From eabd992d1c9c8e7fbcd1d1bb4dd2896d78623873 Mon Sep 17 00:00:00 2001
From: Ilkyu Ju <ju.ilkyu@gmail.com>
Date: Thu, 19 Aug 2021 14:18:33 +0900
Subject: [PATCH] fix: romanization for syllable with a double consonant final

---
 .gitignore                     |  2 ++
 korean_romanizer/pronouncer.py | 41 ++++++++++++++++++----------------
 tests/test_romanizer.py        | 13 +++++++++++
 3 files changed, 37 insertions(+), 19 deletions(-)

diff --git a/.gitignore b/.gitignore
index 2bbdb69..8e5d2c5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,5 @@
 
 *.pyc
 .cache/v/cache/lastfailed
+node_modules/*
+public/build/*
diff --git a/korean_romanizer/pronouncer.py b/korean_romanizer/pronouncer.py
index eeb808e..30f7126 100644
--- a/korean_romanizer/pronouncer.py
+++ b/korean_romanizer/pronouncer.py
@@ -1,17 +1,17 @@
 from korean_romanizer.syllable import Syllable
 
 double_consonant_final = {
-    'ㄳ' : ('ㄱ', 'ㅅ'),
-    'ㄵ' : ('ᆫ', 'ㅈ'),
+    'ᆪ' : ('ᆨ', 'ᆺ'),
+    'ᆬ' : ('ᆫ', 'ᆽ'),
     'ᆭ' : ('ᆫ', 'ᇂ'),
-    'ㄺ' : ('ㄹ', 'ㄱ'),
-    'ㄻ' : ('ㄹ', 'ㅁ'),
-    'ㄼ' : ('ㄹ', 'ㅂ'),
-    'ㄽ' : ('ㄹ', 'ㅅ'),
-    'ㄾ' : ('ㄹ', 'ㅌ'),
-    'ㄿ' : ('ㄹ', 'ㅍ'),
+    'ᆰ' : ('ᆯ', 'ᆨ'),
+    'ᆱ' : ('ᆯ', 'ᆷ'),
+    'ᆲ' : ('ᆯ', 'ᆸ'),
+    'ᆳ' : ('ᆯ', 'ᆻ'),
+    'ᆴ' : ('ᆯ', 'ᇀ'),
+    'ᆵ' : ('ᆯ', 'ᇁ'),
     'ㅀ' : ('ㄹ', 'ᇂ'),
-    'ㅄ' : ('ㅂ', 'ㅅ'),
+    'ᆹ' : ('ᆸ', 'ᆺ'),
     'ㅆ' : ('ㅅ', 'ㅅ')
 }
 
@@ -40,11 +40,13 @@ def final_substitute(self):
             except AttributeError:
                 final_is_before_V = False
 
+            is_last_syllable = syllable.final and next_syllable is None
+
             # 1. 받침 ‘ㄲ, ㅋ’, ‘ㅅ, ㅆ, ㅈ, ㅊ, ㅌ’, ‘ㅍ’은 어말 또는 자음 앞에서 각각 대표음 [ㄱ, ㄷ, ㅂ]으로 발음한다.
             # 2. 겹받침 ‘ㄳ’, ‘ㄵ’, ‘ㄼ, ㄽ, ㄾ’, ‘ㅄ’은 어말 또는 자음 앞에서 각각 [ㄱ, ㄴ, ㄹ, ㅂ]으로 발음한다.
             # 3. 겹받침 ‘ㄺ, ㄻ, ㄿ’은 어말 또는 자음 앞에서 각각 [ㄱ, ㅁ, ㅂ]으로 발음한다.
             # <-> 단, 국어의 로마자 표기법 규정에 의해 된소리되기는 표기에 반영하지 않으므로 제외.
-            if(syllable.final or final_is_before_C):
+            if is_last_syllable or final_is_before_C:
                 if(syllable.final in ['ᆩ', 'ᆿ', 'ᆪ', 'ᆰ']):
                     syllable.final = 'ᆨ'
                 elif(syllable.final in ['ᆺ', 'ᆻ', 'ᆽ', 'ᆾ', 'ᇀ']):
@@ -57,8 +59,7 @@ def final_substitute(self):
                     syllable.final = 'ᆯ'
                 elif(syllable.final in ['ᆱ']):
                     syllable.final = 'ᆷ'
-
-
+            
             # 4. 받침 ‘ㅎ’의 발음은 다음과 같다.
             if syllable.final in ['ᇂ', 'ᆭ', 'ᆶ']:
 
@@ -95,17 +96,19 @@ def final_substitute(self):
                 else:
                     if (syllable.final == 'ᇂ'):
                         syllable.final = None
-            # 5. 홑받침이나 쌍받침이 모음으로 시작된 조사나 어미, 접미사와 결합되는 경우에는,
-            # 제 음가대로 뒤 음절 첫소리로 옮겨 발음한다.
-            if next_syllable and final_is_before_V:
-                if(next_syllable.initial == NULL_CONSONANT and syllable.final not in ["ᆼ", None]): # do nothing if final is ᆼ or null
-                    next_syllable.initial = next_syllable.final_to_initial(syllable.final)
-                    syllable.final = None
 
             # 6. 겹받침이 모음으로 시작된 조사나 어미, 접미사와 결합되는 경우에는,
             # 뒤엣것만을 뒤 음절 첫소리로 옮겨 발음한다.(이 경우, ‘ㅅ’은 된소리로 발음함.)
-            if syllable.final in double_consonant_final:
+            if syllable.final in double_consonant_final and next_syllable.initial == NULL_CONSONANT:
                 double_consonant = double_consonant_final[syllable.final]
                 syllable.final = double_consonant[0]
                 next_syllable.initial = next_syllable.final_to_initial(double_consonant[1])
+
+            # 5. 홑받침이나 쌍받침이 모음으로 시작된 조사나 어미, 접미사와 결합되는 경우에는,
+            # 제 음가대로 뒤 음절 첫소리로 옮겨 발음한다.
+            if next_syllable and final_is_before_V:
+                if(next_syllable.initial == NULL_CONSONANT and syllable.final not in ["ᆼ", None]): # do nothing if final is ᆼ or null
+                    next_syllable.initial = next_syllable.final_to_initial(syllable.final)
+                    syllable.final = None
+                                    
         return self._syllables
diff --git a/tests/test_romanizer.py b/tests/test_romanizer.py
index 66a0630..fa4e59d 100644
--- a/tests/test_romanizer.py
+++ b/tests/test_romanizer.py
@@ -21,6 +21,7 @@ def test_coda_g_d_b():
     assert romanize("바닷가") == "badatga"
     assert romanize("없다") == "eopda"
     assert romanize("앞만") == "apman"
+    assert romanize("읊다") == "eupda"
 
 def test_r_l():
     assert romanize("구리") == "guri"
@@ -34,6 +35,18 @@ def test_next_syllable_null_initial():
     assert romanize("좋아하고") == "joahago"
     assert romanize("좋은") == "joeun"
 
+def test_double_consonant_final_and_next_syllable_null_initial():
+    assert romanize("했었어요") == "haesseosseoyo"
+    assert romanize("없었다") == "eopseotda"
+    assert romanize("앉아봐") == "anjabwa"
+    assert romanize("닭의") == "dalgui"
+    assert romanize("밟아") == "balba"
+    assert romanize("닮았네") == "dalmatne"
+    assert romanize("삯을") == "sakseul"
+    assert romanize("앓았다") == "aratda"
+    assert romanize("읊어 보거라") == "eulpeo bogeora"
+    assert romanize("곬이") == "golssi"
+    assert romanize("훑어보다") == "hulteoboda"
 
 def test_non_syllables():
     assert romanize("ㅠㄴㅁㄱ") == "ㅠㄴㅁㄱ"