def download_fasttext_models(self):
"""Perform complete download of fastText models and save
them in appropriate ``cltk_data`` dir.
TODO: Add tests
TODO: Implement ``overwrite``
TODO: error out better or continue to _load_model?
"""
model_url = self._build_fasttext_url()
if not self.interactive:
if not self.silent:
print(
f"CLTK message: Going to download file '{model_url}' to '{self.model_fp} ..."
) # pragma: no cover
get_file_with_progress_bar(model_url=model_url,
file_path=self.model_fp)
else:
print( # pragma: no cover
"CLTK message: This part of the CLTK depends upon word embedding models from the Fasttext project."
) # pragma: no cover
dl_is_allowed = query_yes_no(
f"Do you want to download file '{model_url}' to '{self.model_fp}'?"
) # type: bool
if dl_is_allowed:
get_file_with_progress_bar(model_url=model_url,
file_path=self.model_fp)
else:
raise CLTKException(
f"Download of necessary Stanza model declined for '{self.iso_code}'. Unable to continue with Stanza's processing."
)
def _download_model(self) -> None:
"""Interface with the `stanza` model downloader."""
if not self.interactive:
if not self.silent:
print(
f"CLTK message: Going to download required Stanza models to ``{self.model_path}`` ..."
) # pragma: no cover
stanza.download(lang=self.stanza_code, package=self.treebank)
else:
print( # pragma: no cover
"CLTK message: This part of the CLTK depends upon the Stanza NLP library."
) # pragma: no cover
dl_is_allowed = query_yes_no(
f"CLTK message: Allow download of Stanza models to ``{self.model_path}``?"
) # type: bool
if dl_is_allowed:
stanza.download(lang=self.stanza_code, package=self.treebank)
else:
raise CLTKException(
f"Download of necessary Stanza model declined for '{self.language}'. Unable to continue with Stanza's processing."
)
# if file model still not available after attempted DL, then raise error
if not file_exists(self.model_path):
raise FileNotFoundError(
"Missing required models for ``stanza`` at ``{0}``.".format(
self.model_path
)
)
def _download_nlpl_models(self) -> None:
"""Perform complete download of Word2Vec models and save
them in appropriate ``cltk_data`` dir.
"""
model_url = self.MAP_LANG_TO_URL[self.iso_code]
if not self.interactive:
if not self.silent:
print(
f"CLTK message: Going to download file '{model_url}' to '{self.fp_zip} ..."
) # pragma: no cover
get_file_with_progress_bar(model_url=model_url,
file_path=self.fp_zip)
else:
print( # pragma: no cover
"CLTK message: This part of the CLTK depends upon word embedding models from the NLPL project."
) # pragma: no cover
dl_is_allowed = query_yes_no(
f"Do you want to download file '{model_url}' to '{self.fp_zip}'?"
) # type: bool
if dl_is_allowed:
get_file_with_progress_bar(model_url=model_url,
file_path=self.fp_zip)
else:
raise CLTKException(
f"Download of necessary Stanza model declined for '{self.language}'. Unable to continue with Stanza's processing."
)