#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Strip leading step numbers from instructions in MariaDB to avoid duplicate numbers in the UI.
"""
import os
import sys
import re

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from app.database import get_connection

sys.stdout.reconfigure(encoding='utf-8')

STEP_REGEX = re.compile(r'^(?:Schritt\s*\d+[:.]?|\d+[\.\)\:])\s*', re.IGNORECASE)

def clean_instructions_text(text: str) -> str:
    if not text:
        return ""
    cleaned_lines = []
    for line in text.split("\n"):
        line_s = line.strip()
        if not line_s:
            continue
        cleaned = STEP_REGEX.sub('', line_s)
        cleaned_lines.append(cleaned)
    return "\n".join(cleaned_lines)

def main():
    conn = get_connection()
    cur = conn.cursor()
    cur.execute("SELECT id, title, instructions FROM recipes ORDER BY id")
    recipes = cur.fetchall()

    updated_count = 0
    total_lines_cleaned = 0

    for r in recipes:
        original = r['instructions'] or ""
        cleaned = clean_instructions_text(original)
        if cleaned != original:
            cur.execute("UPDATE recipes SET instructions = %s WHERE id = %s", (cleaned, r['id']))
            updated_count += 1
            # count cleaned lines
            for orig_line in original.split("\n"):
                if STEP_REGEX.match(orig_line.strip()):
                    total_lines_cleaned += 1

    conn.commit()
    conn.close()

    print(f"Successfully cleaned instructions across {updated_count} of {len(recipes)} recipes.")
    print(f"Total step number prefixes removed: {total_lines_cleaned}.")

if __name__ == "__main__":
    main()