satisfactoscript 0.6.1__tar.gz → 0.6.3__tar.gz

{satisfactoscript-0.6.1 → satisfactoscript-0.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: satisfactoscript
-Version: 0.6.1
+Version: 0.6.3
 Summary: An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse.
 Author: julhouba
 Classifier: Programming Language :: Python :: 3

{satisfactoscript-0.6.1 → satisfactoscript-0.6.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "satisfactoscript"
-version = "0.6.1"
+version = "0.6.3"
 description = "An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse."
 readme = "README.md"
 authors = [

{satisfactoscript-0.6.1 → satisfactoscript-0.6.3}/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.
@@ -546,10 +583,15 @@ class SatisfactoEngine:
             fqn (str): The Fully Qualified Name of the target table.
             label (str): A label to display in the logging output.
         """
-        if df.isEmpty():
-            print(f"     -> [Write] WARNING: Dataframe for {label} is empty. Skipping write.")
-            return
-        
+        try:
+            if df.isEmpty():
+                print(f"     -> [Write] WARNING: Dataframe for {label} is empty. Skipping write.")
+                return
+        except Exception:
+            # isEmpty() triggers collect() via gRPC, which fails with UserContext on
+            # Databricks Connect v2 locally. Skip the check and proceed with the write.
+            pass
+
         print(f"     -> [Write] Writing data to: {fqn} ...")
         df.write.format("delta").mode("overwrite").option("overwriteSchema", "true").saveAsTable(fqn)
         print(f"     -> [Success] Table {label} written successfully.")
@@ -846,5 +888,11 @@ class SatisfactoEngine:
             print(f"     -> [Success] Table {target_table_name} optimized successfully.")
 
         except Exception as e:
-            print(f"     -> ❌ [Error] Optimization failed on {full_target_fqn}: {e}")
-            raise e
+            # OPTIMIZE is a Databricks DDL command with no SDK REST equivalent.
+            # When running locally via Databricks Connect v2, gRPC DDL calls fail with
+            # 'Missing required field UserContext'. In that case, skip silently.
+            if "UserContext" in str(e) or "user_context" in str(e).lower():
+                print(f"     -> ⚠️ [Optimize] Skipped: OPTIMIZE is not supported via Databricks Connect v2 locally.")
+            else:
+                print(f"     -> ❌ [Error] Optimization failed on {full_target_fqn}: {e}")
+                raise e

{satisfactoscript-0.6.1 → satisfactoscript-0.6.3}/src/satisfactoscript.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: satisfactoscript
-Version: 0.6.1
+Version: 0.6.3
 Summary: An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse.
 Author: julhouba
 Classifier: Programming Language :: Python :: 3