fix(rust, python): evaluate whole branch expression to determine if r… (

#5864)
pola-rs · Dec 21, 2022 · 7f304e6 · 7f304e6
1 parent 43598c3
commit 7f304e6
Show file tree

Hide file tree

Showing 3 changed files with 19 additions and 0 deletions.
diff --git a/polars/polars-lazy/polars-pipe/src/pipeline/convert.rs b/polars/polars-lazy/polars-pipe/src/pipeline/convert.rs
@@ -120,6 +120,7 @@ where
             match &payload.file_type {
                 FileType::Parquet(options) => {
                     Box::new(ParquetSink::new(path, *options, input_schema.as_ref())?)
+                        as Box<dyn Sink>
                 }
             }
         }

diff --git a/polars/polars-lazy/src/physical_plan/expressions/binary.rs b/polars/polars-lazy/src/physical_plan/expressions/binary.rs
@@ -525,6 +525,20 @@ mod stats {
 
     impl BinaryExpr {
         fn impl_should_read(&self, stats: &BatchStats) -> PolarsResult<bool> {
+            // See: #5864 for the rationale behind this.
+            use Expr::*;
+            use Operator::*;
+            if !self.expr.into_iter().all(|e| match e {
+                BinaryExpr { op, .. } => !matches!(
+                    op,
+                    Multiply | Divide | TrueDivide | FloorDivide | Modulus | Eq | NotEq
+                ),
+                Column(_) | Literal(_) | Alias(_, _) => true,
+                _ => false,
+            }) {
+                return Ok(true);
+            }
+
             let schema = stats.schema();
             let fld_l = self.left.to_field(schema)?;
             let fld_r = self.right.to_field(schema)?;

diff --git a/py-polars/tests/unit/io/test_lazy_parquet.py b/py-polars/tests/unit/io/test_lazy_parquet.py
@@ -113,6 +113,10 @@ def test_parquet_stats(io_test_dir: str) -> None:
     assert (
         pl.scan_parquet(file).filter(4 < pl.col("a")).select(pl.col("a").sum())
     ).collect()[0, "a"] == 10.0
+    assert pl.scan_parquet(file).filter((pl.col("a") * 10) > 5.0).collect().shape == (
+        8,
+        1,
+    )
 
 
 def test_row_count_schema(io_test_dir: str) -> None: