castor-extractor 0.24.40__tar.gz → 0.24.42__tar.gz

{castor_extractor-0.24.40 → castor_extractor-0.24.42}/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.24.42 - 2025-08-19
+
+* Strategy: exclude COLUMNS from extraction
+
+## 0.24.41 - 2025-08-19
+
+* Sigma: retry on 429 errors when fetching connection paths
+
 ## 0.24.40 - 2025-08-18
 
 * SQLServer: fix database allowlist/blocklist filtering

{castor_extractor-0.24.40 → castor_extractor-0.24.42}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: castor-extractor
-Version: 0.24.40
+Version: 0.24.42
 Summary: Extract your metadata assets.
 Home-page: https://www.castordoc.com/
 License: EULA
@@ -215,6 +215,14 @@ For any questions or bug report, contact us at [support@coalesce.io](mailto:supp
 
 # Changelog
 
+## 0.24.42 - 2025-08-19
+
+* Strategy: exclude COLUMNS from extraction
+
+## 0.24.41 - 2025-08-19
+
+* Sigma: retry on 429 errors when fetching connection paths
+
 ## 0.24.40 - 2025-08-18
 
 * SQLServer: fix database allowlist/blocklist filtering

{castor_extractor-0.24.40 → castor_extractor-0.24.42}/castor_extractor/visualization/sigma/client/sources_transformer.py

@@ -1,6 +1,8 @@
 import logging
+from http import HTTPStatus
 from typing import TYPE_CHECKING, Callable, Iterator
 
+from ....utils import retry_request
 from .endpoints import SigmaEndpointFactory
 
 if TYPE_CHECKING:
@@ -8,6 +10,9 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 
+SIGMA_CONNECTION_PATH_MAX_RETRY = 1
+SIGMA_CONNECTION_PATH_SLEEP_MS = 30_000  # 30 seconds
+
 
 class SigmaSourcesTransformer:
     """Retrieves asset sources and enhances them with additional information."""
@@ -15,6 +20,17 @@ class SigmaSourcesTransformer:
     def __init__(self, api_client: "SigmaClient"):
         self.api_client = api_client
 
+    @retry_request(
+        status_codes=(HTTPStatus.TOO_MANY_REQUESTS,),
+        max_retries=SIGMA_CONNECTION_PATH_MAX_RETRY,
+        base_ms=SIGMA_CONNECTION_PATH_SLEEP_MS,
+    )
+    def _get_connection_path(self, table_id: str) -> dict:
+        """Retrieves the connection path for a given table id"""
+        return self.api_client._get(
+            endpoint=SigmaEndpointFactory.connection_path(table_id)
+        )
+
     def _map_table_id_to_connection_path(
         self, all_sources: list
     ) -> dict[str, dict]:
@@ -29,9 +45,7 @@ class SigmaSourcesTransformer:
         }
 
         return {
-            table_id: self.api_client._get(
-                endpoint=SigmaEndpointFactory.connection_path(table_id)
-            )
+            table_id: self._get_connection_path(table_id)
             for table_id in unique_table_ids
         }
 

{castor_extractor-0.24.40 → castor_extractor-0.24.42}/castor_extractor/visualization/strategy/extract.py

@@ -22,7 +22,7 @@ def iterate_all_data(
 ) -> Iterable[tuple[str, Union[list, dict]]]:
     """Iterate over the extracted data from Strategy"""
 
-    for asset in StrategyAsset:
+    for asset in StrategyAsset.mandatory:
         logger.info(f"Extracting {asset.value.upper()} from REST API")
         data = client.fetch(asset)
         yield asset.name.lower(), list(deep_serialize(data))

{castor_extractor-0.24.40 → castor_extractor-0.24.42}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools>=61.2"]
 
 [tool.poetry]
 name = "castor-extractor"
-version = "0.24.40"
+version = "0.24.42"
 description = "Extract your metadata assets."
 authors = ["Castor <support@castordoc.com>"]
 license = "EULA"