Skip to content

fix(parquet): strip repetition_type from root SchemaElement during serialization #723

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
hcrosse wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix(parquet): strip repetition_type from root SchemaElement during serialization #723

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5ab4477
fix(parquet): strip repetition_type from root SchemaElement during se…
hcrosse Mar 18, 2026
3ef263e
fix(parquet): update expected byte counts after root repetition strip…
hcrosse Mar 18, 2026
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
4 changes: 2 additions & 2 deletions parquet/pqarrow/file_writer_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,7 @@ func TestFileWriterTotalBytes(t *testing.T) {

// Verify total bytes & compressed bytes are correct
assert.Equal(t, int64(408), writer.TotalCompressedBytes())
assert.Equal(t, int64(912), writer.TotalBytesWritten())
assert.Equal(t, int64(910), writer.TotalBytesWritten())
}

func TestFileWriterTotalBytesBuffered(t *testing.T) {
Expand Down Expand Up @@ -206,5 +206,5 @@ func TestFileWriterTotalBytesBuffered(t *testing.T) {

// Verify total bytes & compressed bytes are correct
assert.Equal(t, int64(596), writer.TotalCompressedBytes())
assert.Equal(t, int64(1308), writer.TotalBytesWritten())
assert.Equal(t, int64(1306), writer.TotalBytesWritten())
}
1 change: 1 addition & 0 deletions parquet/schema/schema.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,6 +272,7 @@ func (t *toThriftVisitor) VisitPost(Node) {}
func ToThrift(schema *GroupNode) []*format.SchemaElement {
t := &toThriftVisitor{make([]*format.SchemaElement, 0)}
schema.Visit(t)
t.elements[0].RepetitionType = nil
return t.elements
}

Expand Down
21 changes: 20 additions & 1 deletion parquet/schema/schema_flatten_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,8 +92,10 @@ func (s *SchemaFlattenSuite) TestDecimalMetadata() {

func (s *SchemaFlattenSuite) TestNestedExample() {
elements := make([]*format.SchemaElement, 0)
root := NewGroup(s.name, format.FieldRepetitionType_REPEATED, 2 /* numChildren */, 0 /* fieldID */)
root.RepetitionType = nil
elements = append(elements,
NewGroup(s.name, format.FieldRepetitionType_REPEATED, 2 /* numChildren */, 0 /* fieldID */),
root,
NewPrimitive("a" /* name */, format.FieldRepetitionType_REQUIRED, format.Type_INT32, 1 /* fieldID */),
NewGroup("bag" /* name */, format.FieldRepetitionType_OPTIONAL, 1 /* numChildren */, 2 /* fieldID */))

Expand All @@ -120,6 +122,23 @@ func TestSchemaFlatten(t *testing.T) {
suite.Run(t, new(SchemaFlattenSuite))
}

func TestToThriftRootRepetitionStripped(t *testing.T) {
for _, rep := range []parquet.Repetition{
parquet.Repetitions.Repeated,
parquet.Repetitions.Required,
parquet.Repetitions.Optional,
} {
group := MustGroup(NewGroupNode("schema", rep, FieldList{
NewInt32Node("a", parquet.Repetitions.Required, -1),
}, -1))
elements := ToThrift(group)
assert.False(t, elements[0].IsSetRepetitionType(),
"root element should not have repetition_type set (was %v)", rep)
assert.True(t, elements[1].IsSetRepetitionType(),
"non-root element must have repetition_type set")
}
}

func TestInvalidConvertedTypeInDeserialize(t *testing.T) {
n := MustPrimitive(NewPrimitiveNodeLogical("string" /* name */, parquet.Repetitions.Required, StringLogicalType{},
parquet.Types.ByteArray, -1 /* type len */, -1 /* fieldID */))
Expand Down