import logging
import os
import tempfile

logger = logging.getLogger(__name__)

def process_transcription(audio_content: bytes, whisper_model):
    if not whisper_model:
        raise ValueError("Whisper model not loaded.")

    temp_file_path = None
    try:
        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_file:
            temp_file_path = temp_file.name
            temp_file.write(audio_content)
    
        segments, info = whisper_model.transcribe(temp_file_path, beam_size=5)
        transcript = " ".join([seg.text.strip() for seg in segments])
        return transcript, info
    finally:
        if temp_file_path and os.path.exists(temp_file_path):
            os.remove(temp_file_path)

def process_summary(text: str, summarizer_pipeline, nlp_spacy, config):
    if not summarizer_pipeline:
        raise ValueError("Summarizer model not loaded.")

    processed_text = text
    if nlp_spacy:
        try:
            doc = nlp_spacy(text)
            sentences = [sent.text.strip() for sent in doc.sents]
            processed_text = " ".join(sentences)
        except Exception as e:
             logger.error(f"SpaCy processing failed: {e}", exc_info=True)

    summary_output = summarizer_pipeline(
        processed_text,
        max_length=config.SUMMARIZER_MAX_LENGTH,
        min_length=config.SUMMARIZER_MIN_LENGTH,
        do_sample=False
    )

    final_summary = summary_output[0]['summary_text']
    return final_summary