dcs-sdk 1.7.1__tar.gz → 1.7.3__tar.gz

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dcs-sdk
-Version: 1.7.1
+Version: 1.7.3
 Summary: SDK for DataChecks
 Author: Waterdip Labs
 Author-email: hello@waterdip.ai
@@ -86,7 +86,7 @@ Requires-Dist: vertica-python (>=1.4.0) ; extra == "vertica" or extra == "all-db
 Description-Content-Type: text/markdown
 
 <h1 align="center">
-  DCS SDK v1.7.1
+  DCS SDK v1.7.3
 </h1>
 
 > SDK for DataChecks

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/README.md

@@ -1,5 +1,5 @@
 <h1 align="center">
-  DCS SDK v1.7.1
+  DCS SDK v1.7.3
 </h1>
 
 > SDK for DataChecks

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/dcs_core/integrations/databases/azure_blob.py

@@ -12,21 +12,15 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-import os
-import uuid
-from pathlib import Path
 from typing import Any, Dict, Optional
 
-import duckdb
 from azure.storage.blob import BlobServiceClient
 from loguru import logger
 
 from dcs_core.core.common.errors import (
-    DatachecksColumnFetchError,
     DataChecksDataSourcesConnectionError,
     DatachecksTableFetchError,
 )
-from dcs_core.core.common.models.data_source_resource import RawColumnInfo
 from dcs_core.core.datasource.file_datasource import FileDataSource
 
 

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/dcs_core/integrations/databases/mssql.py

@@ -167,8 +167,6 @@ class MssqlDataSource(SQLDataSource):
         :return: Dictionary with index details
         """
         schema = schema or self.schema_name
-        table = table.upper()
-        schema = schema.upper()
 
         query = f"""
             SELECT
@@ -673,8 +671,6 @@ class MssqlDataSource(SQLDataSource):
 
             quoted_name = self.quote_column(name)
 
-            query_parts.append(f"COUNT(DISTINCT {quoted_name}) AS [{name}_distinct]")
-            query_parts.append(f"COUNT({quoted_name}) - COUNT(DISTINCT {quoted_name}) AS [{name}_duplicate]")
             query_parts.append(f"SUM(CASE WHEN {quoted_name} IS NULL THEN 1 ELSE 0 END) AS [{name}_is_null]")
 
             if dtype in (
@@ -690,13 +686,20 @@ class MssqlDataSource(SQLDataSource):
                 "money",
                 "smallmoney",
             ):
+                query_parts.append(f"COUNT({quoted_name}) - COUNT(DISTINCT {quoted_name}) AS [{name}_duplicate]")
                 query_parts.append(f"MIN({quoted_name}) AS [{name}_min]")
                 query_parts.append(f"MAX({quoted_name}) AS [{name}_max]")
                 query_parts.append(f"AVG(CAST({quoted_name} AS FLOAT)) AS [{name}_average]")
+                query_parts.append(f"COUNT(DISTINCT {quoted_name}) AS [{name}_distinct]")
 
-            elif dtype in ("varchar", "nvarchar", "char", "nchar", "text", "ntext"):
+            elif dtype in ("varchar", "nvarchar", "char", "nchar"):
                 query_parts.append(f"MAX(LEN({quoted_name})) AS [{name}_max_character_length]")
 
+            elif dtype in ("text", "ntext", "xml"):
+                query_parts.append(
+                    f"MAX(LEN(CAST({quoted_name} AS NVARCHAR(MAX)))) " f"AS [{name}_max_character_length]"
+                )
+
         if additional_queries:
             query_parts.extend(additional_queries)
 

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/dcs_core/integrations/databases/oracle.py

@@ -143,8 +143,6 @@ class OracleDataSource(SQLDataSource):
         :return: Dictionary with index details
         """
         schema = schema or self.schema_name
-        table = table.upper()
-        schema = schema.upper()
 
         query = f"""
             SELECT
@@ -696,8 +694,8 @@ class OracleDataSource(SQLDataSource):
                 AND r_ac.OWNER = r_acc.OWNER
                 AND acc.POSITION = r_acc.POSITION
             WHERE ac.CONSTRAINT_TYPE = 'R'
-            AND ac.TABLE_NAME = '{table_name.upper()}'
-            AND ac.OWNER = '{schema.upper()}';
+            AND ac.TABLE_NAME = '{table_name}'
+            AND ac.OWNER = '{schema}';
         """
 
         try:

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/dcs_core/integrations/databases/postgres.py

@@ -136,8 +136,6 @@ class PostgresDataSource(SQLDataSource):
         :return: Dictionary with index details
         """
         schema = schema or self.schema_name
-        table = table.lower()
-        schema = schema.lower()
 
         query = f"""
             SELECT

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/dcs_sdk/__version__.py

@@ -12,4 +12,4 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-__version__ = "1.7.1"
+__version__ = "1.7.3"

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/dcs_sdk/sdk/data_diff/data_differ.py

@@ -738,10 +738,10 @@ class DBTableDiffer:
 
             self.response.update({"column_transforms": column_transforms})
             self.response.update({"schema_overrides": schema_overrides})
-            self.config.source.table = self.original_source_table_name
-            self.config.target.table = self.original_target_table_name
-            self.response["source_dataset"]["table_name"] = self.original_source_table_name
-            self.response["target_dataset"]["table_name"] = self.original_target_table_name
+            self.config.source.table = self.original_source_table_name or self.config.source.table
+            self.config.target.table = self.original_target_table_name or self.config.target.table
+            self.response["source_dataset"]["table_name"] = self.original_source_table_name or self.config.source.table
+            self.response["target_dataset"]["table_name"] = self.original_target_table_name or self.config.target.table
             return self.response
         except Exception as e:
             logger.exception(f"Error during diff_tables: {e}")

{dcs_sdk-1.7.1 → dcs_sdk-1.7.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dcs-sdk"
-version = "1.7.1"
+version = "1.7.3"
 description = "SDK for DataChecks"
 authors = ["Waterdip Labs <hello@waterdip.ai>"]
 readme = "README.md"