Ellipsis

eng_to_ipa/transcribe.py

@@ -27,7 +27,7 @@ def __str__(self):
 
 def preprocess(words):
     """Returns a string of words stripped of punctuation"""
-    punct_str = '!"#$%&\'()*+,-./:;<=>/?@[\\]^_`{|}~«» '
+    punct_str = '!"#$%&\'()*+,-./:;<=>/?@[\\]^_`{|}~«» …'
     return ' '.join([w.strip(punct_str).lower() for w in words.split()])
 
 

tests/test_transcribe.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+
+# USAGE:
+# PYTHONPATH=".." python test_transcribe.py 
+
+from eng_to_ipa import transcribe
+import transcribe_fixtures
+import sys
+
+words6 = "diction… …rocks"
+words6 = [transcribe.preserve_punc(w.lower())[0] for w in words6.split()]
+words6 = [w[1] for w in words6]
+
+ipa6     = [['ˈdɪkʃən'], ['rɑks']]
+
+class TestConversion_default(transcribe_fixtures.BaseConversion):
+    @classmethod
+    def setUpClass(self):
+        self.words6 = words6
+        self.ipa6   = ipa6
+        self.cmu6   = [['d ih1 k sh ah0 n'], ['r aa1 k s']]

tests/transcribe_fixtures.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+
+# USAGE:
+# PYTHONPATH=".." python test_transcribe.py 
+
+from eng_to_ipa import transcribe
+import unittest
+
+class BaseConversion(unittest.TestCase):
+    """Simple unit testing for the transcribe function(s)."""
+
+    def test_get_cmu_ellipsis(self):
+        res1 = transcribe.get_cmu(self.words6, db_type='sql')
+        res2 = transcribe.get_cmu(self.words6, db_type='json')
+        self.assertEqual(res1, self.cmu6)
+        self.assertEqual(res2, self.cmu6)
+        self.assertEqual(res1, res2)
+
+    def test_cmu_to_ipa_ellipsis(self):
+        res1 = transcribe.cmu_to_ipa(self.cmu6, stress_marking='both')
+        self.assertEqual(res1, self.ipa6)