MRG: in core, enable downsample within select (#2931)

Attempting #1292 in order to move forward
sourmash-bio/sourmash_plugin_branchwater#134

Modifies `Signature` `Select` to downsample automatically.

- for scaled sketches, while checking ksize, we also retain only
sketches that have the right scaled or can be downsampled (scaled <=
selection.scaled())
- next, we iterate through the sketches and downsample any where scaled
< selection.scaled()

Note that for `sourmash_plugin_branchwater` compatibility, we need:

- `byteorder` = "1.4.3"
- `wasm-bindgen` = "0.2.89"
- `once_cell` = "1.18.0"
---------

Co-authored-by: Luiz Irber <luizirber@users.noreply.github.com>

src/core/Cargo.toml

@@ -27,7 +27,7 @@ default = []
 
 [dependencies]
 az = "1.0.0"
-byteorder = "1.5.0"
+byteorder = "1.4.3"
 camino = { version = "1.1.6", features = ["serde1"] }
 cfg-if = "1.0"
 counter = "0.5.7"
@@ -45,7 +45,7 @@ murmurhash3 = "0.0.5"
 niffler = { version = "2.3.1", default-features = false, features = [ "gz" ] }
 nohash-hasher = "0.2.0"
 num-iter = "0.1.43"
-once_cell = "1.19.0"
+once_cell = "1.18.0"
 ouroboros = "0.18.3"
 piz = "0.5.0"
 primal-check = "0.3.1"
@@ -88,7 +88,7 @@ skip_feature_sets = [
 ## Wasm section. Crates only used for WASM, as well as specific configurations
 
 [target.'cfg(all(target_arch = "wasm32", target_os="unknown"))'.dependencies.wasm-bindgen]
-version = "0.2.90"
+version = "0.2.89"
 features = ["serde-serialize"]
 
 [target.'cfg(all(target_arch = "wasm32", target_os="unknown"))'.dependencies.web-sys]

src/core/src/signature.rs

@@ -771,8 +771,14 @@ impl Select for Signature {
             } else {
                 valid
             };
-            // TODO: execute downsample if needed
-
+            // keep compatible scaled if applicable
+            if let Some(sel_scaled) = selection.scaled() {
+                valid = if let Sketch::MinHash(mh) = s {
+                    valid && mh.scaled() <= sel_scaled as u64
+                } else {
+                    valid
+                };
+            }
             /*
             valid = if let Some(abund) = selection.abund() {
                 valid && *s.with_abundance() == abund
@@ -785,8 +791,20 @@ impl Select for Signature {
                 valid
             };
             */
+
             valid
         });
+
+        // downsample the retained sketches if needed.
+        if let Some(sel_scaled) = selection.scaled() {
+            for sketch in self.signatures.iter_mut() {
+                if let Sketch::MinHash(mh) = sketch {
+                    if (mh.scaled() as u32) < sel_scaled {
+                        *sketch = Sketch::MinHash(mh.downsample_scaled(sel_scaled as u64)?);
+                    }
+                }
+            }
+        }
         Ok(self)
     }
 }
@@ -841,6 +859,10 @@ mod test {
 
     use super::Signature;
 
+    use crate::prelude::Select;
+    use crate::selection::Selection;
+    use crate::sketch::Sketch;
+
     #[test]
     fn load_sig() {
         let mut filename = PathBuf::from(env!("CARGO_MANIFEST_DIR"));
@@ -979,4 +1001,47 @@ mod test {
             assert_eq!(sk.size(), 500);
         }
     }
+
+    #[test]
+    fn selection_with_downsample() {
+        let mut filename = PathBuf::from(env!("CARGO_MANIFEST_DIR"));
+        filename.push("../../tests/test-data/47+63-multisig.sig");
+
+        let file = File::open(filename).unwrap();
+        let reader = BufReader::new(file);
+        let sigs: Vec<Signature> = serde_json::from_reader(reader).expect("Loading error");
+
+        // create Selection object
+        let mut selection = Selection::default();
+        selection.set_scaled(2000);
+        // iterate and check scaled
+        for sig in &sigs {
+            let modified_sig = sig.clone().select(&selection).unwrap();
+            for sketch in modified_sig.sketches() {
+                if let Sketch::MinHash(mh) = sketch {
+                    dbg!("scaled: {:?}", mh.scaled());
+                    assert_eq!(mh.scaled(), 2000);
+                }
+            }
+        }
+    }
+
+    #[test]
+    fn selection_scaled_too_low() {
+        let mut filename = PathBuf::from(env!("CARGO_MANIFEST_DIR"));
+        filename.push("../../tests/test-data/47+63-multisig.sig");
+
+        let file = File::open(filename).unwrap();
+        let reader = BufReader::new(file);
+        let sigs: Vec<Signature> = serde_json::from_reader(reader).expect("Loading error");
+
+        // create Selection object
+        let mut selection = Selection::default();
+        selection.set_scaled(100);
+        // iterate and check no sigs are returned (original scaled is 1000)
+        for sig in &sigs {
+            let modified_sig = sig.clone().select(&selection).unwrap();
+            assert_eq!(modified_sig.size(), 0);
+        }
+    }
 }