app/processing.py

import os
import pymupdf4llm

from .models import parse_message
from .pipeline import Pipeline

def process_pdf(pdf_path: str) -> str:
    """Extracts text from a PDF file using pymupdf4llm."""
    try:
        text = pymupdf4llm.to_markdown(pdf_path)
        return text
    except Exception as e:
        raise ValueError(f"Error processing PDF: {str(e)}")

def read_text_file(file_path: str) -> str:
    """Reads text from a .txt or .md file."""
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            text = f.read()
        return text
    except Exception as e:
        raise ValueError(f"Error reading text file: {str(e)}")

def process_file(file_obj, output_format: str, pipeline) -> str:
    """Processes the uploaded file based on its type and extracts flashcards."""
    file_path = file_obj.name
    file_ext = os.path.splitext(file_path)[1].lower()
    if file_ext == '.pdf':
        text = process_pdf(file_path)
    elif file_ext in ['.txt', '.md']:
        text = read_text_file(file_path)
    else:
        raise ValueError("Unsupported file type.")
    flashcards = generate_flashcards(output_format, text)
    return flashcards

def reduce_newlines(text: str) -> str:
    """Reduces consecutive newlines exceeding 2 to just 2."""
    while "\n\n\n" in text:
        text = text.replace("\n\n\n", "\n\n")
    return text

def generate_flashcards(output_format: str, content: str) -> str:
    """
    Generates flashcards from the content.
    """
    content = reduce_newlines(content)
    response = Pipeline().extract_flashcards(content)
    return format_flashcards(output_format, response)

def process_text_input(input_text: str, output_format: str = "csv") -> str:
    """Processes the input text and extracts flashcards."""
    if not input_text.strip():
        raise ValueError("No text provided.")
    pipeline = Pipeline()
    flashcards = generate_flashcards(output_format, input_text)
    return flashcards

def format_flashcards(output_format: str, response: str) -> str:
    """Formats the response into the desired output format."""
    output = ""
    try :
        message = parse_message(response)
    except Exception as e:
        raise e
    if output_format.lower() == "json":
        output:str = message.content_to_json()
    elif output_format.lower() == "csv":
        output = message.content_to_csv()
    return output