Skip to content

fix: correct NOT STARTS WITH projection for truncated partitions #3528

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
GayathriSrividya wants to merge 1 commit into
base: main
Choose a base branch
from
+25 −3
Open

fix: correct NOT STARTS WITH projection for truncated partitions #3528

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion pyiceberg/transforms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
17 changes: 15 additions & 2 deletions tests/test_transforms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down