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)
