Pass tests using tokenization.

naive-nlu/tree_nlu/parsing.py

@@ -406,22 +406,33 @@ def all_indexes(collection, element):
 def all_matching_indexes(knowledge_base, collection, element):
     indexes = []
 
-    assert("groups" in element)
+    with session().log('Matching “{}”'.format(element)):
-    element = element["groups"]
+        assert("groups" in element)
-    for i, instance in enumerate(collection):
+        element = element["groups"]
-        if isinstance(instance, dict):
+        for i, instance in enumerate(collection):
-            instance = instance["groups"]
+            session().log('Checking “{}”'.format(instance))
-        elif instance in knowledge_base.knowledge:
-            instance = knowledge_base.knowledge[instance]["groups"]
 
-        intersection = set(instance) & set(element)
+            if isinstance(instance, dict):
-        if (len(intersection) > 0 or (0 == len(instance) == len(element))):
+                instance = instance["groups"]
-            indexes.append((i, intersection))
+            elif instance in knowledge_base.knowledge:
+                session().log('Knowledge about “{}”: ”{}”'.format(instance, knowledge_base.knowledge[instance]))
 
-    return [x[0] for x in sorted(indexes, key=lambda x: len(x[1]), reverse=True)]
+                if "groups" not in knowledge_base.knowledge[instance]:
+                    # This means that is only known as token
+                    # so we should try to avoid using it
+                    continue
+
+                instance = knowledge_base.knowledge[instance]["groups"]
+
+            intersection = set(instance) & set(element)
+            if (len(intersection) > 0 or (0 == len(instance) == len(element))):
+                indexes.append((i, intersection))
+
+        return [x[0] for x in sorted(indexes, key=lambda x: len(x[1]), reverse=True)]
 
 
 def element_matches_groups(knowledge, element: Dict, groups):
+  with session().log("Checking if e “{}” matches groups “{}”".format(element, groups)):
     if isinstance(groups, str) and groups in knowledge:
         return len(knowledge[groups].get("groups", set()) & element['groups']) > 0
     elif isinstance(groups, dict):

naive-nlu/tree_nlu/test.py

@@ -11,9 +11,9 @@ logging.getLogger().setLevel(logging.ERROR)
 
 tests = (
     ("tokenization", tokenization),
-    # ("basic", basic),
+    ("basic", basic),
-    # ("gac 100", gac_100),
+    ("gac 100", gac_100),
-    # ("gac+", gac_extension),
+    ("gac+", gac_extension),
 )
 
 

naive-nlu/tree_nlu/tests/gac_100.py

@@ -668,6 +668,10 @@ base_knowledge = {
     'electricity': {
         "groups": {'power'},
     },
+    'airplanes': {},
+    'white': {
+        'groups': {'property'},
+    }
 }
 
 def main():

naive-nlu/tree_nlu/tests/gac_extension.py

@@ -22,4 +22,5 @@ def ask_then_learn_test(knowledge: KnowledgeBase):
 def main():
     knowledge = gac_100.main()
 
+    knowledge.knowledge['blue'] = {'groups': {'property'}}
     knowledge = ask_then_learn_test(knowledge)