Merge pull request #151 from meilisearch/prepare-for-conversion-from-hannoy

Introduce the `Writer::prepare_for_conversion` method

Author: Kerollmops

.github/workflows/rust.yml

@@ -2,9 +2,9 @@ name: Rust CI
 
 on:
   push:
-    branches: ["main"]
+    branches: ["main", "release-v0.6"]
   pull_request:
-    branches: ["main"]
+    branches: ["main", "release-v0.6"]
 
 env:
   CARGO_TERM_COLOR: always
@@ -24,7 +24,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v1
-      - uses: dtolnay/rust-toolchain@1.81
+      - uses: dtolnay/rust-toolchain@1.85
       - uses: actions-rs/cargo@v1
         with:
           command: build
@@ -41,7 +41,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v1
-      - uses: dtolnay/rust-toolchain@1.81
+      - uses: dtolnay/rust-toolchain@1.85
         with:
           profile: minimal
           components: clippy, rustfmt

Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "arroy"
 description = "Annoy-inspired Approximate Nearest Neighbors in Rust, based on LMDB and optimized for memory usage"
-version = "0.6.2"
+version = "0.6.3"
 documentation = "https://docs.rs/arroy"
 repository = "https://github.com/meilisearch/arroy"
 keywords = ["ANN-search", "Graph-algorithms", "Vector-Search", "Store"]
@@ -31,9 +31,11 @@ enum-iterator = "2.1.0"
 
 [dev-dependencies]
 anyhow = "1.0.95"
+approx = "0.5.1"
 arbitrary = { version = "1.4.1", features = ["derive"] }
 clap = { version = "4.5.24", features = ["derive"] }
 env_logger = "0.11.6"
+hannoy = "0.0.4"
 insta = "1.42.0"
 instant-distance = "0.6.1"
 proptest = "1.6.0"

src/node.rs

@@ -188,7 +188,24 @@ impl<'a, D: Distance> BytesDecode<'a> for NodeCodec<D> {
             [DESCENDANTS_TAG, bytes @ ..] => Ok(Node::Descendants(Descendants {
                 descendants: Cow::Owned(RoaringBitmap::deserialize_from(bytes)?),
             })),
-            unknown => panic!("What the fuck is an {unknown:?}"),
+            [unknown_tag, ..] => {
+                Err(Box::new(InvalidNodeDecoding { unknown_tag: Some(*unknown_tag) }))
+            }
+            [] => Err(Box::new(InvalidNodeDecoding { unknown_tag: None })),
+        }
+    }
+}
+
+#[derive(Debug, thiserror::Error)]
+pub struct InvalidNodeDecoding {
+    unknown_tag: Option<u8>,
+}
+
+impl fmt::Display for InvalidNodeDecoding {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self.unknown_tag {
+            Some(unknown_tag) => write!(f, "Invalid node decoding: unknown tag {unknown_tag}"),
+            None => write!(f, "Invalid node decoding: empty array of bytes"),
         }
     }
 }

src/reader.rs

@@ -321,7 +321,7 @@ impl<'t, D: Distance> Reader<'t, D> {
                     let key = Key::new(self.index, item);
                     match self.database.get(rtxn, &key)?.ok_or(Error::missing_key(key))? {
                         Node::Leaf(_) => {
-                            if opt.candidates.map_or(true, |c| c.contains(item.item)) {
+                            if opt.candidates.is_none_or(|c| c.contains(item.item)) {
                                 nns.push(item.unwrap_item());
                             }
                         }

src/tests/binary_quantized.rs

@@ -44,12 +44,12 @@ fn write_and_retrieve_binary_quantized_vector() {
     writer.builder(&mut rng()).n_trees(1).build(&mut wtxn).unwrap();
     wtxn.commit().unwrap();
 
-    insta::assert_snapshot!(handle, @r#"
+    insta::assert_snapshot!(handle, @r###"
     ==================
     Dumping index 0
     Root: Metadata { dimensions: 16, items: RoaringBitmap<[0]>, roots: [0], distance: "binary quantized euclidean" }
-    Version: Version { major: 0, minor: 6, patch: 2 }
+    Version: Version { major: 0, minor: 6, patch: 3 }
     Tree 0: Descendants(Descendants { descendants: [0] })
     Item 0: Leaf(Leaf { header: NodeHeaderBinaryQuantizedEuclidean { bias: 0.0 }, vector: [-1.0000, -1.0000, 1.0000, -1.0000, 1.0000, 1.0000, -1.0000, 1.0000, -1.0000, -1.0000, "other ..."] })
-    "#);
+    "###);
 }