Skip to content

feat: Support round trip reading/writing Arrow type Dictionary(_, FixedSizeBinary(_)) to Parquet #7446

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
alamb merged 9 commits into from
May 9, 2025
Merged

feat: Support round trip reading/writing Arrow type Dictionary(_, FixedSizeBinary(_)) to Parquet #7446

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
058c669
support FixedSizedBinary in dict encoding
Apr 27, 2025
ab3d7d3
roundtrip works
Apr 27, 2025
9e09d0e
cleanup
Apr 27, 2025
9eef5a5
clippy and linter
Apr 27, 2025
cb7a674
support all types of keys in byte_array_dictionary
Apr 27, 2025
d3701ab
back out change included by mistake
Apr 27, 2025
47c6f7e
linter
Apr 28, 2025
4fdc3c9
PR feedback before cleanup
May 4, 2025
7f2a44e
PR feedback from Weston
May 4, 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
9 changes: 6 additions & 3 deletions parquet/src/arrow/array_reader/builder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -289,9 +289,12 @@ fn build_primitive_reader(
}
_ => make_byte_array_reader(page_iterator, column_desc, arrow_type)?,
},
PhysicalType::FIXED_LEN_BYTE_ARRAY => {
make_fixed_len_byte_array_reader(page_iterator, column_desc, arrow_type)?
}
PhysicalType::FIXED_LEN_BYTE_ARRAY => match arrow_type {
Some(DataType::Dictionary(_, _)) => {
make_byte_array_dictionary_reader(page_iterator, column_desc, arrow_type)?
}
_ => make_fixed_len_byte_array_reader(page_iterator, column_desc, arrow_type)?,
},
};
Ok(Some(reader))
}
Expand Down
16 changes: 8 additions & 8 deletions parquet/src/arrow/array_reader/byte_array_dictionary.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,21 +90,21 @@ pub fn make_byte_array_dictionary_reader(
ArrowType::Dictionary(key_type, value_type) => {
make_reader! {
(pages, column_desc, data_type) => match (key_type.as_ref(), value_type.as_ref()) {
(ArrowType::UInt8, ArrowType::Binary | ArrowType::Utf8) => (u8, i32),
(ArrowType::UInt8, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (u8, i32),
(ArrowType::UInt8, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (u8, i64),
(ArrowType::Int8, ArrowType::Binary | ArrowType::Utf8) => (i8, i32),
(ArrowType::Int8, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (i8, i32),
(ArrowType::Int8, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (i8, i64),
(ArrowType::UInt16, ArrowType::Binary | ArrowType::Utf8) => (u16, i32),
(ArrowType::UInt16, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (u16, i32),
(ArrowType::UInt16, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (u16, i64),
(ArrowType::Int16, ArrowType::Binary | ArrowType::Utf8) => (i16, i32),
(ArrowType::Int16, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (i16, i32),
(ArrowType::Int16, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (i16, i64),
(ArrowType::UInt32, ArrowType::Binary | ArrowType::Utf8) => (u32, i32),
(ArrowType::UInt32, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (u32, i32),
(ArrowType::UInt32, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (u32, i64),
(ArrowType::Int32, ArrowType::Binary | ArrowType::Utf8) => (i32, i32),
(ArrowType::Int32, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (i32, i32),
(ArrowType::Int32, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (i32, i64),
(ArrowType::UInt64, ArrowType::Binary | ArrowType::Utf8) => (u64, i32),
(ArrowType::UInt64, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (u64, i32),
(ArrowType::UInt64, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (u64, i64),
(ArrowType::Int64, ArrowType::Binary | ArrowType::Utf8) => (i64, i32),
(ArrowType::Int64, ArrowType::Binary | ArrowType::Utf8 | ArrowType::FixedSizeBinary(_)) => (i64, i32),
(ArrowType::Int64, ArrowType::LargeBinary | ArrowType::LargeUtf8) => (i64, i64),
}
}
Expand Down
7 changes: 5 additions & 2 deletions parquet/src/arrow/arrow_writer/byte_array.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,8 @@ use crate::schema::types::ColumnDescPtr;
use crate::util::bit_util::num_required_bits;
use crate::util::interner::{Interner, Storage};
use arrow_array::{
Array, ArrayAccessor, BinaryArray, BinaryViewArray, DictionaryArray, LargeBinaryArray,
LargeStringArray, StringArray, StringViewArray,
Array, ArrayAccessor, BinaryArray, BinaryViewArray, DictionaryArray, FixedSizeBinaryArray,
LargeBinaryArray, LargeStringArray, StringArray, StringViewArray,
};
use arrow_schema::DataType;

Expand Down Expand Up @@ -85,6 +85,9 @@ macro_rules! downcast_op {
DataType::LargeBinary => {
downcast_dict_op!(key, LargeBinaryArray, $array, $op$(, $arg)*)
}
DataType::FixedSizeBinary(_) => {
downcast_dict_op!(key, FixedSizeBinaryArray, $array, $op$(, $arg)*)
}
d => unreachable!("cannot downcast {} dictionary value to byte array", d),
},
d => unreachable!("cannot downcast {} to byte array", d),
Expand Down
48 changes: 48 additions & 0 deletions parquet/src/arrow/arrow_writer/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -989,6 +989,9 @@ impl ArrowColumnWriterFactory {
ArrowDataType::Utf8View | ArrowDataType::BinaryView => {
out.push(bytes(leaves.next().unwrap())?)
}
ArrowDataType::FixedSizeBinary(_) => {
out.push(bytes(leaves.next().unwrap())?)
}
_ => {
out.push(col(leaves.next().unwrap())?)
}
Expand Down Expand Up @@ -1333,6 +1336,7 @@ mod tests {
use arrow_buffer::{i256, IntervalDayTime, IntervalMonthDayNano, NullBuffer};
use arrow_schema::Fields;
use half::f16;
use num::{FromPrimitive, ToPrimitive};

use crate::basic::Encoding;
use crate::data_type::AsBytes;
Expand Down Expand Up @@ -1911,6 +1915,50 @@ mod tests {
roundtrip(batch, Some(SMALL_SIZE / 2));
}

#[test]
fn test_fixed_size_binary_in_dict() {
fn test_fixed_size_binary_in_dict_inner<K>()
where
K: ArrowDictionaryKeyType,
K::Native: FromPrimitive + ToPrimitive + TryFrom<u8>,
<<K as arrow_array::ArrowPrimitiveType>::Native as TryFrom<u8>>::Error: std::fmt::Debug,
{
let field = Field::new(
"a",
DataType::Dictionary(
Box::new(K::DATA_TYPE),
Box::new(DataType::FixedSizeBinary(4)),
),
false,
);
let schema = Schema::new(vec![field]);

let keys: Vec<K::Native> = vec![
K::Native::try_from(0u8).unwrap(),
K::Native::try_from(0u8).unwrap(),
K::Native::try_from(1u8).unwrap(),
];
let keys = PrimitiveArray::<K>::from_iter_values(keys);
let values = FixedSizeBinaryArray::try_from_iter(
vec![vec![0, 0, 0, 0], vec![1, 1, 1, 1]].into_iter(),
)
.unwrap();

let data = DictionaryArray::<K>::new(keys, Arc::new(values));
let batch = RecordBatch::try_new(Arc::new(schema), vec![Arc::new(data)]).unwrap();
roundtrip(batch, None);
Copy link
Contributor

@alamb alamb May 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I verified this is doing a read/write round trip

Copy link
Contributor Author

@albertlockett albertlockett May 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes thanks for checking @alamb.

Sorry, I should have replied earlier to your other comment about this and confirmed that we already had the roundtrip test

Copy link
Contributor

@alamb alamb May 9, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no worries -- it was my bad for missing it

}

test_fixed_size_binary_in_dict_inner::<UInt8Type>();
test_fixed_size_binary_in_dict_inner::<UInt16Type>();
test_fixed_size_binary_in_dict_inner::<UInt32Type>();
test_fixed_size_binary_in_dict_inner::<UInt16Type>();
test_fixed_size_binary_in_dict_inner::<Int8Type>();
test_fixed_size_binary_in_dict_inner::<Int16Type>();
test_fixed_size_binary_in_dict_inner::<Int32Type>();
test_fixed_size_binary_in_dict_inner::<Int64Type>();
}

#[test]
fn test_empty_dict() {
let struct_fields = Fields::from(vec![Field::new(
Expand Down
9 changes: 9 additions & 0 deletions parquet/src/arrow/buffer/dictionary_buffer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,15 @@ impl<K: ArrowNativeType + Ord, V: OffsetSizeTrait> DictionaryBuffer<K, V> {
}
}

let ArrowType::Dictionary(_, value_type) = data_type else {
unreachable!()
};
let values = if let ArrowType::FixedSizeBinary(size) = **value_type {
arrow_cast::cast(&values, &ArrowType::FixedSizeBinary(size)).unwrap()
} else {
values
};

let builder = ArrayDataBuilder::new(data_type.clone())
.len(keys.len())
.add_buffer(Buffer::from_vec(keys))
Expand Down
Loading