Skip to content
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

fix: Parquet column writer Dictionary(_, Decimal128) and Dictionary(_, Decimal256) #6987

Merged
merged 1 commit into from
Jan 20, 2025
Merged

fix: Parquet column writer Dictionary(_, Decimal128) and Dictionary(_, Decimal256) #6987

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
53 changes: 53 additions & 0 deletions parquet/src/arrow/array_reader/primitive_array.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,6 +270,59 @@ where

Arc::new(array) as ArrayRef
}
ArrowType::Dictionary(_, value_type) => match value_type.as_ref() {
Copy link
Contributor

Choose a reason for hiding this comment

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

This looks correct to me. It would be nice if we could get some code reuse here.

ArrowType::Decimal128(p, s) => {
let array = match array.data_type() {
ArrowType::Int32 => array
.as_any()
.downcast_ref::<Int32Array>()
.unwrap()
.unary(|i| i as i128)
as Decimal128Array,
ArrowType::Int64 => array
.as_any()
.downcast_ref::<Int64Array>()
.unwrap()
.unary(|i| i as i128)
as Decimal128Array,
_ => {
return Err(arrow_err!(
"Cannot convert {:?} to decimal dictionary",
array.data_type()
));
}
}
.with_precision_and_scale(*p, *s)?;

arrow_cast::cast(&array, target_type)?
Copy link
Contributor

@etseidl etseidl Jan 16, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

Taking a second look, I'm curious why the cast here rather than creating the ArrayRef directly as is done above? Will this have any performance implications?

Edit: ah, ok. We need to cast to dictionary. Disregard 😅

}
ArrowType::Decimal256(p, s) => {
let array = match array.data_type() {
ArrowType::Int32 => array
.as_any()
.downcast_ref::<Int32Array>()
.unwrap()
.unary(i256::from)
as Decimal256Array,
ArrowType::Int64 => array
.as_any()
.downcast_ref::<Int64Array>()
.unwrap()
.unary(i256::from)
as Decimal256Array,
_ => {
return Err(arrow_err!(
"Cannot convert {:?} to decimal dictionary",
array.data_type()
));
}
}
.with_precision_and_scale(*p, *s)?;

arrow_cast::cast(&array, target_type)?
}
_ => arrow_cast::cast(&array, target_type)?,
},
_ => arrow_cast::cast(&array, target_type)?,
};

Expand Down
90 changes: 89 additions & 1 deletion parquet/src/arrow/arrow_writer/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -843,6 +843,27 @@ fn write_leaf(writer: &mut ColumnWriter<'_>, levels: &ArrayLevels) -> Result<usi
.unary::<_, Int32Type>(|v| v.as_i128() as i32);
write_primitive(typed, array.values(), levels)
}
ArrowDataType::Dictionary(_, value_type) => match value_type.as_ref() {
ArrowDataType::Decimal128(_, _) => {
let array = arrow_cast::cast(column, value_type)?;
let array = array
.as_primitive::<Decimal128Type>()
.unary::<_, Int32Type>(|v| v as i32);
write_primitive(typed, array.values(), levels)
}
ArrowDataType::Decimal256(_, _) => {
let array = arrow_cast::cast(column, value_type)?;
let array = array
.as_primitive::<Decimal256Type>()
.unary::<_, Int32Type>(|v| v.as_i128() as i32);
write_primitive(typed, array.values(), levels)
}
_ => {
let array = arrow_cast::cast(column, &ArrowDataType::Int32)?;
let array = array.as_primitive::<Int32Type>();
write_primitive(typed, array.values(), levels)
}
},
_ => {
let array = arrow_cast::cast(column, &ArrowDataType::Int32)?;
let array = array.as_primitive::<Int32Type>();
Expand Down Expand Up @@ -891,6 +912,27 @@ fn write_leaf(writer: &mut ColumnWriter<'_>, levels: &ArrayLevels) -> Result<usi
.unary::<_, Int64Type>(|v| v.as_i128() as i64);
write_primitive(typed, array.values(), levels)
}
ArrowDataType::Dictionary(_, value_type) => match value_type.as_ref() {
ArrowDataType::Decimal128(_, _) => {
let array = arrow_cast::cast(column, value_type)?;
let array = array
.as_primitive::<Decimal128Type>()
.unary::<_, Int64Type>(|v| v as i64);
write_primitive(typed, array.values(), levels)
}
ArrowDataType::Decimal256(_, _) => {
let array = arrow_cast::cast(column, value_type)?;
let array = array
.as_primitive::<Decimal256Type>()
.unary::<_, Int64Type>(|v| v.as_i128() as i64);
write_primitive(typed, array.values(), levels)
}
_ => {
let array = arrow_cast::cast(column, &ArrowDataType::Int64)?;
let array = array.as_primitive::<Int64Type>();
write_primitive(typed, array.values(), levels)
}
},
_ => {
let array = arrow_cast::cast(column, &ArrowDataType::Int64)?;
let array = array.as_primitive::<Int64Type>();
Expand Down Expand Up @@ -1093,7 +1135,7 @@ mod tests {
use arrow::util::data_gen::create_random_array;
use arrow::util::pretty::pretty_format_batches;
use arrow::{array::*, buffer::Buffer};
use arrow_buffer::{IntervalDayTime, IntervalMonthDayNano, NullBuffer};
use arrow_buffer::{i256, IntervalDayTime, IntervalMonthDayNano, NullBuffer};
use arrow_schema::Fields;
use half::f16;

Expand Down Expand Up @@ -2670,6 +2712,52 @@ mod tests {
one_column_roundtrip_with_schema(Arc::new(d), schema);
}

#[test]
fn arrow_writer_decimal128_dictionary() {
Copy link
Contributor

Choose a reason for hiding this comment

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

Verified that tests fail if the read changes are reverted.

let integers = vec![12345, 56789, 34567];

let keys = UInt8Array::from(vec![Some(0), None, Some(1), Some(2), Some(1)]);

let values = Decimal128Array::from(integers.clone())
.with_precision_and_scale(5, 2)
.unwrap();

let array = DictionaryArray::new(keys, Arc::new(values));
one_column_roundtrip(Arc::new(array.clone()), true);

let values = Decimal128Array::from(integers)
.with_precision_and_scale(12, 2)
.unwrap();

let array = array.with_values(Arc::new(values));
one_column_roundtrip(Arc::new(array), true);
}

#[test]
fn arrow_writer_decimal256_dictionary() {
let integers = vec![
i256::from_i128(12345),
i256::from_i128(56789),
i256::from_i128(34567),
];

let keys = UInt8Array::from(vec![Some(0), None, Some(1), Some(2), Some(1)]);

let values = Decimal256Array::from(integers.clone())
.with_precision_and_scale(5, 2)
.unwrap();

let array = DictionaryArray::new(keys, Arc::new(values));
one_column_roundtrip(Arc::new(array.clone()), true);

let values = Decimal256Array::from(integers)
.with_precision_and_scale(12, 2)
.unwrap();

let array = array.with_values(Arc::new(values));
one_column_roundtrip(Arc::new(array), true);
}

#[test]
fn arrow_writer_string_dictionary_unsigned_index() {
// define schema
Expand Down
Loading