Method _parse_input_keys

scrapegraphai/nodes/base_node.py:136–235

Parses the input keys expression to extract relevant keys from the state based on logical conditions. The expression can contain AND (&), OR (|), and parentheses to group conditions. Args: state (dict): The current state of the graph. express

(self, state: dict, expression: str)

            )

    def _parse_input_keys(self, state: dict, expression: str) -> List[str]:
        """
        Parses the input keys expression to extract
        relevant keys from the state based on logical conditions.
        The expression can contain AND (&), OR (|), and parentheses to group conditions.

        Args:
            state (dict): The current state of the graph.
            expression (str): The input keys expression to parse.

        Returns:
            List[str]: A list of key names that match the input keys expression logic.

        Raises:
            ValueError: If the expression is invalid or if no state keys match the expression.
        """

        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 == ")":
                close_parentheses += 1
            # Check for invalid operator sequences
            if char in "&|" and i + 1 < len(expression) and expression[i + 1] in "&|":
                raise ValueError(
                    "Invalid operator placement: operators cannot be adjacent."
                )

        if open_parentheses != close_parentheses:
            raise ValueError("Missing or unbalanced parentheses in expression.")