Skip to content

fix(parquet/pqarrow): Fix propagation of field-ids for Lists #397

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

Merged
zeroshade merged 2 commits into from
Jun 6, 2025
Merged

fix(parquet/pqarrow): Fix propagation of field-ids for Lists #397

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
236c4bb
fix(parquet/pqarrow): Fix propagation of field-ids for Lists
zeroshade Jun 5, 2025
42850a9
fix another test
zeroshade Jun 5, 2025
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: 3 additions & 1 deletion parquet/pqarrow/encode_dictionary_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -688,7 +688,9 @@ func TestArrowWriteNestedSubfieldDictionary(t *testing.T) {
dictValues := array.NewDictionaryArray(dictType, indices, dict)
defer dictValues.Release()

data := array.NewData(arrow.ListOf(dictType), 3, []*memory.Buffer{nil, offsets.Data().Buffers()[1]},
data := array.NewData(arrow.ListOfField(arrow.Field{
Name: "element", Type: dictType, Nullable: true,
Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"-1"})}), 3, []*memory.Buffer{nil, offsets.Data().Buffers()[1]},
[]arrow.ArrayData{dictValues.Data()}, 0, 0)
defer data.Release()
values := array.NewListData(data)
Expand Down
6 changes: 3 additions & 3 deletions parquet/pqarrow/schema.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1011,19 +1011,19 @@ func getNestedFactory(origin, inferred arrow.DataType) func(fieldList []arrow.Fi
switch origin.ID() {
case arrow.LIST:
return func(list []arrow.Field) arrow.DataType {
return arrow.ListOf(list[0].Type)
return arrow.ListOfField(list[0])
}
case arrow.FIXED_SIZE_LIST:
sz := origin.(*arrow.FixedSizeListType).Len()
return func(list []arrow.Field) arrow.DataType {
return arrow.FixedSizeListOf(sz, list[0].Type)
return arrow.FixedSizeListOfField(sz, list[0])
}
}
case arrow.MAP:
if origin.ID() == arrow.MAP {
return func(list []arrow.Field) arrow.DataType {
valType := list[0].Type.(*arrow.StructType)
return arrow.MapOf(valType.Field(0).Type, valType.Field(1).Type)
return arrow.MapOfFields(valType.Field(0), valType.Field(1))
}
}
}
Expand Down
30 changes: 30 additions & 0 deletions parquet/pqarrow/schema_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -473,6 +473,36 @@ func TestProperListElementNullability(t *testing.T) {
assert.True(t, arrSchema.Equal(outSchema), "expected: %s, got: %s", arrSchema, outSchema)
}

func TestFieldNestedPropagate(t *testing.T) {
arrSchema := arrow.NewSchema([]arrow.Field{
{Name: "transformations", Type: arrow.ListOfField(
arrow.Field{
Name: "element",
Type: arrow.StructOf(
arrow.Field{Name: "destination", Type: arrow.BinaryTypes.String,
Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"6"})},
arrow.Field{Name: "transform_type", Type: arrow.BinaryTypes.String,
Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"7"})},
arrow.Field{Name: "transform_value", Type: arrow.BinaryTypes.String,
Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"8"})},
arrow.Field{Name: "source_cols", Type: arrow.ListOfField(
arrow.Field{Name: "element", Type: arrow.BinaryTypes.String, Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"10"})}),
Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"9"})},
),
Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"5"}),
},
), Metadata: arrow.NewMetadata([]string{"PARQUET:field_id"}, []string{"4"})},
}, nil)

pqSchema, err := pqarrow.ToParquet(arrSchema, nil, pqarrow.DefaultWriterProps())
require.NoError(t, err)

result, err := pqarrow.FromParquet(pqSchema, nil, metadata.KeyValueMetadata{})
require.NoError(t, err)

assert.True(t, arrSchema.Equal(result), "expected: %s, got: %s", arrSchema, result)
}

func TestConvertSchemaParquetVariant(t *testing.T) {
// unshredded variant:
// optional group variant_col {
Expand Down
Loading