import re
import numpy as np
import soundfile as sf
import os
import tempfile
from pydub import AudioSegment
import io

class ScriptProcessor:
    def __init__(self, engine):
        self.engine = engine

    def split_text_into_chunks(self, text, max_chars=500):
        """
        Splits text into chunks based on sentence boundaries.
        """
        # Clean text
        text = text.replace('\n', ' ').strip()
        
        # Split by sentence boundaries but keep the punctuation
        sentences = re.split('(?<=[.!?]) +', text)
        
        chunks = []
        current_chunk = ""
        
        for sentence in sentences:
            if len(current_chunk) + len(sentence) < max_chars:
                current_chunk += " " + sentence
            else:
                if current_chunk:
                    chunks.append(current_chunk.strip())
                current_chunk = sentence
        
        if current_chunk:
            chunks.append(current_chunk.strip())
            
        return chunks

    def process_long_script(self, text, voice, speed=1.0, lang='a'):
        """
        Processes a long script by chunking, generating audio for each, and merging.
        """
        chunks = self.split_text_into_chunks(text)
        print(f"Split script into {len(chunks)} chunks.")
        
        combined_audio = []
        
        for i, chunk in enumerate(chunks):
            print(f"Processing chunk {i+1}/{len(chunks)}...")
            audio, _ = self.engine.generate(chunk, voice=voice, speed=speed, lang=lang)
            combined_audio.append(audio)
            
        # Concatenate numpy arrays
        final_audio = np.concatenate(combined_audio)
        return final_audio, 24000

    def save_audio(self, audio_data, sample_rate, output_path):
        """
        Saves numpy audio data to a file.
        """
        sf.write(output_path, audio_data, sample_rate)
        return output_path