Fix NotStartsWith residual evaluation to return correct result

Author: ebyhr

pyiceberg/expressions/visitors.py

@@ -1905,10 +1905,11 @@ def visit_starts_with(self, term: BoundTerm, literal: LiteralValue) -> BooleanEx
             return AlwaysFalse()
 
     def visit_not_starts_with(self, term: BoundTerm, literal: LiteralValue) -> BooleanExpression:
-        if not self.visit_starts_with(term, literal):
-            return AlwaysTrue()
-        else:
+        starts_with_result = self.visit_starts_with(term, literal)
+        if isinstance(starts_with_result, AlwaysTrue):
             return AlwaysFalse()
+        else:
+            return AlwaysTrue()
 
     def visit_bound_predicate(self, predicate: BoundPredicate) -> BooleanExpression:
         """

tests/expressions/test_residual_evaluator.py

@@ -41,7 +41,7 @@
 from pyiceberg.schema import Schema
 from pyiceberg.transforms import DayTransform, IdentityTransform
 from pyiceberg.typedef import Record
-from pyiceberg.types import DoubleType, FloatType, IntegerType, NestedField, TimestampType
+from pyiceberg.types import DoubleType, FloatType, IntegerType, NestedField, StringType, TimestampType
 
 
 def test_identity_transform_residual() -> None:
@@ -249,3 +249,16 @@ def test_not_in_timestamp() -> None:
     ts_day += 3  # type: ignore
     residual = res_eval.residual_for(Record(ts_day))
     assert residual == AlwaysTrue()
+
+
+def test_not_starts_with() -> None:
+    schema = Schema(NestedField(1, "x", StringType()))
+    spec = PartitionSpec(PartitionField(1, 1001, IdentityTransform(), "x_part"))
+
+    predicate = NotStartsWith("x", "a")
+    res_eval = residual_evaluator_of(spec=spec, expr=predicate, case_sensitive=True, schema=schema)
+
+    assert res_eval.residual_for(Record("bb")) == AlwaysTrue()
+    assert res_eval.residual_for(Record("abc")) == AlwaysFalse()
+    assert res_eval.residual_for(Record("a")) == AlwaysFalse()
+    assert res_eval.residual_for(Record("zoo")) == AlwaysTrue()