databricks-sql-connector 4.1.2__tar.gz → 4.1.3__tar.gz

{databricks_sql_connector-4.1.2 → databricks_sql_connector-4.1.3}/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Release History
 
+# 4.1.3 (2025-09-17)
+- Query tags integration (databricks/databricks-sql-python#663 by @sreekanth-db)
+- Add variant support (databricks/databricks-sql-python#560 by @shivam2680)
+
 # 4.1.2 (2025-08-22)
 - Streaming ingestion support for PUT operation (databricks/databricks-sql-python#643 by @sreekanth-db)
 - Removed use_threads argument on concat_tables for compatibility with pyarrow<14 (databricks/databricks-sql-python#684 by @jprakash-db)

{databricks_sql_connector-4.1.2 → databricks_sql_connector-4.1.3}/PKG-INFO

@@ -1,8 +1,9 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: databricks-sql-connector
-Version: 4.1.2
+Version: 4.1.3
 Summary: Databricks SQL Connector for Python
 License: Apache-2.0
+License-File: LICENSE
 Author: Databricks
 Author-email: databricks-sql-connector-maintainers@databricks.com
 Requires-Python: >=3.8.0,<4.0.0
@@ -14,6 +15,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Provides-Extra: pyarrow
 Requires-Dist: lz4 (>=4.0.2,<5.0.0)
 Requires-Dist: oauthlib (>=3.1.0,<4.0.0)

{databricks_sql_connector-4.1.2 → databricks_sql_connector-4.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "databricks-sql-connector"
-version = "4.1.2"
+version = "4.1.3"
 description = "Databricks SQL Connector for Python"
 authors = ["Databricks <databricks-sql-connector-maintainers@databricks.com>"]
 license = "Apache-2.0"

{databricks_sql_connector-4.1.2 → databricks_sql_connector-4.1.3}/src/databricks/sql/__init__.py

@@ -68,7 +68,7 @@ DATETIME = DBAPITypeObject("timestamp")
 DATE = DBAPITypeObject("date")
 ROWID = DBAPITypeObject()
 
-__version__ = "4.1.2"
+__version__ = "4.1.3"
 USER_AGENT_NAME = "PyDatabricksSqlConnector"
 
 # These two functions are pyhive legacy

{databricks_sql_connector-4.1.2 → databricks_sql_connector-4.1.3}/src/databricks/sql/backend/sea/utils/constants.py

@@ -15,6 +15,7 @@ ALLOWED_SESSION_CONF_TO_DEFAULT_VALUES_MAP: Dict[str, str] = {
     "STATEMENT_TIMEOUT": "0",
     "TIMEZONE": "UTC",
     "USE_CACHED_RESULT": "true",
+    "QUERY_TAGS": "",
 }
 
 

{databricks_sql_connector-4.1.2 → databricks_sql_connector-4.1.3}/src/databricks/sql/backend/thrift_backend.py

@@ -735,7 +735,7 @@ class ThriftDatabricksClient(DatabricksClient):
         return pyarrow.schema([convert_col(col) for col in t_table_schema.columns])
 
     @staticmethod
-    def _col_to_description(col, session_id_hex=None):
+    def _col_to_description(col, field=None, session_id_hex=None):
         type_entry = col.typeDesc.types[0]
 
         if type_entry.primitiveEntry:
@@ -764,12 +764,39 @@ class ThriftDatabricksClient(DatabricksClient):
         else:
             precision, scale = None, None
 
+        # Extract variant type from field if available
+        if field is not None:
+            try:
+                # Check for variant type in metadata
+                if field.metadata and b"Spark:DataType:SqlName" in field.metadata:
+                    sql_type = field.metadata.get(b"Spark:DataType:SqlName")
+                    if sql_type == b"VARIANT":
+                        cleaned_type = "variant"
+            except Exception as e:
+                logger.debug(f"Could not extract variant type from field: {e}")
+
         return col.columnName, cleaned_type, None, None, precision, scale, None
 
     @staticmethod
-    def _hive_schema_to_description(t_table_schema, session_id_hex=None):
+    def _hive_schema_to_description(
+        t_table_schema, schema_bytes=None, session_id_hex=None
+    ):
+        field_dict = {}
+        if pyarrow and schema_bytes:
+            try:
+                arrow_schema = pyarrow.ipc.read_schema(pyarrow.py_buffer(schema_bytes))
+                # Build a dictionary mapping column names to fields
+                for field in arrow_schema:
+                    field_dict[field.name] = field
+            except Exception as e:
+                logger.debug(f"Could not parse arrow schema: {e}")
+
         return [
-            ThriftDatabricksClient._col_to_description(col, session_id_hex)
+            ThriftDatabricksClient._col_to_description(
+                col,
+                field_dict.get(col.columnName) if field_dict else None,
+                session_id_hex,
+            )
             for col in t_table_schema.columns
         ]
 
@@ -802,11 +829,6 @@ class ThriftDatabricksClient(DatabricksClient):
             or direct_results.resultSet.hasMoreRows
         )
 
-        description = self._hive_schema_to_description(
-            t_result_set_metadata_resp.schema,
-            self._session_id_hex,
-        )
-
         if pyarrow:
             schema_bytes = (
                 t_result_set_metadata_resp.arrowSchema
@@ -819,6 +841,12 @@ class ThriftDatabricksClient(DatabricksClient):
         else:
             schema_bytes = None
 
+        description = self._hive_schema_to_description(
+            t_result_set_metadata_resp.schema,
+            schema_bytes,
+            self._session_id_hex,
+        )
+
         lz4_compressed = t_result_set_metadata_resp.lz4Compressed
         command_id = CommandId.from_thrift_handle(resp.operationHandle)
 
@@ -863,11 +891,6 @@ class ThriftDatabricksClient(DatabricksClient):
 
         t_result_set_metadata_resp = resp.resultSetMetadata
 
-        description = self._hive_schema_to_description(
-            t_result_set_metadata_resp.schema,
-            self._session_id_hex,
-        )
-
         if pyarrow:
             schema_bytes = (
                 t_result_set_metadata_resp.arrowSchema
@@ -880,6 +903,12 @@ class ThriftDatabricksClient(DatabricksClient):
         else:
             schema_bytes = None
 
+        description = self._hive_schema_to_description(
+            t_result_set_metadata_resp.schema,
+            schema_bytes,
+            self._session_id_hex,
+        )
+
         lz4_compressed = t_result_set_metadata_resp.lz4Compressed
         is_staging_operation = t_result_set_metadata_resp.isStagingOperation
         has_more_rows = resp.hasMoreRows