marvinlanhenke commented on code in PR #309:
URL: https://github.com/apache/iceberg-rust/pull/309#discussion_r1542902827
##########
crates/iceberg/src/spec/transform.rs:
##########
@@ -261,6 +270,174 @@ impl Transform {
_ => self == other,
}
}
+
+ /// Projects a given predicate according to the transformation
+ /// specified by the `Transform` instance.
+ ///
+ /// This allows predicates to be effectively applied to data
+ /// that has undergone transformation, enabling efficient querying
+ /// and filtering based on the original, untransformed data.
+ ///
+ /// # Example
+ /// Suppose, we have row filter `a = 10`, and a partition spec
+ /// `bucket(a, 37) as bs`, if one row matches `a = 10`, then its partition
+ /// value should match `bucket(10, 37) as bs`, and we project `a = 10` to
+ /// `bs = bucket(10, 37)`
+ pub fn project(&self, name: String, predicate: &BoundPredicate) ->
Result<Option<Predicate>> {
+ let func = create_transform_function(self)?;
+
+ let projection = match self {
+ Transform::Bucket(_) => match predicate {
+ BoundPredicate::Unary(expr) =>
Some(Predicate::Unary(UnaryExpression::new(
+ expr.op(),
+ Reference::new(name),
+ ))),
+ BoundPredicate::Binary(expr) => {
+ if expr.op() != PredicateOperator::Eq {
+ return Ok(None);
+ }
+
+ let new_datum =
func.transform_literal(expr.literal())?.ok_or_else(|| {
+ Error::new(
+ ErrorKind::DataInvalid,
+ "Transformed datum must not be 'None'",
+ )
+ })?;
+
+ Some(Predicate::Binary(BinaryExpression::new(
+ expr.op(),
+ Reference::new(name),
+ new_datum,
+ )))
+ }
+ BoundPredicate::Set(expr) => {
+ if expr.op() != PredicateOperator::In {
+ return Ok(None);
+ }
+
+ Some(Predicate::Set(SetExpression::new(
+ expr.op(),
+ Reference::new(name),
+ self.apply_transform_on_set(expr.literals(), &func)?,
+ )))
+ }
+ _ => None,
+ },
+ Transform::Identity => match predicate {
+ BoundPredicate::Unary(expr) =>
Some(Predicate::Unary(UnaryExpression::new(
+ expr.op(),
+ Reference::new(name),
+ ))),
+ BoundPredicate::Binary(expr) =>
Some(Predicate::Binary(BinaryExpression::new(
+ expr.op(),
+ Reference::new(name),
+ expr.literal().to_owned(),
+ ))),
+ BoundPredicate::Set(expr) =>
Some(Predicate::Set(SetExpression::new(
+ expr.op(),
+ Reference::new(name),
+ expr.literals().to_owned(),
+ ))),
+ _ => None,
+ },
+ Transform::Truncate(_) => match predicate {
+ BoundPredicate::Unary(expr) =>
Some(Predicate::Unary(UnaryExpression::new(
+ expr.op(),
+ Reference::new(name),
+ ))),
+ BoundPredicate::Binary(expr) => {
+ let op = expr.op();
+ let primitive = expr.literal().literal();
+
+ match primitive {
+ PrimitiveLiteral::Int(v) => {
+ self.apply_transform_boundary(name, v, op, &func)?
+ }
+ PrimitiveLiteral::Long(v) => {
+ self.apply_transform_boundary(name, v, op, &func)?
+ }
+ PrimitiveLiteral::Decimal(v) => {
+ self.apply_transform_boundary(name, v, op, &func)?
+ }
+ PrimitiveLiteral::Fixed(v) => {
+ self.apply_transform_boundary(name, v, op, &func)?
+ }
+ _ => return Ok(None),
+ }
+ }
+ BoundPredicate::Set(expr) => {
+ if expr.op() != PredicateOperator::In {
+ return Ok(None);
+ }
+
+ Some(Predicate::Set(SetExpression::new(
+ expr.op(),
+ Reference::new(name),
+ self.apply_transform_on_set(expr.literals(), &func)?,
+ )))
+ }
+ _ => None,
+ },
+ _ => None,
+ };
+
+ Ok(projection)
+ }
+
+ /// Transform each literal value of `FnvHashSet<Datum>`
+ fn apply_transform_on_set(
+ &self,
+ literals: &FnvHashSet<Datum>,
+ func: &BoxedTransformFunction,
+ ) -> Result<FnvHashSet<Datum>> {
+ literals
+ .iter()
+ .map(|lit| {
+ func.transform_literal(lit).and_then(|d| {
+ d.ok_or_else(|| {
+ Error::new(
+ ErrorKind::DataInvalid,
+ "Transformed datum must not be 'None'",
Review Comment:
I like this - thank you
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
