steve-cli 0.3.9__tar.gz → 0.3.11__tar.gz

{steve_cli-0.3.9 → steve_cli-0.3.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: steve-cli
-Version: 0.3.9
+Version: 0.3.11
 Summary: A simple CLI tool to run jobs from jobs.yaml with proper environment setup
 Author: Frank
 License: MIT

{steve_cli-0.3.9 → steve_cli-0.3.11}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "steve-cli"
-version = "0.3.9"
+version = "0.3.11"
 description = "A simple CLI tool to run jobs from jobs.yaml with proper environment setup"
 readme = "README.md"
 license = {text = "MIT"}

{steve_cli-0.3.9 → steve_cli-0.3.11}/steve_cli/decorators/lineage_job.py

@@ -26,6 +26,10 @@ def lineage_job(
 
         @functools.wraps(fn)
         def wrapper(*args: Any, **kwargs: Any) -> Any:
+            from dotenv import load_dotenv
+            load_dotenv(".env", override=False)
+            load_dotenv(".workspaces.env", override=False)
+
             session = make_session(
                 namespace=namespace,
                 job_name=job_name,

{steve_cli-0.3.9 → steve_cli-0.3.11}/steve_cli/lineage/collector.py

@@ -18,16 +18,21 @@ class LineageSession:
     _inputs: set[str] = field(default_factory=set)
     _outputs: set[str] = field(default_factory=set)
     _facets: Dict[str, Dict[str, Any]] = field(default_factory=dict)
+    _dataset_namespaces: Dict[str, str] = field(default_factory=dict)
 
-    def record_read(self, dataset: str, facets: Dict[str, Any] | None = None) -> None:
+    def record_read(self, dataset: str, facets: Dict[str, Any] | None = None, namespace: str | None = None) -> None:
         self._inputs.add(dataset)
         if facets:
             self._facets.setdefault(dataset, {}).update(facets)
+        if namespace:
+            self._dataset_namespaces[dataset] = namespace
 
-    def record_write(self, dataset: str, facets: Dict[str, Any] | None = None) -> None:
+    def record_write(self, dataset: str, facets: Dict[str, Any] | None = None, namespace: str | None = None) -> None:
         self._outputs.add(dataset)
         if facets:
             self._facets.setdefault(dataset, {}).update(facets)
+        if namespace:
+            self._dataset_namespaces[dataset] = namespace
 
     def attach_facets(self, dataset: str, facets: Dict[str, Any]) -> None:
         self._facets.setdefault(dataset, {}).update(facets)
@@ -42,8 +47,8 @@ class LineageSession:
             namespace=self.namespace,
             run_id=self.run_id,
             state=state,
-            inputs=[DatasetRef(namespace=self.namespace, name=x, facets=self._facets.get(x, {})) for x in self._inputs],
-            outputs=[DatasetRef(namespace=self.namespace, name=x, facets=self._facets.get(x, {})) for x in self._outputs],
+            inputs=[DatasetRef(namespace=self._dataset_namespaces.get(x, self.namespace), name=x, facets=self._facets.get(x, {})) for x in self._inputs],
+            outputs=[DatasetRef(namespace=self._dataset_namespaces.get(x, self.namespace), name=x, facets=self._facets.get(x, {})) for x in self._outputs],
             run_facets=run_facets or {},
         )
 

{steve_cli-0.3.9 → steve_cli-0.3.11}/steve_cli/lineage/storage.py

@@ -58,23 +58,30 @@ class LineageStorage:
                 self.__resolved = self._storage_or_factory  # type: ignore[assignment]
         return self.__resolved
 
+    @property
+    def _dataset_namespace(self) -> str | None:
+        s = self._storage
+        if hasattr(s, 'endpoint') and hasattr(s, 'bucket'):
+            return f"{s.endpoint.rstrip('/')}/{s.bucket}"
+        return None
+
     def put_file(self, local_path: str, path: str) -> None:
         self._storage.put_file(local_path, path)
-        self._session.record_write(path)
+        self._session.record_write(path, namespace=self._dataset_namespace)
 
     def get_file(self, path: str, local_path: str) -> None:
         self._storage.get_file(path, local_path)
-        self._session.record_read(path)
+        self._session.record_read(path, namespace=self._dataset_namespace)
 
     def put_bytes(self, data: bytes, path: str) -> None:
         self._storage.put_bytes(data, path)
         facets = _extract_facets(data, path)
-        self._session.record_write(path, facets or None)
+        self._session.record_write(path, facets or None, namespace=self._dataset_namespace)
 
     def get_bytes(self, path: str) -> bytes:
         data = self._storage.get_bytes(path)
         facets = _extract_facets(data, path)
-        self._session.record_read(path, facets or None)
+        self._session.record_read(path, facets or None, namespace=self._dataset_namespace)
         return data
 
     def read(self, path: str) -> DatasetHandle:

{steve_cli-0.3.9 → steve_cli-0.3.11}/steve_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: steve-cli
-Version: 0.3.9
+Version: 0.3.11
 Summary: A simple CLI tool to run jobs from jobs.yaml with proper environment setup
 Author: Frank
 License: MIT