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
def _reader_factory(fformat: Text) -> Optional["TrainingDataReader"]:
"""Generates the appropriate reader class based on the file format."""
from rasa.shared.nlu.training_data.formats import (
RasaYAMLReader,
MarkdownReader,
WitReader,
LuisReader,
RasaReader,
DialogflowReader,
NLGMarkdownReader,
)
reader = None
if fformat == LUIS:
reader = LuisReader()
elif fformat == WIT:
reader = WitReader()
elif fformat in DIALOGFLOW_RELEVANT:
reader = DialogflowReader()
elif fformat == RASA:
reader = RasaReader()
elif fformat == MARKDOWN:
reader = MarkdownReader()
elif fformat == MARKDOWN_NLG:
reader = NLGMarkdownReader()
elif fformat == RASA_YAML:
reader = RasaYAMLReader()
return reader
def guess_format(filename: Text) -> Text:
"""Applies heuristics to guess the data format of a file.
Args:
filename: file whose type should be guessed
Returns:
Guessed file format.
"""
from rasa.shared.nlu.training_data.formats import RasaYAMLReader
guess = UNK
if not os.path.isfile(filename):
return guess
try:
content = rasa.shared.utils.io.read_file(filename)
js = json.loads(content)
except ValueError:
if MarkdownReader.is_markdown_nlu_file(filename):
guess = MARKDOWN
elif NLGMarkdownReader.is_markdown_nlg_file(filename):
guess = MARKDOWN_NLG
elif RasaYAMLReader.is_yaml_nlu_file(filename):
guess = RASA_YAML
else:
for file_format, format_heuristic in _json_format_heuristics.items():
if format_heuristic(js, filename):
guess = file_format
break
logger.debug(f"Training data format of '{filename}' is '{guess}'.")
return guess
def filter(cls, source_path: Path) -> bool:
"""Checks if the given training data file contains NLU data in `Markdown` format
and can be converted to `YAML`.
Args:
source_path: Path to the training data file.
Returns:
`True` if the given file can be converted, `False` otherwise
"""
return MarkdownReader.is_markdown_nlu_file(source_path)
def convert_and_write(cls, source_path: Path, output_path: Path) -> None:
"""Converts the given training data file and saves it to the output directory.
Args:
source_path: Path to the training data file.
output_path: Path to the output directory.
"""
output_nlu_path = cls.generate_path_for_converted_training_data_file(
source_path, output_path)
yaml_training_data = MarkdownReader().read(source_path)
RasaYAMLWriter().dump(output_nlu_path, yaml_training_data)
for lookup_table in yaml_training_data.lookup_tables:
cls._write_nlu_lookup_table_yaml(lookup_table, output_path)
print_success(
f"Converted NLU file: '{source_path}' >> '{output_nlu_path}'.")
def test_skip_markdown_reading_deprecation():
with pytest.warns(None) as warnings:
MarkdownReader(ignore_deprecation_warning=True)
assert not warnings
def test_markdown_reading_deprecation():
with pytest.warns(FutureWarning):
MarkdownReader()
