5505-public/dima
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Included additional directory path validation based on dir keywords

Browse Source
This commit is contained in:
florez_j
2024-04-23 11:05:20 +02:00
parent 9d9e9dcfe5
commit d3ec0bd473
1 changed files with 21 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/hdf5_lib.py
View File

@ -232,6 +232,21 @@ import shutil
# select_dir_keywords = [], # select_dir_keywords = [],
# select_file_keywords =[], # select_file_keywords =[],
# top_sub_dir_mask : bool = True): # top_sub_dir_mask : bool = True):
def is_valid_directory_path(dirpath,select_dir_keywords):
activated_keywords = []
for item in select_dir_keywords:
if len(item.split(os.sep))>1:
is_sublist = all([x in dirpath.split(os.sep) for x in item.split(os.sep)])
activated_keywords.append(is_sublist)
else:
activated_keywords.append(item in dirpath)
return any(activated_keywords)
def create_hdf5_file_from_filesystem_path(output_filename : str, def create_hdf5_file_from_filesystem_path(output_filename : str,
input_file_system_path : str, input_file_system_path : str,
select_dir_keywords = [], select_dir_keywords = [],
@ -320,7 +335,7 @@ def create_hdf5_file_from_filesystem_path(output_filename : str,
# continue # continue
# Add files with name, that contains any of the file_keywords # Add files with name, that contains any of the file_keywords
if any([keyword in filename for keyword in select_file_keywords]): if any([keyword in filename for keyword in select_file_keywords]):
file_paths_dict[dirpath].append(filename) file_paths_dict[dirpath].append(filename)
else: else:
file_paths_dict[dirpath] = admissible_filenames file_paths_dict[dirpath] = admissible_filenames
@ -352,16 +367,18 @@ def create_hdf5_file_from_filesystem_path(output_filename : str,
#if (dirpath.count(os.sep) > offset) and not any([item in dirpath for item in select_dir_keywords]): #if (dirpath.count(os.sep) > offset) and not any([item in dirpath for item in select_dir_keywords]):
#tail, dirname = os.path.split(dirpath) #tail, dirname = os.path.split(dirpath)
#if not any([item in dirname for item in select_dir_keywords]): #if not any([item in dirname for item in select_dir_keywords]):
if not any([item in dirpath for item in select_dir_keywords]): #if not any([item in dirpath for item in select_dir_keywords]):
if not is_valid_directory_path(dirpath,select_dir_keywords):
continue continue
group_name = dirpath.replace(os.sep,'/') group_name = dirpath.replace(os.sep,'/')
group_name = group_name.replace(root_dir.replace(os.sep,'/') + '/', '/') group_name = group_name.replace(root_dir.replace(os.sep,'/') + '/', '/')
# flatten group name to one level # flatten group name to one level
offset = sum([len(i.split(os.sep)) if i in dirpath else 0 for i in select_dir_keywords])
tmp_list = group_name.split('/') tmp_list = group_name.split('/')
if len(tmp_list)>2: if len(tmp_list) > offset+1:
group_name = '/'.join([tmp_list[0],tmp_list[1]]) group_name = '/'.join([tmp_list[i] for i in range(offset+1)])
# Group hierarchy is implicitly defined by the forward slashes # Group hierarchy is implicitly defined by the forward slashes
if not group_name in h5file.keys(): if not group_name in h5file.keys():