Increased modularity in MistakeFinder, changed Statistics accordingly and made...

Increased modularity in MistakeFinder, changed Statistics accordingly and made MistakeDefinitions.txt more readable.

documentation/MistakeDefinitions.txt

 Stuttering/repetition mistakes:
 
-- 2 or more times the same word in a row in the shadow, while it only appears once in the source. Example: 'en' and 'en' in file 7 (2nd 'en' is repetition)
-- incorrectly shadowed word before a correctly shadowed word is the beginning of the correctly shadowed word. Example: 'toe' and 'toestuurt' in file 7 ('toe' is repetition)
-- incorrectly shadowed word after a correctly shadowed word is the end of the correctly shadowed word. Example: 'bestaat' and 'staat' in file 9 ('staat' is repetition)
-- Same as two above, but with more than 1 word. Example 'je', 'dat', 'je' and 'dat' in file 17 (latter 'je' and 'dat' are repetitions)
\ No newline at end of file
+- 2 or more times the same word in a row in the shadow, while it only appears
+once in the source. Example: 'en' and 'en' in file 7 (2nd 'en' is repetition)
+- incorrectly shadowed word before a correctly shadowed word is the beginning
+of the correctly shadowed word. Example: 'toe' and 'toestuurt' in file 7
+('toe' is repetition)
+- incorrectly shadowed word after a correctly shadowed word is the end of the
+correctly shadowed word. Example: 'bestaat' and 'staat' in file 9
+('staat' is repetition)
+- Same as two above, but with more than 1 word. Example 'je', 'dat', 'je' and
+'dat' in file 17 (latter 'je' and 'dat' are repetitions)
\ No newline at end of file

umbra/mistake_finder.py

@@ -5,24 +5,33 @@ from mistake_enum import Mistake
 class MistakeFinder:
     """Finds the mistakes in already aligned lists of Words"""
 
-    @staticmethod
+    def __init__(self):
+        self.source = None
+        self.shadow = None
+
     def start(self, source, shadow):
         """Find all the mistakes and classify them."""
+        self.source = source
+        self.shadow = shadow
         # Loop over the shadow:
-        for index, word in enumerate(shadow):
-            if not self._check_repetition(word, index):  # If not a repetition,
-                if not self._check_semantic_mistake(word):  # semantic,
-                    if not self._check_phonentic_mistake(word):  # or phonetic,
-                        # ... then shadow word is random:
-                        word.mistake = Mistake.RANDOM
+        for index, word in enumerate(self.shadow):
+            if not word.correct:
+                self._determine_mistake(index, word)
         # Loop over the source:
         for word in source:
             if not word.shadowed and word.mistake is None:
                 # If not yet marked as mistake, then it is skipped:
                 word.mistake = Mistake.SKIPPED
 
-    # def _check_repetition(self, word, index):
-    #
+    def _determine_mistake(self, index, word):
+        if not self._check_repetition(word, index):  # If not a repetition,
+            if not self._check_semantic_mistake(word):  # semantic,
+                if not self._check_phonentic_mistake(word):  # or phonetic,
+                    # ... then shadow word is random:
+                    word.mistake = Mistake.RANDOM
+
+    def _check_repetition(self, word, index):
+        raise
 
     # TODO: WordNet integration. Function below should be usable already!
     # def _check_semantic_mistake(self, shd_word):

umbra/statistics.py

@@ -53,7 +53,8 @@ class Statistics:
                 print(f'source: {s_word.source} shadow: {s_word}')
         correctness = self._strategy.correctly_shadowed(source)
         # TODO: Make the mistake finding work with the statement below
-        # MistakeFinder.start(source_align_em, shadow_align_em)
+        # finder = MistakeFinder()
+        # finder.start(source_align_em, shadow_align_em)
         
         return source_align, shadow_align, correctness