ruby : Fix of C++ header guard name, model URI support, type signatur…

…e and more (#2683)

* Add test to make Whisper::Context.new accept URI string

* Add test to make Whisper::Context.new accept URI

* Make Whisper::Context.new accept URI string and URI

* Update README

Revert "Fix argument of rb_undefine_finalizer"

* Fix typos

* Add type signature file

* Assign literarl to const variable

* Load Whisper::Model::URI from Init_whisper

* Simplify .gitignore

* Don't load whisper.so from whisper/model/uri.rb

* Use each_with_object instead of each

* Add Development section to README

* Rename header guard to conform to C++ naming convention

bindings/ruby/.gitignore

@@ -1,5 +1,3 @@
 LICENSE
 pkg/
-lib/whisper.so
-lib/whisper.bundle
-lib/whisper.dll
+lib/whisper.*

bindings/ruby/README.md

@@ -60,10 +60,10 @@ You also can use shorthand for pre-converted models:
 whisper = Whisper::Context.new("base.en")
 ```
 
-You can see the list of prepared model names by `Whisper::Model.preconverted_models.keys`:
+You can see the list of prepared model names by `Whisper::Model.pre_converted_models.keys`:
 
 ```ruby
-puts Whisper::Model.preconverted_models.keys
+puts Whisper::Model.pre_converted_models.keys
 # tiny
 # tiny.en
 # tiny-q5_1
@@ -87,8 +87,9 @@ whisper = Whisper::Context.new("path/to/your/model.bin")
 Or, you can download model files:
 
 ```ruby
-model_uri = Whisper::Model::URI.new("http://example.net/uri/of/your/model.bin")
-whisper = Whisper::Context.new(model_uri)
+whisper = Whisper::Context.new("https://example.net/uri/of/your/model.bin")
+# Or
+whisper = Whisper::Context.new(URI("https://example.net/uri/of/your/model.bin"))
 ```
 
 See [models][] page for details.
@@ -222,6 +223,17 @@ end
 
 The second argument `samples` may be an array, an object with `length` and `each` method, or a MemoryView. If you can prepare audio data as C array and export it as a MemoryView, whispercpp accepts and works with it with zero copy.
 
+Development
+-----------
+
+    % git clone https://github.com/ggerganov/whisper.cpp.git
+    % cd whisper.cpp/bindings/ruby
+    % rake test
+
+First call of `rake test` builds an extension and downloads a model for testing. After that, you add tests in `tests` directory and modify `ext/ruby_whisper.cpp`.
+
+If something seems wrong on build, running `rake clean` solves some cases.
+
 License
 -------
 

bindings/ruby/ext/ruby_whisper.cpp

@@ -49,6 +49,7 @@ static ID id_length;
 static ID id_next;
 static ID id_new;
 static ID id_to_path;
+static ID id_URI;
 static ID id_pre_converted_models;
 
 static bool is_log_callback_finalized = false;
@@ -283,6 +284,17 @@ static VALUE ruby_whisper_initialize(int argc, VALUE *argv, VALUE self) {
   if (!NIL_P(pre_converted_model)) {
     whisper_model_file_path = pre_converted_model;
   }
+  if (TYPE(whisper_model_file_path) == T_STRING) {
+    const char * whisper_model_file_path_str = StringValueCStr(whisper_model_file_path);
+    if (strncmp("http://", whisper_model_file_path_str, 7) == 0 || strncmp("https://", whisper_model_file_path_str, 8) == 0) {
+      VALUE uri_class = rb_const_get(cModel, id_URI);
+      whisper_model_file_path = rb_class_new_instance(1, &whisper_model_file_path, uri_class);
+    }
+  }
+  if (rb_obj_is_kind_of(whisper_model_file_path, rb_path2class("URI::HTTP"))) {
+    VALUE uri_class = rb_const_get(cModel, id_URI);
+    whisper_model_file_path = rb_class_new_instance(1, &whisper_model_file_path, uri_class);
+  }
   if (rb_respond_to(whisper_model_file_path, id_to_path)) {
     whisper_model_file_path = rb_funcall(whisper_model_file_path, id_to_path, 0);
   }
@@ -837,7 +849,7 @@ static VALUE ruby_whisper_full_get_segment_text(VALUE self, VALUE i_segment) {
 
 /*
  * call-seq:
- *   full_get_segment_no_speech_prob -> Float
+ *   full_get_segment_no_speech_prob(segment_index) -> Float
  */
 static VALUE ruby_whisper_full_get_segment_no_speech_prob(VALUE self, VALUE i_segment) {
   ruby_whisper *rw;
@@ -1755,7 +1767,7 @@ static VALUE ruby_whisper_c_model_type(VALUE self) {
 
 static VALUE ruby_whisper_error_initialize(VALUE self, VALUE code) {
   const int c_code = NUM2INT(code);
-  char *raw_message;
+  const char *raw_message;
   switch (c_code) {
   case -2:
     raw_message = "failed to compute log mel spectrogram";
@@ -1802,6 +1814,7 @@ void Init_whisper() {
   id_next = rb_intern("next");
   id_new = rb_intern("new");
   id_to_path = rb_intern("to_path");
+  id_URI = rb_intern("URI");
   id_pre_converted_models = rb_intern("pre_converted_models");
 
   mWhisper = rb_define_module("Whisper");
@@ -1941,6 +1954,8 @@ void Init_whisper() {
   rb_define_method(cModel, "n_mels", ruby_whisper_c_model_n_mels, 0);
   rb_define_method(cModel, "ftype", ruby_whisper_c_model_ftype, 0);
   rb_define_method(cModel, "type", ruby_whisper_c_model_type, 0);
+
+  rb_require("whisper/model/uri");
 }
 #ifdef __cplusplus
 }

bindings/ruby/ext/ruby_whisper.h

@@ -1,5 +1,5 @@
-#ifndef __RUBY_WHISPER_H
-#define __RUBY_WHISPER_H
+#ifndef RUBY_WHISPER_H
+#define RUBY_WHISPER_H
 
 #include "whisper.h"