Fixed #1055

Author: wannaphong

pythainlp/util/syllable.py

@@ -81,14 +81,20 @@ def sound_syllable(syllable: str) -> str:
         print(sound_syllable("เลข"))
         # output: dead
     """
+    # if len of syllable < 2
+    if len(syllable) < 2:
+        return "dead"
     # get consonants
     consonants = [i for i in syllable if i in list(thai_consonants_all)]
+    if (len(consonants) == 0 and
+        "อ" in syllable
+        and any((c in set("เ")) for c in syllable)
+        and len(syllable)== 2
+    ):
+        return "live"
     # get spelling consonants
     spelling_consonant = consonants[-1]
-    # if len of syllable < 2
-    if len(syllable) < 2:
-        return "dead"
-    elif (spelling_consonant in _check_2) and (
+    if (spelling_consonant in _check_2) and (
         any((c in set("าีืแูาเโ")) for c in syllable) is False
         and any((c in set("ำใไ")) for c in syllable) is False
         and bool(pattern.search(syllable)) is not True
@@ -122,6 +128,8 @@ def sound_syllable(syllable: str) -> str:
             or any((c in set(short)) for c in syllable)
         ) and len(consonants) < 2:
             return "dead"
+        elif syllable[-1] in set(short):
+            return "dead"
         return "live"
     elif bool(
         re_short.search(syllable)

tests/core/test_util.py

@@ -680,9 +680,14 @@ def test_sound_syllable(self):
             ("เพราะ", "dead"),
             ("เกาะ", "dead"),
             ("แคะ", "dead"),
+            ("ประ", "dead"),
         ]
         for i, j in test:
-            self.assertEqual(sound_syllable(i), j)
+            self.assertEqual(
+                sound_syllable(i),
+                j,
+                f"{i} should be determined to be a '{j}' syllable."
+            )
 
     def test_tone_detector(self):
         data = [
@@ -710,9 +715,14 @@ def test_tone_detector(self):
             ("f", "ผู้"),
             ("h", "ครับ"),
             ("f", "ค่ะ"),
+            ("m", "เอ"),
         ]
         for i, j in data:
-            self.assertEqual(tone_detector(j), i)
+            self.assertEqual(
+                tone_detector(j),
+                i,
+                f"{j} should be determined to be a '{i}' tone."
+            )
 
     def test_syllable_length(self):
         self.assertEqual(syllable_length("มาก"), "long")