import csv
import re

def extract_insulin_data(input_file, output_file):
    with open(input_file, "r", encoding="utf-8") as file:
        lines = file.readlines()
    
    data = []
    food_description = []
    capturing = False

    for i in range(len(lines)):
        # Check if line starts with a whole number followed by a period (e.g., "1.", "2.")
        if re.match(r"^\d+\.$", lines[i].strip()):
            food_description = []  # Reset food description
            capturing = True  # Start capturing text
        
        if capturing:
            food_description.append(lines[i].strip())

        # Stop capturing at "SINGLE" or "MIXED MEAL"
        if "SINGLE" in lines[i] or "MIXED MEAL" in lines[i]:
            capturing = False
            if food_description:
                full_food_name = " ".join(food_description)  # Merge lines into one, replacing new lines with spaces
                insulin_index = lines[i + 1].strip()
                
                # Ensure insulin index is numeric for sorting
                try:
                    insulin_index_value = float(re.sub(r"[^\d.]", "", insulin_index))  # Remove non-numeric characters
                    data.append((full_food_name, insulin_index_value))
                except ValueError:
                    pass  # Skip if conversion fails

    # Sort data by insulin index (ascending order)
    data.sort(key=lambda x: x[1])

    # Save results to CSV
    with open(output_file, "w", encoding="utf-8", newline="") as csv_file:
        writer = csv.writer(csv_file)
        writer.writerow(["Food Description", "Insulin Index"])
        writer.writerows(data)

# Usage example
input_file = "all_text"  # Update with your actual text file name
output_file = "insulin_data_sorted.csv"
extract_insulin_data(input_file, output_file)