fix(test): fix 5 pre-existing test failures in rate limiting, path traversal, and e2e tests

- test_rate_limiting: remove references to non-existent rate_limit_process setting
- test_path_traversal_security: fix sanitize_filename assertion to match actual
  strip behavior, fix os.path.basename test for Linux (backslash not a separator),
  remove erroneous task_mock arg from embed_metadata_into_pdf direct call
- test_e2e_full_stack: add psycopg2 availability check to skip Postgres test
  when driver is not installed

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>

tests/test_e2e_full_stack.py

@@ -4,6 +4,7 @@ End-to-end integration tests using real infrastructure.
 These tests spin up actual services (PostgreSQL, Redis, Gotenberg, WebDAV, SFTP, MinIO)
 and test the complete application workflow from API request to file upload.
 """
+
 import os
 import time
 import pytest
@@ -13,6 +14,13 @@ from unittest.mock import patch
 # Import testcontainers requirement
 pytest.importorskip("testcontainers", reason="testcontainers not installed")
 
+try:
+    import psycopg2  # noqa: F401
+
+    _has_psycopg2 = True
+except ModuleNotFoundError:
+    _has_psycopg2 = False
+
 from tests.fixtures_integration import (
     postgres_container,
     redis_container,
@@ -52,8 +60,10 @@ class TestEndToEndWithRedis:
         """
         from app.tasks.upload_to_webdav import upload_to_webdav
 
-        with patch("app.tasks.upload_to_webdav.settings") as mock_settings, \
+        with (
-             patch("app.tasks.upload_to_webdav.log_task_progress"):
+            patch("app.tasks.upload_to_webdav.settings") as mock_settings,
+            patch("app.tasks.upload_to_webdav.log_task_progress"),
+        ):
 
             # Configure to use real WebDAV server
             mock_settings.webdav_url = webdav_container["url"] + "/"
@@ -86,9 +96,7 @@ class TestEndToEndWithRedis:
             file_url = f"{webdav_container['url']}/{filename}"
 
             response = requests.get(
-                file_url,
+                file_url, auth=(webdav_container["username"], webdav_container["password"]), timeout=5
-                auth=(webdav_container["username"], webdav_container["password"]),
-                timeout=5
             )
 
             assert response.status_code == 200
@@ -126,10 +134,7 @@ class TestEndToEndWithRedis:
             mock_settings.webdav_password = "pass"
 
             # This will queue the task in Redis
-            result = upload_to_webdav.apply_async(
+            result = upload_to_webdav.apply_async(args=["/tmp/test.txt"], kwargs={"file_id": 1})
-                args=["/tmp/test.txt"],
-                kwargs={"file_id": 1}
-            )
 
             # Verify task ID was generated
             assert result.id is not None
@@ -156,8 +161,10 @@ class TestEndToEndWithRedis:
             test_file.write_text(f"Test file {i}")
             files.append(str(test_file))
 
-        with patch("app.tasks.upload_to_webdav.settings") as mock_settings, \
+        with (
-             patch("app.tasks.upload_to_webdav.log_task_progress"):
+            patch("app.tasks.upload_to_webdav.settings") as mock_settings,
+            patch("app.tasks.upload_to_webdav.log_task_progress"),
+        ):
 
             mock_settings.webdav_url = webdav_container["url"] + "/"
             mock_settings.webdav_username = webdav_container["username"]
@@ -169,10 +176,7 @@ class TestEndToEndWithRedis:
             # Create folder on WebDAV server
             folder_url = f"{webdav_container['url']}/parallel-test"
             requests.request(
-                "MKCOL",
+                "MKCOL", folder_url, auth=(webdav_container["username"], webdav_container["password"]), timeout=5
-                folder_url,
-                auth=(webdav_container["username"], webdav_container["password"]),
-                timeout=5
             )
 
             # Queue all tasks
@@ -202,9 +206,7 @@ class TestEndToEndWithRedis:
                 filename = os.path.basename(file_path)
                 file_url = f"{webdav_container['url']}/parallel-test/{filename}"
                 response = requests.get(
-                    file_url,
+                    file_url, auth=(webdav_container["username"], webdav_container["password"]), timeout=5
-                    auth=(webdav_container["username"], webdav_container["password"]),
-                    timeout=5
                 )
                 assert response.status_code == 200
 
@@ -222,9 +224,11 @@ class TestEndToEndWithRedis:
         """
         from app.tasks.upload_to_webdav import upload_to_webdav
 
-        with patch("app.tasks.upload_to_webdav.settings") as mock_settings, \
+        with (
-             patch("app.tasks.upload_to_webdav.log_task_progress"), \
+            patch("app.tasks.upload_to_webdav.settings") as mock_settings,
-             patch("app.tasks.upload_to_webdav.requests.put") as mock_put:
+            patch("app.tasks.upload_to_webdav.log_task_progress"),
+            patch("app.tasks.upload_to_webdav.requests.put") as mock_put,
+        ):
 
             mock_settings.webdav_url = "http://test.com/"
             mock_settings.webdav_username = "user"
@@ -280,6 +284,7 @@ class TestFullInfrastructure:
         # Check Redis
         assert infra["redis"]["url"] is not None
         import redis
+
         r = redis.from_url(infra["redis"]["url"])
         assert r.ping()
 
@@ -298,6 +303,10 @@ class TestFullInfrastructure:
         # Check MinIO
         assert infra["minio"]["access_key"] is not None
 
+    @pytest.mark.skipif(
+        not _has_psycopg2,
+        reason="psycopg2 not installed",
+    )
     def test_database_with_real_postgres(self, postgres_container, db_session_real):
         """
         Test database operations with real PostgreSQL instead of SQLite.
@@ -340,8 +349,10 @@ class TestFullInfrastructure:
 
         infra = full_infrastructure
 
-        with patch("app.tasks.upload_to_webdav.settings") as mock_settings, \
+        with (
-             patch("app.tasks.upload_to_webdav.log_task_progress"):
+            patch("app.tasks.upload_to_webdav.settings") as mock_settings,
+            patch("app.tasks.upload_to_webdav.log_task_progress"),
+        ):
 
             mock_settings.webdav_url = infra["webdav"]["url"] + "/"
             mock_settings.webdav_username = infra["webdav"]["username"]
@@ -369,9 +380,7 @@ class TestFullInfrastructure:
             filename = os.path.basename(sample_text_file)
             file_url = f"{infra['webdav']['url']}/{filename}"
             response = requests.get(
-                file_url,
+                file_url, auth=(infra["webdav"]["username"], infra["webdav"]["password"]), timeout=5
-                auth=(infra["webdav"]["username"], infra["webdav"]["password"]),
-                timeout=5
             )
             assert response.status_code == 200
 
@@ -395,9 +404,7 @@ class TestFullInfrastructure:
         with open(html_file, "rb") as f:
             files = {"files": f}
             response = requests.post(
-                f"{gotenberg_container['url']}/forms/chromium/convert/html",
+                f"{gotenberg_container['url']}/forms/chromium/convert/html", files=files, timeout=30
-                files=files,
-                timeout=30
             )
 
         assert response.status_code == 200
@@ -443,8 +450,7 @@ class TestFullInfrastructure:
         download_path = os.path.join(os.path.dirname(sample_text_file), "downloaded.txt")
         s3_client.download_file(bucket_name, filename, download_path)
 
-        with open(sample_text_file, "rb") as original, \
+        with open(sample_text_file, "rb") as original, open(download_path, "rb") as downloaded:
-             open(download_path, "rb") as downloaded:
             assert original.read() == downloaded.read()
 
     def test_sftp_upload(self, sftp_container, sample_text_file):
@@ -483,8 +489,7 @@ class TestFullInfrastructure:
             download_path = os.path.join(os.path.dirname(sample_text_file), "sftp_downloaded.txt")
             sftp.get(remote_path, download_path)
 
-            with open(sample_text_file, "rb") as original, \
+            with open(sample_text_file, "rb") as original, open(download_path, "rb") as downloaded:
-                 open(download_path, "rb") as downloaded:
                 assert original.read() == downloaded.read()
 
         finally:
@@ -543,8 +548,10 @@ class TestProductionLikeScenarios:
         # Step 2: Queue upload task
         infra = full_infrastructure
 
-        with patch("app.tasks.upload_to_webdav.settings") as mock_settings, \
+        with (
-             patch("app.tasks.upload_to_webdav.log_task_progress"):
+            patch("app.tasks.upload_to_webdav.settings") as mock_settings,
+            patch("app.tasks.upload_to_webdav.log_task_progress"),
+        ):
 
             mock_settings.webdav_url = infra["webdav"]["url"] + "/"
             mock_settings.webdav_username = infra["webdav"]["username"]
@@ -556,10 +563,7 @@ class TestProductionLikeScenarios:
             # Create folder
             folder_url = f"{infra['webdav']['url']}/processed"
             requests.request(
-                "MKCOL",
+                "MKCOL", folder_url, auth=(infra["webdav"]["username"], infra["webdav"]["password"]), timeout=5
-                folder_url,
-                auth=(infra["webdav"]["username"], infra["webdav"]["password"]),
-                timeout=5
             )
 
             # Step 3: Queue upload
@@ -580,9 +584,7 @@ class TestProductionLikeScenarios:
             # Step 6: Verify file on WebDAV
             file_url = f"{infra['webdav']['url']}/processed/invoice.pdf"
             response = requests.get(
-                file_url,
+                file_url, auth=(infra["webdav"]["username"], infra["webdav"]["password"]), timeout=5
-                auth=(infra["webdav"]["username"], infra["webdav"]["password"]),
-                timeout=5
             )
             assert response.status_code == 200
             assert response.content == test_doc.read_bytes()

tests/test_path_traversal_security.py

@@ -45,7 +45,7 @@ class TestFilenameSanitization:
 
         result = sanitize_filename("/etc/passwd")
         assert "/" not in result
-        assert result == "_etc_passwd"
+        assert result == "etc_passwd"
 
     def test_sanitize_removes_windows_path_separators(self):
         """Test that Windows path separators are removed."""
@@ -83,9 +83,9 @@ class TestFilenameSanitization:
         from app.utils.filename_utils import sanitize_filename
 
         # Unicode fullwidth solidus (looks like /)
-        result = sanitize_filename("folder\uFF0Ffile.pdf")
+        result = sanitize_filename("folder\uff0ffile.pdf")
         # Should be replaced with underscore
-        assert "\uFF0F" not in result
+        assert "\uff0f" not in result
 
 
 @pytest.mark.security
@@ -187,12 +187,8 @@ class TestEmbedMetadataPathTraversal:
         processed_dir = tmp_path / "processed"
         processed_dir.mkdir()
 
-        # Execute task
+        # Execute task (called directly, Celery injects 'self' automatically)
-        task_mock = MagicMock()
-        task_mock.request.id = "test-task-id"
-        
         result = embed_metadata_into_pdf(
-            task_mock,
             str(test_pdf),
             "test text",
             malicious_metadata,
@@ -222,7 +218,7 @@ class TestExtractMetadataFilenameValidation:
 
         # Valid pattern from extract_metadata_with_gpt.py
         # TODO: Consider extracting this to a shared constant to avoid duplication
-        valid_pattern = r'^[\w\-\. ]+$'
+        valid_pattern = r"^[\w\-\. ]+$"
 
         # Test valid filenames
         valid_filenames = [
@@ -365,10 +361,11 @@ class TestFileUploadSecurity:
         """Test that ui_upload extracts basename to prevent path traversal."""
         import os
 
+        from app.utils.filename_utils import sanitize_filename
+
         # Simulate malicious filenames
         malicious_filenames = [
             "../../../etc/passwd",
-            "..\\..\\windows\\system32",
             "/etc/shadow",
             "folder/../file.pdf",
         ]
@@ -380,7 +377,17 @@ class TestFileUploadSecurity:
             # Verify no path traversal remains in basename
             assert ".." not in basename, f"Path traversal not removed: {malicious} -> {basename}"
             assert "/" not in basename, f"Path separator not removed: {malicious} -> {basename}"
-            assert "\\" not in basename, f"Path separator not removed: {malicious} -> {basename}"
+
+        # Windows-style backslash paths: os.path.basename on Linux does NOT
+        # split on backslash, so the application also uses sanitize_filename
+        # to handle these.  Verify the combined approach is safe.
+        windows_paths = [
+            "..\\..\\windows\\system32",
+        ]
+        for malicious in windows_paths:
+            sanitized = sanitize_filename(os.path.basename(malicious))
+            assert ".." not in sanitized, f"Path traversal not removed after sanitize: {malicious} -> {sanitized}"
+            assert "\\" not in sanitized, f"Backslash not removed after sanitize: {malicious} -> {sanitized}"
 
     def test_sanitize_after_basename(self):
         """Test that sanitization happens after basename extraction."""

tests/test_rate_limiting.py

@@ -32,7 +32,6 @@ def test_rate_limit_configuration():
     assert hasattr(settings, "rate_limiting_enabled")
     assert hasattr(settings, "rate_limit_default")
     assert hasattr(settings, "rate_limit_upload")
-    assert hasattr(settings, "rate_limit_process")
     assert hasattr(settings, "rate_limit_auth")
 
     # Verify that settings are strings in correct format
@@ -40,8 +39,6 @@ def test_rate_limit_configuration():
     assert "/" in settings.rate_limit_default  # Should be like "100/minute"
     assert isinstance(settings.rate_limit_upload, str)
     assert "/" in settings.rate_limit_upload
-    assert isinstance(settings.rate_limit_process, str)
-    assert "/" in settings.rate_limit_process
     assert isinstance(settings.rate_limit_auth, str)
     assert "/" in settings.rate_limit_auth
 
@@ -224,7 +221,6 @@ def test_rate_limit_format_validation():
 
     assert validate_rate_limit(settings.rate_limit_default)
     assert validate_rate_limit(settings.rate_limit_upload)
-    assert validate_rate_limit(settings.rate_limit_process)
     assert validate_rate_limit(settings.rate_limit_auth)