http_parser.rb 0.6.0 → 0.7.0

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    MGMxN2Q5N2MzMTlmNjEyY2NhMmQzNjdjMDRiYmQxNGY4ZjIyMzM0Mg==
-  data.tar.gz: !binary |-
-    YmVhZTVjYmMxNGM3YjUwOWQ3NmUwYzEwZThlZWM5NDQ0ZGMwYTgwNA==
+SHA256:
+  metadata.gz: afdb28464ccb0f753a1d66be02b667683d6aadfe31fe03a88f889252b457761d
+  data.tar.gz: 6041b3dc3f212160ae00b72b193e4620c5facd59096a28b122c0ef5a901dc80b
 SHA512:
-  metadata.gz: !binary |-
-    YWM3ZDZmMjdmYzQxMTZiN2VjZTMxYjczMjgxN2ZjYWY0YjE3ODllYjM5Nzg0
-    OTUwOTk3ODYwZGJhNGIwMjA0Mjg1MTFkNDgxY2ZlMGIzZjQwNmQ1ODVkMjFj
-    ZjQyYzVmNjlkYTQ0NDZkMzhhYjE1M2FhZTdiOTdlYzAxMzljOWY=
-  data.tar.gz: !binary |-
-    M2ZiYTcwYTg2ZDJjZDc2N2Y0NzhmMzE0MzExNTY5M2I3MzAxMTkzNzUyYzUz
-    NGM2YzRmOGM3OGQ4NDNkMmIwYjM2MjYyMGJlNTU1MTVlNzFiYjgxZjJiYmNi
-    Y2Q4N2YyZWFjODYwYzlhNGMwMzcxNTcwZjIwMWJjNDViNjQ1MTc=
+  metadata.gz: 41249c628f931cd9721e32bd378a44b8e49b25706b491ae3761d641e55bac1205afe9d3d02d88d5b4f3161adee4a65416c5eec2a51fcacad1b050d6f6d2637fc
+  data.tar.gz: ae5718390cce25d2ee7fcbaf923fac015189079b64ea2f37759c41ee2e7f2714dafaf6bf37ed6434f540e82e87c6a13723e226ac27000d1f0e2d7b2681643514

data/.github/workflows/linux.yml

@@ -0,0 +1,23 @@
+name: Testing on Ubuntu
+on:
+  - push
+  - pull_request
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby: [ '2.6', '2.7', '3.0' ]
+        os: [ 'ubuntu-latest' ]
+    name: Ruby ${{ matrix.ruby }} unit testing on ${{ matrix.os }}
+    steps:
+    - uses: actions/checkout@v2
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+    - name: unit testing
+      run: |
+        gem install bundler rake
+        bundle install --jobs 4 --retry 3
+        bundle exec rake

data/.github/workflows/windows.yml

@@ -0,0 +1,23 @@
+name: Testing on Windows
+on:
+  - push
+  - pull_request
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby: [ '2.6', '2.7', '3.0' ]
+        os: [ 'windows-latest' ]
+    name: Ruby ${{ matrix.ruby }} unit testing on ${{ matrix.os }}
+    steps:
+    - uses: actions/checkout@v2
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+    - name: unit testing
+      run: |
+        gem install bundler rake
+        bundle install --jobs 4 --retry 3
+        bundle exec rake

data/.gitignore

@@ -1,11 +1,12 @@
-tmp
+*.bundle
 *.bundle
 *.gem
+*.jar
 *.o
+*.rbc
 *.so
-*.bundle
-*.jar
 *.swp
+Gemfile.lock
 Makefile
 tags
-*.rbc
+tmp

data/.gitmodules

@@ -1,6 +1,6 @@
 [submodule "http-parser"]
 	path = ext/ruby_http_parser/vendor/http-parser
-	url = git://github.com/joyent/http-parser.git
+	url = https://github.com/nodejs/http-parser.git
 [submodule "http-parser-java"]
 	path = ext/ruby_http_parser/vendor/http-parser-java
-	url = git://github.com/tmm1/http-parser.java
+	url = https://github.com/tmm1/http-parser.java

data/README.md

@@ -3,13 +3,13 @@
 A simple callback-based HTTP request/response parser for writing http
 servers, clients and proxies.
 
-This gem is built on top of [joyent/http-parser](http://github.com/joyent/http-parser) and its java port [http-parser/http-parser.java](http://github.com/http-parser/http-parser.java).
+This gem is built on top of [joyent/http-parser](https://github.com/joyent/http-parser) and its java port [http-parser/http-parser.java](https://github.com/http-parser/http-parser.java).
 
 ## Supported Platforms
 
 This gem aims to work on all major Ruby platforms, including:
 
-- MRI 1.8 and 1.9
+- MRI 1.8, 1.9 and 2.0; should work on MRI 2.4+
 - Rubinius
 - JRuby
 - win32

data/Rakefile

@@ -1,4 +1,5 @@
 # load tasks
+require 'bundler/gem_tasks'
 Dir['tasks/*.rake'].sort.each { |f| load f }
 
 # default task

data/ext/ruby_http_parser/extconf.rb

@@ -18,7 +18,7 @@ src_dir = File.expand_path('../', __FILE__)
   }
 end
 
-$CFLAGS << " -I#{src_dir}"
+$CFLAGS << " -I\"#{src_dir}\""
 
 dir_config("ruby_http_parser")
 create_makefile("ruby_http_parser")

data/ext/ruby_http_parser/org/ruby_http_parser/RubyHttpParser.java

@@ -64,6 +64,7 @@ public class RubyHttpParser extends RubyObject {
   private IRubyObject on_body;
   private IRubyObject on_message_complete;
 
+  private IRubyObject status;
   private IRubyObject requestUrl;
   private IRubyObject requestPath;
   private IRubyObject queryString;
@@ -106,6 +107,18 @@ public class RubyHttpParser extends RubyObject {
   private void initSettings() {
     this.settings = new ParserSettings();
 
+    this.settings.on_status = new HTTPDataCallback() {
+      public int cb(http_parser.lolevel.HTTPParser p, ByteBuffer buf, int pos, int len) {
+        byte[] data = fetchBytes(buf, pos, len);
+        if (runtime.is1_9() || runtime.is2_0()) {
+          ((RubyString) status).cat(data, 0, data.length, UTF8);
+        } else {
+          ((RubyString) status).cat(data);
+        }
+        return 0;
+      }
+    };
+
     this.settings.on_url = new HTTPDataCallback() {
       public int cb(http_parser.lolevel.HTTPParser p, ByteBuffer buf, int pos, int len) {
         byte[] data = fetchBytes(buf, pos, len);
@@ -202,12 +215,14 @@ public class RubyHttpParser extends RubyObject {
         headers = new RubyHash(runtime);
 
         if (runtime.is1_9() || runtime.is2_0()) {
+          status = RubyString.newEmptyString(runtime, UTF8);
           requestUrl = RubyString.newEmptyString(runtime, UTF8);
           requestPath = RubyString.newEmptyString(runtime, UTF8);
           queryString = RubyString.newEmptyString(runtime, UTF8);
           fragment = RubyString.newEmptyString(runtime, UTF8);
           upgradeData = RubyString.newEmptyString(runtime, UTF8);
         } else {
+          status = RubyString.newEmptyString(runtime);
           requestUrl = RubyString.newEmptyString(runtime);
           requestPath = RubyString.newEmptyString(runtime);
           queryString = RubyString.newEmptyString(runtime);
@@ -309,7 +324,8 @@ public class RubyHttpParser extends RubyObject {
     this.parser = new HTTPParser();
     this.parser.HTTP_PARSER_STRICT = true;
     this.headers = null;
-
+    
+    this.status = runtime.getNil();
     this.requestUrl = runtime.getNil();
     this.requestPath = runtime.getNil();
     this.queryString = runtime.getNil();
@@ -446,6 +462,11 @@ public class RubyHttpParser extends RubyObject {
     return headers == null ? runtime.getNil() : headers;
   }
 
+  @JRubyMethod(name = "status")
+  public IRubyObject getStatus() {
+    return status == null ? runtime.getNil() : status;
+  }
+
   @JRubyMethod(name = "request_url")
   public IRubyObject getRequestUrl() {
     return requestUrl == null ? runtime.getNil() : requestUrl;

data/ext/ruby_http_parser/ruby_http_parser.c

@@ -16,6 +16,7 @@
 typedef struct ParserWrapper {
   ryah_http_parser parser;
 
+  VALUE status;
   VALUE request_url;
 
   VALUE headers;
@@ -45,6 +46,7 @@ void ParserWrapper_init(ParserWrapper *wrapper) {
   wrapper->parser.http_major = 0;
   wrapper->parser.http_minor = 0;
 
+  wrapper->status = Qnil;
   wrapper->request_url = Qnil;
 
   wrapper->upgrade_data = Qnil;
@@ -59,6 +61,7 @@ void ParserWrapper_init(ParserWrapper *wrapper) {
 void ParserWrapper_mark(void *data) {
   if(data) {
     ParserWrapper *wrapper = (ParserWrapper *) data;
+    rb_gc_mark_maybe(wrapper->status);
     rb_gc_mark_maybe(wrapper->request_url);
     rb_gc_mark_maybe(wrapper->upgrade_data);
     rb_gc_mark_maybe(wrapper->headers);
@@ -101,6 +104,7 @@ static VALUE Smixed;
 int on_message_begin(ryah_http_parser *parser) {
   GET_WRAPPER(wrapper, parser);
 
+  wrapper->status = rb_str_new2("");
   wrapper->request_url = rb_str_new2("");
   wrapper->headers = rb_hash_new();
   wrapper->upgrade_data = rb_str_new2("");
@@ -121,9 +125,28 @@ int on_message_begin(ryah_http_parser *parser) {
   }
 }
 
+int on_status(ryah_http_parser *parser, const char *at, size_t length) {
+  GET_WRAPPER(wrapper, parser);
+
+  if (at && length) {
+    if (wrapper->status == Qnil) {
+      wrapper->status = rb_str_new(at, length);
+    } else {
+      rb_str_cat(wrapper->status, at, length);
+    }
+  }
+  return 0;
+}
+
 int on_url(ryah_http_parser *parser, const char *at, size_t length) {
   GET_WRAPPER(wrapper, parser);
-  rb_str_cat(wrapper->request_url, at, length);
+  if (at && length) {
+    if (wrapper->request_url == Qnil) {
+      wrapper->request_url = rb_str_new(at, length);
+    } else {
+      rb_str_cat(wrapper->request_url, at, length);
+    }
+  }
   return 0;
 }
 
@@ -136,7 +159,6 @@ int on_header_field(ryah_http_parser *parser, const char *at, size_t length) {
   } else {
     rb_str_cat(wrapper->curr_field_name, at, length);
   }
-
   return 0;
 }
 
@@ -248,6 +270,7 @@ int on_message_complete(ryah_http_parser *parser) {
 
 static ryah_http_parser_settings settings = {
   .on_message_begin = on_message_begin,
+  .on_status = on_status,
   .on_url = on_url,
   .on_header_field = on_header_field,
   .on_header_value = on_header_value,
@@ -320,11 +343,12 @@ VALUE Parser_execute(VALUE self, VALUE data) {
   size_t nparsed = ryah_http_parser_execute(&wrapper->parser, &settings, ptr, len);
 
   if (wrapper->parser.upgrade) {
-    if (RTEST(wrapper->stopped))
+    if (RTEST(wrapper->stopped) && !RTEST(wrapper->completed))
       nparsed += 1;
 
-    rb_str_cat(wrapper->upgrade_data, ptr + nparsed, len - nparsed);
-
+    if (nparsed < len)
+      rb_str_cat(wrapper->upgrade_data, ptr + nparsed, len - nparsed);
+    
   } else if (nparsed != (size_t)len) {
     if (!RTEST(wrapper->stopped) && !RTEST(wrapper->completed))
       rb_raise(eParserError, "Could not parse data entirely (%zu != %zu)", nparsed, len);
@@ -438,6 +462,7 @@ VALUE Parser_status_code(VALUE self) {
     return wrapper->name;                    \
   }
 
+DEFINE_GETTER(status);
 DEFINE_GETTER(request_url);
 DEFINE_GETTER(headers);
 DEFINE_GETTER(upgrade_data);
@@ -505,6 +530,7 @@ void Init_ruby_http_parser() {
   rb_define_method(cParser, "http_method", Parser_http_method, 0);
   rb_define_method(cParser, "status_code", Parser_status_code, 0);
 
+  rb_define_method(cParser, "status", Parser_status, 0);
   rb_define_method(cParser, "request_url", Parser_request_url, 0);
   rb_define_method(cParser, "headers", Parser_headers, 0);
   rb_define_method(cParser, "upgrade_data", Parser_upgrade_data, 0);

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

@@ -28,5 +28,41 @@ Andre Caron <andre.l.caron@gmail.com>
 Ivo Raisr <ivosh@ivosh.net>
 James McLaughlin <jamie@lacewing-project.org>
 David Gwynne <loki@animata.net>
-LE ROUX Thomas <thomas@procheo.fr>
+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

@@ -1,8 +1,4 @@
-http_parser.c is based on src/http/ngx_http_parse.c from NGINX copyright
-Igor Sysoev.
-
-Additional changes are licensed under the same terms as NGINX and
-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
@@ -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_uri,
+    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_*)
      ------------------------ ------------ --------------------------------------------
@@ -174,5 +242,5 @@ 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