def get_file_format_extension(resource_name: Text) -> Text:
"""
Get the file extension based on training data format. It supports both a folder and
a file, and tries to guess the format as follows:
- if the resource is a file and has a known format, return this format's extension
- if the resource is a folder and all the resources have the
same known format, return it's extension
- otherwise, default to DEFAULT_FILE_FORMAT (yml).
Args:
resource_name: The name of the resource, can be a file or a folder.
Returns:
The resource file format.
"""
from rasa.shared.nlu.training_data import loading
if resource_name is None or not os.path.exists(resource_name):
raise AttributeError(f"Resource '{resource_name}' does not exist.")
files = rasa.shared.utils.io.list_files(resource_name)
file_formats = list(map(lambda f: loading.guess_format(f), files))
if not file_formats:
return rasa.shared.data.yaml_file_extension()
known_file_formats = {
loading.RASA_YAML: rasa.shared.data.yaml_file_extension(),
}
fformat = file_formats[0]
if all(f == fformat for f in file_formats):
return known_file_formats.get(fformat, rasa.shared.data.yaml_file_extension())
return rasa.shared.data.yaml_file_extension()
def is_nlu_file(file_path: Text) -> bool:
"""Checks if a file is a Rasa compatible nlu file.
Args:
file_path: Path of the file which should be checked.
Returns:
`True` if it's a nlu file, otherwise `False`.
"""
return nlu_loading.guess_format(file_path) != nlu_loading.UNK
def is_nlu_file(file_path: Text) -> bool:
"""Checks if a file is a Rasa compatible nlu file.
Args:
file_path: Path of the file which should be checked.
Returns:
`True` if it's a nlu file, otherwise `False`.
"""
from rasa.shared.nlu.training_data import loading as nlu_loading
return nlu_loading.guess_format(file_path) != nlu_loading.UNK
def get_file_format(resource_name: Text) -> Text:
from rasa.shared.nlu.training_data import loading
if resource_name is None or not os.path.exists(resource_name):
raise AttributeError(f"Resource '{resource_name}' does not exist.")
files = rasa.shared.utils.io.list_files(resource_name)
file_formats = list(map(lambda f: loading.guess_format(f), files))
if not file_formats:
return "json"
fformat = file_formats[0]
if fformat in [loading.MARKDOWN, loading.RASA_YAML] and all(
f == fformat for f in file_formats):
return fformat
return "json"
def test_guess_format_from_non_existing_file_path():
assert guess_format("not existing path") == UNK
