Update link references of ownership from nexB to aboutcode-org

Signed-off-by: Chin Yeung Li <[email protected]>
aboutcode-org · Aug 7, 2024 · 5ccab02 · 5ccab02
1 parent 9af4202
commit 5ccab02
Show file tree

Hide file tree

Showing 12 changed files with 67 additions and 40 deletions.
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -1,6 +1,12 @@
 Changelog
 =========
 
+v5.1.1
+------
+
+*2024-08-07* -- Update link references of ownership from nexB to aboutcode-org.
+
+
 v5.1.0
 ------
 

diff --git a/NOTICE b/NOTICE
@@ -2,7 +2,7 @@
 # Copyright (c) nexB Inc. and others.
 # SPDX-License-Identifier: Apache-2.0
 #
-# Visit https://aboutcode.org and https://github.com/nexB/matchcode-toolkit for support and download.
+# Visit https://aboutcode.org and https://github.com/aboutcode-org/matchcode-toolkit for support and download.
 # ScanCode is a trademark of nexB Inc.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");

diff --git a/README.rst b/README.rst
@@ -2,8 +2,8 @@ MatchCode toolkit
 =================
 MatchCode toolkit is a Python library that provides the file and directory
 fingerprinting functionality for `ScanCode toolkit
-<https://github.com/nexB/scancode-toolkit>`_ and `ScanCode.io
-<https://github.com/nexB/scancode.io>`_ by implementing the HaloHash algorithm
+<https://github.com/aboutcode-org/scancode-toolkit>`_ and `ScanCode.io
+<https://github.com/aboutcode-org/scancode.io>`_ by implementing the HaloHash algorithm
 and using it in ScanCode toolkit and ScanCode.io plugins and pipelines.
 
 

diff --git a/setup.cfg b/setup.cfg
@@ -6,7 +6,7 @@ license = Apache-2.0
 description = matchcode-toolkit
 long_description = file:README.rst
 long_description_content_type = text/x-rst
-url = https://github.com/nexB/matchcode-toolkit
+url = https://github.com/aboutcode-org/matchcode-toolkit
 
 author = nexB. Inc. and others
 author_email = [email protected]

diff --git a/src/matchcode_toolkit/fingerprinting.py b/src/matchcode_toolkit/fingerprinting.py
@@ -3,7 +3,7 @@
 # purldb is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/purldb for support or download.
+# See https://github.com/aboutcode-org/purldb for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 

diff --git a/src/matchcode_toolkit/halohash.py b/src/matchcode_toolkit/halohash.py
@@ -3,7 +3,7 @@
 # purldb is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/purldb for support or download.
+# See https://github.com/aboutcode-org/purldb for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 

diff --git a/src/matchcode_toolkit/pipelines/fingerprint_codebase.py b/src/matchcode_toolkit/pipelines/fingerprint_codebase.py
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 #
-# http://nexb.com and https://github.com/nexB/scancode.io
+# http://nexb.com and https://github.com/aboutcode-org/scancode.io
 # The ScanCode.io software is licensed under the Apache License version 2.0.
 # Data generated with ScanCode.io is provided as-is without warranties.
 # ScanCode is a trademark of nexB Inc.
@@ -18,7 +18,7 @@
 # for any legal advice.
 #
 # ScanCode.io is a free software code scanning tool from nexB Inc. and others.
-# Visit https://github.com/nexB/scancode.io for support and download.
+# Visit https://github.com/aboutcode-org/scancode.io for support and download.
 
 from scanpipe.pipelines import Pipeline
 from scanpipe.pipes import matchcode

diff --git a/src/matchcode_toolkit/pipelines/scan_and_fingerprint_package.py b/src/matchcode_toolkit/pipelines/scan_and_fingerprint_package.py
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 #
-# http://nexb.com and https://github.com/nexB/scancode.io
+# http://nexb.com and https://github.com/aboutcode-org/scancode.io
 # The ScanCode.io software is licensed under the Apache License version 2.0.
 # Data generated with ScanCode.io is provided as-is without warranties.
 # ScanCode is a trademark of nexB Inc.
@@ -18,7 +18,7 @@
 # for any legal advice.
 #
 # ScanCode.io is a free software code scanning tool from nexB Inc. and others.
-# Visit https://github.com/nexB/scancode.io for support and download.
+# Visit https://github.com/aboutcode-org/scancode.io for support and download.
 
 from scanpipe.pipelines.scan_single_package import ScanSinglePackage
 from scanpipe.pipes import matchcode

diff --git a/src/matchcode_toolkit/plugin_fingerprint.py b/src/matchcode_toolkit/plugin_fingerprint.py
@@ -3,7 +3,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/scancode-toolkit for support or download.
+# See https://github.com/aboutcode-org/scancode-toolkit for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -40,7 +40,7 @@ class FingerprintScanner(ScanPlugin):
 
     def is_enabled(self, fingerprint, **kwargs):
         return fingerprint
-        
+
     def get_scanner(self, **kwargs):
         return get_file_fingerprint_hashes
 

diff --git a/tests/test_fingerprinting.py b/tests/test_fingerprinting.py
@@ -3,7 +3,7 @@
 # purldb is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/purldb for support or download.
+# See https://github.com/aboutcode-org/purldb for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -31,7 +31,8 @@ def __init__(self, path='', size=0, sha1=''):
 
 
 class TestFingerprintingFunctions(FileBasedTesting):
-    test_data_dir = os.path.join(os.path.dirname(__file__), 'testfiles/fingerprinting')
+    test_data_dir = os.path.join(os.path.dirname(
+        __file__), 'testfiles/fingerprinting')
 
     def test__create_directory_fingerprint(self):
         test_input = [
@@ -48,10 +49,12 @@ def test__create_directory_fingerprint(self):
 
     def test_split_fingerprint(self):
         directory_fingerprint = '0000000410d24471969646cb5402032288493126'
-        indexed_elements_count, bah128 = split_fingerprint(directory_fingerprint)
+        indexed_elements_count, bah128 = split_fingerprint(
+            directory_fingerprint)
 
         expected_indexed_elements_count = 4
-        self.assertEqual(expected_indexed_elements_count, indexed_elements_count)
+        self.assertEqual(expected_indexed_elements_count,
+                         indexed_elements_count)
 
         expected_bah128 = '10d24471969646cb5402032288493126'
         self.assertEqual(expected_bah128, bah128)
@@ -81,7 +84,8 @@ def test_create_structure_fingerprint(self):
             Resource(path='package/index.js', size=608),
             Resource(path='package/package.json', size=677),
         ]
-        fingerprint = create_structure_fingerprint(test_top_resource, test_child_resources)
+        fingerprint = create_structure_fingerprint(
+            test_top_resource, test_child_resources)
         expected_fingerprint = '00000003ce72f4308a1bc1afb0fb47ed590b5c53'
         self.assertEqual(expected_fingerprint, fingerprint)
 
@@ -134,8 +138,10 @@ def test_get_file_fingerprint_hashes_one_line_removed(self):
         result2 = get_file_fingerprint_hashes(test_file2)
         result1 = result1.get('halo1')
         result2 = result2.get('halo1')
-        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(result1)
-        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(result2)
+        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(
+            result1)
+        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(
+            result2)
 
         expected_result1_indexed_elements_count = 6395
         expected_result2_indexed_elements_count = 6388
@@ -147,7 +153,8 @@ def test_get_file_fingerprint_hashes_one_line_removed(self):
         assert result1_fingerprint == expected_result1_fingerprint
         assert result2_fingerprint == expected_result2_fingerprint
 
-        assert byte_hamming_distance(result1_fingerprint, result2_fingerprint) == 2
+        assert byte_hamming_distance(
+            result1_fingerprint, result2_fingerprint) == 2
 
     def test_get_file_fingerprint_hashes_one_line_added(self):
         test_file1 = self.get_test_loc('inflate.c')
@@ -156,8 +163,10 @@ def test_get_file_fingerprint_hashes_one_line_added(self):
         result2 = get_file_fingerprint_hashes(test_file2)
         result1 = result1.get('halo1')
         result2 = result2.get('halo1')
-        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(result1)
-        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(result2)
+        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(
+            result1)
+        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(
+            result2)
 
         expected_result1_indexed_elements_count = 6395
         expected_result2_indexed_elements_count = 6398
@@ -169,4 +178,5 @@ def test_get_file_fingerprint_hashes_one_line_added(self):
         assert result1_fingerprint == expected_result1_fingerprint
         assert result2_fingerprint == expected_result2_fingerprint
 
-        assert byte_hamming_distance(result1_fingerprint, result2_fingerprint) == 3
+        assert byte_hamming_distance(
+            result1_fingerprint, result2_fingerprint) == 3
diff --git a/tests/test_halohash.py b/tests/test_halohash.py
@@ -3,7 +3,7 @@
 # purldb is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/purldb for support or download.
+# See https://github.com/aboutcode-org/purldb for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -85,7 +85,8 @@ def calculate_mean_and_standard_deviation(hamming_distances):
     number_of_hamming_distances = len(hamming_distances)
 
     # 1: Find the mean.
-    mean_hamming_distance = sum(hamming_distances) / number_of_hamming_distances
+    mean_hamming_distance = sum(hamming_distances) / \
+        number_of_hamming_distances
 
     # 2: For each data point, find the square of its distance to the mean, then sum the values.
     s0 = sum(
@@ -103,7 +104,8 @@ def calculate_mean_and_standard_deviation(hamming_distances):
 
 
 class TestHalohash(FileBasedTesting):
-    test_data_dir = os.path.join(os.path.dirname(__file__), 'testfiles/halohash')
+    test_data_dir = os.path.join(
+        os.path.dirname(__file__), 'testfiles/halohash')
 
     def setUp(self):
         words_loc = self.get_test_loc('words.txt')
@@ -128,13 +130,16 @@ def test_halohash_random_delete(self, regen=False):
                         modified_content
                     )
                     number_of_elements = len(modified_content)
-                    hamming_distance_by_number_of_elements[number_of_elements].append(hamming_distance)
-                    modified_content.pop(random.randint(0, len(modified_content) - 1))
+                    hamming_distance_by_number_of_elements[number_of_elements].append(
+                        hamming_distance)
+                    modified_content.pop(random.randint(
+                        0, len(modified_content) - 1))
 
             # Take mean and standard deviation
             results = []
             for number_of_elements, hamming_distances in hamming_distance_by_number_of_elements.items():
-                mean_hamming_distance, standard_deviation = calculate_mean_and_standard_deviation(hamming_distances)
+                mean_hamming_distance, standard_deviation = calculate_mean_and_standard_deviation(
+                    hamming_distances)
                 results.append(
                     {
                         'number of hashed elements': int(number_of_elements),
@@ -143,8 +148,10 @@ def test_halohash_random_delete(self, regen=False):
                     }
                 )
 
-            expected_results_loc = self.get_test_loc(f'{number_of_words}-delete-expected-results.csv')
-            check_results(results, expected_results_loc, ['number of hashed elements', 'mean hamming distance', 'standard deviation'], regen=regen)
+            expected_results_loc = self.get_test_loc(
+                f'{number_of_words}-delete-expected-results.csv')
+            check_results(results, expected_results_loc, [
+                          'number of hashed elements', 'mean hamming distance', 'standard deviation'], regen=regen)
 
     def test_halohash_random_replace(self, regen=False):
         for number_of_words in [500,]:
@@ -165,9 +172,11 @@ def test_halohash_random_replace(self, regen=False):
                         original_hash,
                         modified_content
                     )
-                    hamming_distance_by_number_of_words_replaced[words_replaced].append(hamming_distance)
+                    hamming_distance_by_number_of_words_replaced[words_replaced].append(
+                        hamming_distance)
 
-                    modified_content.pop(random.randint(0, len(modified_content) - 1))
+                    modified_content.pop(random.randint(
+                        0, len(modified_content) - 1))
                     new_word = (
                         subprocess.run(
                             ['shuf', '-n', '1', '/usr/share/dict/american-english'],
@@ -178,14 +187,15 @@ def test_halohash_random_replace(self, regen=False):
                         .strip()
                         .replace('"', '')
                     )
-                    modified_content[random.randint(0, len(modified_content) - 1)] = bytes(new_word, 'utf-8')
+                    modified_content[random.randint(
+                        0, len(modified_content) - 1)] = bytes(new_word, 'utf-8')
                     words_replaced += 1
 
-
             # Take mean and standard deviation
             results = []
             for words_replaced, hamming_distances in hamming_distance_by_number_of_words_replaced.items():
-                mean_hamming_distance, standard_deviation = calculate_mean_and_standard_deviation(hamming_distances)
+                mean_hamming_distance, standard_deviation = calculate_mean_and_standard_deviation(
+                    hamming_distances)
                 results.append(
                     {
                         'words replaced': int(words_replaced),
@@ -194,5 +204,7 @@ def test_halohash_random_replace(self, regen=False):
                     }
                 )
 
-            expected_results_loc = self.get_test_loc(f'{number_of_words}-replaced-expected-results.csv')
-            check_results(results, expected_results_loc, ['words replaced', 'mean hamming distance', 'standard deviation'], regen=regen)
+            expected_results_loc = self.get_test_loc(
+                f'{number_of_words}-replaced-expected-results.csv')
+            check_results(results, expected_results_loc, [
+                          'words replaced', 'mean hamming distance', 'standard deviation'], regen=regen)
diff --git a/tests/test_plugin_fingerprinting.py b/tests/test_plugin_fingerprinting.py
@@ -3,7 +3,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/scancode-toolkit for support or download.
+# See https://github.com/aboutcode-org/scancode-toolkit for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -17,7 +17,6 @@
 from matchcode_toolkit.fingerprinting import get_file_fingerprint_hashes
 
 
-
 """
 These tests spawn new process as if launched from the command line.
 """