hawkingrei commented on code in PR #181:
URL: https://github.com/apache/datasketches-rust/pull/181#discussion_r3718512216
##########
datasketches/src/thetafamily/common/jaccard_similarity.rs:
##########
@@ -299,6 +269,71 @@ impl JaccardSimilarityOperator {
union.theta64(),
)
}
+
+ pub(crate) fn exactly_equal<A, B>(&self, sketch_a: &A, sketch_b: &B) ->
Result<bool, Error>
+ where
+ A: ThetaKeySketchView,
+ B: ThetaKeySketchView,
+ {
+ if sketch_a.is_empty() && sketch_b.is_empty() {
+ return Ok(true);
+ }
+ if sketch_a.is_empty() || sketch_b.is_empty() {
+ return Ok(false);
+ }
+
+ let union = self.compute_union(sketch_a, sketch_b)?;
+ Ok(identical_sets(sketch_a, sketch_b, &union))
+ }
+
+ fn compute_union<A, B>(
+ &self,
+ sketch_a: &A,
+ sketch_b: &B,
+ ) -> Result<CompactSketchParts<KeyEntry>, Error>
+ where
+ A: ThetaKeySketchView,
+ B: ThetaKeySketchView,
+ {
+ self.validate_seed_hash(sketch_a)?;
+ self.validate_seed_hash(sketch_b)?;
+
+ let sketch_a = KeySketchView::new(sketch_a);
+ let sketch_b = KeySketchView::new(sketch_b);
+ let mut union = UnionState::new(
+ union_lg_k(sketch_a.num_retained(), sketch_b.num_retained()),
+ ResizeFactor::X8,
+ 1.0,
+ self.seed,
+ NoopMergePolicy,
+ );
+ union.update(&sketch_a)?;
+ union.update(&sketch_b)?;
+ Ok(union.to_compact_parts(false))
+ }
+
+ fn validate_seed_hash<S: ThetaKeySketchView>(&self, sketch: &S) ->
Result<(), Error> {
+ let expected = compute_seed_hash(self.seed);
+ if expected != sketch.seed_hash() {
+ return Err(Error::invalid_argument(format!(
+ "incompatible seed hash: expected {}, got {}",
+ expected,
+ sketch.seed_hash(),
+ )));
+ }
+ Ok(())
+ }
+}
+
+fn identical_sets<A, B>(sketch_a: &A, sketch_b: &B, union:
&CompactSketchParts<KeyEntry>) -> bool
Review Comment:
Thanks. I kept the C++-aligned name and added documentation in f67e857
explaining why no additional retained union keys plus matching theta values
proves that both sketches have the same retained key set and theta.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
