satisfactoscript 0.6.2__tar.gz → 0.6.5__tar.gz

{satisfactoscript-0.6.2 → satisfactoscript-0.6.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: satisfactoscript
-Version: 0.6.2
+Version: 0.6.5
 Summary: An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse.
 Author: julhouba
 Classifier: Programming Language :: Python :: 3

{satisfactoscript-0.6.2 → satisfactoscript-0.6.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "satisfactoscript"
-version = "0.6.2"
+version = "0.6.5"
 description = "An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse."
 readme = "README.md"
 authors = [

{satisfactoscript-0.6.2 → satisfactoscript-0.6.5}/src/satisfactoscript/core/__init__.py

@@ -1,5 +1,6 @@
 from .core import SatisfactoEngine
 from .registry import RuleRegistry
 from .config import ConfigurationManager
+from . import loaders  # noqa: F401 — triggers loader registration via decorators
 
 __all__ = ["SatisfactoEngine", "RuleRegistry", "ConfigurationManager"]

{satisfactoscript-0.6.2 → satisfactoscript-0.6.5}/src/satisfactoscript/core/core.py

@@ -210,6 +210,7 @@ class SatisfactoEngine:
             raise RuntimeError("CRITICAL: Failed to initialize Spark Session.")
 
         self._patch_connect_debugging()
+        self._patch_connect_user_context()
         self.dbutils = DBUtils(self.spark)
 
         # ======================================================================
@@ -279,6 +280,42 @@ class SatisfactoEngine:
             except Exception:
                 pass
 
+    def _patch_connect_user_context(self):
+        """
+        Patches SparkConnectClient._user_id when it is empty or missing.
+
+        Root cause: on Databricks Connect v2 from local environments (Windows/PyCharm),
+        the gRPC session is created successfully but _user_id is not populated from the
+        SDK config. PySpark's execute_command only injects user_context.user_id when
+        self._user_id is truthy — so every gRPC execution call (saveAsTable, collect,
+        execute_command for DDL) fails immediately with:
+            'Missing required field UserContext'
+
+        Fix: after session creation, if _user_id is absent on the SparkConnectClient,
+        fetch the current user's email via the Databricks SDK REST API (which is not
+        affected by the gRPC issue) and inject it directly into the client object.
+        This is a one-time init patch with no functional side effects.
+        """
+        try:
+            client = getattr(self.spark, 'client', None)
+            if client is None:
+                return  # Standard SparkSession (not a Connect session) — nothing to patch
+
+            if getattr(client, '_user_id', None):
+                return  # Already properly set — no patch needed
+
+            from databricks.sdk import WorkspaceClient
+            host = os.getenv("DATABRICKS_HOST")
+            token = os.getenv("DATABRICKS_TOKEN")
+            if host and token:
+                w = WorkspaceClient(host=host, token=token)
+                email = w.current_user.me().user_name
+                if email:
+                    client._user_id = email
+                    print(f"   [Init] ⚙️ Applied UserContext patch: user_id injected ('{email}').")
+        except Exception:
+            pass
+
     def _find_file_upwards(self, filename):
         """
         Searches for a file starting from current working directory and moving up.

{satisfactoscript-0.6.2 → satisfactoscript-0.6.5}/src/satisfactoscript.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: satisfactoscript
-Version: 0.6.2
+Version: 0.6.5
 Summary: An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse.
 Author: julhouba
 Classifier: Programming Language :: Python :: 3

{satisfactoscript-0.6.2 → satisfactoscript-0.6.5}/tests/test_core.py

@@ -250,9 +250,9 @@ def test_process_schema_raises_error_on_unknown_rule(mock_engine):
     mock_engine.spark.catalog.dropTempView("some_table")
 
 
-def test_run_split_to_org(mock_engine, mocker, spark):
+def test_run_process_and_split(mock_engine, mocker, spark):
     """
-    Tests the run_split_to_org runner. It spies on the _write_dataframe method
+    Tests the run_process_and_split runner. It spies on the _write_dataframe method
     to ensure it's called correctly without actually writing any data.
     """
     # 0. Create the schema required for the test before running the engine
@@ -271,19 +271,20 @@ def test_run_split_to_org(mock_engine, mocker, spark):
     source_df = spark.createDataFrame(source_data, ["id", "sales_org_code"])
     source_df.createOrReplaceTempView("source_for_split")
 
-    # 3. Define schema and org list
+    # 3. Define schema and split values
     schema_dict = {"tables": [{"name": "source_for_split", "alias": "t"}]}
-    org_list = [
-        {"label": "france", "org_code": "FR"},
-        {"label": "germany", "org_code": "DE"}
+    split_values = [
+        {"label": "france", "value": "FR"},
+        {"label": "germany", "value": "DE"}
     ]
 
     # 4. Execute the runner
-    mock_engine.run_split_to_org(
+    mock_engine.run_process_and_split(
         schema_dict=schema_dict,
-        org_list=org_list,
+        split_values=split_values,
         target_layer="gold",
-        target_base_name="sales"
+        target_base_name="sales",
+        split_column="sales_org_code"
     )
 
     # 5. Assertions on the spy

satisfactoscript-0.6.5/tests/test_registry_import_paths.py

@@ -0,0 +1,51 @@
+"""
+Tests for RuleRegistry import path compatibility and core __init__ exports.
+All import paths must resolve to the same singleton class.
+"""
+from satisfactoscript.core.registry import RuleRegistry as RR_core
+from satisfactoscript.registry import RuleRegistry as RR_shim
+from satisfactoscript import RuleRegistry as RR_top
+
+
+def test_all_import_paths_resolve_to_same_class():
+    """All three import paths must return the exact same class (same singleton)."""
+    assert RR_core is RR_shim
+    assert RR_core is RR_top
+
+
+def test_rule_registered_via_shim_is_visible_everywhere():
+    """A rule registered using the shim import must be retrievable from all paths."""
+    @RR_shim.register_rule(name="__test_shim_rule__")
+    def _my_rule(df):
+        return df
+
+    assert RR_core.get_rule("__test_shim_rule__") is _my_rule
+    assert RR_top.get_rule("__test_shim_rule__") is _my_rule
+
+    # Cleanup
+    RR_core._rules.pop("__test_shim_rule__", None)
+
+
+# ==============================================================================
+# TESTS FOR core/__init__.py EXPORTS AND LOADER REGISTRATION
+# ==============================================================================
+
+def test_core_init_exports_public_api():
+    """Importing satisfactoscript.core must expose SatisfactoEngine, RuleRegistry, ConfigurationManager."""
+    import satisfactoscript.core as core_pkg
+
+    assert hasattr(core_pkg, "SatisfactoEngine"), "SatisfactoEngine missing from satisfactoscript.core"
+    assert hasattr(core_pkg, "RuleRegistry"), "RuleRegistry missing from satisfactoscript.core"
+    assert hasattr(core_pkg, "ConfigurationManager"), "ConfigurationManager missing from satisfactoscript.core"
+
+
+def test_core_init_triggers_loader_registration():
+    """Importing satisfactoscript.core must register built-in loaders via the loaders side-effect import."""
+    import satisfactoscript.core  # noqa: F401 — ensures the __init__ has been executed
+
+    assert "load_and_union_tables" in RR_core._loaders, (
+        "load_and_union_tables not registered — loaders side-effect import may be broken"
+    )
+    assert "load_generic_explode_union" in RR_core._loaders, (
+        "load_generic_explode_union not registered — loaders side-effect import may be broken"
+    )

satisfactoscript-0.6.2/tests/test_registry_import_paths.py

@@ -1,26 +0,0 @@
-"""
-Tests for RuleRegistry import path compatibility.
-All import paths must resolve to the same singleton class.
-"""
-from satisfactoscript.core.registry import RuleRegistry as RR_core
-from satisfactoscript.registry import RuleRegistry as RR_shim
-from satisfactoscript import RuleRegistry as RR_top
-
-
-def test_all_import_paths_resolve_to_same_class():
-    """All three import paths must return the exact same class (same singleton)."""
-    assert RR_core is RR_shim
-    assert RR_core is RR_top
-
-
-def test_rule_registered_via_shim_is_visible_everywhere():
-    """A rule registered using the shim import must be retrievable from all paths."""
-    @RR_shim.register_rule(name="__test_shim_rule__")
-    def _my_rule(df):
-        return df
-
-    assert RR_core.get_rule("__test_shim_rule__") is _my_rule
-    assert RR_top.get_rule("__test_shim_rule__") is _my_rule
-
-    # Cleanup
-    RR_core._rules.pop("__test_shim_rule__", None)