daft.functions.substring_index#

def substring_index(
    expr: Expression,
    delim: str | Expression,
    count: int | Expression,
) -> Expression:
    """Returns the substring from string before count occurrences of the delimiter.

    If count is positive, returns everything to the left of the final delimiter (counting from left).
    If count is negative, returns everything to the right of the final delimiter (counting from right).
    This is compatible with Spark's substring_index function.

    Args:
        expr: The string expression
        delim: The delimiter string
        count: The number of occurrences of the delimiter

    Returns:
        Expression: a String expression with the substring result

    Examples:
        >>> import daft
        >>> from daft.functions import substring_index
        >>> df = daft.from_pydict({"x": ["www.apache.org", "a.b.c.d"]})
        >>> df = df.select(substring_index(df["x"], ".", 2))
        >>> df.show()
        ╭────────────╮
        │ x          │
        │ ---        │
        │ String     │
        ╞════════════╡
        │ www.apache │
        ├╌╌╌╌╌╌╌╌╌╌╌╌┤
        │ a.b        │
        ╰────────────╯
        <BLANKLINE>
        (Showing first 2 of 2 rows)

    """
    return Expression._call_builtin_scalar_fn("substring_index", expr, delim, count)