def _vtt_process()

in chunking/chunkers/transcription_chunker.py [0:0]

• 16 lines of code
• 7 McCabe index (conditional complexity)

    def _vtt_process(self):
        blob_data = self.document_bytes
        blob_stream = BytesIO(blob_data)
        vtt = webvtt.read_buffer(blob_stream)
        data, text, voice = [], "", ""

        for caption in vtt:
            current_voice = caption.voice or ""
            
            if current_voice != voice:
                if text:
                    data.append(text.replace("\n", " "))
                voice, text = current_voice, f"{voice}: {caption.text} " if voice else caption.text + " "
            else:
                text += caption.text + " "

        if text:
            data.append(text.replace("\n", " "))

        return "\n".join(data).strip()