sws-spark-dissemination-helper 0.0.98__tar.gz → 0.0.100__tar.gz

{sws_spark_dissemination_helper-0.0.98 → sws_spark_dissemination_helper-0.0.100}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sws-spark-dissemination-helper
-Version: 0.0.98
+Version: 0.0.100
 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-0.0.98 → sws_spark_dissemination_helper-0.0.100}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sws-spark-dissemination-helper"
-version = "0.0.98"
+version = "0.0.100"
 dependencies = [
     "annotated-types==0.7.0",
     "boto3==1.36.18",

{sws_spark_dissemination_helper-0.0.98 → sws_spark_dissemination_helper-0.0.100}/src/sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py

@@ -464,6 +464,7 @@ class SWSBronzeIcebergSparkHelper:
         logging.info(f"bronze refs: {refs}")
 
         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}`
+        create_branch_query = f"ALTER TABLE {self.iceberg_tables.BRONZE.iceberg_id} CREATE OR REPLACE BRANCH `diss_tag_{self.tag_name}`"
         logging.info(f"create_branch_query: {create_branch_query}")
         create_branch_query_result = self.spark.sql(create_branch_query).collect()
 
@@ -493,27 +494,27 @@ class SWSBronzeIcebergSparkHelper:
             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])
-                # 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}")
-                # 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.disseminated_tag_df.filter(
-                    col(dimension_name).isin(codes)
+                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}")
+                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.disseminated_tag_df.filter(
+                #     col(dimension_name).isin(codes)
+                # )
 
-        # self.disseminated_tag_df = self.spark.read.option(
-        #     "branch", f"`diss_tag_{self.tag_name}`"
-        # ).table(self.iceberg_tables.BRONZE.iceberg_id)
+        self.disseminated_tag_df = self.spark.read.option(
+            "branch", f"`diss_tag_{self.tag_name}`"
+        ).table(self.iceberg_tables.BRONZE.iceberg_id)
 
-        self.disseminated_tag_df.writeTo(
-            f"{self.iceberg_tables.BRONZE.iceberg_id}.`branch_diss_tag_{self.tag_name}`"
-        ).overwritePartitions()
+        # self.disseminated_tag_df.writeTo(
+        #     f"{self.iceberg_tables.BRONZE.iceberg_id}.`branch_diss_tag_{self.tag_name}`"
+        # ).overwritePartitions()
 
         disseminated_tag_df = self.disseminated_tag_df.withColumn(
             "metadata", F.to_json(col("metadata"))