fabricks 3.0.2__tar.gz → 3.0.3__tar.gz

{fabricks-3.0.2 → fabricks-3.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fabricks
-Version: 3.0.2
+Version: 3.0.3
 Author-email: BMS DWH Team <bi_support@bmsuisse.ch>
 Requires-Python: <4,>=3.9
 Requires-Dist: azure-data-tables<13,>=12.5.0

{fabricks-3.0.2 → fabricks-3.0.3}/fabricks/core/jobs/base/configurator.py

@@ -301,9 +301,8 @@ class Configurator(ABC):
         """
         if self.mode == "memory":
             DEFAULT_LOGGER.debug("memory (no optimize)", extra={"job": self})
-        else:
-            assert self.table.exists()
 
+        else:
             if vacuum:
                 self.vacuum()
             if optimize:
@@ -312,19 +311,23 @@ class Configurator(ABC):
                 self.table.compute_statistics()
 
     def vacuum(self):
-        job = self.options.table.get("retention_days")
-        step = self.step_conf.get("table_options", {}).get("retention_days", None)
-        runtime = CONF_RUNTIME.get("options", {}).get("retention_days")
-
-        if job is not None:
-            retention_days = job
-        elif step:
-            retention_days = step
+        if self.mode == "memory":
+            DEFAULT_LOGGER.debug("memory (no vacuum)", extra={"job": self})
+
         else:
-            assert runtime
-            retention_days = runtime
+            job = self.options.table.get("retention_days")
+            step = self.step_conf.get("table_options", {}).get("retention_days", None)
+            runtime = CONF_RUNTIME.get("options", {}).get("retention_days")
+
+            if job is not None:
+                retention_days = job
+            elif step:
+                retention_days = step
+            else:
+                assert runtime
+                retention_days = runtime
 
-        self.table.vacuum(retention_days=retention_days)
+            self.table.vacuum(retention_days=retention_days)
 
     def __str__(self):
         return f"{self.step}.{self.topic}_{self.item}"

{fabricks-3.0.2 → fabricks-3.0.3}/fabricks/core/jobs/bronze.py

@@ -103,6 +103,21 @@ class Bronze(BaseJob):
         DEFAULT_LOGGER.debug("drop external table", extra={"job": self})
         self.spark.sql(f"drop table if exists {self.qualified_name}")
 
+    def analyze_external_table(self):
+        DEFAULT_LOGGER.debug("analyze external table", extra={"job": self})
+        self.spark.sql(f"analyze table {self.qualified_name} compute statistics")
+
+    def vacuum_external_table(self, retention_hours: Optional[int] = 168):
+        from delta import DeltaTable
+
+        DEFAULT_LOGGER.debug("vacuum external table", extra={"job": self})
+        try:
+            dt = DeltaTable.forPath(self.spark, self.data_path.string)
+            self.spark.sql("SET self.spark.databricks.delta.retentionDurationCheck.enabled = False")
+            dt.vacuum(retention_hours)
+        finally:
+            self.spark.sql("SET self.spark.databricks.delta.retentionDurationCheck.enabled = True")
+
     def optimize_external_table(
         self,
         vacuum: Optional[bool] = True,
@@ -110,20 +125,10 @@ class Bronze(BaseJob):
     ):
         DEFAULT_LOGGER.debug("optimize external table", extra={"job": self})
         if vacuum:
-            from delta import DeltaTable
-
-            dt = DeltaTable.forPath(self.spark, self.data_path.string)
-            retention_days = 7
-            DEFAULT_LOGGER.debug(f"{self.data_path} - vacuum table (removing files older than {retention_days} days)")
-            try:
-                self.spark.sql("SET self.spark.databricks.delta.retentionDurationCheck.enabled = False")
-                dt.vacuum(retention_days * 24)
-            finally:
-                self.spark.sql("SET self.spark.databricks.delta.retentionDurationCheck.enabled = True")
+            self.vacuum_external_table()
 
         if analyze:
-            DEFAULT_LOGGER.debug(f"{self.data_path} - compute delta statistics")
-            self.spark.sql(f"analyze table delta.`{self.data_path}` compute delta statistics")
+            self.analyze_external_table()
 
     @property
     def parser(self) -> BaseParser:
@@ -370,6 +375,14 @@ class Bronze(BaseJob):
         else:
             super().optimize(vacuum=vacuum, optimize=optimize, analyze=analyze)
 
+    def vacuum(self):
+        if self.mode == "memory":
+            DEFAULT_LOGGER.info("memory (no vacuum)", extra={"job": self})
+        elif self.mode == "register":
+            self.vacuum_external_table()
+        else:
+            super().vacuum()
+
     def overwrite(self):
         self.truncate()
         self.run()

{fabricks-3.0.2 → fabricks-3.0.3}/fabricks/metastore/table.py

@@ -433,7 +433,11 @@ class Table(DbObject):
         cols = [
             f"`{name}`"
             for name, dtype in self.dataframe.dtypes
-            if not dtype.startswith("struct") and not dtype.startswith("array") and name not in ["__metadata"]
+            if not dtype.startswith("struct")
+            and not dtype.startswith("array")
+            and not dtype.startswith("variant")
+            and not dtype.startswith("map")
+            and name not in ["__metadata"]
         ]
         cols = ", ".join(sorted(cols))
         self.spark.sql(f"analyze table {self.qualified_name} compute statistics for columns {cols}")

{fabricks-3.0.2 → fabricks-3.0.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fabricks"
-version = "3.0.2"
+version = "3.0.3"
 description = ""
 authors = [
     { name = "BMS DWH Team", email = "bi_support@bmsuisse.ch" },

{fabricks-3.0.2 → fabricks-3.0.3}/uv.lock

@@ -627,7 +627,7 @@ wheels = [
 
 [[package]]
 name = "fabricks"
-version = "3.0.2"
+version = "3.0.3"
 source = { editable = "." }
 dependencies = [
     { name = "azure-data-tables" },