Skip to content

Commit

Permalink
parquet: Add support for row group pruning on FixedSizeBinary (#9646)
Browse files Browse the repository at this point in the history 
* Add support for row group pruning on FixedSizeBinary

* Check statistics values are valid for their type
  • Loading branch information
@progval
progval authored Mar 19, 2024
1 parent 8074ca1 commit ad8d552
Show file tree
Hide file tree
Showing 3 changed files with 127 additions and 2 deletions.
1 change: 1 addition & 0 deletions datafusion/core/src/datasource/physical_plan/parquet/row_groups.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,7 @@ impl PruningStatistics for BloomFilterStatistics {
match value {
ScalarValue::Utf8(Some(v)) => sbbf.check(&v.as_str()),
ScalarValue::Binary(Some(v)) => sbbf.check(v),
ScalarValue::FixedSizeBinary(_size, Some(v)) => sbbf.check(v),
ScalarValue::Boolean(Some(v)) => sbbf.check(v),
ScalarValue::Float64(Some(v)) => sbbf.check(v),
ScalarValue::Float32(Some(v)) => sbbf.check(v),
Expand Down
27 changes: 25 additions & 2 deletions datafusion/core/src/datasource/physical_plan/parquet/statistics.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -105,21 +105,44 @@ macro_rules! get_statistic {
let s = std::str::from_utf8(s.$bytes_func())
.map(|s| s.to_string())
.ok();
if s.is_none() {
log::debug!(
"Utf8 statistics is a non-UTF8 value, ignoring it."
);
}
Some(ScalarValue::Utf8(s))
}
}
}
// type not supported yet
// type not fully supported yet
ParquetStatistics::FixedLenByteArray(s) => {
match $target_arrow_type {
// just support the decimal data type
// just support specific logical data types, there are others each
// with their own ordering
Some(DataType::Decimal128(precision, scale)) => {
Some(ScalarValue::Decimal128(
Some(from_bytes_to_i128(s.$bytes_func())),
*precision,
*scale,
))
}
Some(DataType::FixedSizeBinary(size)) => {
let value = s.$bytes_func().to_vec();
let value = if value.len().try_into() == Ok(*size) {
Some(value)
} else {
log::debug!(
"FixedSizeBinary({}) statistics is a binary of size {}, ignoring it.",
size,
value.len(),
);
None
};
Some(ScalarValue::FixedSizeBinary(
*size,
value,
))
}
_ => None,
}
}
Expand Down
101 changes: 101 additions & 0 deletions datafusion/core/tests/parquet/row_group_pruning.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -948,6 +948,107 @@ async fn prune_binary_lt() {
.await;
}

#[tokio::test]
async fn prune_fixedsizebinary_eq_match() {
RowGroupPruningTest::new()
.with_scenario(Scenario::ByteArray)
.with_query(
"SELECT name, service_fixedsize FROM t WHERE service_fixedsize = ARROW_CAST(CAST('fe6' AS bytea), 'FixedSizeBinary(3)')",
)
.with_expected_errors(Some(0))
// false positive on 'all frontends' batch: 'fe1' < 'fe6' < 'fe7'
.with_matched_by_stats(Some(2))
.with_pruned_by_stats(Some(1))
.with_matched_by_bloom_filter(Some(1))
.with_pruned_by_bloom_filter(Some(1))
.with_expected_rows(1)
.test_row_group_prune()
.await;

RowGroupPruningTest::new()
.with_scenario(Scenario::ByteArray)
.with_query(
"SELECT name, service_fixedsize FROM t WHERE service_fixedsize = ARROW_CAST(CAST('fe6' AS bytea), 'FixedSizeBinary(3)')",
)
.with_expected_errors(Some(0))
// false positive on 'all frontends' batch: 'fe1' < 'fe6' < 'fe7'
.with_matched_by_stats(Some(2))
.with_pruned_by_stats(Some(1))
.with_matched_by_bloom_filter(Some(1))
.with_pruned_by_bloom_filter(Some(1))
.with_expected_rows(1)
.test_row_group_prune()
.await;
}

#[tokio::test]
async fn prune_fixedsizebinary_eq_no_match() {
RowGroupPruningTest::new()
.with_scenario(Scenario::ByteArray)
.with_query(
"SELECT name, service_fixedsize FROM t WHERE service_fixedsize = ARROW_CAST(CAST('be9' AS bytea), 'FixedSizeBinary(3)')",
)
.with_expected_errors(Some(0))
// false positive on 'mixed' batch: 'be1' < 'be9' < 'fe4'
.with_matched_by_stats(Some(1))
.with_pruned_by_stats(Some(2))
.with_matched_by_bloom_filter(Some(0))
.with_pruned_by_bloom_filter(Some(1))
.with_expected_rows(0)
.test_row_group_prune()
.await;
}

#[tokio::test]
async fn prune_fixedsizebinary_neq() {
RowGroupPruningTest::new()
.with_scenario(Scenario::ByteArray)
.with_query(
"SELECT name, service_fixedsize FROM t WHERE service_fixedsize != ARROW_CAST(CAST('be1' AS bytea), 'FixedSizeBinary(3)')",
)
.with_expected_errors(Some(0))
.with_matched_by_stats(Some(3))
.with_pruned_by_stats(Some(0))
.with_matched_by_bloom_filter(Some(3))
.with_pruned_by_bloom_filter(Some(0))
.with_expected_rows(14)
.test_row_group_prune()
.await;
}

#[tokio::test]
async fn prune_fixedsizebinary_lt() {
RowGroupPruningTest::new()
.with_scenario(Scenario::ByteArray)
.with_query(
"SELECT name, service_fixedsize FROM t WHERE service_fixedsize < ARROW_CAST(CAST('be3' AS bytea), 'FixedSizeBinary(3)')",
)
.with_expected_errors(Some(0))
// matches 'all backends' only
.with_matched_by_stats(Some(1))
.with_pruned_by_stats(Some(2))
.with_matched_by_bloom_filter(Some(0))
.with_pruned_by_bloom_filter(Some(0))
.with_expected_rows(2)
.test_row_group_prune()
.await;

RowGroupPruningTest::new()
.with_scenario(Scenario::ByteArray)
.with_query(
"SELECT name, service_fixedsize FROM t WHERE service_fixedsize < ARROW_CAST(CAST('be9' AS bytea), 'FixedSizeBinary(3)')",
)
.with_expected_errors(Some(0))
.with_matched_by_stats(Some(2))
.with_pruned_by_stats(Some(1))
.with_matched_by_bloom_filter(Some(0))
.with_pruned_by_bloom_filter(Some(0))
// all backends from 'mixed' and 'all backends'
.with_expected_rows(8)
.test_row_group_prune()
.await;
}

#[tokio::test]
async fn prune_periods_in_column_names() {
// There are three row groups for "service.name", each with 5 rows = 15 rows total
Expand Down

0 comments on commit ad8d552

Please sign in to comment.