157 @@
+/* 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;
+}