Skip to content

Preserve source columns across Iceberg partition spec changes #111

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
osipovartem merged 2 commits into from
Oct 15, 2026
Merged

Preserve source columns across Iceberg partition spec changes #111

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4a9aa75
Preserve source columns across Iceberg partition spec changes
osipovartem Oct 15, 2026
115439a
Avoid cloning manifest entries in scan tests
osipovartem Oct 15, 2026
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
84 changes: 51 additions & 33 deletions datafusion_iceberg/src/pruning_statistics.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -262,6 +262,18 @@ impl<'table, 'manifests> PruneDataFiles<'table, 'manifests> {
files,
}
}

fn can_prune_column(entry: &ManifestEntry, column_id: i32) -> bool {
match entry.data_file().content() {
Content::Data => true,
Content::EqualityDeletes => entry
.data_file()
.equality_ids()
.as_ref()
.is_some_and(|ids| ids.contains(&column_id)),
Content::PositionDeletes => false,
}
}
}

impl PruningStatistics for PruneDataFiles<'_, '_> {
Expand All @@ -273,19 +285,21 @@ impl PruningStatistics for PruneDataFiles<'_, '_> {
.field_with_name(&column.name)
.ok()?
.data_type();
let min_values =
self.files
.iter()
.map(|manifest| match &manifest.1.data_file().lower_bounds() {
Some(map) => map.get(&column_id).and_then(|value| {
value
.clone()
.cast(&field.field_type)
.ok()
.map(Value::into_any)
}),
None => None,
});
let min_values = self.files.iter().map(|manifest| {
if !Self::can_prune_column(&manifest.1, column_id) {
return None;
}
match &manifest.1.data_file().lower_bounds() {
Some(map) => map.get(&column_id).and_then(|value| {
value
.clone()
.cast(&field.field_type)
.ok()
.map(Value::into_any)
}),
None => None,
}
});
any_iter_to_array(min_values, datatype).ok()
}
fn max_values(&self, column: &Column) -> Option<ArrayRef> {
Expand All @@ -296,33 +310,37 @@ impl PruningStatistics for PruneDataFiles<'_, '_> {
.field_with_name(&column.name)
.ok()?
.data_type();
let max_values =
self.files
.iter()
.map(|manifest| match &manifest.1.data_file().upper_bounds() {
Some(map) => map.get(&column_id).and_then(|value| {
value
.clone()
.cast(&field.field_type)
.ok()
.map(Value::into_any)
}),
None => None,
});
let max_values = self.files.iter().map(|manifest| {
if !Self::can_prune_column(&manifest.1, column_id) {
return None;
}
match &manifest.1.data_file().upper_bounds() {
Some(map) => map.get(&column_id).and_then(|value| {
value
.clone()
.cast(&field.field_type)
.ok()
.map(Value::into_any)
}),
None => None,
}
});
any_iter_to_array(max_values, datatype).ok()
}
fn num_containers(&self) -> usize {
self.files.len()
}
fn null_counts(&self, column: &Column) -> Option<ArrayRef> {
let column_id = self.schema.fields().get_name(&column.name)?.id;
let null_counts =
self.files.iter().map(
|manifest| match &manifest.1.data_file().null_value_counts() {
Some(map) => map.get(&{ column_id }).copied(),
None => None,
},
);
let null_counts = self.files.iter().map(|manifest| {
if !Self::can_prune_column(&manifest.1, column_id) {
return None;
}
match &manifest.1.data_file().null_value_counts() {
Some(map) => map.get(&{ column_id }).copied(),
None => None,
}
});
ScalarValue::iter_to_array(null_counts.map(ScalarValue::Int64)).ok()
}
fn contained(
Expand Down
Loading
Loading