Skip to content

feat: add support for binaryview type #96

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
merged 1 commit into from
Jun 26, 2025
Merged

feat: add support for binaryview type #96

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
15 changes: 10 additions & 5 deletions arrow-pg/src/datatypes.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,12 +35,15 @@ pub fn into_pg_type(arrow_type: &DataType) -> PgWireResult<Type> {
DataType::Time32(_) | DataType::Time64(_) => Type::TIME,
DataType::Date32 | DataType::Date64 => Type::DATE,
DataType::Interval(_) => Type::INTERVAL,
DataType::Binary | DataType::FixedSizeBinary(_) | DataType::LargeBinary => Type::BYTEA,
DataType::Binary
| DataType::FixedSizeBinary(_)
| DataType::LargeBinary
| DataType::BinaryView => Type::BYTEA,
DataType::Float16 | DataType::Float32 => Type::FLOAT4,
DataType::Float64 => Type::FLOAT8,
DataType::Decimal128(_, _) => Type::NUMERIC,
DataType::Utf8 => Type::VARCHAR,
DataType::LargeUtf8 => Type::TEXT,
DataType::LargeUtf8 | DataType::Utf8View => Type::TEXT,
DataType::List(field) | DataType::FixedSizeList(field, _) | DataType::LargeList(field) => {
match field.data_type() {
DataType::Boolean => Type::BOOL_ARRAY,
Expand All @@ -58,11 +61,14 @@ pub fn into_pg_type(arrow_type: &DataType) -> PgWireResult<Type> {
DataType::Time32(_) | DataType::Time64(_) => Type::TIME_ARRAY,
DataType::Date32 | DataType::Date64 => Type::DATE_ARRAY,
DataType::Interval(_) => Type::INTERVAL_ARRAY,
DataType::FixedSizeBinary(_) | DataType::Binary => Type::BYTEA_ARRAY,
DataType::FixedSizeBinary(_)
| DataType::Binary
| DataType::LargeBinary
| DataType::BinaryView => Type::BYTEA_ARRAY,
DataType::Float16 | DataType::Float32 => Type::FLOAT4_ARRAY,
DataType::Float64 => Type::FLOAT8_ARRAY,
DataType::Utf8 => Type::VARCHAR_ARRAY,
DataType::LargeUtf8 => Type::TEXT_ARRAY,
DataType::LargeUtf8 | DataType::Utf8View => Type::TEXT_ARRAY,
struct_type @ DataType::Struct(_) => Type::new(
Type::RECORD_ARRAY.name().into(),
Type::RECORD_ARRAY.oid(),
Expand All @@ -78,7 +84,6 @@ pub fn into_pg_type(arrow_type: &DataType) -> PgWireResult<Type> {
}
}
}
DataType::Utf8View => Type::TEXT,
DataType::Dictionary(_, value_type) => into_pg_type(value_type)?,
DataType::Struct(fields) => {
let name: String = fields
Expand Down
27 changes: 22 additions & 5 deletions arrow-pg/src/encoder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,6 +143,15 @@ fn get_utf8_view_value(arr: &Arc<dyn Array>, idx: usize) -> Option<&str> {
})
}

fn get_binary_view_value(arr: &Arc<dyn Array>, idx: usize) -> Option<&[u8]> {
(!arr.is_null(idx)).then(|| {
arr.as_any()
.downcast_ref::<BinaryViewArray>()
.unwrap()
.value(idx)
})
}

fn get_utf8_value(arr: &Arc<dyn Array>, idx: usize) -> Option<&str> {
(!arr.is_null(idx)).then(|| {
arr.as_any()
Expand All @@ -161,12 +170,15 @@ fn get_large_utf8_value(arr: &Arc<dyn Array>, idx: usize) -> Option<&str> {
})
}

fn get_binary_value(arr: &Arc<dyn Array>, idx: usize) -> Option<&[u8]> {
fn get_binary_value(arr: &Arc<dyn Array>, idx: usize) -> Option<String> {
(!arr.is_null(idx)).then(|| {
arr.as_any()
.downcast_ref::<BinaryArray>()
.unwrap()
.value(idx)
String::from_utf8_lossy(
arr.as_any()
.downcast_ref::<BinaryArray>()
.unwrap()
.value(idx),
)
.to_string()
})
}

Expand Down Expand Up @@ -330,6 +342,11 @@ pub fn encode_value<T: Encoder>(
type_,
format,
)?,
DataType::BinaryView => encoder.encode_field_with_type_and_format(
&get_binary_view_value(arr, idx),
type_,
format,
)?,
DataType::LargeUtf8 => encoder.encode_field_with_type_and_format(
&get_large_utf8_value(arr, idx),
type_,
Expand Down
Loading