Skip to content

perf: Ensure string literals actually generate ColumnPredicates #25495

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
itamarst wants to merge 2 commits into
base: main
Choose a base branch
from
Open

perf: Ensure string literals actually generate ColumnPredicates #25495

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1299cbe
Tests and fix for string contains in ColumnPredicates generation.
pythonspeed Nov 25, 2025
a26d5cc
Merge remote-tracking branch 'origin/main' into column_predicates-str…
pythonspeed Dec 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 25 additions & 2 deletions crates/polars-plan/src/plans/aexpr/predicates/column_expr.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,8 @@ pub fn aexpr_to_column_predicates(
options: _,
} if matches!(
str_function,
crate::plans::IRStringFunction::Contains { literal: _, strict: true } |
crate::plans::IRStringFunction::Contains { literal: false, strict: true } |
crate::plans::IRStringFunction::Contains { literal: true, strict: _ } |
crate::plans::IRStringFunction::EndsWith |
crate::plans::IRStringFunction::StartsWith
) => {
Expand Down Expand Up @@ -364,7 +365,7 @@ mod tests {
use polars_error::PolarsResult;

use super::*;
use crate::dsl::{Expr, col};
use crate::dsl::{Expr, col, lit};
use crate::plans::{ExprToIRContext, to_expr_ir, typed_lit};

/// Given a single-column `Expr`, call `aexpr_to_column_predicates()` and
Expand Down Expand Up @@ -420,6 +421,28 @@ mod tests {
Ok(())
}

#[test]
fn column_predicates_string_contains() -> PolarsResult<()> {
let col_name = "testcol";
let test_values: [(Expr, &str); _] = [
(col(col_name).str().contains(lit("x.*y"), true), "x.*y"),
(col(col_name).str().contains_literal(lit("abc")), "abc"),
(
col(col_name).str().contains_literal(lit("x.*y")),
"x\\.\\*y",
),
];
for (expr, expected_regex_string) in test_values {
let predicate = column_predicate_for_expr(DataType::String, col_name, expr.clone())?;
if let Some(SpecializedColumnPredicate::RegexMatch(regex)) = predicate {
assert_eq!(&format!("{regex}"), expected_regex_string);
} else {
panic!("{predicate:?} is unexpected for {expr:?}");
}
}
Ok(())
}

#[test]
fn column_predicate_is_between() -> PolarsResult<()> {
let col_name = "testcol";
Expand Down
Loading