fix domain_label_extractor to deal with frozen config

fkie-cad · Aug 31, 2024 · ea8df41 · ea8df41
1 parent 20860af
commit ea8df41
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 4 deletions.
diff --git a/logprep/processor/domain_label_extractor/processor.py b/logprep/processor/domain_label_extractor/processor.py
@@ -50,7 +50,7 @@
 from logprep.processor.domain_label_extractor.rule import DomainLabelExtractorRule
 from logprep.processor.field_manager.processor import FieldManager
 from logprep.util.getter import GetterFactory
-from logprep.util.helper import add_field_to, get_dotted_field_value, add_and_overwrite
+from logprep.util.helper import add_and_overwrite, add_field_to, get_dotted_field_value
 from logprep.util.validators import list_of_urls_validator
 
 logger = logging.getLogger("DomainLabelExtractor")
@@ -101,7 +101,6 @@ def setup(self):
                         list_path.touch()
                         list_path.write_bytes(GetterFactory.from_string(tld_list).get_raw())
                 downloaded_tld_lists_paths.append(f"file://{str(list_path.absolute())}")
-            self._config.tld_lists = downloaded_tld_lists_paths
             logger.debug("finished tldlists download...")
 
     def _apply_rules(self, event, rule: DomainLabelExtractorRule):

diff --git a/tests/unit/processor/domain_label_extractor/test_domain_label_extractor.py b/tests/unit/processor/domain_label_extractor/test_domain_label_extractor.py
@@ -1,6 +1,7 @@
 # pylint: disable=protected-access
 # pylint: disable=missing-docstring
 
+import copy
 import hashlib
 import os
 import shutil
@@ -347,7 +348,9 @@ def test_setup_downloads_tld_lists_to_separate_process_file(self):
         tld_list_content = tld_list_path.read_bytes()
         expected_checksum = hashlib.md5(tld_list_content).hexdigest()  # nosemgrep
         responses.add(responses.GET, tld_list, tld_list_content)
-        self.object._config.tld_lists = [tld_list]
+        config = copy.deepcopy(self.CONFIG)
+        config["tld_lists"] = [tld_list]
+        self.object = Factory.create({"domain_label_extractor": config})
         self.object.setup()
         logprep_tmp_dir = Path(tempfile.gettempdir()) / "logprep"
         downloaded_file = logprep_tmp_dir / f"{self.object.name}-tldlist-0.dat"
@@ -370,7 +373,9 @@ def test_setup_doesnt_overwrite_already_existing_tld_list_file(self):
         pre_existing_content = "file exists already"
         tld_temp_file.touch()
         tld_temp_file.write_bytes(pre_existing_content.encode("utf8"))
-        self.object._config.tld_lists = [tld_list]
+        config = copy.deepcopy(self.CONFIG)
+        config["tld_lists"] = [tld_list]
+        self.object = Factory.create({"domain_label_extractor": config})
         self.object.setup()
         assert tld_temp_file.exists()
         assert tld_temp_file.read_bytes().decode("utf8") == pre_existing_content