ruby : output format (#3237)

* Fix a typo

* Don't allocate output string unless needed

* Add methods to output SRT and WebVTT

* Add tests for output methods

* Make constants for output private

* Add signatures for output methods

* Add document on output methods

* Fix method name: Segment#speaker_next_turn? -> #speacker_turn_next?

* Add Whisper::Segment#descotruct_keys

* Add test for Whisper::Context#descotruct_keys

* Add signature of Whisper::Segment#deconstruct_keys

* Use parentheses to suppress warning

* Update date

bindings/ruby/test/test_segment.rb

@@ -71,4 +71,66 @@ class TestSegment < TestBase
     end
     whisper.transcribe(AUDIO, params)
   end
+
+  def test_pattern_matching
+    segment = whisper.each_segment.first
+    segment => {start_time:, end_time:, text:, no_speech_prob:, speaker_turn_next:}
+
+    assert_equal segment.start_time, start_time
+    assert_equal segment.end_time, end_time
+    assert_equal segment.text, text
+    assert_equal segment.no_speech_prob, no_speech_prob
+    assert_equal segment.speaker_turn_next?, speaker_turn_next
+  end
+
+  def test_pattern_matching_partial
+    segment = whisper.each_segment.first
+    segment => {start_time:, end_time:, text:}
+
+    assert_equal segment.start_time, start_time
+    assert_equal segment.end_time, end_time
+    assert_equal segment.text, text
+  end
+
+  def test_deconstruct_keys
+    segment = whisper.each_segment.first
+    expected = {
+      start_time: segment.start_time,
+      end_time: segment.end_time,
+      text: segment.text,
+      no_speech_prob: segment.no_speech_prob,
+      speaker_turn_next: segment.speaker_turn_next?
+    }
+    assert_equal expected, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next])
+  end
+
+  def test_deconstruct_keys_non_existent
+    omit "Undefined behavior"
+
+    segment = whisper.each_segment.first
+
+    assert_equal({}, segment.deconstruct_keys([:non_existent]))
+  end
+
+  def test_deconstruct_keys_too_many_keys
+    omit "Undefined behavior"
+
+    segment = whisper.each_segment.first
+
+    assert_equal({}, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next, :extra_key]))
+  end
+
+  def test_deconstruct_keys_includes_non_existent_keys_not_too_many
+    omit "Undefined behavior"
+
+    segment = whisper.each_segment.first
+
+    expected = {
+      start_time: segment.start_time,
+      end_time: segment.end_time,
+      text: segment.text,
+      no_speech_prob: segment.no_speech_prob
+    }
+    assert_equal(expected, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :non_existent]))
+  end
 end

bindings/ruby/test/test_whisper.rb

@@ -113,7 +113,7 @@ class TestWhisper < TestBase
   end
 
   def test_system_info_str
-    assert_match /\AWHISPER : COREML = \d | OPENVINO = \d |/, Whisper.system_info_str
+    assert_match(/\AWHISPER : COREML = \d | OPENVINO = \d |/, Whisper.system_info_str)
   end
 
   def test_log_set
@@ -245,4 +245,48 @@ class TestWhisper < TestBase
       assert_match(/for your country/i, text)
     end
   end
+
+  def test_to_srt
+    whisper = Whisper::Context.new("base.en")
+    whisper.transcribe AUDIO, @params
+
+    lines = whisper.to_srt.lines
+    assert_match(/\A\d+\n/, lines[0])
+    assert_match(/\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3}\n/, lines[1])
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, lines[2])
+  end
+
+  def test_to_webvtt
+    whisper = Whisper::Context.new("base.en")
+    whisper.transcribe AUDIO, @params
+
+    lines = whisper.to_webvtt.lines
+    assert_equal "WEBVTT\n", lines[0]
+    assert_equal "\n", lines[1]
+    assert_match(/\A\d+\n/, lines[2])
+    assert_match(/\d{2}:\d{2}:\d{2}\.\d{3} --> \d{2}:\d{2}:\d{2}\.\d{3}\n/, lines[3])
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, lines[4])
+  end
+
+  sub_test_case "Format needs escape" do
+    def setup
+      @whisper = Whisper::Context.new("base.en")
+      @whisper.transcribe AUDIO, Whisper::Params.new
+      segment = @whisper.each_segment.first
+      segment.define_singleton_method :text do
+        "& so my fellow Americans --> ask not what your country can do for you <-- ask what you can do for your country."
+      end
+      @whisper.define_singleton_method :each_segment do
+        Enumerator.new(3) {|yielder| 3.times {yielder << segment}}
+      end
+    end
+
+    def test_to_srt_escape
+      assert_equal "&amp; so my fellow Americans --&gt; ask not what your country can do for you &lt;-- ask what you can do for your country.\n", @whisper.to_srt.lines[2]
+    end
+
+    def test_to_webvtt_escape
+      assert_equal "&amp; so my fellow Americans --&gt; ask not what your country can do for you &lt;-- ask what you can do for your country.\n", @whisper.to_webvtt.lines[4]
+    end
+  end
 end