chore: Using a fork of the fst library that support Arc<[u8]>

meilidb-core/Cargo.toml

@@ -6,10 +6,8 @@ edition = "2018"
 
 [dependencies]
 byteorder = "1.3.1"
-fst = "0.3.3"
 hashbrown = "0.1.8"
 lazy_static = "1.2.0"
-levenshtein_automata = { version = "0.1.1", features = ["fst_automaton"] }
 log = "0.4.6"
 meilidb-tokenizer = { path = "../meilidb-tokenizer", version = "0.1.0" }
 rayon = "1.0.3"
@@ -17,6 +15,15 @@ sdset = "0.3.1"
 serde = { version = "1.0.88", features = ["derive"] }
 slice-group-by = "0.2.4"
 
+[dependencies.fst]
+git = "https://github.com/Kerollmops/fst.git"
+branch = "arc-byte-slice"
+
+[dependencies.levenshtein_automata]
+git = "https://github.com/Kerollmops/levenshtein-automata.git"
+branch = "arc-byte-slice"
+features = ["fst_automaton"]
+
 [features]
 i128 = ["byteorder/i128"]
 nightly = ["hashbrown/nightly", "slice-group-by/nightly"]

meilidb-core/src/data/shared_data.rs

@@ -1,9 +1,9 @@
 use std::sync::Arc;
 use std::ops::Deref;
 
-#[derive(Default, Clone)]
+#[derive(Clone)]
 pub struct SharedData {
-    pub bytes: Arc<Vec<u8>>,
+    pub bytes: Arc<[u8]>,
     pub offset: usize,
     pub len: usize,
 }
@@ -15,7 +15,7 @@ impl SharedData {
         SharedData::new(bytes, 0, len)
     }
 
-    pub fn new(bytes: Arc<Vec<u8>>, offset: usize, len: usize) -> SharedData {
+    pub fn new(bytes: Arc<[u8]>, offset: usize, len: usize) -> SharedData {
         SharedData { bytes, offset, len }
     }
 
@@ -33,6 +33,16 @@ impl SharedData {
     }
 }
 
+impl Default for SharedData {
+    fn default() -> SharedData {
+        SharedData {
+            bytes: Arc::from(Vec::new()),
+            offset: 0,
+            len: 0,
+        }
+    }
+}
+
 impl Deref for SharedData {
     type Target = [u8];
 

meilidb-core/src/shared_data_cursor.rs

@@ -7,12 +7,12 @@ pub struct SharedDataCursor(Cursor<SharedData>);
 impl SharedDataCursor {
     pub fn from_bytes(bytes: Vec<u8>) -> SharedDataCursor {
         let len = bytes.len();
-        let bytes = Arc::new(bytes);
+        let bytes = Arc::from(bytes);
 
         SharedDataCursor::from_shared_bytes(bytes, 0, len)
     }
 
-    pub fn from_shared_bytes(bytes: Arc<Vec<u8>>, offset: usize, len: usize) -> SharedDataCursor {
+    pub fn from_shared_bytes(bytes: Arc<[u8]>, offset: usize, len: usize) -> SharedDataCursor {
         let data = SharedData::new(bytes, offset, len);
         let cursor = Cursor::new(data);