Reverting Back to Working Branch

utils/pathfunctions.py

@@ -57,9 +57,12 @@ def filepathInitialGroup(df: pd.DataFrame):
                 break
         return join_parts(prefix)
 
+<<<<<<< HEAD
 <<<<<<< HEAD
     # Step 6: Group directories by shared prefix
 =======
+=======
+>>>>>>> b187d8cd79c04d364185a4e366d0432841a3372a
     # Step 6: Group directories by shared prefix using custom logic
     """
     Loop through each directory path
@@ -67,7 +70,10 @@ def filepathInitialGroup(df: pd.DataFrame):
     groups: will hold lists of grouped directories.
     used: tracks which directories have already been grouped.
     """
+<<<<<<< HEAD
 >>>>>>> ccbf716 (Zar-Branch (#6))
+=======
+>>>>>>> b187d8cd79c04d364185a4e366d0432841a3372a
     directories = df["directory"].tolist()
     groups = []
     used = set()
@@ -85,6 +91,7 @@ def filepathInitialGroup(df: pd.DataFrame):
         group = [path]
         parts_i = get_parts(path)
 
+<<<<<<< HEAD
 <<<<<<< HEAD
         for j in range(i + 1, len(directories)):
             parts_j = get_parts(directories[j])
@@ -107,6 +114,23 @@ def filepathInitialGroup(df: pd.DataFrame):
             common = os.path.commonprefix([parts_i, parts_j])
         #Apply grouping rules
 >>>>>>> ccbf716 (Zar-Branch (#6))
+=======
+    #Compare with all other directories: For each other directory, split it into parts and find the common prefix (shared folder structure).
+        """
+        Logic:
+        If the directory is deep (>3 parts) and shares at least 3 parts → group it.
+        If it's exactly 3 parts long and shares at least 2 → group it.
+        Or, if it shares all but one part and is deep → group it.
+        These rules are designed to:
+        Group directories that are closely related in structure.
+        Avoid grouping unrelated paths that just happen to start similarly.
+        """  
+
+        for j in range(i + 1, len(directories)):
+            parts_j = get_parts(directories[j])
+            common = os.path.commonprefix([parts_i, parts_j])
+        #Apply grouping rules
+>>>>>>> b187d8cd79c04d364185a4e366d0432841a3372a
             if (len(parts_i) > 3 and len(common) >= 3) or (len(parts_i) == 3 and len(common) >= 2):
                 group.append(directories[j])
                 used.add(directories[j])
@@ -134,11 +158,15 @@ def filepathInitialGroup(df: pd.DataFrame):
     path_eligible = grouped_df[grouped_df["depth"] > 2].drop(columns=["depth"])
     path_ineligible = grouped_df[grouped_df["depth"] <= 2].drop(columns=["depth"])
 
+<<<<<<< HEAD
 <<<<<<< HEAD
     # Step 10: Move entries from eligible to ineligible if grouped_directory contains excluded directories
 =======
     # Step 10: Move entries from eligible to ineligible if grouped_directory contains 'C:\Users' or 'c$\Users'
 >>>>>>> ccbf716 (Zar-Branch (#6))
+=======
+    # Step 10: Move entries from eligible to ineligible if grouped_directory contains 'C:\Users' or 'c$\Users'
+>>>>>>> b187d8cd79c04d364185a4e366d0432841a3372a
     mask = path_eligible["grouped_directory"].str.contains(r"(?i)(?:\\Users|\\c\$\\Users|inetpub\\wwwroot|windows\\temp)", na=False)
     move_to_ineligible = path_eligible[mask]
     path_eligible = path_eligible[~mask]