Skip to content

Support Decimal and Decimal256 Parquet Data Page Statistics #11138

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 3 commits into from
Jun 27, 2024
Merged

Support Decimal and Decimal256 Parquet Data Page Statistics #11138

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
7328bc1
Support Decimal and Decimal256 Parquet Data Page Statistics
Lordworms Jun 26, 2024
022fe50
Merge remote-tracking branch 'apache/main' into issue_11111
alamb Jun 27, 2024
261d058
Merge remote-tracking branch 'apache/main' into issue_11111
alamb Jun 27, 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
118 changes: 118 additions & 0 deletions datafusion/core/src/datasource/physical_plan/parquet/statistics.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -600,6 +600,119 @@ make_data_page_stats_iterator!(
Index::DOUBLE,
f64
);

macro_rules! get_decimal_page_stats_iterator {
($iterator_type: ident, $func: ident, $stat_value_type: ident, $convert_func: ident) => {
struct $iterator_type<'a, I>
where
I: Iterator<Item = (usize, &'a Index)>,
{
iter: I,
}

impl<'a, I> $iterator_type<'a, I>
where
I: Iterator<Item = (usize, &'a Index)>,
{
fn new(iter: I) -> Self {
Self { iter }
}
}

impl<'a, I> Iterator for $iterator_type<'a, I>
where
I: Iterator<Item = (usize, &'a Index)>,
{
type Item = Vec<Option<$stat_value_type>>;

fn next(&mut self) -> Option<Self::Item> {
let next = self.iter.next();
match next {
Some((len, index)) => match index {
Index::INT32(native_index) => Some(
native_index
.indexes
.iter()
.map(|x| {
Some($stat_value_type::from(
x.$func.unwrap_or_default(),
))
})
.collect::<Vec<_>>(),
),
Index::INT64(native_index) => Some(
native_index
.indexes
.iter()
.map(|x| {
Some($stat_value_type::from(
x.$func.unwrap_or_default(),
))
})
.collect::<Vec<_>>(),
),
Index::BYTE_ARRAY(native_index) => Some(
native_index
.indexes
.iter()
.map(|x| {
Some($convert_func(
x.clone().$func.unwrap_or_default().data(),
))
})
.collect::<Vec<_>>(),
),
Index::FIXED_LEN_BYTE_ARRAY(native_index) => Some(
native_index
.indexes
.iter()
.map(|x| {
Some($convert_func(
x.clone().$func.unwrap_or_default().data(),
))
})
.collect::<Vec<_>>(),
),
_ => Some(vec![None; len]),
},
_ => None,
}
}

fn size_hint(&self) -> (usize, Option<usize>) {
self.iter.size_hint()
}
}
};
}

get_decimal_page_stats_iterator!(
MinDecimal128DataPageStatsIterator,
min,
i128,
from_bytes_to_i128
);

get_decimal_page_stats_iterator!(
MaxDecimal128DataPageStatsIterator,
max,
i128,
from_bytes_to_i128
);

get_decimal_page_stats_iterator!(
MinDecimal256DataPageStatsIterator,
min,
i256,
from_bytes_to_i256
);

get_decimal_page_stats_iterator!(
MaxDecimal256DataPageStatsIterator,
max,
i256,
from_bytes_to_i256
);
make_data_page_stats_iterator!(
MinByteArrayDataPageStatsIterator,
|x: &PageIndex<ByteArray>| { x.min.clone() },
Expand All @@ -612,6 +725,7 @@ make_data_page_stats_iterator!(
Index::BYTE_ARRAY,
ByteArray
);

macro_rules! get_data_page_statistics {
($stat_type_prefix: ident, $data_type: ident, $iterator: ident) => {
paste! {
Expand Down Expand Up @@ -755,6 +869,10 @@ macro_rules! get_data_page_statistics {
)
)
),
Some(DataType::Decimal128(precision, scale)) => Ok(Arc::new(
Decimal128Array::from_iter([<$stat_type_prefix Decimal128DataPageStatsIterator>]::new($iterator).flatten()).with_precision_and_scale(*precision, *scale)?)),
Some(DataType::Decimal256(precision, scale)) => Ok(Arc::new(
Decimal256Array::from_iter([<$stat_type_prefix Decimal256DataPageStatsIterator>]::new($iterator).flatten()).with_precision_and_scale(*precision, *scale)?)),
_ => unimplemented!()
}
}
Expand Down
4 changes: 2 additions & 2 deletions datafusion/core/tests/parquet/arrow_statistics.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1683,7 +1683,7 @@ async fn test_decimal() {
expected_null_counts: UInt64Array::from(vec![0, 0, 0]),
expected_row_counts: Some(UInt64Array::from(vec![5, 5, 5])),
column_name: "decimal_col",
check: Check::RowGroup,
check: Check::Both,
}
.run();
}
Expand Down Expand Up @@ -1721,7 +1721,7 @@ async fn test_decimal_256() {
expected_null_counts: UInt64Array::from(vec![0, 0, 0]),
expected_row_counts: Some(UInt64Array::from(vec![5, 5, 5])),
column_name: "decimal256_col",
check: Check::RowGroup,
check: Check::Both,
}
.run();
}
Expand Down