devicer.py 0.1.6__tar.gz → 0.2.0__tar.gz

{devicer_py-0.1.6 → devicer_py-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devicer.py
-Version: 0.1.6
+Version: 0.2.0
 Summary: Open-Source Python Middleware for Digital Fingerprinting
 Author: One anonymous contributor
 Author-email: Samuel Roux <sam.roux.com@gmail.com>, Stephen Perso <stephenrperso@gmail.com>

{devicer_py-0.1.6 → devicer_py-0.2.0}/pyproject.toml

@@ -6,7 +6,7 @@ requires = [
 build-backend = "setuptools.build_meta"
 [project]
 name = "devicer.py"
-version = "0.1.6"
+version = "0.2.0"
 authors = [
     {name = "Samuel Roux", email = "sam.roux.com@gmail.com"},
     {name = "Stephen Perso", email = "stephenrperso@gmail.com"},

{devicer_py-0.1.6 → devicer_py-0.2.0}/src/devicer/confidence.py

@@ -1,59 +1,72 @@
 from .hashing import get_tlsh_hash, get_hash_difference
 import math
 
-def compare_lists(data1: list, data2: list) -> tuple[int, int]:
+def compare_lists(data1: list, data2: list, max_depth: int = 5) -> tuple[int, int]:
     """
     Compare two lists and return the count of matching elements and total elements.
     
     Args:
         data1 (list): First list containing data.
         data2 (list): Second list containing data.
+        max_depth (int): Maximum depth to compare nested lists. Default is 5.
     
     Returns:
         tuple: A tuple containing the count of matching elements and total elements compared.
     """
     fields = 0
     matches = 0
-    max_length = max(len(data1), len(data2))
+
+    if max_depth <= 0:
+        return matches, fields
+
+    sorted_data1 = sorted(data1, key=lambda x: str(x) if isinstance(x, (dict, list)) else x)
+    sorted_data2 = sorted(data2, key=lambda x: str(x) if isinstance(x, (dict, list)) else x)
+
+    max_length = min(len(data1), len(data2))
     for i in range(max_length):
-        if data1[i] and data2[i]:
+        if sorted_data1[i] and sorted_data2[i]:
             fields += 1
-            if isinstance(data1[i], dict) and isinstance(data2[i], dict):
-                sub_matches, sub_fields = compare_dictionaries(data1[i], data2[i])
-                matches += sub_matches
+            if isinstance(sorted_data1[i], list) and isinstance(sorted_data2[i], list):
+                sub_matches, sub_fields = compare_lists(sorted_data1[i], sorted_data2[i], max_depth - 1)
                 fields += sub_fields - 1
-            elif isinstance(data1[i], list) and isinstance(data2[i], list):
-                sub_matches, sub_fields = compare_lists(data1[i], data2[i])
                 matches += sub_matches
+            elif isinstance(sorted_data1[i], dict) and isinstance(sorted_data2[i], dict):
+                sub_matches, sub_fields = compare_dictionaries(sorted_data1[i], sorted_data2[i], max_depth - 1)
                 fields += sub_fields - 1
-            if data1[i] == data2[i]:
+                matches += sub_matches
+            if sorted_data1[i] in sorted_data2:
                 matches += 1
     return matches, fields
 
-def compare_dictionaries(data1: dict, data2: dict) -> tuple[int, int]:
+def compare_dictionaries(data1: dict, data2: dict, max_depth: int = 5) -> tuple[int, int]:
     """
     Compare two dictionaries and return the count of matching fields and total fields.
     
     Args:
         data1 (dict): First dictionary containing data.
         data2 (dict): Second dictionary containing data.
+        max_depth (int): Maximum depth to compare nested dictionaries. Default is 5.
     
     Returns:
         tuple: A tuple containing the count of matching fields and total fields compared.
     """
     fields = 0
     matches = 0
+
+    if max_depth <= 0:
+        return matches, fields
+
     for key in data1:
         if key in data2:
             fields += 1
             if isinstance(data1[key], dict) and isinstance(data2[key], dict):
-                sub_matches, sub_fields = compare_dictionaries(data1[key], data2[key])
+                sub_matches, sub_fields = compare_dictionaries(data1[key], data2[key], max_depth - 1)
+                fields += sub_fields - 1
                 matches += sub_matches
-                fields += sub_fields - 1 # Subtract 1 to avoid double counting the key
             elif isinstance(data1[key], list) and isinstance(data2[key], list):
-                sub_matches, sub_fields = compare_lists(data1[key], data2[key])
-                matches += sub_matches
+                sub_matches, sub_fields = compare_lists(data1[key], data2[key], max_depth - 1)
                 fields += sub_fields - 1
+                matches += sub_matches
             if data1[key] == data2[key]:
                 matches += 1
     return matches, fields

{devicer_py-0.1.6 → devicer_py-0.2.0}/src/devicer.py.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devicer.py
-Version: 0.1.6
+Version: 0.2.0
 Summary: Open-Source Python Middleware for Digital Fingerprinting
 Author: One anonymous contributor
 Author-email: Samuel Roux <sam.roux.com@gmail.com>, Stephen Perso <stephenrperso@gmail.com>