Added tests for new to_traditional, to_simplified, Tokeniser

taibun/data/words.json

@@ -13364,7 +13364,7 @@
     "雞籠蜂": "ke-lang-phang/kue-lang-phang",
     "加了工": "ke-liáu-kang",
     "加囉嗦": "ke-lo-so",
-    "街裡": "ke-lí-lí/kue-lí-lí",
+    "街裡": "ke-lí/kue-lí",
     "雞鱸": "ke-lôo/kue-lôo",
     "家內": "ke-lāi",
     "家內穡": "ke-lāi-sit",
@@ -13866,7 +13866,7 @@
     "空講": "khang-kóng",
     "空股": "khang-kóo",
     "空拳": "khang-kûn",
-    "空裡": "khang-lí-lí",
+    "空裡": "khang-lí",
     "空閬閬": "khang-lòng-lòng",
     "空勞": "khang-lô",
     "空囉嗦": "khang-lô-so",
@@ -23254,9 +23254,9 @@
     "履歷": "lí-li̍k",
     "履歷表": "lí-li̍k-pió",
     "理落": "lí-lo̍h",
-    "裡": "lí-lí",
+    "裡": "lí",
     "里里擴擴": "lí-lí-khok-khok",
-    "裡外": "lí-lí-lí",
+    "裡外": "lí-guā",
     "李老君": "lí-ló-kun",
     "女郎": "lí-lông/lú-lông",
     "女奴": "lí-lôo/lú-lôo",
@@ -23937,7 +23937,7 @@
     "內陸": "lāi-lio̍k",
     "內亂": "lāi-luān",
     "內里": "lāi-lí",
-    "內裡": "lāi-lí-lí",
+    "內裡": "lāi-lí",
     "內籬仔": "lāi-lî-á",
     "內門": "lāi-mn̂g",
     "內媽": "lāi-má",
@@ -24728,7 +24728,7 @@
     "麻稿": "muâ-kó",
     "麻糊": "muâ-kôo",
     "麻栗樹": "muâ-li̍k-tshiū",
-    "蔴潁": "muâ-muâ-muâ",
+    "蔴潁": "muâ-ínn",
     "麻芳範": "muâ-phang-huān",
     "麻芳斜": "muâ-phang-tshua̍h",
     "瞞騙": "muâ-phiàn",
@@ -29079,7 +29079,7 @@
     "婊囝": "piáu-kiánn",
     "表哥": "piáu-ko",
     "表決": "piáu-kuat",
-    "表裡": "piáu-lí-lí",
+    "表裡": "piáu-lí",
     "表露": "piáu-lōo",
     "表名": "piáu-miâ",
     "表妹": "piáu-muē/piáu-bē",
@@ -30827,7 +30827,7 @@
     "布料": "pòo-liāu",
     "布攄仔": "pòo-lu-á",
     "佈雷": "pòo-luî",
-    "布裡": "pòo-lí-lí",
+    "布裡": "pòo-lí",
     "布里斯瑪": "pòo-lí-su-má",
     "布里斯托": "pòo-lí-su-thuh",
     "布籬仔": "pòo-lî-á",
@@ -35022,7 +35022,7 @@
     "山欖": "suann-lám",
     "山荖葉": "suann-láu-hio̍h",
     "山藍": "suann-lâm",
-    "山裡花": "suann-lí-lí-lí",
+    "山裡花": "suann-lí-hue",
     "山龍": "suann-lîng",
     "山龍眼": "suann-lîng-gíng",
     "山內": "suann-lāi",
@@ -39485,7 +39485,7 @@
     "套口供": "thò-kháu-king",
     "套供": "thò-king",
     "套劇": "thò-kio̍k",
-    "套裡": "thò-lí-lí",
+    "套裡": "thò-lí",
     "套牢": "thò-lô",
     "套利": "thò-lī",
     "套袍": "thò-phâu",
@@ -47562,8 +47562,8 @@
     "妝閣": "tsng-koh",
     "莊官": "tsng-kuann",
     "裝奇做怪": "tsng-kî-tsò-kuài/tsng-kî-tsuè-kuài",
-    "莊裡": "tsng-lí-lí",
-    "莊裡人": "tsng-lí-lí-lí",
+    "莊裡": "tsng-lí",
+    "莊裡人": "tsng-lí-lâng",
     "裝滿": "tsng-muá",
     "裝配": "tsng-phuè/tsng-phè",
     "裝盤": "tsng-puânn",
@@ -51678,7 +51678,7 @@
     "底稿": "té-kó/tué-kó",
     "短裙": "té-kûn",
     "短理": "té-lí",
-    "底裡": "té-lí-lí/tué-lí-lí",
+    "底裡": "té-lí/tué-lí",
     "短路": "té-lōo",
     "短命": "té-miā",
     "短波": "té-pho",
@@ -56000,8 +56000,8 @@
     "南州鄉": "Lâm-tsiu-hiong",
     "南莊": "Lâm-tsng",
     "南莊鄉": "Lâm-tsng-hiong",
-    "楠梓": "Lâm-tsú-tsú",
-    "楠梓區": "Lâm-tsú-tsú-tsú",
+    "楠梓": "Lâm-tsú",
+    "楠梓區": "Lâm-tsú-khu",
     "南靖": "Lâm-tsīng",
     "南台": "Lâm-tâi",
     "南投": "Lâm-tâu",
@@ -57472,7 +57472,7 @@
     "水堀頭": "Tsuí-khut-thâu",
     "水里": "Tsuí-lí",
     "水里鄉": "Tsuí-lí-hiong",
-    "水裡坑": "Tsuí-lí-lí-lí",
+    "水裡坑": "Tsuí-lí-khenn/Tsuí-lí-khinn",
     "水利會": "Tsuí-lī-huē/Tsuí-lī-hē",
     "水利局": "Tsuí-lī-kio̍k",
     "水麵龜": "Tsuí-mī-ku",
@@ -57557,7 +57557,7 @@
     "子貢": "Tsú-kòng",
     "子路": "Tsú-lōo",
     "子張": "Tsú-tiunn",
-    "梓官區": "Tsú-tsú-tsú",
+    "梓官區": "Tsú-kuann-khu",
     "主後": "Tsú-āu",
     "慈惠堂": "Tsû-huī-tn̂g",
     "慈利": "Tsû-lī",
@@ -57862,8 +57862,8 @@
     "溫嶺": "Un-niá",
     "溫州": "Un-tsiu",
     "尉遲": "Ut-tî",
-    "苑裡": "Uán-lí-lí",
-    "苑裡鎮": "Uán-lí-lí-lí",
+    "苑裡": "Uán-lí",
+    "苑裡鎮": "Uán-lí-tìn",
     "遠哲": "Uán-tiat",
     "遠東": "Uán-tong",
     "遠東區": "Uán-tong-khu",

tests/test_additional.py

@@ -5,10 +5,49 @@ def test_convert_simplified():
 	assert(c.get('我爱学语言')) == 'Guá ài o̍h gí-giân'
 
 def test_to_traditional():
-	assert '漢字是台灣用來寫幾若種現代佮古代語文个書寫文字系統' == to_traditional('汉字是台湾用来写几若种现代佮古代语文个书写文字系统')
+	assert to_traditional('干休') == '干休'
+	assert to_traditional('干杯') == '乾杯'
+	assert to_traditional('干部') == '幹部'
+	assert to_traditional('周密') == '周密'
+	assert to_traditional('周期') == '週期'
+	assert to_traditional('天后') == '天后'
+	assert to_traditional('大后日') == '大後日'
+	assert to_traditional('不只') == '不只'
+	assert to_traditional('船只') == '船隻'
+	assert to_traditional('台语') == '台語'
+	assert to_traditional('寝台车') == '寢臺車'
+	assert to_traditional('台面') == '檯面'
+	assert to_traditional('风台') == '風颱'
+	assert to_traditional('两个') == '兩个'
+	assert to_traditional('个人') == '個人'
+
+def test_vars():
+	c = Converter(punctuation='none')
+	assert(c.get('木蝨')) == 'ba̍k-sat'
+	assert(c.get('爲啥物')) == 'uī-siánn-mi̍h'
+	assert(c.get('白癡')) == 'pe̍h-tshi'
+	assert(c.get('牛肉麪')) == 'gû-bah-mī'
+	assert(c.get('臺北人')) == 'Tâi-pak-lâng'
+	assert(c.get('聲説')) == 'siann-sueh'
+	assert(c.get('研鉢')) == 'gíng-puah'
+	assert(c.get('踊躍')) == 'ióng-io̍k'
 
 def test_to_simplified():
-	assert '汉字是台湾用来写几若种现代佮古代语文个书写文字系统' == to_simplified('漢字是臺灣用來寫幾若種現代佮古代語文个書寫文字系統')
+    assert to_simplified('干休') == '干休'
+    assert to_simplified('乾杯') == '干杯'
+    assert to_simplified('幹部') == '干部'
+    assert to_simplified('周密') == '周密'
+    assert to_simplified('週期') == '周期'
+    assert to_simplified('天后') == '天后'
+    assert to_simplified('大後日') == '大后日'
+    assert to_simplified('不只') == '不只'
+    assert to_simplified('船隻') == '船只'
+    assert to_simplified('台語') == '台语'
+    assert to_simplified('寢臺車') == '寝台车'
+    assert to_simplified('檯面') == '台面'
+    assert to_simplified('風颱') == '风台'
+    assert to_simplified('兩个') == '两个'
+    assert to_simplified('個人') == '个人'
 
 def test_is_cjk():
 	assert is_cjk('漢') == True

tests/test_tokenisation.py

@@ -13,4 +13,9 @@ def test_suffix():
 def test_simplified():
 	t = Tokeniser()
 	assert ['汉字', '是', '用来', '写', '几若', '种', '现代', '佮', '古代', '语文', '个', '书写', '文字', '系统', '。'] == t.tokenise('汉字是用来写几若种现代佮古代语文个书写文字系统。')
-	assert ['现代', '个', '中国', '、', '日本', '、', '韩国', '、', '台湾', '拢', '有', '使用', '汉字'] == t.tokenise('现代个中国、日本、韩国、台湾拢有使用汉字')
+	assert ['现代', '个', '中国', '、', '日本', '、', '韩国', '、', '台湾', '拢', '有', '使用', '汉字'] == t.tokenise('现代个中国、日本、韩国、台湾拢有使用汉字')
+
+def test_false():
+	t = Tokeniser(False)
+	assert ['漢字', '是', '用來', '寫', '幾若', '種', '現代', '佮', '古代', '語文', '个', '書寫', '文字', '系統', '。'] == t.tokenise('汉字是用来写几若种现代佮古代语文个书写文字系统。')
+	assert ['現代', '个', '中國', '、', '日本', '、', '韓國', '、', '台灣', '攏', '有', '使用', '漢字'] == t.tokenise('现代个中国、日本、韩国、台湾拢有使用汉字')