devicer.py 0.1.1__tar.gz → 0.1.3__tar.gz

{devicer_py-0.1.1 → devicer_py-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devicer.py
-Version: 0.1.1
+Version: 0.1.3
 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>
@@ -29,7 +29,7 @@ FP-Devicer is a digital fingerprinting middleware library designed for ease of u
 
 Importing and using the library to compare fingerprints between users is as simple as collecting some user data and running the calculateConfidence function.
 ```python
-from devicer.confidence import calculate_condifence
+from devicer.confidence import calculate_confidence
 
 user1, user2 = {
   """Collected data goes here"""

{devicer_py-0.1.1 → devicer_py-0.1.3}/README.md

@@ -5,7 +5,7 @@ FP-Devicer is a digital fingerprinting middleware library designed for ease of u
 
 Importing and using the library to compare fingerprints between users is as simple as collecting some user data and running the calculateConfidence function.
 ```python
-from devicer.confidence import calculate_condifence
+from devicer.confidence import calculate_confidence
 
 user1, user2 = {
   """Collected data goes here"""

{devicer_py-0.1.1 → devicer_py-0.1.3}/pyproject.toml

@@ -6,7 +6,7 @@ requires = [
 build-backend = "setuptools.build_meta"
 [project]
 name = "devicer.py"
-version = "0.1.1"
+version = "0.1.3"
 authors = [
     {name = "Samuel Roux", email = "sam.roux.com@gmail.com"},
     {name = "Stephen Perso", email = "stephenrperso@gmail.com"},

{devicer_py-0.1.1 → devicer_py-0.1.3}/src/devicer/confidence.py

@@ -1,4 +1,4 @@
-from hashing import get_tlsh_hash, get_hash_difference
+from .hashing import get_tlsh_hash, get_hash_difference
 import math
 
 def compare_dictionaries(data1: dict, data2: dict) -> tuple[int, int]:
@@ -38,14 +38,12 @@ def calculate_confidence(data1: dict, data2: dict) -> float:
     """
     matches, fields = compare_dictionaries(data1, data2)
     
-    if fields == 0:
-        return 0.0
+    if fields == 0 or matches == 0:
+        return 0
 
     hash1 = get_tlsh_hash(str(data1).encode('utf-8'))
     hash2 = get_tlsh_hash(str(data2).encode('utf-8'))
     difference_score = get_hash_difference(hash1, hash2)
-    
-    print(f"Matches: {matches}, Fields: {fields}, Difference Score: {difference_score}")
 
     inverse_match_score = 1 - (matches / fields)
     x = (difference_score / 1.5) * inverse_match_score

{devicer_py-0.1.1 → devicer_py-0.1.3}/src/devicer.py.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devicer.py
-Version: 0.1.1
+Version: 0.1.3
 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>
@@ -29,7 +29,7 @@ FP-Devicer is a digital fingerprinting middleware library designed for ease of u
 
 Importing and using the library to compare fingerprints between users is as simple as collecting some user data and running the calculateConfidence function.
 ```python
-from devicer.confidence import calculate_condifence
+from devicer.confidence import calculate_confidence
 
 user1, user2 = {
   """Collected data goes here"""

{devicer_py-0.1.1 → devicer_py-0.1.3}/src/devicer.py.egg-info/SOURCES.txt

@@ -3,10 +3,7 @@ license.txt
 pyproject.toml
 src/devicer/__init__.py
 src/devicer/confidence.py
-src/devicer/confidence_test.py
-src/devicer/data_test.py
 src/devicer/hashing.py
-src/devicer/hashing_test.py
 src/devicer.py.egg-info/PKG-INFO
 src/devicer.py.egg-info/SOURCES.txt
 src/devicer.py.egg-info/dependency_links.txt

devicer_py-0.1.1/src/devicer/confidence_test.py

@@ -1,112 +0,0 @@
-import unittest
-from confidence import calculate_confidence
-from hashing_test import random_string
-
-sampleData1 = {
-  "fonts": ['Arial', 'Verdana'],
-  "hardware": {
-    "cpu": 'Intel Core i7',
-    "gpu": 'NVIDIA GTX 1080',
-    "ram": 16384
-  },
-  "userAgent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
-  "screen": {
-    "width": 1920,
-    "height": 1080,
-    "colorDepth": 24
-  },
-  "timezone": 'America/New_York',
-  "ip": '157.185.170.244',
-  "languages": ['en-US', 'en'],
-  "plugins": ['Chrome PDF Viewer', 'Shockwave Flash'],
-  "canvasHash": random_string().encode('utf-8'),
-  "audioHash": random_string().encode('utf-8'),
-  "webglHash": random_string().encode('utf-8'),
-}
-
-sampleData2 = {
-  "fonts": ['Arial', 'Verdana'],
-  "hardware": {
-    "cpu": 'Pentium 4',
-    "gpu": 'Intel HD Graphics',
-    "ram": 4096
-  },
-  "userAgent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
-  "screen": {
-    "width": 1280,
-    "height": 720,
-    "colorDepth": 24
-  },
-  "timezone": 'Europe/London',
-  "ip": '178.238.11.6',
-  "languages": ['en-GB', 'en'],
-  "plugins": ['Chrome PDF Viewer', 'Shockwave Flash'],
-  "canvasHash": random_string().encode('utf-8'),
-  "audioHash": random_string().encode('utf-8'),
-  "webglHash": random_string().encode('utf-8'),
-}
-
-
-class TestConfidenceCalculation(unittest.TestCase):
-    def test_confidence_range(self):
-        """
-        Test that the confidence score is between 0 and 100.
-        """
-        confidence = calculate_confidence(sampleData1, sampleData2)
-        self.assertGreaterEqual(confidence, 0, "Confidence score should be at least 0.")
-        self.assertLessEqual(confidence, 100, "Confidence score should not exceed 100.")
-
-    def test_confidence_identical_data(self):
-        """
-        Test that the confidence score is 100 when both data dictionaries are identical.
-        """
-        confidence = calculate_confidence(sampleData1, sampleData1)
-        self.assertEqual(confidence, 100, "Confidence score should be 100 for identical data.")
-    
-    def test_confidence_different_data(self):
-        """
-        Test that the confidence score is less than 10 when data dictionaries are different.
-        """
-        confidence = calculate_confidence(sampleData1, sampleData2)
-        self.assertLess(confidence, 10, "Confidence score should be less than 10 for different data.")
-
-    def test_confidence_similar_data(self):
-        """
-        Test that the confidence score is greater than 80 when data dictionaries are similar.
-        """
-        similar_data = sampleData2.copy()
-        similar_data['hardware']['ram'] = 8192
-        confidence = calculate_confidence(sampleData2, similar_data)
-        self.assertGreater(confidence, 80, "Confidence score should be greater than 80 for similar data.")
-
-    def test_confidence_partial_data(self):
-        """
-        Test that the confidence score is calculated correctly when some fields match.
-        """
-        partial_data = sampleData1.copy()
-        partial_data['hardware']['cpu'] = 'Pentium 4'
-        partial_data['hardware']['gpu'] = 'Intel HD Graphics'
-        partial_data['hardware']['ram'] = 4096
-        partial_data['timezone'] = 'Europe/London'
-        partial_data['ip'] = '178.238.11.6'
-        partial_data['languages'] = ['en-GB', 'en']
-        partial_data['userAgent'] = 'Mozilla/5.0 (compatible; Konqueror/2.2.2-3; Linux)'
-        confidence = calculate_confidence(sampleData1, partial_data)
-        self.assertGreater(confidence, 10, "Confidence score should be greater than 10 for partially matching data.")
-        self.assertLess(confidence, 95, "Confidence score should be less than 95 for partially matching data.")
-
-    def test_confidence_empty_data(self):
-        """
-        Test that the confidence score is 0 when one of the data dictionaries is empty.
-        """
-        confidence = calculate_confidence({}, sampleData2)
-        self.assertEqual(confidence, 0, "Confidence score should be 0 for empty data.")
-        
-        confidence = calculate_confidence(sampleData1, {})
-        self.assertEqual(confidence, 0, "Confidence score should be 0 for empty data.")
-        
-        confidence = calculate_confidence({}, {})
-        self.assertEqual(confidence, 0, "Confidence score should be 0 for both data dictionaries being empty.")
-
-if __name__ == '__main__':
-    unittest.main()

devicer_py-0.1.1/src/devicer/data_test.py

@@ -1,98 +0,0 @@
-import unittest
-import random
-from hashing import get_tlsh_hash, get_hash_difference
-from hashing_test import random_string
-
-sampleData1 = {
-  "fonts": ['Arial', 'Verdana'],
-  "hardware": {
-    "cpu": 'Intel Core i7',
-    "gpu": 'NVIDIA GTX 1080',
-    "ram": 16384
-  },
-  "userAgent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
-  "screen": {
-    "width": 1920,
-    "height": 1080,
-    "colorDepth": 24
-  },
-  "timezone": 'America/New_York',
-  "ip": '157.185.170.244',
-  "languages": ['en-US', 'en'],
-  "plugins": ['Chrome PDF Viewer', 'Shockwave Flash'],
-  "canvasHash": random_string().encode('utf-8'),
-  "audioHash": random_string().encode('utf-8'),
-  "webglHash": random_string().encode('utf-8'),
-}
-
-sampleData2 = {
-  "fonts": ['Arial', 'Verdana'],
-  "hardware": {
-    "cpu": 'Pentium 4',
-    "gpu": 'Intel HD Graphics',
-    "ram": 4096
-  },
-  "userAgent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
-  "screen": {
-    "width": 1280,
-    "height": 720,
-    "colorDepth": 24
-  },
-  "timezone": 'Europe/London',
-  "ip": '178.238.11.6',
-  "languages": ['en-GB', 'en'],
-  "plugins": ['Chrome PDF Viewer', 'Shockwave Flash'],
-  "canvasHash": random_string().encode('utf-8'),
-  "audioHash": random_string().encode('utf-8'),
-  "webglHash": random_string().encode('utf-8'),
-}
-
-
-class TestHashingData(unittest.TestCase):
-    def test_hash_nonempty(self):
-        """
-        Test that the hashing function returns a non-empty string for a non-empty input.
-        """
-        data = str(sampleData1).encode('utf-8')
-        hash_value = get_tlsh_hash(data)
-        self.assertTrue(hash_value, "Hash value should not be empty for non-empty input.")
-
-    def test_hash_identical_inputs(self):
-        """
-        Test that the hashing function returns the same hash for identical inputs.
-        Also checks that the difference between the hashes is zero.
-        """
-        data = str(sampleData1).encode('utf-8')
-        hash1 = get_tlsh_hash(data)
-        hash2 = get_tlsh_hash(data)
-        difference = get_hash_difference(hash1, hash2)
-        self.assertEqual(hash1, hash2, "Hash values should be identical for identical inputs.")
-        self.assertEqual(difference, 0, "Hash difference should be zero for identical inputs.")
-      
-    def test_hash_distance_when_different(self):
-        """
-        Test that the hash difference is non-zero for different inputs.
-        Also checks that the difference is large for sufficiently different inputs.
-        """
-        data1 = str(sampleData1).encode('utf-8')
-        data2 = str(sampleData2).encode('utf-8')
-        hash1 = get_tlsh_hash(data1)
-        hash2 = get_tlsh_hash(data2)
-        difference = get_hash_difference(hash1, hash2)
-        self.assertGreater(difference, 0, "Hash difference should be greater than zero for different inputs.")
-        self.assertGreater(difference, 80, "Hash difference should be large for sufficiently different inputs.")
-
-    def test_hash_distance_when_similar(self):
-        """
-        Test that the hash difference is small for similar inputs.
-        """
-        data1 = str(sampleData1).encode('utf-8')
-        random_index = random.randint(0, len(data1) - 4)
-        data2 = data1[:random_index] + random_string(length=4).encode('utf-8') + data1[random_index + 4:]
-        hash1 = get_tlsh_hash(data1)
-        hash2 = get_tlsh_hash(data2)
-        difference = get_hash_difference(hash1, hash2)
-        self.assertLess(difference, 140, "Hash difference should be small for similar inputs.")
-
-if __name__ == '__main__':
-    unittest.main()

devicer_py-0.1.1/src/devicer/hashing_test.py

@@ -1,66 +0,0 @@
-import unittest
-import random
-from hashing import get_tlsh_hash, get_hash_difference
-
-def random_string(length=524):
-    """
-    Generate a random string of specified length.
-
-    Args:
-        length (int): The length of the string to generate. Default is 524.
-
-    Returns:
-        str: A random string of the specified length.
-    """
-    characters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789[];!@#$%^&*()-_=+|;:,.<>?"
-    return ''.join(random.choice(characters) for _ in range(length))
-
-
-class TestHashingMethods(unittest.TestCase):
-    def test_hash_nonempty(self):
-        """
-        Test that the hashing function returns a non-empty string for a non-empty input.
-        """
-        data = random_string()
-        hash_value = get_tlsh_hash(data.encode('utf-8'))
-        self.assertTrue(hash_value, "Hash value should not be empty for non-empty input.")
-
-    def test_hash_identical_inputs(self):
-        """
-        Test that the hashing function returns the same hash for identical inputs.
-        Also checks that the difference between the hashes is zero.
-        """
-        data = random_string()
-        hash1 = get_tlsh_hash(data.encode('utf-8'))
-        hash2 = get_tlsh_hash(data.encode('utf-8'))
-        difference = get_hash_difference(hash1, hash2)
-        self.assertEqual(hash1, hash2, "Hash values should be identical for identical inputs.")
-        self.assertEqual(difference, 0, "Hash difference should be zero for identical inputs.")
-
-    def test_hash_distance_when_different(self):
-        """
-        Test that the hash difference is non-zero for different inputs.
-        Also checks that the difference is large for sufficiently different inputs.
-        """
-        data1 = random_string()
-        data2 = random_string()
-        hash1 = get_tlsh_hash(data1.encode('utf-8'))
-        hash2 = get_tlsh_hash(data2.encode('utf-8'))
-        difference = get_hash_difference(hash1, hash2)
-        self.assertGreater(difference, 0, "Hash difference should be greater than zero for different inputs.")
-        self.assertGreater(difference, 180, "Hash difference should be large for sufficiently different inputs.")
-
-    def test_hash_distance_when_similar(self):
-        """
-        Test that the hash difference is small for similar inputs.
-        """
-        data1 = random_string()
-        random_index = random.randint(0, len(data1) - 4)
-        data2 = data1[:random_index] + random_string(length=4) + data1[random_index + 4:]
-        hash1 = get_tlsh_hash(data1.encode('utf-8'))
-        hash2 = get_tlsh_hash(data2.encode('utf-8'))
-        difference = get_hash_difference(hash1, hash2)
-        self.assertLess(difference, 200, "Hash difference should be small for similar inputs.")
-
-if __name__ == '__main__':
-    unittest.main()