def batch_profile_factory(batch_profile, base_directory):
"""Wrapper function for getting a batch profile.
Args:
batch_profile (None, string or BatchProfile): indication of the batch profile to use.
If a string is given it is loaded from the users home folder. Else the best matching profile is returned.
base_directory (str): the data folder we want to use the batch profile on.
Returns:
BatchProfile: If the given batch profile is None we return the output from get_best_batch_profile().
If batch profile is a string we use it from the batch profiles loader. Else we return the input.
"""
if batch_profile is None:
return get_best_batch_profile(base_directory)
elif isinstance(batch_profile, str):
return get_batch_profile(batch_profile)()
return batch_profile
def get_best_batch_profile(data_folder):
"""Get the batch profile that best matches the given directory.
Args:
data_folder (str): the directory for which to get the best batch profile.
Returns:
BatchProfile: the best matching batch profile.
"""
profiles = [
get_batch_profile(name)()
for name in get_component_list('batch_profiles')
]
best_crawler = None
best_subjects_count = 0
for profile in profiles:
if profile.is_suitable(data_folder):
tmp_count = len(profile.get_subjects(data_folder))
if tmp_count > best_subjects_count:
best_crawler = profile
best_subjects_count = tmp_count
return best_crawler