receipt_processor/parsers/plodine_parser.py

from .base import BaseParser
import re
from datetime import datetime

class PlodineParser(BaseParser):
    def parse(self, text: str) -> dict:
        result = {
            "store": "Plodine",
            "date": None,
            "address": None,
            "items": [],
            "parser_used": "PlodineParser"
        }

        # Address extraction (Improved)
        address_lines = text.splitlines()

        street_name = None
        house_number = None
        postal_city = None

        for i, line in enumerate(address_lines):
            if "HIPERMARKET" in line.upper() or "SUPERMARKET" in line.upper():
                # This should contain something like "HIPERMARKET ZAGREB Karla Metikosa"
                parts = line.strip().split()
                if len(parts) >= 3:
                    street_name = " ".join(parts[2:])

            if re.match(r'^\d+\s+[A-Za-zČĆŽŠĐčćžšđ ]+$', line.strip()):
                house_number = line.strip()

            if re.match(r'^\d{5}\s+[A-Za-zČĆŽŠĐčćžšđ]+$', line.strip()):
                postal_city = line.strip()

        if street_name and house_number and postal_city:
            result['address'] = f"{street_name}, {postal_city}"        

        # Date extraction (just the date, no time)
        date_match = re.search(r'(\d{2}\.\d{2}\.\d{4})', text)
        if date_match:
            try:
                result['date'] = datetime.strptime(
                    date_match.group(1),
                    '%d.%m.%Y'
                ).date().isoformat()  # Only YYYY-MM-DD
            except:
                pass

        # Item parsing
        item_section = re.search(
            r'(?<=Artikal\nKol\nCijena\nIznos €\n)(.*?)(?=\nZA PLATITI)',
            text,
            re.DOTALL
        )
        if item_section:
            item_pattern = re.compile(
                r'^([^\n]+)\n'                        # Item name
                r'(\d+,\d+|\d+)\s*x\s*([\d,]+)?\n?'   # Quantity x UnitPrice
                r'([\d,]+)?',                        # Total price
                re.MULTILINE
            )
            matches = item_pattern.finditer(item_section.group(1))
            for match in matches:
                name = match.group(1).strip()
                quantity = float(match.group(2).replace(',', '.'))
                price_str = match.group(3) or match.group(4)
                
                if price_str:
                    result['items'].append({
                        "name": name,
                        "quantity": quantity,
                        "price": float(price_str.replace(',', '.'))
                    })

        return result