perf: Support datetime in predicate during hive partition pruning (#1…

…7545)
pola-rs · Jul 11, 2024 · 662696a · 662696a
1 parent fbc56ff
commit 662696a
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 1 deletion.
diff --git a/crates/polars-io/src/predicates.rs b/crates/polars-io/src/predicates.rs
@@ -190,7 +190,7 @@ impl ColumnStats {
 
 /// Returns whether the [`DataType`] supports minimum/maximum operations.
 fn use_min_max(dtype: &DataType) -> bool {
-    dtype.is_numeric()
+    dtype.to_physical().is_numeric()
         || matches!(
             dtype,
             DataType::String | DataType::Binary | DataType::Boolean

diff --git a/py-polars/tests/unit/io/test_hive.py b/py-polars/tests/unit/io/test_hive.py
@@ -729,3 +729,15 @@ def test_hive_write_dates(tmp_path: Path) -> None:
         lf.collect(),
         df.with_columns(pl.col("date1", "date2").cast(pl.String)),
     )
+
+
+@pytest.mark.write_disk()
+def test_hive_predicate_dates_14712(
+    tmp_path: Path, monkeypatch: Any, capfd: Any
+) -> None:
+    monkeypatch.setenv("POLARS_VERBOSE", "1")
+    pl.DataFrame({"a": [datetime(2024, 1, 1)]}).write_parquet_partitioned(
+        tmp_path, ["a"]
+    )
+    pl.scan_parquet(tmp_path).filter(pl.col("a") != datetime(2024, 1, 1)).collect()
+    assert "hive partitioning: skipped 1 files" in capfd.readouterr().err