Fix Position.after_mora classmethod and add tests

allzweckmesser/model.py

@@ -448,30 +448,48 @@ class Verse:
 class Position:
 
     def __init__(self, reading: Reading, mora: int, word_boundary: bool,
-                 token: Token, syllable: Syllable,
+                 token: Token, syllable: Syllable, punctuation: str = None,
                  meter: '.meters.Meter' = None, element: int = None):
         self.reading = reading
         self.mora = mora
         self.word_boundary = word_boundary
+        self.token = token
+        self.syllable = syllable
+        self.punctuation = punctuation
         self.meter = meter
         self.element = element
 
     @classmethod
     def after_mora(cls, reading: Reading, mora: int) -> 'Position':
         morae = 0
-        position = None
+        punctuation = ''
         for token in reading.tokens:
+            if token.is_punct():
+                punctuation += token.text
             for i, syllable in enumerate(token.syllables):
                 word_boundary = i == 0
-                if morae == mora:
+                if morae == mora and syllable.syllable_length > 0:
                     position = cls(
                         reading=reading, mora=mora, token=token,
                         syllable=syllable, word_boundary=word_boundary,
-                        meter=meter
+                        punctuation=punctuation
                     )
+                    return position
                 else:
                     morae += syllable.syllable_length
-        return position
+                    punctuation = ''
+        else:
+            # The position has not been found. There are two possibilities:
+            if morae == mora:
+                # The position is at the end of the sentence.
+                position = cls(
+                    reading=reading, mora=mora, token=None, syllable=None,
+                    word_boundary=True, punctuation=punctuation
+                )
+                return position
+            else:
+                # There is no syllable boundary at the given mora.
+                return None
 
     @classmethod
     def after_element(cls, reading: Reading, meter: '.meters.Meter',
@@ -483,11 +501,18 @@ class Position:
     def after(cls, type: str, reading: Reading, position_number: int,
              meter: '.meters.Meter') -> 'Position':
         if type == 'mora':
-            return cls.after_mora(*args, reading, position_number)
+            return cls.after_mora(reading, position_number)
         elif type == 'element':
-            return cls.after_element(*args, reading, meter, position_number)
+            return cls.after_element(reading, meter, position_number)
         else:
             raise ValueError(
                 'The after type has to be "mora" or "element", but is {!r}'
                 .format(spec)
             )
+
+    def __repr__(self):
+        return 'Position(' + ', '.join(
+            '{key}={val!r}'.format(key=attr, val=getattr(self, attr))
+            for attr in ['reading', 'mora', 'word_boundary', 'token', 'syllable',
+                         'punctuation', 'meter', 'element']
+        ) + ')'

tests/test_model.py

@@ -3,18 +3,30 @@
 import os.path
 import json
 
+import pytest
+
 import allzweckmesser as azm
 
+Position = azm.model.Position
+
 TEST_DIR = os.path.dirname(__file__)
 
 
+@pytest.fixture()
+def verse_models():
+    verse_filepath = os.path.join(TEST_DIR, 'verses.json')
+    verse_models = azm.model.from_json(verse_filepath)
+    return verse_models
+
+
 def test_import_json():
 
     verse_filepath = os.path.join(TEST_DIR, 'verses.json')
 
     verse_models = azm.model.from_json(verse_filepath)
 
-    verse_list_from_model = [verse_model.to_dict() for verse_model in verse_models]
+    verse_list_from_model = [verse_model.to_dict()
+                             for verse_model in verse_models]
 
     with open(verse_filepath, 'r') as verse_file:
         verse_list_from_json = json.loads(verse_file.read())
@@ -23,10 +35,173 @@ def test_import_json():
 
     for verse in verse_models:
         parsed_verses = azm.scanner.parse_verse(verse)
-    
+
     for verse_model in parsed_verses:
-        #print(json.dumps(json.loads(verse_model.to_json()), indent=4, sort_keys=True))
+        #print(json.dumps(json.loads(verse_model.to_json()), indent=4,
+        #                 sort_keys=True))
         pass
 
+
+def test_position_after_mora(verse_models):
+    hex_reading = verse_models[3].readings[0]
+    begin = Position.after_mora(hex_reading, 0)
+    assert isinstance(begin, Position)
+    assert begin.mora == 0
+    assert begin.word_boundary
+    assert begin.token.text == 'an'
+    assert begin.syllable.text == 'an'
+    assert begin.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 1) is None
+
+    after2 = Position.after_mora(hex_reading, 2)
+    assert isinstance(after2, Position)
+    assert after2.mora == 2
+    assert after2.word_boundary
+    assert after2.token.text == 'quod'
+    assert after2.syllable.text == 'quod'
+    assert after2.punctuation == ','
+
+    after3 = Position.after_mora(hex_reading, 3)
+    assert isinstance(after3, Position)
+    assert after3.mora == 3
+    assert after3.word_boundary
+    assert after3.token.text == 'ubique'
+    assert after3.syllable.text == 'u'
+    assert after3.punctuation == ''
+
+    after4 = Position.after_mora(hex_reading, 4)
+    assert isinstance(after4, Position)
+    assert after4.mora == 4
+    assert not after4.word_boundary
+    assert after4.token.text == 'ubique'
+    assert after4.syllable.text == 'bi'
+    assert after4.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 5) is None
+
+    after6 = Position.after_mora(hex_reading, 6)
+    assert isinstance(after6, Position)
+    assert after6.mora == 6
+    assert not after6.word_boundary
+    assert after6.token.text == 'ubique'
+    assert after6.syllable.text == 'que'
+    assert after6.punctuation == ''
+
+    after7 = Position.after_mora(hex_reading, 7)
+    assert isinstance(after7, Position)
+    assert after7.mora == 7
+    assert after7.word_boundary
+    assert after7.token.text == 'tuum'
+    assert after7.syllable.text == 'tu'
+    assert after7.punctuation == ','
+
+    after8 = Position.after_mora(hex_reading, 8)
+    assert isinstance(after8, Position)
+    assert after8.mora == 8
+    assert not after8.word_boundary
+    assert after8.token.text == 'tuum'
+    assert after8.syllable.text == 'um'
+    assert after8.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 9) is None
+
+    after10 = Position.after_mora(hex_reading, 10)
+    assert isinstance(after10, Position)
+    assert after10.mora == 10
+    assert after10.word_boundary
+    assert after10.token.text == 'tua'
+    assert after10.syllable.text == 'tu'
+    assert after10.punctuation == '?'
+
+    after11 = Position.after_mora(hex_reading, 11)
+    assert isinstance(after11, Position)
+    assert after11.mora == 11
+    assert not after11.word_boundary
+    assert after11.token.text == 'tua'
+    assert after11.syllable.text == 'a'
+    assert after11.punctuation == ''
+
+    after12 = Position.after_mora(hex_reading, 12)
+    assert isinstance(after12, Position)
+    assert after12.mora == 12
+    assert after12.word_boundary
+    assert after12.token.text == 'sunt'
+    assert after12.syllable.text == 'sunt'
+    assert after12.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 13) is None
+
+    after14 = Position.after_mora(hex_reading, 14)
+    assert isinstance(after14, Position)
+    assert after14.mora == 14
+    assert after14.word_boundary
+    assert after14.token.text == 'Heliconia'
+    assert after14.syllable.text == 'He'
+    assert after14.punctuation == ''
+
+    after15 = Position.after_mora(hex_reading, 15)
+    assert isinstance(after15, Position)
+    assert after15.mora == 15
+    assert not after15.word_boundary
+    assert after15.token.text == 'Heliconia'
+    assert after15.syllable.text == 'li'
+    assert after15.punctuation == ''
+
+    after16 = Position.after_mora(hex_reading, 16)
+    assert isinstance(after16, Position)
+    assert after16.mora == 16
+    assert not after16.word_boundary
+    assert after16.token.text == 'Heliconia'
+    assert after16.syllable.text == 'co'
+    assert after16.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 17) is None
+
+    after18 = Position.after_mora(hex_reading, 18)
+    assert isinstance(after18, Position)
+    assert after18.mora == 18
+    assert not after18.word_boundary
+    assert after18.token.text == 'Heliconia'
+    assert after18.syllable.text == 'ni'
+    assert after18.punctuation == ''
+
+    after19 = Position.after_mora(hex_reading, 19)
+    assert isinstance(after19, Position)
+    assert after19.mora == 19
+    assert not after19.word_boundary
+    assert after19.token.text == 'Heliconia'
+    assert after19.syllable.text == 'a'
+    assert after19.punctuation == ''
+
+    after20 = Position.after_mora(hex_reading, 20)
+    assert isinstance(after20, Position)
+    assert after20.mora == 20
+    assert after20.word_boundary
+    assert after20.token.text == 'Tempe'
+    assert after20.syllable.text == 'Tem'
+    assert after20.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 21) is None
+
+    after22 = Position.after_mora(hex_reading, 22)
+    assert isinstance(after22, Position)
+    assert after22.mora == 22
+    assert not after22.word_boundary
+    assert after22.token.text == 'Tempe'
+    assert after22.syllable.text == 'pe'
+    assert after22.punctuation == ''
+
+    assert Position.after_mora(hex_reading, 23) is None
+
+    after24 = Position.after_mora(hex_reading, 24)
+    assert isinstance(after24, Position)
+    assert after24.mora == 24
+    assert after24.word_boundary
+    assert after24.token is None
+    assert after24.syllable is None
+    assert after24.punctuation == '?'
+
+
 if __name__ == "__main__":
     test_import_json()