Merge branch 'master' into filter-operation

Author: alwx

changelog/5587.misc.rst

@@ -0,0 +1,5 @@
+Fixed misleading error message for a situation when ``rasa train nlu --nlu`` is given a file with a wrong format.
+
+Before this change the output message was always: ``No NLU data given.``
+
+Now in case the format is wrong the command prints: ``Path `nlu_data` doesn't contain valid NLU data in it. Please verify the data format. The NLU model training will be skipped now.``

data/test/markdown_single_sections/incorrect_nlu_format.md

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

poetry.lock

@@ -104,7 +104,7 @@ cloudpickle = ">=1.2,<1.4"
 multidict = "^4.6"
 aiohttp = "~3.6"
 questionary = "~1.5.1"
-python-socketio = "~4.4"
+python-socketio = ">=4.4,<4.6"
 python-engineio = ">=3.11,<3.13"
 pydot = "~1.4"
 async_generator = "~1.10"

pyproject.toml

@@ -424,6 +424,13 @@ async def _train_nlu_async(
     fixed_model_name: Optional[Text] = None,
     persist_nlu_training_data: bool = False,
 ):
+    if not nlu_data:
+        print_error(
+            "No NLU data given. Please provide NLU data in order to train "
+            "a Rasa NLU model using the '--nlu' argument."
+        )
+        return
+
     # training NLU only hence the training files still have to be selected
     file_importer = TrainingDataImporter.load_nlu_importer_from_config(
         config, training_data_paths=[nlu_data]
@@ -432,8 +439,9 @@ 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."
+            f"Path '{nlu_data}' doesn't contain valid NLU data in it. "
+            "Please verify the data format. "
+            "The NLU model training will be skipped now."
         )
         return
 

rasa/train.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/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/core/conftest.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 +130,38 @@ 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
+
+
+def test_train_nlu_no_nlu_file_error_message(
+    capsys: CaptureFixture,
+    tmp_path: Text,
+    monkeypatch: MonkeyPatch,
+    default_stack_config: Text,
+):
+    monkeypatch.setattr(tempfile, "tempdir", tmp_path)
+
+    train_nlu(
+        default_stack_config, "", output="test_train_nlu_temp_files_models",
+    )
+
+    captured = capsys.readouterr()
+    assert "No NLU data given" in captured.out