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

Write FixedLenByteArray stats for FixedLenByteArray columns (not ByteArray stats) #662

Merged
merged 1 commit into from
Aug 10, 2021
Merged

Write FixedLenByteArray stats for FixedLenByteArray columns (not ByteArray stats) #662

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
31 changes: 24 additions & 7 deletions parquet/src/column/writer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -924,11 +924,28 @@ impl<T: DataType> ColumnWriterImpl<T> {
Type::INT96 => gen_stats_section!(Int96, int96, min, max, distinct, nulls),
Type::FLOAT => gen_stats_section!(f32, float, min, max, distinct, nulls),
Type::DOUBLE => gen_stats_section!(f64, double, min, max, distinct, nulls),
Type::BYTE_ARRAY | Type::FIXED_LEN_BYTE_ARRAY => {
Type::BYTE_ARRAY => {
let min = min.as_ref().map(|v| ByteArray::from(v.as_bytes().to_vec()));
let max = max.as_ref().map(|v| ByteArray::from(v.as_bytes().to_vec()));
Statistics::byte_array(min, max, distinct, nulls, false)
}
Type::FIXED_LEN_BYTE_ARRAY => {
let min = min
.as_ref()
.map(|v| ByteArray::from(v.as_bytes().to_vec()))
.map(|ba| {
let ba: FixedLenByteArray = ba.into();
ba
});
let max = max
.as_ref()
.map(|v| ByteArray::from(v.as_bytes().to_vec()))
.map(|ba| {
let ba: FixedLenByteArray = ba.into();
ba
});
Statistics::fixed_len_byte_array(min, max, distinct, nulls, false)
}
}
}

Expand Down Expand Up @@ -1799,13 +1816,13 @@ mod tests {

let stats = statistics_roundtrip::<FixedLenByteArrayType>(&input);
assert!(stats.has_min_max_set());
// should it be FixedLenByteArray?
// https://github.com/apache/arrow-rs/issues/660
if let Statistics::ByteArray(stats) = stats {
assert_eq!(stats.min(), &ByteArray::from("aaw "));
assert_eq!(stats.max(), &ByteArray::from("zz "));
if let Statistics::FixedLenByteArray(stats) = stats {
let expected_min: FixedLenByteArray = ByteArray::from("aaw ").into();
assert_eq!(stats.min(), &expected_min);
let expected_max: FixedLenByteArray = ByteArray::from("zz ").into();
assert_eq!(stats.max(), &expected_max);
} else {
panic!("expecting Statistics::ByteArray, got {:?}", stats);
panic!("expecting Statistics::FixedLenByteArray, got {:?}", stats);
}
}

Expand Down