fix!: Renmae to_kana to transliterate_to_kana

.github/workflows/ci_js.yaml

@@ -32,7 +32,9 @@ jobs:
           node-version: '24'
 
       - name: Install wasm-bindgen-cli
-        run: cargo install wasm-bindgen-cli --version 0.2.114
+        uses: taiki-e/install-action@v2
+        with:
+          tool: wasm-bindgen-cli@0.2.114
 
       - name: Install Node.js dependencies
         run: npm ci

README.md

@@ -3,7 +3,7 @@
 [![CI: Rust](https://github.com/aynumosir/ainu-utils/actions/workflows/ci_rust.yaml/badge.svg)](https://github.com/aynumosir/ainu-utils/actions/workflows/ci_rust.yaml)
 [![codecov](https://codecov.io/gh/aynumosir/ainu-utils/graph/badge.svg?token=aQHfYRVtsd)](https://codecov.io/gh/aynumosir/ainu-utils)
 
-A collection of utility for with the Ainu language
+A toolkit for Ainu language processing, available in Rust, JavaScript, and Python.
 
 ## Releases
 
@@ -19,7 +19,7 @@ ainu-utils is distributed as a Rust crate, but you can also use its binding for
 
 `ainu-utils` provides several features for working with the Ainu language:
 
-### `tokenize`
+### Tokenization
 
 Tokenizes Ainu text into morphemes.
 
@@ -41,70 +41,71 @@ tokenize("irankarapte. e=iwanke ya?", { keepWhitespace: false });
 // => ["irankarapte", ".", "e=", "iwanke", "ya?"]
 ```
 
-### `to_kana`
+### Syllabication
 
-Converts Ainu text written in Latin script to Kana.
+Parses Ainu text into syllables.
 
 **Python:**
 
 ```py
-from ainu_utils import to_kana
+from ainu_utils import syllabicate
 
-to_kana("irankarapte. e=iwanke ya?")
-# => "イランカラㇷ゚テ。　エイワンケ　ヤ？"
+syllabicate("irankarapte. e=iwanke ya?")
+# => ["i", "ran", "ka", "rap", "te", ".", " ", "e", "=", "i", "wan", "ke", " ", "ya", "?"]
 ```
 
 **JS:**
 
 ```js
-import { toKana } from "ainu-utils";
+import { syllabicate } from "ainu-utils";
 
-toKana("irankarapte. e=iwanke ya?");
-// => "イランカラㇷ゚テ。　エイワンケ　ヤ？"
+syllabicate("irankarapte. e=iwanke ya?")
+// => ["i", "ran", "ka", "rap", "te", ".", " ", "e", "=", "i", "wan", "ke", " ", "ya", "?"]
 ```
 
-### `number_to_words`
 
-Converts integers between 1 and 100 to Ainu words.
+### Transliteration
+
+Converts Ainu text written in Latin script to Kana.
 
 **Python:**
 
 ```py
-from ainu_utils import number_to_words
+from ainu_utils import transliterate_to_kana
 
-number_to_words(91)
-# => "sine ikasma wan easiknehotne"
+transliterate_to_kana("irankarapte. e=iwanke ya?")
+# => "イランカラㇷ゚テ。　エイワンケ　ヤ？"
 ```
 
 **JS:**
 
 ```js
-import { numberToWords } from "ainu-utils";
+import { transliterateToKana } from "ainu-utils";
 
-numberToWords(91);
-// => "sine ikasma wan easiknehotne"
+transliterateToKana("irankarapte. e=iwanke ya?");
+// => "イランカラㇷ゚テ。　エイワンケ　ヤ？"
 ```
 
-### `syllabicate`
+### Convertion from a number to words
 
-Parses Ainu text into syllables.
+Converts integers between 1 and 100 to Ainu words.
 
 **Python:**
 
 ```py
-from ainu_utils import syllabicate
+from ainu_utils import number_to_words
 
-syllabicate("irankarapte. e=iwanke ya?")
-# => ["i", "ran", "ka", "rap", "te", ".", " ", "e", "=", "i", "wan", "ke", " ", "ya", "?"]
+number_to_words(91)
+# => "sine ikasma wan easiknehotne"
 ```
 
 **JS:**
 
 ```js
-import { syllabicate } from "ainu-utils";
+import { numberToWords } from "ainu-utils";
 
-syllabicate("irankarapte. e=iwanke ya?")
-// => ["i", "ran", "ka", "rap", "te", ".", " ", "e", "=", "i", "wan", "ke", " ", "ya", "?"]
+numberToWords(91);
+// => "sine ikasma wan easiknehotne"
 ```
 
 ## License

ainu-utils-js/Cargo.toml

@@ -1,8 +1,8 @@
 [package]
 name = "ainu-utils-js"
-version = "0.5.1"
+version = "0.5.3"
 edition = "2024"
-description = "A collection of utilities for the Ainu language"
+description = "A toolkit for Ainu language processing, available in Rust, JavaScript, and Python."
 license = "MIT"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

ainu-utils-js/src/lib.rs

@@ -11,17 +11,17 @@ pub fn tokenize(text: &str, options: JsValue) -> Vec<String> {
     tokenizer::tokenize(text, keep_whitespace)
 }
 
-#[wasm_bindgen(js_name = toKana)]
-pub fn to_kana(text: &str) -> String {
-    kana::to_kana(text)
+#[wasm_bindgen]
+pub fn syllabicate(text: &str) -> Vec<String> {
+    syllables::parse(text)
+}
+
+#[wasm_bindgen(js_name = transliterateToKana)]
+pub fn transliterate_to_kana(text: &str) -> String {
+    kana::transliterate_to_kana(text)
 }
 
 #[wasm_bindgen(js_name = numberToWords)]
 pub fn number_to_words(input: i32) -> String {
     numbers::parse(input).unwrap().to_string()
 }
-
-#[wasm_bindgen]
-pub fn syllabicate(text: &str) -> Vec<String> {
-    syllables::parse(text)
-}

ainu-utils-js/tests/index.spec.js

@@ -1,7 +1,13 @@
 import { test, expect } from "vitest";
-import { tokenize } from "../dist/index.js";
+import { tokenize, transliterateToKana } from "../dist/index.js";
 
 test("tokenize", () => {
   const tokens = tokenize("irankarapte. e=iwanke ya?", { keepWhitespace: false });
   expect(tokens).toEqual(["irankarapte", ".", "e=", "iwanke", "ya", "?"]);
 });
+
+
+test("transliterateToKana", () => {
+  const tokens = transliterateToKana("irankarapte. e=iwanke ya?");
+  expect(tokens).toBe("イランカラㇷ゚テ。　エイワンケ　ヤ？");
+});

ainu-utils-python/Cargo.toml

@@ -1,8 +1,8 @@
 [package]
 name = "ainu-utils-python"
-version = "0.5.1"
+version = "0.5.3"
 edition = "2021"
-description = "A collection of utilities for the Ainu language"
+description = "A toolkit for Ainu language processing, available in Rust, JavaScript, and Python."
 license = "MIT"
 
 [lib]

ainu-utils-python/pyproject.toml

@@ -7,9 +7,9 @@ features = ["pyo3/extension-module"]
 
 [project]
 name = "ainu-utils"
-description = "A collection of utility for with the Ainu language"
+description = "A toolkit for Ainu language processing"
 requires-python = ">=3.8"
-version = "0.5.1"
+version = "0.5.3"
 license = "MIT"
 
 [project.optional-dependencies]

ainu-utils-python/src/lib.rs

@@ -9,8 +9,8 @@ fn tokenize(text: &str, keep_whitespace: bool) -> Vec<String> {
 }
 
 #[pyfunction]
-fn to_kana(text: &str) -> String {
-    ainu_utils_rust::kana::to_kana(text)
+fn transliterate_to_kana(text: &str) -> String {
+    ainu_utils_rust::kana::transliterate_to_kana(text)
 }
 
 #[pyfunction]
@@ -26,7 +26,7 @@ fn syllabicate(text: &str) -> Vec<String> {
 #[pymodule]
 fn ainu_utils(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(tokenize, m)?)?;
-    m.add_function(wrap_pyfunction!(to_kana, m)?)?;
+    m.add_function(wrap_pyfunction!(transliterate_to_kana, m)?)?;
     m.add_function(wrap_pyfunction!(number_to_words, m)?)?;
     m.add_function(wrap_pyfunction!(syllabicate, m)?)?;
     m.add("test_number", 123)?;

ainu-utils-python/tests/test_transliterate_to_kana.py

@@ -0,0 +1,6 @@
+import ainu_utils
+
+
+def test_transliterate_to_kana():
+    result = ainu_utils.transliterate_to_kana("irankarapte. e=iwanke ya?")
+    assert result == "イランカラㇷ゚テ。　エイワンケ　ヤ？"

ainu-utils/Cargo.toml

@@ -1,8 +1,8 @@
 [package]
 name = "ainu-utils"
-version = "0.5.1"
+version = "0.5.3"
 edition = "2024"
-description = "A collection of utilities for the Ainu language"
+description = "A toolkit for Ainu language processing, available in Rust, JavaScript, and Python."
 license = "MIT"
 
 [dependencies]

ainu-utils/src/kana/kana.rs

@@ -1,21 +1,22 @@
-use crate::normalizer::normalize;
 use crate::phoneme::Phoneme;
+use unicode_normalization::UnicodeNormalization;
+use unicode_normalization::char::is_combining_mark;
 
 use super::kana_linking::link;
 use super::kana_map_c::map_c;
 use super::kana_map_cv::map_cv;
 use super::kana_map_punc::map_punc;
 use super::kana_map_v::map_v;
 
-pub fn to_kana(input: &str) -> String {
+pub fn transliterate_to_kana(input: &str) -> String {
     let mut input: String = input.to_string();
     input = link(&input);
 
     let words: Vec<&str> = input.split(' ').collect();
     let mut output = String::new();
 
     for word in words {
-        let kana = word_to_kana(word);
+        let kana = transliterate_word_to_kana(word);
 
         if kana.chars().any(|c| c.is_ascii_alphabetic()) {
             output += word;
@@ -31,10 +32,15 @@ pub fn to_kana(input: &str) -> String {
     output
 }
 
-fn word_to_kana(input: &str) -> String {
+fn strip_accents(input: &str) -> String {
+    input.nfkd().filter(|c| !is_combining_mark(*c)).collect()
+}
+
+fn transliterate_word_to_kana(input: &str) -> String {
     let mut input: String = input.to_string();
 
-    input = normalize(&input);
+    input = input.to_lowercase();
+    input = strip_accents(&input);
     input = map_punc(&input);
 
     let chars: Vec<char> = input.chars().collect();