fix call auto_rule_corpus_tester with config tuple instead of str (#527)

Co-authored-by: dtrai2 <[email protected]>

CHANGELOG.md

@@ -8,11 +8,12 @@
 ### Improvements
 
 ### Bugfix
+* fix loading of configuration inside the `AutoRuleCorpusTester` for `logprep test integration`
 
 ## v10.0.2
 ### Bugfix
 * fix versioneer import
-* fix logprep does not complain about missing PROMETHEUS_MULTIPROC_DIR 
+* fix logprep does not complain about missing PROMETHEUS_MULTIPROC_DIR
 
 ## v10.0.1
 ### Bugfix
@@ -46,7 +47,7 @@
 * make store_custom in s3, opensearch and elasticsearch connector not call `batch_finished_callback` to prevent data loss that could be caused by partially processed events
 * remove the `schema_and_rule_checker` module
 * rewrite Logprep Configuration object see documentation for more details
-* rewrite Runner 
+* rewrite Runner
 * delete MultiProcessingPipeline class to simplify multiprocesing
 * add FDA to the quickstart setup
 * bump versions for `fastapi` and `aiohttp` to address CVEs

logprep/util/auto_rule_tester/auto_rule_corpus_tester.py

@@ -129,7 +129,7 @@ class RuleCorpusTester:
     _tmp_dir: str
     """ Temporary directory where test files will be saved temporarily """
 
-    _original_config_path: str
+    _original_config_paths: tuple[str]
     """ Path to the original configuration that should be tested """
 
     _input_test_data_path: str
@@ -149,8 +149,8 @@ class TestCase:
         report: List = Factory(list)
         warnings: str = field(default="")
 
-    def __init__(self, config_path, input_test_data_path):
-        self._original_config_path = config_path
+    def __init__(self, config_paths: tuple[str], input_test_data_path: str):
+        self._original_config_paths = config_paths
         self._input_test_data_path = input_test_data_path
         self.log_capture_string = None
 
@@ -193,7 +193,7 @@ def _pipeline(self):
         patched_config.input = {
             "patched_input": {"type": "json_input", "documents_path": str(merged_input_file_path)}
         }
-        config = Configuration.from_sources([self._original_config_path])
+        config = Configuration.from_sources(self._original_config_paths)
         input_config = config.input
         connector_name = list(input_config.keys())[0]
         if "preprocessing" in input_config[connector_name]:

tests/unit/util/test_auto_rule_corpus_tester.py

@@ -15,7 +15,7 @@
 
 @pytest.fixture(name="corpus_tester")
 def fixture_auto_rule_corpus_tester():
-    config_path = "tests/testdata/config/config.yml"
+    config_path = ("tests/testdata/config/config.yml",)
     data_dir = "will be overwritten in test cases"
     corpus_tester = RuleCorpusTester(config_path, data_dir)
     return corpus_tester
@@ -385,7 +385,7 @@ def test_run_with_two_processors_that_have_different_extra_outputs(
         )
         test_config_path = tmp_path / "test_config.yml"
         test_config_path.write_text(json.dumps(config), encoding="utf8")
-        corpus_tester = RuleCorpusTester(str(test_config_path), "")
+        corpus_tester = RuleCorpusTester([str(test_config_path)], "")
         test_data = {
             "input": {
                 "message": "A B",
@@ -450,7 +450,7 @@ def test_corpus_tests_dont_share_cache_between_runs_by_resetting_processors(
         # the cache realizes it as an existing pseudonym already.
         write_test_case_data_tmp_files(test_data_dir, "test_case_one", test_case_data)
         write_test_case_data_tmp_files(test_data_dir, "test_case_two", test_case_data)
-        config_path = "tests/testdata/config/config.yml"
+        config_path = ["tests/testdata/config/config.yml"]
         corpus_tester = RuleCorpusTester(config_path, test_data_dir)
         corpus_tester.run()
         console_output, console_error = capsys.readouterr()
@@ -482,7 +482,7 @@ def test_warnings_are_printed_inside_the_detailed_reports(self, mock_exit, tmp_p
         test_data_dir = tmp_path / "test_data"
         os.makedirs(test_data_dir, exist_ok=True)
         write_test_case_data_tmp_files(test_data_dir, "test_case_one", test_case_data)
-        config_path = "tests/testdata/config/config.yml"
+        config_path = ["tests/testdata/config/config.yml"]
         corpus_tester = RuleCorpusTester(config_path, test_data_dir)
         corpus_tester.run()
         console_output, console_error = capsys.readouterr()