Reimplemented file filtering, first file extension contraints are imposed and then file keyword contraints.

This commit is contained in:
2024-04-03 13:49:16 +02:00
parent 9cde013be0
commit f9b31c06fd

View File

@ -268,24 +268,23 @@ def create_hdf5_file_from_filesystem_path(config_param : dict ,
raise ValueError('input_file_system_path needs to be specified using forward slashes "/".' )
for i, keyword in enumerate(select_dir_keywords):
select_dir_keywords[i] = keyword.replace('/',os.sep)
select_dir_keywords[i] = keyword.replace('/',os.sep)
# Visit each subdirectory from top to bottom, root directory defined by input_file_sytem_path to the lower
# level directories.
with h5py.File(output_filename, 'w') as h5file:
# Constrain walkable paths on the specified directory tree by allowing walks that start from root
# through subdirectories specified by dir_keywords. This improves efficiency especially, in deep
# directory trees with many leaves.
paths = []
if top_sub_dir_mask:
for item in os.listdir(input_file_system_path):
if any([item in keyword for keyword in select_dir_keywords]):
paths.append(os.path.join(input_file_system_path,item))
else:
paths.append(input_file_system_path)
# Visit each subdirectory from top to bottom, root directory defined by input_file_sytem_path to the lower
# level directories.
# Constrain walkable paths on the specified directory tree by allowing walks that start from root
# through subdirectories specified by dir_keywords. This improves efficiency especially, in deep
# directory trees with many leaves.
paths = []
if top_sub_dir_mask:
for item in os.listdir(input_file_system_path):
if any([item in keyword for keyword in select_dir_keywords]):
paths.append(os.path.join(input_file_system_path,item))
else:
paths.append(input_file_system_path)
with h5py.File(output_filename, 'w') as h5file:
for item in paths:
@ -294,23 +293,34 @@ def create_hdf5_file_from_filesystem_path(config_param : dict ,
# Create dictionary with directory-files pairs where files satisfy keyword and admisible type contraints
# It requires an extra pass over directory three and additional memory for dictionary, but it may be useful
# to speed up subsequent step and prune resulting directory tree.
file_paths_dict = {}
if select_file_keywords:
for dirpath, _, filenames_list in os.walk(item,topdown=False):
file_paths_dict[dirpath] = []
for filename in filenames_list:
if not any([ext in filename for ext in admissible_file_ext_list]):
continue
# For each directory and/or subdirectory, keep files that satisfy file_keyword constraints, and store
# (directory_path, suitable files) relationships in a dictionary.
file_paths_dict = {}
check_file_ext = lambda filename: any([ext in filename for ext in admissible_file_ext_list])
for dirpath, _, filenames in os.walk(item,topdown=False):
file_paths_dict[dirpath] = []
# Check files that have an admissible extension and store them in admissible_filenames list
admissible_filenames = []
for fn in filenames:
if check_file_ext(fn):
admissible_filenames.append(fn)
if select_file_keywords: # when select_file_keywords = [], all files are considered
for filename in admissible_filenames:
# Do not consider files with types for which there is still no file_reader. TODO: extend file_reader library.
#if not any([ext in filename for ext in admissible_file_ext_list]):
# continue
# Add files with name, that contains any of the file_keywords
if any([keyword in filename for keyword in select_file_keywords]):
file_paths_dict[dirpath].append(filename)
#admissible_file_ext_list = list(config_file.ext_to_reader_dict.keys())
#for filename in filtered_filename_list.copy():
# if not any([ext in filename for ext in admissible_file_ext_list]):
# filtered_filename_list.remove(filename)
else:
file_paths_dict[dirpath] = admissible_filenames
for node_number, node in enumerate(os.walk(item, topdown=True)):
dirpath, dirnames, filenames_list = node