sws-spark-dissemination-helper 0.0.90__tar.gz → 0.0.92__tar.gz

{sws_spark_dissemination_helper-0.0.90 → sws_spark_dissemination_helper-0.0.92}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sws-spark-dissemination-helper
-Version: 0.0.90
+Version: 0.0.92
 Summary: A Python helper package providing streamlined Spark functions for efficient data dissemination processes
 Project-URL: Repository, https://bitbucket.org/cioapps/sws-it-python-spark-dissemination-helper
 Author-email: Daniele Mansillo <danielemansillo@gmail.com>

{sws_spark_dissemination_helper-0.0.90 → sws_spark_dissemination_helper-0.0.92}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sws-spark-dissemination-helper"
-version = "0.0.90"
+version = "0.0.92"
 dependencies = [
     "annotated-types==0.7.0",
     "boto3==1.36.18",

{sws_spark_dissemination_helper-0.0.90 → sws_spark_dissemination_helper-0.0.92}/src/sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py

@@ -447,18 +447,23 @@ class SWSBronzeIcebergSparkHelper:
     def write_bronze_disseminated_tag_data_to_iceberg_and_csv(
         self, dimensions: Dict[str, List[str]]
     ) -> DataFrame:
-        self.spark.sql(
-            f"ALTER TABLE {self.iceberg_tables.BRONZE.iceberg_id}.`tag_{self.tag_name}` CREATE OR REPLACE BRANCH `diss_tag_{self.tag_name}`"  # AS OF VERSION `{tag_name}`
-        )
+
+        create_branch_query = f"ALTER TABLE {self.iceberg_tables.BRONZE.iceberg_id}.`tag_{self.tag_name}` CREATE OR REPLACE BRANCH `diss_tag_{self.tag_name}`"  # AS OF VERSION `{tag_name}`
+        logging.info(f"create_branch_query: {create_branch_query}")
+        self.spark.sql(create_branch_query)
+        logging.info(f"dimensions: {dimensions}")
 
         for dimension_name, codes in dimensions.items():
+            logging.info(f"dimension_name: {dimension_name}")
+            logging.info(f"codes: {codes}")
             if len(codes) != 0:
                 not_in_codes = ",".join([f"'{code}'" for code in codes])
-                self.spark.sql(
-                    f"DELETE FROM {self.iceberg_tables.BRONZE.iceberg_id}.`branch_diss_tag_{self.tag_name}` WHERE {dimension_name} NOT IN ({not_in_codes})"
-                )
+                delete_from_branch_query = f"DELETE FROM {self.iceberg_tables.BRONZE.iceberg_id}.`branch_diss_tag_{self.tag_name}` WHERE {dimension_name} NOT IN ({not_in_codes})"
+                logging.info(f"delete_from_branch_query: {delete_from_branch_query}")
+                self.spark.sql(delete_from_branch_query)
+
         self.disseminated_tag_df = self.spark.read.option(
-            "branch", self.tag_name
+            "branch", f"`diss_tag_{self.tag_name}`"
         ).table(self.iceberg_tables.BRONZE.iceberg_id)
 
         disseminated_tag_df = self.disseminated_tag_df.withColumn(