def test_dump_nlu_with_responses():
md = """## intent:greet
- hey
- howdy
- hey there
- hello
- hi
- good morning
- good evening
- dear sir
## intent:chitchat/ask_name
- What's your name?
- What can I call you?
## intent:chitchat/ask_weather
- How's the weather?
- Is it too hot outside?
"""
r = MarkdownReader()
nlu_data = r.reads(md)
dumped = nlu_data.nlu_as_markdown()
assert dumped == md
def test_check_check_correct_entity_annotations(text: Text, warnings: int):
reader = MarkdownReader()
tokenizer = WhitespaceTokenizer()
training_data = reader.reads(text)
tokenizer.train(training_data)
with pytest.warns(UserWarning) as record:
EntityExtractor.check_correct_entity_annotations(training_data)
assert len(record) == warnings
assert all([excerpt in record[0].message.args[0]]
for excerpt in ["Misaligned entity annotation in sentence"])
def test_markdown_order():
r = MarkdownReader()
md = """## intent:z
- i'm looking for a place to eat
- i'm looking for a place in the [north](loc-direction) of town
## intent:a
- intent a
- also very important
"""
training_data = r.reads(md)
assert training_data.nlu_as_markdown() == md
def test_markdown_entity_regex(example: Text, expected_num_entities: int):
r = MarkdownReader()
md = f"""
## intent:test-intent
- {example}
"""
result = r.reads(md)
assert len(result.training_examples) == 1
actual_example = result.training_examples[0]
assert actual_example.data["intent"] == "test-intent"
assert len(actual_example.data.get("entities", [])) == expected_num_entities
def test_markdown_unespace_tokens():
r = MarkdownReader()
md = """## intent:test-intent
- Hi \\t Can you help me?\\n I want to go to [Alexandria]{"entity": "city"}
"""
expected_num_entities = 1
training_data = r.reads(md)
assert len(training_data.training_examples) == 1
actual_example = training_data.training_examples[0]
assert actual_example.data["intent"] == "test-intent"
assert len(actual_example.data.get("entities", [])) == expected_num_entities
