Skip to content

fix(parquet): Reading UUID columns #173

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 3 commits into from
Oct 26, 2024
Merged

fix(parquet): Reading UUID columns #173

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5057471
fix(parquet): Reading UUID columns
zeroshade Oct 25, 2024
33a2b9b
fix handling stored schema uuid
zeroshade Oct 25, 2024
5f354bc
Apply suggestions from code review
zeroshade Oct 26, 2024
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 arrow/extensions/extensions.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,8 @@ import (
)

var canonicalExtensionTypes = []arrow.ExtensionType{
&Bool8Type{},
&UUIDType{},
NewBool8Type(),
NewUUIDType(),
&OpaqueType{},
&JSONType{},
}
Expand Down
1 change: 1 addition & 0 deletions parquet/pqarrow/encode_arrow_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2057,6 +2057,7 @@ func (ps *ParquetIOTestSuite) TestArrowExtensionTypeRoundTrip() {
defer tbl.Release()

ps.roundTripTable(mem, tbl, true)
ps.roundTripTable(mem, tbl, false)
}

func (ps *ParquetIOTestSuite) TestArrowUnknownExtensionTypeRoundTrip() {
Expand Down
21 changes: 14 additions & 7 deletions parquet/pqarrow/schema.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -514,8 +514,14 @@ func arrowFromFLBA(logical schema.LogicalType, length int) (arrow.DataType, erro
switch logtype := logical.(type) {
case schema.DecimalLogicalType:
return arrowDecimal(logtype), nil
case schema.NoLogicalType, schema.IntervalLogicalType, schema.UUIDLogicalType:
case schema.NoLogicalType, schema.IntervalLogicalType:
return &arrow.FixedSizeBinaryType{ByteWidth: int(length)}, nil
case schema.UUIDLogicalType:
uuidType := arrow.GetExtensionType("arrow.uuid")
if uuidType == nil {
return &arrow.FixedSizeBinaryType{ByteWidth: int(length)}, nil
}
return uuidType, nil
case schema.Float16LogicalType:
return &arrow.Float16Type{}, nil
default:
Expand Down Expand Up @@ -984,13 +990,14 @@ func applyOriginalStorageMetadata(origin arrow.Field, inferred *SchemaField) (mo
return
}

if !arrow.TypeEqual(extType.StorageType(), inferred.Field.Type) {
return modified, fmt.Errorf("%w: mismatch storage type '%s' for extension type '%s'",
arrow.ErrInvalid, inferred.Field.Type, extType)
}
if modified && !arrow.TypeEqual(extType, inferred.Field.Type) {
if !arrow.TypeEqual(extType.StorageType(), inferred.Field.Type) {
return modified, fmt.Errorf("%w: mismatch storage type '%s' for extension type '%s'",
arrow.ErrInvalid, inferred.Field.Type, extType)
}

inferred.Field.Type = extType
modified = true
inferred.Field.Type = extType
}
case arrow.SPARSE_UNION, arrow.DENSE_UNION:
err = xerrors.New("unimplemented type")
case arrow.STRUCT:
Expand Down