From d724b403f94b7fd1ecec3f6d2e4f5a1ed805c6ec Mon Sep 17 00:00:00 2001
From: Cashew <52880648+cashewnuttynuts@users.noreply.github.com>
Date: Sat, 22 Jun 2024 03:24:21 +0700
Subject: Add diacritics normalization preprocessors for Vietnamese (#1107)

* add viet diacritics normalization

* move regexp construction outside of function

* fix eslint

* add 'off' option

* fix lint

* fix type
---
 test/language/viet-text-preprocessors.test.js | 60 +++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 test/language/viet-text-preprocessors.test.js

(limited to 'test')

diff --git a/test/language/viet-text-preprocessors.test.js b/test/language/viet-text-preprocessors.test.js
new file mode 100644
index 00000000..56593c63
--- /dev/null
+++ b/test/language/viet-text-preprocessors.test.js
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2023-2024  Yomitan Authors
+ * Copyright (C) 2020-2022  Yomichan Authors
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import {normalizeDiacritics} from '../../ext/js/language/vi/viet-text-preprocessors.js';
+import {describe, expect, test} from 'vitest';
+
+const testCasesOldStyle = [
+    ['hoạ', 'họa'],
+    ['choàng', 'choàng'],
+    ['thuỷ', 'thủy'],
+    ['oà', 'òa'],
+    ['toà', 'tòa'],
+    ['toàn', 'toàn'],
+    ['tòan', 'toàn'],
+];
+
+const testCasesNewStyle = [
+    ['ngòăng', 'ngoằng'],
+    ['họa', 'hoạ'],
+    ['chòang', 'choàng'],
+    ['giừơng', 'giường'],
+    ['baỷ', 'bảy'],
+    ['cuả', 'của'],
+    ['òa', 'oà'],
+    ['toàn', 'toàn'],
+];
+
+describe('diacritics normalization', () => {
+    const {options, process} = normalizeDiacritics;
+    for (const option of options) {
+        if (option === 'off') { return; }
+
+        describe(`${option} style`, () => {
+            if (option === 'new') {
+                test.each(testCasesNewStyle)('%s normalizes to %s', (input, expected) => {
+                    expect(process(input, option)).toStrictEqual(expected);
+                });
+            } else {
+                test.each(testCasesOldStyle)('%s normalizes to %s', (input, expected) => {
+                    expect(process(input, option)).toStrictEqual(expected);
+                });
+            }
+        });
+    }
+});
-- 
cgit v1.2.3