satisfactoscript 0.5.10__tar.gz → 0.6.0__tar.gz

{satisfactoscript-0.5.10 → satisfactoscript-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: satisfactoscript
-Version: 0.5.10
+Version: 0.6.0
 Summary: An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse.
 Author: julhouba
 Classifier: Programming Language :: Python :: 3

{satisfactoscript-0.5.10 → satisfactoscript-0.6.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "satisfactoscript"
-version = "0.5.10"
+version = "0.6.0"
 description = "An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse."
 readme = "README.md"
 authors = [

{satisfactoscript-0.5.10 → satisfactoscript-0.6.0}/src/satisfactoscript/core/core.py

@@ -686,37 +686,50 @@ class SatisfactoEngine:
 
         return df_main
 
-    def run_split_to_org(self, schema_dict, org_list, target_layer, target_base_name, split_column="sales_org_code"):
+    def run_process_and_split(self, schema_dict, split_values, target_layer, target_base_name, split_column):
         """
-        Executes a pattern where the processed DataFrame is split based on an organization
-        column and written to multiple Delta tables.
-        
+        Processes the schema and splits the resulting DataFrame into multiple Delta tables,
+        one per value in split_values, filtering on split_column.
+
         Args:
             schema_dict (dict): The pipeline dictionary schema.
-            org_list (list of dict): List of organizations containing 'org_code' and 'label'.
+            split_values (list of dict): Each item must have:
+                - 'value' (str): The column value to filter on.
+                - 'label' (str): The suffix appended to target_base_name for the table name.
             target_layer (str): The target database layer (e.g., 'silver').
             target_base_name (str): The base name for the target tables.
             split_column (str): The column used to split the data.
         """
-        print(f"--- Executing Pattern: split_to_org (Base: {target_base_name}) ---")
+        print(f"--- Executing Pattern: process_and_split (Base: {target_base_name}, Column: {split_column}) ---")
         df_full = self.process_schema(schema_dict)
         actual_schema = self.get_target_schema(target_layer)
-        df_full.cache()
-        
-        for org in org_list:
-            fqn = f"`{self.db}`.`{actual_schema}`.`{target_base_name}_{org['label']}`"
+
+        cached = False
+        try:
+            df_full.cache()
+            cached = True
+        except Exception:
+            print("   -> [Cache] WARNING: cache() failed (UserContext gRPC issue). Continuing without caching.")
+
+        for item in split_values:
+            fqn = f"`{self.db}`.`{actual_schema}`.`{target_base_name}_{item['label']}`"
             self._drop_table_if_exists(fqn)
-            print(f"  -> Processing Org: {org['label']}")
-            df_org = df_full.filter(F.col(split_column) == org["org_code"])
-            self._write_dataframe(df_org, fqn, org["label"])
-            
-        df_full.unpersist()
-        print("--- Pattern 'split_to_org' completed. ---")
+            print(f"  -> Processing split value: {item['label']} ({split_column} = '{item['value']}')")
+            df_slice = df_full.filter(F.col(split_column) == item["value"])
+            self._write_dataframe(df_slice, fqn, item["label"])
+
+        if cached:
+            try:
+                df_full.unpersist()
+            except Exception:
+                pass
+
+        print("--- Pattern 'process_and_split' completed. ---")
 
-    def run_follow_schema(self, schema_dict, target_layer, target_table_name):
+    def run_process_to_table(self, schema_dict, target_layer, target_table_name):
         """
-        Standard execution pattern: Process a schema and write to a single target table.
-        
+        Processes a schema and writes the result to a single Delta table.
+
         Args:
             schema_dict (dict): The pipeline dictionary schema.
             target_layer (str): The target database layer (e.g., 'gold').
@@ -724,55 +737,57 @@ class SatisfactoEngine:
         """
         actual_schema = self.get_target_schema(target_layer)
         fqn = f"`{self.db}`.`{actual_schema}`.`{target_table_name}`"
-        print(f"--- Executing Pattern: follow_schema (Target: {target_table_name}) ---")
+        print(f"--- Executing Pattern: process_to_table (Target: {target_table_name}) ---")
         self._drop_table_if_exists(fqn)
         df = self.process_schema(schema_dict)
         self._write_dataframe(df, fqn, target_table_name)
-        print("--- Pattern 'follow_schema' completed. ---")
+        print("--- Pattern 'process_to_table' completed. ---")
     
-    def run_unify_and_process(self, schema_dict, org_list, source_layer, target_layer, target_table_name, unified_source_base_names, unified_temp_view_key):
+    def run_union_sources_to_table(self, schema_dict, source_partitions, source_layer, target_layer, target_table_name, source_base_names, source_alias):
         """
-        Executes a pattern where data from multiple organizations is first unified (unioned)
-        and then passed through the schema processing.
-        
+        Unions source tables (one per partition label per base name), processes the
+        combined DataFrame through the schema, and writes the result to a single Delta table.
+
+        Source table names are resolved as: {db}.{source_layer}.{base_name}_{partition['label']}
+
         Args:
             schema_dict (dict): The pipeline dictionary schema.
-            org_list (list of dict): List of organizations defining expected source tables.
+            source_partitions (list of dict): Each item must have a 'label' key (str) used
+                as the suffix when resolving source table names.
             source_layer (str): The database layer containing the source tables.
             target_layer (str): The database layer to write the output to.
             target_table_name (str): The name of the target output table.
-            unified_source_base_names (list of str): Base names of the source tables to unify.
-            unified_temp_view_key (str): The alias/key to use for the unified DataFrame
-                                         in the schema logic.
-                                         
+            source_base_names (list of str): Base names of the source tables to union.
+            source_alias (str): The key under which the unioned DataFrame is injected
+                                into the schema processing (replaces the table alias in schema_dict).
+
         Raises:
-            ValueError: If no source tables can be found to unify.
+            ValueError: If no source tables can be found to union.
         """
         actual_schema_source = self.get_target_schema(source_layer)
         actual_schema_target = self.get_target_schema(target_layer)
         fqn = f"`{self.db}`.`{actual_schema_target}`.`{target_table_name}`"
-        print(f"--- Executing Pattern: unify_and_process (Target: {target_table_name}) ---")
+        print(f"--- Executing Pattern: union_sources_to_table (Target: {target_table_name}) ---")
         self._drop_table_if_exists(fqn)
-        
+
         list_of_dfs = []
-        for base in unified_source_base_names:
-            for org in org_list:
-                source_fqn = f"`{self.db}`.`{actual_schema_source}`.`{base}_{org['label']}`"
+        for base in source_base_names:
+            for partition in source_partitions:
+                source_fqn = f"`{self.db}`.`{actual_schema_source}`.`{base}_{partition['label']}`"
                 try:
                     list_of_dfs.append(self.spark.table(source_fqn))
                 except Exception:
                     print(f"     - WARNING: Missing table {source_fqn}")
 
-        if not list_of_dfs: raise ValueError("No sources found.")
-        
+        if not list_of_dfs:
+            raise ValueError("No sources found to union.")
+
         print(f" -> [Union] Merging {len(list_of_dfs)} tables...")
         unioned_df = reduce(lambda x, y: x.unionByName(y, allowMissingColumns=True), list_of_dfs).dropDuplicates()
-        
-        input_dfs = {unified_temp_view_key: unioned_df}
-        
-        df_final = self.process_schema(schema_dict, dataframes_in=input_dfs)
+
+        df_final = self.process_schema(schema_dict, dataframes_in={source_alias: unioned_df})
         self._write_dataframe(df_final, fqn, target_table_name)
-        print("--- Pattern 'unify_and_process' completed. ---")
+        print("--- Pattern 'union_sources_to_table' completed. ---")
 
     def optimize_table(self, target_layer, target_table_name, zorder_cols=None):
         """

{satisfactoscript-0.5.10 → satisfactoscript-0.6.0}/src/satisfactoscript.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: satisfactoscript
-Version: 0.5.10
+Version: 0.6.0
 Summary: An Enterprise-Ready, Declarative Data Engineering Framework for Databricks Lakehouse.
 Author: julhouba
 Classifier: Programming Language :: Python :: 3