import re
import urllib.parse as urllib

OPERATORS = [
    '!=',
    '>=',
    '<=',
    '=',
    '>',
    '<',
    'TO',
    'EXISTS',
    'IN',
    'NOT IN',
]


def remove_quotes(value: str) -> str:
    if (value.startswith('"') and value.endswith('"')) or (
        value.startswith("'") and value.endswith("'")
    ):
        return value[1:-1]
    return value


def parse_condition(condition: str) -> dict[str, str] | None:
    for op in OPERATORS:
        parts = condition.split(op)

        if len(parts) == 2:
            attr, value = parts
            attr = attr.strip()
            value = remove_quotes(value.strip())

            return {
                'attr': attr,
                'op': op,
                'value': value,
            }

    return None


def parse(s: str) -> list[dict]:
    filter_expr = re.sub(r'\s+', ' ', urllib.unquote(s)).strip()

    if filter_expr == '':
        return []

    parts = re.split(r'\b(?:AND|OR)\b', filter_expr)
    conditions = []

    for part in parts:
        condition = parse_condition(part.strip())

        if condition:
            conditions.append(condition)

    return conditions


def encode(conditions: list[dict]):
    return ' AND '.join(' '.join(c.values()).strip() for c in conditions if c)