def test_filter_files_orphan_ref():
from utilities.utilities import Utilities
u = Utilities()
data = ['blah.txt', 'blah.ogg', 'orphan.txt']
expected = ['blah.txt', 'blah.ogg']
result = u.filter_files(data)
assert result == expected
def test_filter_files_doc():
from utilities.utilities import Utilities
u = Utilities()
data = ['file.txt', 'hello.doc', 'file.wav']
expected = ['file.txt', 'file.wav']
result = u.filter_files(data)
assert result == expected
raw_file_list = list()
# Get either local files or cloud storage
if not local_files_path:
# Get list of all files in google cloud storage (gcs) bucket
gcs = GCS()
raw_file_list = gcs.get_file_list(cloud_store_uri)
else:
raw_file_list = utilities.local_files(local_files_path)
logger.debug(f'RAW FILE LIST: {raw_file_list}')
# Filter file list
filtered_file_list = utilities.filter_files(raw_file_list, only_transcribe)
if not local_files_path:
final_file_list = [utilities.append_uri(cloud_store_uri, file) for file in filtered_file_list]
else:
final_file_list = filtered_file_list
logger.debug(f'FINAL FILE LIST: {final_file_list}')
# if only doing transcriptions, add diarization and punctuation?
dia = False
punct = False
c = None
if only_transcribe:
dia = input('Add Diarization Y/N ')
if dia.lower() == 'y':
