sws-spark-dissemination-helper 0.0.91__tar.gz → 0.0.93__tar.gz

{sws_spark_dissemination_helper-0.0.91 → sws_spark_dissemination_helper-0.0.93}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sws-spark-dissemination-helper
-Version: 0.0.91
+Version: 0.0.93
 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-0.0.91 → sws_spark_dissemination_helper-0.0.93}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sws-spark-dissemination-helper"
-version = "0.0.91"
+version = "0.0.93"
 dependencies = [
     "annotated-types==0.7.0",
     "boto3==1.36.18",

{sws_spark_dissemination_helper-0.0.91 → sws_spark_dissemination_helper-0.0.93}/src/sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py

@@ -450,9 +450,11 @@ class SWSBronzeIcebergSparkHelper:
 
         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}")
+        create_branch_query_result = self.spark.sql(create_branch_query).collect()
+
+        logging.info(f"result of create_branch_query: {create_branch_query_result}")
 
+        logging.info(f"dimensions: {dimensions}")
         for dimension_name, codes in dimensions.items():
             logging.info(f"dimension_name: {dimension_name}")
             logging.info(f"codes: {codes}")
@@ -460,9 +462,16 @@ class SWSBronzeIcebergSparkHelper:
                 not_in_codes = ",".join([f"'{code}'" for code 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)
+                delete_from_branch_query_result = self.spark.sql(
+                    delete_from_branch_query
+                ).collect()
+
+                logging.info(
+                    f"result of delete_from_branch_query: {delete_from_branch_query_result}"
+                )
+
         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(