fix: Don't panic on hashing nested list types (#16555)

pola-rs · May 28, 2024 · cb40bbd · cb40bbd
1 parent 52c919f
commit cb40bbd
Show file tree

Hide file tree

Showing 3 changed files with 21 additions and 6 deletions.
diff --git a/crates/polars-core/src/series/mod.rs b/crates/polars-core/src/series/mod.rs
@@ -146,9 +146,14 @@ impl Hash for Wrap<Series> {
     fn hash<H: Hasher>(&self, state: &mut H) {
         let rs = RandomState::with_seeds(0, 0, 0, 0);
         let mut h = vec![];
-        self.0.vec_hash(rs, &mut h).unwrap();
-        let h = h.into_iter().fold(0, |a: u64, b| a.wrapping_add(b));
-        h.hash(state)
+        if self.0.vec_hash(rs, &mut h).is_ok() {
+            let h = h.into_iter().fold(0, |a: u64, b| a.wrapping_add(b));
+            h.hash(state)
+        } else {
+            self.len().hash(state);
+            self.null_count().hash(state);
+            self.dtype().hash(state);
+        }
     }
 }
 

diff --git a/crates/polars-plan/src/logical_plan/lit.rs b/crates/polars-plan/src/logical_plan/lit.rs
@@ -4,6 +4,7 @@ use std::hash::{Hash, Hasher};
 use polars_core::export::chrono::{Duration as ChronoDuration, NaiveDate, NaiveDateTime};
 use polars_core::prelude::*;
 use polars_core::utils::materialize_dyn_int;
+use polars_utils::hashing::hash_to_partition;
 #[cfg(feature = "serde")]
 use serde::{Deserialize, Serialize};
 
@@ -453,9 +454,12 @@ impl Hash for LiteralValue {
                 let len = s.len();
                 len.hash(state);
                 s.null_count().hash(state);
-                // Hash 5 first values. Still a poor hash, but it removes the pathological clashes.
-                for i in 0..std::cmp::min(5, len) {
-                    s.get(i).unwrap().hash(state);
+                const RANDOM: u64 = 0x2c194fa5df32a367;
+                let mut rng = (len as u64) ^ RANDOM;
+                for _ in 0..5 {
+                    let idx = hash_to_partition(rng, len);
+                    s.get(idx).unwrap().hash(state);
+                    rng = rng.rotate_right(17).wrapping_add(RANDOM);
                 }
             },
             LiteralValue::Range {

diff --git a/py-polars/tests/unit/test_cse.py b/py-polars/tests/unit/test_cse.py
@@ -768,3 +768,9 @@ def test_cse_series_collision_16138(capfd: Any, monkeypatch: Any) -> None:
     }
     captured = capfd.readouterr().err
     assert "3 CSE" in captured
+
+
+def test_nested_cache_no_panic_16553() -> None:
+    assert pl.LazyFrame().select(a=[[[1]]]).collect(comm_subexpr_elim=True).to_dict(
+        as_series=False
+    ) == {"a": [[[[1]]]]}