fix: Fix athena connection and scanning logic.

Update dbcat to 0.10.6 which has part of the fixes.
Fix cli and API to make access and secret keys optional

Fix #153
Fix #155

piicatcher/__init__.py

@@ -1,2 +1,2 @@
 # flake8: noqa
-__version__ = "0.17.3"
+__version__ = "0.17.4"

piicatcher/api.py

@@ -375,10 +375,10 @@ def scan_snowflake(
 def scan_athena(
     catalog_params: Dict[str, Any],
     name: str,
-    aws_access_key_id: str,
-    aws_secret_access_key: str,
     region_name: str,
     s3_staging_dir: str,
+    aws_access_key_id: Optional[str] = None,
+    aws_secret_access_key: Optional[str] = None,
     scan_type: ScanTypeEnum = ScanTypeEnum.shallow,
     incremental: bool = True,
     output_format: OutputFormat = OutputFormat.tabular,

piicatcher/cli.py

@@ -330,8 +330,8 @@ def snowflake(
 @app.command()
 def athena(
     name: str = typer.Option(..., help="A memorable name for the database"),
-    aws_access_key_id: str = typer.Option(..., help="AWS Access Key"),
-    aws_secret_access_key: str = typer.Option(..., help="AWS Secret Key"),
+    aws_access_key_id: str = typer.Option(None, help="AWS Access Key"),
+    aws_secret_access_key: str = typer.Option(None, help="AWS Secret Key"),
     region_name: str = typer.Option(..., help="AWS Region Name"),
     s3_staging_dir: str = typer.Option(..., help="S3 Staging Dir"),
     scan_type: ScanTypeEnum = typer.Option(

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "piicatcher"
-version = "0.17.3"
+version = "0.17.4"
 description = "Find PII data in databases"
 authors = ["Tokern <[email protected]>"]
 license = "Apache 2.0"

tests/test_api.py

@@ -167,3 +167,17 @@ def test_scan_athena(mocker, temp_sqlite_path, app_dir_path):
     )
     piicatcher.api.scan_database.assert_called_once()
     Catalog.add_source.assert_called_once()
+
+
+def test_scan_athena_iam(mocker, temp_sqlite_path, app_dir_path):
+    mocker.patch("piicatcher.api.scan_database")
+    mocker.patch.object(Catalog, "add_source")
+
+    scan_athena(
+        catalog_params={"path": temp_sqlite_path, "app_dir": app_dir_path},
+        name="test_scan_athena",
+        region_name="r",
+        s3_staging_dir="s3",
+    )
+    piicatcher.api.scan_database.assert_called_once()
+    Catalog.add_source.assert_called_once()

tests/test_cli.py

@@ -102,6 +102,19 @@ def case_athena_cli():
     ]
 
 
+def case_athena_cli_iam():
+    return [
+        "scan",
+        "athena",
+        "--name",
+        "athena_cli",
+        "--region-name",
+        "us-east-1",
+        "--s3-staging-dir",
+        "s3://dummy",
+    ]
+
+
 @parametrize_with_cases("args", cases=".")
 def test_cli(mocker, temp_sqlite_path, args):
     mocker.patch("piicatcher.api.scan_database")