Fixed types, added singapore test case

andreihar · Aug 2, 2024 · 33a72be · 33a72be
1 parent c7d4e3f
commit 33a72be
Show file tree

Hide file tree

Showing 8 changed files with 51 additions and 23 deletions.
diff --git a/README.md b/README.md
@@ -132,10 +132,11 @@ c.get(input);
 
 * `south` (default) - [Zhangzhou][zhangzhou-wiki]-leaning pronunciation
 * `north` - [Quanzhou][quanzhou-wiki]-leaning pronunciation
+* `singapore` - Quanzhou-leaning pronunciation with [Singaporean characteristics][singapore-wiki]
 
-| text   | south         | north         |
-| ------ | ------------- | ------------- |
-| 五月節 | Gōo-gue̍h-tseh | Gōo-ge̍h-tsueh |
+| text           | south                       | north                       | singapore                  |
+| -------------- | --------------------------- | --------------------------- | -------------------------- |
+| 五月節我啉咖啡 | Gōo-gue̍h-tseh guá lim ka-pi | Gōo-ge̍h-tsueh guá lim ka-pi | Gōo-ge̍h-tsueh uá lim ko-pi |
 
 #### Format
 
@@ -185,9 +186,9 @@ Default value depends on the chosen `system`:
 
 Sandhi rules also change depending on the dialect chosen.
 
-| text | no sandhi | south   | north   |
-| ---- | --------- | ------- | ------- |
-| 台灣 | Tâi-uân   | Tāi-uân | Tài-uân |
+| text | no sandhi | south   | north / singapore |
+| ---- | --------- | ------- | ----------------- |
+| 台灣 | Tâi-uân   | Tāi-uân | Tài-uân           |
 
 #### Punctuation
 
@@ -279,6 +280,10 @@ c = new Converter({ dialect: 'north' });
 c.get("我欲用箸食魚");
 >> Guá bueh īng tū tsia̍h hû
 
+c = new Converter({ dialect: 'singapore' });
+c.get("我欲用箸食魚");
+>> Uá bueh ēng tū tsia̍h hû
+
 //// Format
 c = new Converter(); // for Tailo, mark by default
 c.get("生日快樂");
@@ -446,5 +451,6 @@ The data is licensed under [CC BY-SA 4.0][data-cc]
 [ipa-wiki]: https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
 [zhangzhou-wiki]: https://en.wikipedia.org/wiki/Zhangzhou_dialects
 [quanzhou-wiki]: https://en.wikipedia.org/wiki/Quanzhou_dialects
+[singapore-wiki]: https://en.wikipedia.org/wiki/Singaporean_Hokkien
 [nltk-tokenize]: https://nltk.org/api/nltk.tokenize.html
 [sandhi-wiki]: https://en.wikipedia.org/wiki/Taiwanese_Hokkien#Tone%20sandhi:~:text=thng%E2%9F%A9%20(%22soup%22).-,Tone%20sandhi,-%5Bedit%5D
diff --git a/package-lock.json b/package-lock.json
diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "taibun",
-  "version": "1.1.2",
+  "version": "1.1.3",
   "description": "Taiwanese Hokkien Transliterator and Tokeniser",
   "main": "taibun/index.js",
   "types": "taibun/index.d.ts",

diff --git a/readme/README-cmn.md b/readme/README-cmn.md
@@ -132,10 +132,11 @@ c.get(input);
 
 * `south` (預設) - 發音更接近[漳州話][zhangzhou-wiki]
 * `north` - 發音更接近[泉州話][quanzhou-wiki]
+* `singapore` - 帶有[新加坡特色][singapore-wiki]的泉州話發音
 
-| 文本   | south         | north         |
-| ------ | ------------- | ------------- |
-| 五月節 | Gōo-gue̍h-tseh | Gōo-ge̍h-tsueh |
+| 文本           | south                       | north                       | singapore                  |
+| -------------- | --------------------------- | --------------------------- | -------------------------- |
+| 五月節我啉咖啡 | Gōo-gue̍h-tseh guá lim ka-pi | Gōo-ge̍h-tsueh guá lim ka-pi | Gōo-ge̍h-tsueh uá lim ko-pi |
 
 #### Format
 
@@ -185,9 +186,9 @@ c.get(input);
 
 變調規則也會根據所選擇的方言而變化。
 
-| 文本 | 沒有變調 | south   | north   |
-| ---- | -------- | ------- | ------- |
-| 台灣 | Tâi-uân  | Tāi-uân | Tài-uân |
+| 文本 | 沒有變調 | south   | north / singapore |
+| ---- | -------- | ------- | ----------------- |
+| 台灣 | Tâi-uân  | Tāi-uân | Tài-uân           |
 
 #### Punctuation
 
@@ -279,6 +280,10 @@ c = new Converter({ dialect: 'north' });
 c.get("我欲用箸食魚");
 >> Guá bueh īng tū tsia̍h hû
 
+c = new Converter({ dialect: 'singapore' });
+c.get("我欲用箸食魚");
+>> Uá bueh ēng tū tsia̍h hû
+
 //// Format
 c = new Converter(); // 在 Tailo 中，format 預設值: mark
 c.get("生日快樂");
@@ -446,5 +451,6 @@ isCjk('我食pháng');
 [ipa-wiki]: https://zh.wikipedia.org/zh-tw/%E5%9C%8B%E9%9A%9B%E9%9F%B3%E6%A8%99
 [zhangzhou-wiki]: https://zh.wikipedia.org/zh-tw/%E6%BC%B3%E5%B7%9E%E8%AF%9D
 [quanzhou-wiki]: https://zh.wikipedia.org/zh-tw/%E6%B3%89%E5%B7%9E%E8%AF%9D
+[singapore-wiki]: https://zh.wikipedia.org/wiki/%E6%96%B0%E5%8A%A0%E5%9D%A1%E7%A6%8F%E5%BB%BA%E8%A9%B1
 [nltk-tokenize]: https://nltk.org/api/nltk.tokenize.html
 [sandhi-wiki]: https://zh.wikipedia.org/zh-tw/%E8%87%BA%E7%81%A3%E8%A9%B1#%E9%80%A3%E8%AE%80%E8%AE%8A%E8%AA%BF:~:text=%E3%80%82%5B144%5D-,%E9%80%A3%E8%AE%80%E8%AE%8A%E8%AA%BF,-%E9%80%A3%E8%AE%80%E8%AE%8A%E8%AA%BF
diff --git a/readme/README-oan.md b/readme/README-oan.md
@@ -132,10 +132,11 @@ c.get(input);
 
 * `south` (預設) - 發音較像[漳州話][zhangzhou-wiki]
 * `north` - 發音較像[泉州話][quanzhou-wiki]
+* `singapore` - 帶有[新加坡特色][singapore-wiki]的泉州話發音
 
-| 文本   | south         | north         |
-| ------ | ------------- | ------------- |
-| 五月節 | Gōo-gue̍h-tseh | Gōo-ge̍h-tsueh |
+| 文本           | south                       | north                       | singapore                  |
+| -------------- | --------------------------- | --------------------------- | -------------------------- |
+| 五月節我啉咖啡 | Gōo-gue̍h-tseh guá lim ka-pi | Gōo-ge̍h-tsueh guá lim ka-pi | Gōo-ge̍h-tsueh uá lim ko-pi |
 
 #### Format
 
@@ -185,9 +186,9 @@ c.get(input);
 
 變調規則也會隨著選的方言而有所改變。
 
-| 文本 | 無變調  | south   | north   |
-| ---- | ------- | ------- | ------- |
-| 台灣 | Tâi-uân | Tāi-uân | Tài-uân |
+| 文本 | 無變調  | south   | north / singapore |
+| ---- | ------- | ------- | ----------------- |
+| 台灣 | Tâi-uân | Tāi-uân | Tài-uân           |
 
 #### Punctuation
 
@@ -279,6 +280,10 @@ c = new Converter({ dialect: 'north' });
 c.get("我欲用箸食魚");
 >> Guá bueh īng tū tsia̍h hû
 
+c = new Converter({ dialect: 'singapore' });
+c.get("我欲用箸食魚");
+>> Uá bueh ēng tū tsia̍h hû
+
 //// Format
 c = new Converter(); // 佇 Tailo 中，format 預設值: mark
 c.get("生日快樂");
@@ -446,5 +451,6 @@ isCjk('我食pháng');
 [ipa-wiki]: https://zh.wikipedia.org/zh-tw/%E5%9C%8B%E9%9A%9B%E9%9F%B3%E6%A8%99
 [zhangzhou-wiki]: https://zh.wikipedia.org/zh-tw/%E6%BC%B3%E5%B7%9E%E8%AF%9D
 [quanzhou-wiki]: https://zh.wikipedia.org/zh-tw/%E6%B3%89%E5%B7%9E%E8%AF%9D
+[singapore-wiki]: https://zh.wikipedia.org/wiki/%E6%96%B0%E5%8A%A0%E5%9D%A1%E7%A6%8F%E5%BB%BA%E8%A9%B1
 [nltk-tokenize]: https://nltk.org/api/nltk.tokenize.html
 [sandhi-wiki]: https://zh.wikipedia.org/zh-tw/%E8%87%BA%E7%81%A3%E8%A9%B1#%E9%80%A3%E8%AE%80%E8%AE%8A%E8%AA%BF:~:text=%E3%80%82%5B144%5D-,%E9%80%A3%E8%AE%80%E8%AE%8A%E8%AA%BF,-%E9%80%A3%E8%AE%80%E8%AE%8A%E8%AA%BF
diff --git a/taibun/index.d.ts b/taibun/index.d.ts
@@ -1,6 +1,6 @@
 interface ConverterOptions {
     system?: 'Tailo' | 'POJ' | 'Zhuyin' | 'TLPA' | 'Pingyim' | 'Tongiong' | 'IPA';
-    dialect?: 'south' | 'north';
+    dialect?: 'south' | 'north' | 'singapore';
     format?: 'mark' | 'number' | 'strip';
     delimiter?: string;
     sandhi?: 'auto' | 'none' | 'excLast' | 'inclLast';

diff --git a/taibun/index.js b/taibun/index.js
@@ -70,7 +70,7 @@ function toTraditional(input) {
 Description: Converts Chinese characters to Taiwanese Hokkien phonetic transcriptions.
 			 Supports both Traditional and Simplified characters.
 Invariant: system = `Tailo` (default), `POJ`, `Zhuyin`, `TLPA`, `Pingyim`, `Tongiong`, `IPA`
-		   dialect = `south` (Zhangzhou-leaning, default), `north` (Quanzhou-leaning)
+		   dialect = `south` (Zhangzhou-leaning, default), `north` (Quanzhou-leaning), `singapore` (Quanzhou-leaning with Singaporean characteristics)
 		   format = `mark` (diacritical), `number` (numeric), `strip` (no tones)
 		   delimiter = String that replaces the default delimiter
 		   sandhi = `auto`, `none`, `excLast`, `inclLast`

diff --git a/tests/singapore.test.js b/tests/singapore.test.js
@@ -46,6 +46,16 @@ test('sandhi', () => {
 	});
 });
 
+test('additional vocabulary', () => {
+	const c = new Converter({ dialect: "Singapore", punctuation: 'none' });
+	const kos = ['我', '你', '甚物', '食物'];
+	const expectedResults = ['uá', 'lú', 'sīm-mi̍h', 'si̍t-bu̍t'];
+
+	kos.forEach((ko, index) => {
+		expect(c.get(ko)).toBe(expectedResults[index]);
+	});
+});
+
 test('kopi', () => {
 	const c = new Converter({ dialect: "Singapore", punctuation: 'none' });
 	const kos = ['咖啡', '烏咖啡', '咖啡杯', '咖哩', '咖咖仔'];