Cleanup

utils/pathfunctions.py

@@ -19,9 +19,6 @@ from itertools import chain
 import ast
 import re
 
-
-
-
 def split_path(path):
     parts = []
     while True:
@@ -64,7 +61,6 @@ def local_common_pass(paths, min_parts=3):
         results[path] = best
     return results
 
-
 def add_longest_common_two_local(df, col="filename_x", new_col="longestcfp", min_parts=3):
     dirs_series = df[col].astype(str).apply(os.path.dirname)
     first_pass = local_common_pass(dirs_series.tolist(), min_parts)
@@ -72,7 +68,6 @@ def add_longest_common_two_local(df, col="filename_x", new_col="longestcfp", min
     df[new_col] = dirs_series.map(lambda d: second_pass[first_pass[d]])
     return df
 
-
 def export_groups_for_review(df, col, group_col, min_number_in_group, path_length_constant):
     """
     Compute longest common paths, group filepaths, write CSV for review.
@@ -88,8 +83,6 @@ def export_groups_for_review(df, col, group_col, min_number_in_group, path_lengt
 
     return filtered, df
 
-
-
 def mask_from_csv(df, csv_path, filepath_col):
     """
     Reads reviewed CSV of groups, keeps only files in approved groups.
@@ -120,7 +113,6 @@ def mask_from_csv(df, csv_path, filepath_col):
     remainder = df[~df[filepath_col].isin(approved_files)].copy()
     return remainder
 
-
 def filter_and_drop(approved, eligiblepaths, min_hashes):
     """
     Filters eligiblepaths to rows where all hashes are in approved,
@@ -136,7 +128,6 @@ def filter_and_drop(approved, eligiblepaths, min_hashes):
     
     return filtered
 
-
 def inspect_parquet(path):
     try:
         df = pd.read_parquet(path)
@@ -149,7 +140,6 @@ def inspect_parquet(path):
         return pd.DataFrame()
 
 
-
 def regulator(paths, case_insensitive=True):
     """
     Build a Python raw string regex that matches any of the given Windows path fragments.