nevi-me commented on a change in pull request #6770:
URL: https://github.com/apache/arrow/pull/6770#discussion_r419233839
##########
File path: rust/parquet/src/arrow/array_reader.rs
##########
@@ -468,6 +491,391 @@ where
}
}
+/// Implementation of list array reader.
+pub struct ListArrayReader {
+ item_reader: Box<dyn ArrayReader>,
+ data_type: ArrowType,
+ item_type: ArrowType,
+ list_def_level: i16,
+ list_rep_level: i16,
+ def_level_buffer: Option<Buffer>,
+ rep_level_buffer: Option<Buffer>,
+}
+
+impl ListArrayReader {
+ /// Construct list array reader.
+ pub fn new(
+ item_reader: Box<dyn ArrayReader>,
+ data_type: ArrowType,
+ item_type: ArrowType,
+ def_level: i16,
+ rep_level: i16,
+ ) -> Self {
+ Self {
+ item_reader,
+ data_type,
+ item_type,
+ list_def_level: def_level,
+ list_rep_level: rep_level,
+ def_level_buffer: None,
+ rep_level_buffer: None,
+ }
+ }
+}
+
+macro_rules! build_empty_list_array_with_primitive_items {
+ ($item_type:ident) => {{
+ let values_builder = PrimitiveBuilder::<$item_type>::new(0);
+ let mut builder = ListBuilder::new(values_builder);
+ let empty_list_array = builder.finish();
+ Ok(Arc::new(empty_list_array))
+ }};
+}
+
+macro_rules! build_empty_list_array_with_non_primitive_items {
+ ($builder:ident) => {{
+ let values_builder = $builder::new(0);
+ let mut builder = ListBuilder::new(values_builder);
+ let empty_list_array = builder.finish();
+ Ok(Arc::new(empty_list_array))
+ }};
+}
+
+fn build_empty_list_array(item_type: ArrowType) -> Result<ArrayRef> {
+ match item_type {
+ ArrowType::UInt8 =>
build_empty_list_array_with_primitive_items!(ArrowUInt8Type),
+ ArrowType::UInt16 => {
+ build_empty_list_array_with_primitive_items!(ArrowUInt16Type)
+ }
+ ArrowType::UInt32 => {
+ build_empty_list_array_with_primitive_items!(ArrowUInt32Type)
+ }
+ ArrowType::UInt64 => {
+ build_empty_list_array_with_primitive_items!(ArrowUInt64Type)
+ }
+ ArrowType::Int8 =>
build_empty_list_array_with_primitive_items!(ArrowInt8Type),
+ ArrowType::Int16 =>
build_empty_list_array_with_primitive_items!(ArrowInt16Type),
+ ArrowType::Int32 =>
build_empty_list_array_with_primitive_items!(ArrowInt32Type),
+ ArrowType::Int64 =>
build_empty_list_array_with_primitive_items!(ArrowInt64Type),
+ ArrowType::Float32 => {
+ build_empty_list_array_with_primitive_items!(ArrowFloat32Type)
+ }
+ ArrowType::Float64 => {
+ build_empty_list_array_with_primitive_items!(ArrowFloat64Type)
+ }
+ ArrowType::Boolean => {
+ build_empty_list_array_with_primitive_items!(ArrowBooleanType)
+ }
+ ArrowType::Date32(_) => {
+ build_empty_list_array_with_primitive_items!(ArrowDate32Type)
+ }
+ ArrowType::Date64(_) => {
+ build_empty_list_array_with_primitive_items!(ArrowDate64Type)
+ }
+ ArrowType::Time32(ArrowTimeUnit::Second) => {
+ build_empty_list_array_with_primitive_items!(ArrowTime32SecondType)
+ }
+ ArrowType::Time32(ArrowTimeUnit::Millisecond) => {
+
build_empty_list_array_with_primitive_items!(ArrowTime32MillisecondType)
+ }
+ ArrowType::Time64(ArrowTimeUnit::Microsecond) => {
+
build_empty_list_array_with_primitive_items!(ArrowTime64MicrosecondType)
+ }
+ ArrowType::Time64(ArrowTimeUnit::Nanosecond) => {
+
build_empty_list_array_with_primitive_items!(ArrowTime64NanosecondType)
+ }
+ ArrowType::Duration(ArrowTimeUnit::Second) => {
Review comment:
That's probably incorrect, but we can clarify/fix the behaviour of the
readers at a later stage.
##########
File path: rust/parquet/src/arrow/array_reader.rs
##########
@@ -468,6 +491,391 @@ where
}
}
+/// Implementation of list array reader.
+pub struct ListArrayReader {
+ item_reader: Box<dyn ArrayReader>,
+ data_type: ArrowType,
+ item_type: ArrowType,
+ list_def_level: i16,
+ list_rep_level: i16,
+ def_level_buffer: Option<Buffer>,
+ rep_level_buffer: Option<Buffer>,
+}
+
+impl ListArrayReader {
+ /// Construct list array reader.
+ pub fn new(
+ item_reader: Box<dyn ArrayReader>,
+ data_type: ArrowType,
+ item_type: ArrowType,
+ def_level: i16,
+ rep_level: i16,
+ ) -> Self {
+ Self {
+ item_reader,
+ data_type,
+ item_type,
+ list_def_level: def_level,
+ list_rep_level: rep_level,
+ def_level_buffer: None,
+ rep_level_buffer: None,
+ }
+ }
+}
+
+macro_rules! build_empty_list_array_with_primitive_items {
+ ($item_type:ident) => {{
+ let values_builder = PrimitiveBuilder::<$item_type>::new(0);
+ let mut builder = ListBuilder::new(values_builder);
+ let empty_list_array = builder.finish();
+ Ok(Arc::new(empty_list_array))
+ }};
+}
+
+macro_rules! build_empty_list_array_with_non_primitive_items {
+ ($builder:ident) => {{
+ let values_builder = $builder::new(0);
+ let mut builder = ListBuilder::new(values_builder);
+ let empty_list_array = builder.finish();
+ Ok(Arc::new(empty_list_array))
+ }};
+}
+
+fn build_empty_list_array(item_type: ArrowType) -> Result<ArrayRef> {
+ match item_type {
+ ArrowType::UInt8 =>
build_empty_list_array_with_primitive_items!(ArrowUInt8Type),
+ ArrowType::UInt16 => {
+ build_empty_list_array_with_primitive_items!(ArrowUInt16Type)
+ }
+ ArrowType::UInt32 => {
+ build_empty_list_array_with_primitive_items!(ArrowUInt32Type)
+ }
+ ArrowType::UInt64 => {
+ build_empty_list_array_with_primitive_items!(ArrowUInt64Type)
+ }
+ ArrowType::Int8 =>
build_empty_list_array_with_primitive_items!(ArrowInt8Type),
+ ArrowType::Int16 =>
build_empty_list_array_with_primitive_items!(ArrowInt16Type),
+ ArrowType::Int32 =>
build_empty_list_array_with_primitive_items!(ArrowInt32Type),
+ ArrowType::Int64 =>
build_empty_list_array_with_primitive_items!(ArrowInt64Type),
+ ArrowType::Float32 => {
+ build_empty_list_array_with_primitive_items!(ArrowFloat32Type)
+ }
+ ArrowType::Float64 => {
+ build_empty_list_array_with_primitive_items!(ArrowFloat64Type)
+ }
+ ArrowType::Boolean => {
+ build_empty_list_array_with_primitive_items!(ArrowBooleanType)
+ }
+ ArrowType::Date32(_) => {
+ build_empty_list_array_with_primitive_items!(ArrowDate32Type)
+ }
+ ArrowType::Date64(_) => {
+ build_empty_list_array_with_primitive_items!(ArrowDate64Type)
+ }
+ ArrowType::Time32(ArrowTimeUnit::Second) => {
+ build_empty_list_array_with_primitive_items!(ArrowTime32SecondType)
+ }
+ ArrowType::Time32(ArrowTimeUnit::Millisecond) => {
+
build_empty_list_array_with_primitive_items!(ArrowTime32MillisecondType)
+ }
+ ArrowType::Time64(ArrowTimeUnit::Microsecond) => {
+
build_empty_list_array_with_primitive_items!(ArrowTime64MicrosecondType)
+ }
+ ArrowType::Time64(ArrowTimeUnit::Nanosecond) => {
+
build_empty_list_array_with_primitive_items!(ArrowTime64NanosecondType)
+ }
+ ArrowType::Duration(ArrowTimeUnit::Second) => {
Review comment:
That's probably incorrect, but we can clarify/fix the behaviour of the
readers at a later stage.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
