initial

.gitignore

@@ -0,0 +1,14 @@
+# Generated by Cargo
+# will have compiled files and executables
+debug/
+target/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
+Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb

Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "yake-rust"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+regex = "1"
+streaming-stats = "0.1.28"
+contractions = "0.5.4"
+unicode-segmentation = "1.9.0"
+natural = "0.3.0"
+serde_json = "1.0"
+pragmatic-segmenter = "0.1.2"
+
+[profile.dev]
+opt-level = 0
+
+[profile.release]
+opt-level = 3

src/keywords/levenshtein.rs

@@ -0,0 +1,12 @@
+use std::cmp::max;
+
+use natural::distance::levenshtein_distance;
+
+pub(crate) struct Levenshtein {}
+impl Levenshtein {
+    pub fn ratio(seq1: String, seq2: String) -> f64 {
+        let distance = levenshtein_distance(&seq1, &seq2);
+        let length = max(seq1.len(), seq2.len());
+        1.0 - (distance as f64 / length as f64)
+    }
+}