Function build_not_like_match

datafusion/pruning/src/pruning_predicate.rs:1886–1937

For predicate `col NOT LIKE 'const_prefix%'`, we rewrite it as `(col_min NOT LIKE 'const_prefix%' OR col_max NOT LIKE 'const_prefix%')`. The intuition is that if both `col_min` and `col_max` begin with `const_prefix` that means all** data in this row group begins with `const_prefix` as well (and therefore the predicate looking for rows that don't begin with `const_prefix` can never be true)

(
    expr_builder: &mut PruningExpressionBuilder<'_>,
)

// **all** data in this row group begins with `const_prefix` as well (and therefore the predicate
// looking for rows that don't begin with `const_prefix` can never be true)
fn build_not_like_match(
    expr_builder: &mut PruningExpressionBuilder<'_>,
) -> Result<Arc<dyn PhysicalExpr>> {
    // col NOT LIKE 'const_prefix%' -> !(col_min LIKE 'const_prefix%' && col_max LIKE 'const_prefix%') -> (col_min NOT LIKE 'const_prefix%' || col_max NOT LIKE 'const_prefix%')

    let min_column_expr = expr_builder.min_column_expr()?;
    let max_column_expr = expr_builder.max_column_expr()?;

    let scalar_expr = expr_builder.scalar_expr();

    let pattern = extract_string_literal(scalar_expr).ok_or_else(|| {
        plan_datafusion_err!("cannot extract literal from NOT LIKE expression")
    })?;

    let (const_prefix, remaining) = split_constant_prefix(pattern);
    if const_prefix.is_empty() || remaining != "%" {
        // we can not handle `%` at the beginning or in the middle of the pattern
        // Example: For pattern "foo%bar", the row group might include values like
        // ["foobar", "food", "foodbar"], making it unsafe to prune.
        // Even if the min/max values in the group (e.g., "foobar" and "foodbar")
        // match the pattern, intermediate values like "food" may not
        // match the full pattern "foo%bar", making pruning unsafe.
        // (truncate foo%bar to foo% have same problem)

        // we can not handle pattern containing `_`
        // Example: For pattern "foo_", row groups might contain ["fooa", "fooaa", "foob"],
        // which means not every row is guaranteed to match the pattern.
        return Err(plan_datafusion_err!(
            "NOT LIKE expressions only support constant_prefix+wildcard`%`"
        ));
    }

    let min_col_not_like_epxr = Arc::new(phys_expr::LikeExpr::new(
        true,
        false,
        Arc::clone(&min_column_expr),
        Arc::clone(scalar_expr),
    ));

    let max_col_not_like_expr = Arc::new(phys_expr::LikeExpr::new(
        true,
        false,
        Arc::clone(&max_column_expr),
        Arc::clone(scalar_expr),
    ));

    Ok(Arc::new(phys_expr::BinaryExpr::new(
        min_col_not_like_epxr,
        Operator::Or,
        max_col_not_like_expr,
    )))
}

/// Returns unescaped constant prefix of a LIKE pattern (possibly empty) and the remaining pattern (possibly empty)
fn split_constant_prefix(pattern: &str) -> (String, &str) {