Fixed misleading error message for rasa train nlu

- Clarify a situation when the command is given a file with a wrong format

Author: Alexander Khizov

changelog/5587.misc.rst

@@ -0,0 +1 @@
+Fixed misleading error message for a situation when ``rasa train nlu --nlu`` is given a file with a wrong format.

data/test/markdown_single_sections/incorrect_nlu_format.md

@@ -0,0 +1,4 @@
+## deny
+- non, merci
+- non merci
+- non

examples/formbot/actions.py

@@ -29,7 +29,9 @@ def slot_mappings(self) -> Dict[Text, Union[Dict, List[Dict]]]:
         return {
             "cuisine": self.from_entity(entity="cuisine", not_intent="chitchat"),
             "num_people": [
-                self.from_entity(entity="number", intent=["inform", "request_restaurant"]),
+                self.from_entity(
+                    entity="number", intent=["inform", "request_restaurant"]
+                ),
             ],
             "outdoor_seating": [
                 self.from_entity(entity="seating"),

rasa/train.py

@@ -431,10 +431,16 @@ async def _train_nlu_async(
 
     training_datas = await file_importer.get_nlu_data()
     if training_datas.is_empty():
-        print_error(
-            "No NLU data given. Please provide NLU data in order to train "
-            "a Rasa NLU model using the '--nlu' argument."
-        )
+        if nlu_data:
+            print_error(
+                f"Path '{nlu_data}' doesn't contain valid NLU data in it. "
+                "Please verify the data format."
+            )
+        else:
+            print_error(
+                "No NLU data given. Please provide NLU data in order to train "
+                "a Rasa NLU model using the '--nlu' argument."
+            )
         return
 
     return await _train_nlu_with_validated_data(

tests/conftest.py

@@ -39,6 +39,7 @@
     DEFAULT_STORIES_FILE,
     END_TO_END_STORY_FILE,
     MOODBOT_MODEL_PATH,
+    INCORRECT_NLU_DATA,
 )
 from tests.utilities import update_number_of_epochs
 
@@ -142,6 +143,11 @@ def default_nlu_data() -> Text:
     return DEFAULT_NLU_DATA
 
 
+@pytest.fixture(scope="session")
+def incorrect_nlu_data() -> Text:
+    return INCORRECT_NLU_DATA
+
+
 @pytest.fixture(scope="session")
 def end_to_end_story_file() -> Text:
     return END_TO_END_STORY_FILE

tests/core/conftest.py

@@ -37,6 +37,8 @@
 
 DEFAULT_NLU_DATA = "examples/moodbot/data/nlu.md"
 
+INCORRECT_NLU_DATA = "data/test/markdown_single_sections/incorrect_nlu_format.md"
+
 END_TO_END_STORY_FILE = "data/test_evaluations/end_to_end_story.md"
 
 E2E_STORY_FILE_UNKNOWN_ENTITY = "data/test_evaluations/story_unknown_entity.md"

tests/test_train.py

@@ -3,6 +3,7 @@
 from typing import Text
 
 import pytest
+from _pytest.capture import CaptureFixture
 from _pytest.monkeypatch import MonkeyPatch
 
 import rasa.model
@@ -129,3 +130,22 @@ def test_train_nlu_temp_files(
     )
 
     assert count_temp_rasa_files(tempfile.tempdir) == 0
+
+
+def test_train_nlu_wrong_format_error_message(
+    capsys: CaptureFixture,
+    tmp_path: Text,
+    monkeypatch: MonkeyPatch,
+    default_stack_config: Text,
+    incorrect_nlu_data: Text,
+):
+    monkeypatch.setattr(tempfile, "tempdir", tmp_path)
+
+    train_nlu(
+        default_stack_config,
+        incorrect_nlu_data,
+        output="test_train_nlu_temp_files_models",
+    )
+
+    captured = capsys.readouterr()
+    assert "Please verify the data format" in captured.out