Fix masked license validation test names (#5257)

AUTHORS.rst

@@ -108,3 +108,4 @@ The following organizations or individuals have contributed to ScanCode:
 - Yash Sharma @yasharmaster
 - Yunus Rahbar @yns88
 - Stefano Zacchiroli @zacchiro
+- Harish Wargad @harishwargad

CHANGELOG.rst

@@ -8,6 +8,11 @@ Next release
   ``licensedcode-data``.
   https://github.com/aboutcode-org/scancode-toolkit/pull/5056
 
+- Ensure each license rule has a unique generated validation 
+  test name, by renaming colliding rule files and adding a 
+  regression test to prevent rule name collisions.
+  https://github.com/aboutcode-org/scancode-toolkit/issues/5257
+
 - Improve copyright detection for statements with parens or trailing "authors"
 
 

tests/licensedcode/test_rule_file_names.py

@@ -0,0 +1,21 @@
+from collections import defaultdict
+from pathlib import Path
+
+from commoncode.text import python_safe_name
+from licensedcode.models import rules_data_dir
+
+
+def test_rule_file_names_generate_unique_test_method_names():
+    method_to_files = defaultdict(list)
+
+    for rule_file in Path(rules_data_dir).glob("*.RULE"):
+        method_name = python_safe_name(rule_file.stem)
+        method_to_files[method_name].append(rule_file.name)
+
+    duplicate_names = [
+        (method_name, files)
+        for method_name, files in method_to_files.items()
+        if len(files) > 1
+    ]
+
+    assert not duplicate_names, f"Duplicate test method names found: {duplicate_names}"