fix(expressions): return fresh residual evaluator instances

Author: ForeverAngry

pyiceberg/expressions/visitors.py

@@ -14,6 +14,7 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+import copy
 import math
 import threading
 from abc import ABC, abstractmethod
@@ -1988,11 +1989,23 @@ def _residual_evaluator_cache_key(
     key=_residual_evaluator_cache_key,
     lock=threading.RLock(),
 )
-def residual_evaluator_of(
+def _cached_residual_evaluator_template(
     spec: PartitionSpec, expr: BooleanExpression, case_sensitive: bool, schema: Schema
 ) -> ResidualEvaluator:
     return (
         UnpartitionedResidualEvaluator(schema=schema, expr=expr)
         if spec.is_unpartitioned()
         else ResidualEvaluator(spec=spec, expr=expr, schema=schema, case_sensitive=case_sensitive)
     )
+
+
+def residual_evaluator_of(
+    spec: PartitionSpec, expr: BooleanExpression, case_sensitive: bool, schema: Schema
+) -> ResidualEvaluator:
+    """Create a residual evaluator.
+
+    Always returns a fresh evaluator instance because evaluators are stateful
+    (they set `self.struct` during evaluation) and may be used from multiple
+    threads.
+    """
+    return copy.copy(_cached_residual_evaluator_template(spec=spec, expr=expr, case_sensitive=case_sensitive, schema=schema))

tests/expressions/test_residual_evaluator.py

@@ -88,6 +88,19 @@ def test_identity_transform_residual() -> None:
     assert residual == AlwaysFalse()
 
 
+def test_residual_evaluator_of_returns_fresh_instance() -> None:
+    schema = Schema(NestedField(50, "dateint", IntegerType()), NestedField(51, "hour", IntegerType()))
+    spec = PartitionSpec(PartitionField(50, 1050, IdentityTransform(), "dateint_part"))
+    predicate = LessThan("dateint", 20170815)
+
+    res_eval_1 = residual_evaluator_of(spec=spec, expr=predicate, case_sensitive=True, schema=schema)
+    res_eval_2 = residual_evaluator_of(spec=spec, expr=predicate, case_sensitive=True, schema=schema)
+
+    assert res_eval_1 is not res_eval_2
+    assert res_eval_1.residual_for(Record(20170814)) == AlwaysTrue()
+    assert res_eval_2.residual_for(Record(20170816)) == AlwaysFalse()
+
+
 def test_case_insensitive_identity_transform_residuals() -> None:
     schema = Schema(NestedField(50, "dateint", IntegerType()), NestedField(51, "hour", IntegerType()))