From d3ec0bd473bae74b0e5db479c25e7a8565799c3e Mon Sep 17 00:00:00 2001
From: Florez Ospina Juan Felipe <juan.florez-ospina@psi.ch>
Date: Tue, 23 Apr 2024 11:05:20 +0200
Subject: [PATCH] Included additional directory path validation based on dir
 keywords

---
 src/hdf5_lib.py | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/src/hdf5_lib.py b/src/hdf5_lib.py
index 1f32524..9cf8080 100644
--- a/src/hdf5_lib.py
+++ b/src/hdf5_lib.py
@@ -232,6 +232,21 @@ import shutil
 #                                          select_dir_keywords = [], 
 #                                          select_file_keywords =[], 
 #                                          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, 
                                           input_file_system_path : str, 
                                           select_dir_keywords = [], 
@@ -320,7 +335,7 @@ def create_hdf5_file_from_filesystem_path(output_filename : str,
                         #    continue
 
                         # 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)
                 else:
                     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]):
                     #tail, dirname = os.path.split(dirpath)
                     #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
 
                 group_name = dirpath.replace(os.sep,'/')
                 group_name = group_name.replace(root_dir.replace(os.sep,'/') + '/', '/')
 
                 # 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('/')
-                if len(tmp_list)>2:
-                    group_name = '/'.join([tmp_list[0],tmp_list[1]])                
+                if len(tmp_list) > offset+1:
+                    group_name = '/'.join([tmp_list[i] for i in range(offset+1)])                
 
                 # Group hierarchy is implicitly defined by the forward slashes
                 if not group_name in h5file.keys():