async 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.
"""
reader = NLGMarkdownReader()
writer = RasaYAMLWriter()
output_nlg_path = cls.generate_path_for_converted_training_data_file(
source_path, output_path
)
training_data = reader.read(source_path)
converted_responses = {}
for response_name, examples in training_data.responses.items():
new_response_name = cls._normalize_response_name(response_name)
converted_responses[new_response_name] = examples
converted_training_data = TrainingData(responses=converted_responses)
writer.dump(output_nlg_path, converted_training_data)
print_success(f"Converted NLG file: '{source_path}' >> '{output_nlg_path}'.")
def test_markdow_nlg_read_newlines():
md = """
## Ask something
* faq/ask_something
- Super answer in 2\\nlines
"""
reader = NLGMarkdownReader()
result = reader.reads(md)
assert result.responses == {
"faq/ask_something": [{
"text": "Super answer in 2\nlines"
}]
}
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 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.
"""
reader = NLGMarkdownReader()
writer = RasaYAMLWriter()
output_nlg_path = cls.generate_path_for_converted_training_data_file(
source_path, output_path)
yaml_training_data = reader.read(source_path)
writer.dump(output_nlg_path, yaml_training_data)
print_success(
f"Converted NLG file: '{source_path}' >> '{output_nlg_path}'.")
def filter(cls, source_path: Path) -> bool:
"""Checks if the given training data file contains NLG 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 NLGMarkdownReader.is_markdown_nlg_file(source_path)
def test_responses_are_converted_from_markdown():
responses_md = textwrap.dedent("""
## ask name
* chitchat/ask_name
- my name is Sara, Rasa's documentation bot!
""")
result = NLGMarkdownReader().reads(responses_md)
dumped = RasaYAMLWriter().dumps(result)
validation_reader = RasaYAMLReader()
dumped_result = validation_reader.reads(dumped)
assert dumped_result.responses == result.responses
# dumping again should also not change the format
assert dumped == RasaYAMLWriter().dumps(dumped_result)
def test_skip_markdown_reading_deprecation():
with pytest.warns(None) as warnings:
NLGMarkdownReader(ignore_deprecation_warning=True)
assert not warnings
def test_markdown_reading_deprecation():
with pytest.warns(FutureWarning):
NLGMarkdownReader()
