fix: correct NOT STARTS WITH projection for truncated partitions

Author: Gayathri Srividya Rajavarapu

pyiceberg/transforms.py

@@ -813,7 +813,16 @@ def project(self, name: str, pred: BoundPredicate) -> UnboundPredicate | None:
                 return _truncate_number(name, pred, self.transform(field_type))
         elif isinstance(field_type, (BinaryType, StringType)):
             if isinstance(pred, BoundLiteralPredicate):
-                return _truncate_array(name, pred, self.transform(field_type))
+                if isinstance(pred, BoundNotStartsWith):
+                    literal_width = len(pred.literal.value)
+                    if literal_width < self.width:
+                        return pred.as_unbound(name, pred.literal.value)
+                    elif literal_width == self.width:
+                        return NotEqualTo(name, pred.literal.value)
+                    else:
+                        return None
+                else:
+                    return _truncate_array(name, pred, self.transform(field_type))
 
     def strict_project(self, name: str, pred: BoundPredicate) -> UnboundPredicate | None:
         field_type = pred.term.ref().field.field_type

tests/test_transforms.py

@@ -1026,9 +1026,22 @@ def test_projection_truncate_string_starts_with(bound_reference_str: BoundRefere
 
 
 def test_projection_truncate_string_not_starts_with(bound_reference_str: BoundReference) -> None:
+    # literal_width (5) > truncate width (2): no inclusive projection possible (unsafe)
+    assert TruncateTransform(2).project("name", BoundNotStartsWith(term=bound_reference_str, literal=literal("hello"))) is None
+
+
+def test_projection_truncate_string_not_starts_with_shorter_literal(bound_reference_str: BoundReference) -> None:
+    # literal_width (2) == truncate width (2): project to !=
+    assert TruncateTransform(2).project(
+        "name", BoundNotStartsWith(term=bound_reference_str, literal=literal("he"))
+    ) == NotEqualTo(term="name", literal=literal("he"))
+
+
+def test_projection_truncate_string_not_starts_with_original_literal(bound_reference_str: BoundReference) -> None:
+    # literal_width (1) < truncate width (2): keep original literal
     assert TruncateTransform(2).project(
-        "name", BoundNotStartsWith(term=bound_reference_str, literal=literal("hello"))
-    ) == NotStartsWith(term="name", literal=literal("he"))
+        "name", BoundNotStartsWith(term=bound_reference_str, literal=literal("h"))
+    ) == NotStartsWith(term="name", literal=literal("h"))
 
 
 def _test_projection(lhs: UnboundPredicate | None, rhs: UnboundPredicate | None) -> None: