From 86eb997ada39e7c764da20878ab6845b86971006 Mon Sep 17 00:00:00 2001
From: "HOME-2022\\User" <niradar@gmail.com>
Date: Mon, 3 Jun 2024 17:34:56 +0300
Subject: [PATCH] use dict instead of defaultdict

+ POC to compare it
---
 POCs/dict_vs_defaultdict.py                   | 29 +++++++++++++++++++
 .../duplicates_finder.py                      |  5 ++--
 2 files changed, 32 insertions(+), 2 deletions(-)
 create mode 100644 POCs/dict_vs_defaultdict.py

diff --git a/POCs/dict_vs_defaultdict.py b/POCs/dict_vs_defaultdict.py
new file mode 100644
index 0000000..a29e9f8
--- /dev/null
+++ b/POCs/dict_vs_defaultdict.py
@@ -0,0 +1,29 @@
+import timeit
+from collections import defaultdict
+
+
+def dict_performance(n):
+    regular_dict = {}
+    for i in range(n):
+        if i not in regular_dict:
+            regular_dict[i] = []
+        regular_dict[i].append(i)
+
+
+def defaultdict_performance(n):
+    default_dict = defaultdict(list)
+    for i in range(n):
+        default_dict[i].append(i)
+
+
+if __name__ == '__main__':
+    n = 3000000  # Number of iterations
+    dict_time = timeit.timeit(lambda: dict_performance(n), number=10)
+    defaultdict_time = timeit.timeit(lambda: defaultdict_performance(n), number=10)
+
+    print(f'Time taken by dict: {dict_time:.6f} seconds')
+    print(f'Time taken by defaultdict: {defaultdict_time:.6f} seconds')
+
+# Sample output:
+#   Time taken by dict: 4.709627 seconds
+#   Time taken by defaultdict: 5.102884 seconds
diff --git a/duplicate_files_in_folders/duplicates_finder.py b/duplicate_files_in_folders/duplicates_finder.py
index 24e4b9e..8ce33ea 100644
--- a/duplicate_files_in_folders/duplicates_finder.py
+++ b/duplicate_files_in_folders/duplicates_finder.py
@@ -1,6 +1,5 @@
 import os
 import concurrent.futures
-from collections import defaultdict
 from probables import BloomFilter
 from duplicate_files_in_folders.hash_manager import HashManager
 from duplicate_files_in_folders.file_manager import FileManager
@@ -111,6 +110,8 @@ def aggregate_duplicate_candidates(potential_duplicates: List[Dict], combined: D
     """
     parallel_results = key_func(args, potential_duplicates)
     for file_info_key, file_infos in parallel_results.items():
+        if file_info_key not in combined:
+            combined[file_info_key] = {}
         if key not in combined[file_info_key]:
             combined[file_info_key][key] = []
         for file_info in file_infos:
@@ -134,7 +135,7 @@ def find_duplicates_files_v3(args: Namespace, scan_dir: str, ref_dir: str) -> (D
     potential_ref_duplicates = find_potential_duplicates(scan_stats, ref_stats, args.ignore_diff)
 
     # Aggregate the potential duplicates into one dictionary
-    combined = defaultdict(defaultdict)
+    combined = {}
     combined = aggregate_duplicate_candidates(potential_scan_duplicates, combined, 'scan', args)
     get_keys_function = get_files_keys_parallel \
         if (len(hash_manager.get_hashes_by_folder(ref_dir)) > len(ref_stats) / 2) else get_files_keys