Function parse_expression

scrapegraphai/utils/parse_state_keys.py:8–103

Parses a complex boolean expression involving state keys. Args: expression (str): The boolean expression to parse. state (dict): Dictionary of state keys used to evaluate the expression. Raises: ValueError: If the expression is empty, has adjacent state keys wi

(expression, state: dict)

def parse_expression(expression, state: dict) -> list:
    """
    Parses a complex boolean expression involving state keys.

    Args:
        expression (str): The boolean expression to parse.
        state (dict): Dictionary of state keys used to evaluate the expression.

    Raises:
        ValueError: If the expression is empty, has adjacent state keys without operators,
        invalid operator usage, unbalanced parentheses, or if no state keys match the expression.

    Returns:
        list: A list of state keys that match the boolean expression,
        ensuring each key appears only once.

    Example:
        >>> parse_expression("user_input & (relevant_chunks | parsed_document | document)",
                            {"user_input": None, "document": None,
                            "parsed_document": None, "relevant_chunks": None})
        ['user_input', 'relevant_chunks', 'parsed_document', 'document']

    This function evaluates the expression to determine the
    logical inclusion of state keys based on provided boolean logic.
    It checks for syntax errors such as unbalanced parentheses,
    incorrect adjacency of operators, and empty expressions.
    """

    if not expression:
        raise ValueError("Empty expression.")

    pattern = (
        r"\b("
        + "|".join(re.escape(key) for key in state.keys())
        + r")(\b\s*\b)("
        + "|".join(re.escape(key) for key in state.keys())
        + r")\b"
    )
    if re.search(pattern, expression):
        raise ValueError("Adjacent state keys found without an operator between them.")

    expression = expression.replace(" ", "")

    if (
        expression[0] in "&|"
        or expression[-1] in "&|"
        or "&&" in expression
        or "||" in expression
        or "&|" in expression
        or "|&" in expression
    ):
        raise ValueError("Invalid operator usage.")

    open_parentheses = close_parentheses = 0
    for i, char in enumerate(expression):
        if char == "(":
            open_parentheses += 1
        elif char == ")":