Merge branch 'exec-resp-norm' into sea-res-set

Author: varun-edachali-dbx

src/databricks/sql/backend/sea/models/requests.py

@@ -4,7 +4,7 @@
 
 @dataclass
 class CreateSessionRequest:
-    """Request to create a new session."""
+    """Representation of a request to create a new session."""
 
     warehouse_id: str
     session_confs: Optional[Dict[str, str]] = None
@@ -29,7 +29,7 @@ def to_dict(self) -> Dict[str, Any]:
 
 @dataclass
 class DeleteSessionRequest:
-    """Request to delete a session."""
+    """Representation of a request to delete a session."""
 
     warehouse_id: str
     session_id: str

src/databricks/sql/backend/sea/models/responses.py

@@ -4,7 +4,7 @@
 
 @dataclass
 class CreateSessionResponse:
-    """Response from creating a new session."""
+    """Representation of the response from creating a new session."""
 
     session_id: str
 

src/databricks/sql/backend/thrift_backend.py

@@ -3,22 +3,20 @@
 import logging
 import math
 import time
-import uuid
 import threading
 from typing import List, Union, Any, TYPE_CHECKING
 
 if TYPE_CHECKING:
     from databricks.sql.client import Cursor
 
-from databricks.sql.thrift_api.TCLIService.ttypes import TOperationState
 from databricks.sql.backend.types import (
     CommandState,
     SessionId,
     CommandId,
-    BackendType,
-    guid_to_hex_id,
     ExecuteResponse,
 )
+from databricks.sql.backend.utils import guid_to_hex_id
+
 
 try:
     import pyarrow
@@ -759,11 +757,13 @@ def _results_message_to_execute_response(self, resp, operation_state):
             )
         direct_results = resp.directResults
         has_been_closed_server_side = direct_results and direct_results.closeOperation
-        has_more_rows = (
+
+        is_direct_results = (
             (not direct_results)
             or (not direct_results.resultSet)
             or direct_results.resultSet.hasMoreRows
         )
+
         description = self._hive_schema_to_description(
             t_result_set_metadata_resp.schema
         )
@@ -779,43 +779,25 @@ def _results_message_to_execute_response(self, resp, operation_state):
             schema_bytes = None
 
         lz4_compressed = t_result_set_metadata_resp.lz4Compressed
-        is_staging_operation = t_result_set_metadata_resp.isStagingOperation
-        if direct_results and direct_results.resultSet:
-            assert direct_results.resultSet.results.startRowOffset == 0
-            assert direct_results.resultSetMetadata
-
-            arrow_queue_opt = ResultSetQueueFactory.build_queue(
-                row_set_type=t_result_set_metadata_resp.resultFormat,
-                t_row_set=direct_results.resultSet.results,
-                arrow_schema_bytes=schema_bytes,
-                max_download_threads=self.max_download_threads,
-                lz4_compressed=lz4_compressed,
-                description=description,
-                ssl_options=self._ssl_options,
-            )
-        else:
-            arrow_queue_opt = None
-
         command_id = CommandId.from_thrift_handle(resp.operationHandle)
 
         status = CommandState.from_thrift_state(operation_state)
         if status is None:
             raise ValueError(f"Unknown command state: {operation_state}")
 
-        return (
-            ExecuteResponse(
-                command_id=command_id,
-                status=status,
-                description=description,
-                has_more_rows=has_more_rows,
-                results_queue=arrow_queue_opt,
-                has_been_closed_server_side=has_been_closed_server_side,
-                lz4_compressed=lz4_compressed,
-                is_staging_operation=is_staging_operation,
-            ),
-            schema_bytes,
+        execute_response = ExecuteResponse(
+            command_id=command_id,
+            status=status,
+            description=description,
+            has_been_closed_server_side=has_been_closed_server_side,
+            lz4_compressed=lz4_compressed,
+            is_staging_operation=t_result_set_metadata_resp.isStagingOperation,
+            arrow_schema_bytes=schema_bytes,
+            result_format=t_result_set_metadata_resp.resultFormat,
         )
 
+        return execute_response, is_direct_results
+
     def get_execution_result(
         self, command_id: CommandId, cursor: "Cursor"
     ) -> "ResultSet":
@@ -840,9 +822,6 @@ def get_execution_result(
 
         t_result_set_metadata_resp = resp.resultSetMetadata
 
-        lz4_compressed = t_result_set_metadata_resp.lz4Compressed
-        is_staging_operation = t_result_set_metadata_resp.isStagingOperation
-        has_more_rows = resp.hasMoreRows
         description = self._hive_schema_to_description(
             t_result_set_metadata_resp.schema
         )
@@ -857,27 +836,21 @@ def get_execution_result(
         else:
             schema_bytes = None
 
-        queue = ResultSetQueueFactory.build_queue(
-            row_set_type=resp.resultSetMetadata.resultFormat,
-            t_row_set=resp.results,
-            arrow_schema_bytes=schema_bytes,
-            max_download_threads=self.max_download_threads,
-            lz4_compressed=lz4_compressed,
-            description=description,
-            ssl_options=self._ssl_options,
-        )
+        lz4_compressed = t_result_set_metadata_resp.lz4Compressed
+        is_staging_operation = t_result_set_metadata_resp.isStagingOperation
+        is_direct_results = resp.hasMoreRows
 
         status = self.get_query_state(command_id)
 
         execute_response = ExecuteResponse(
             command_id=command_id,
             status=status,
             description=description,
-            has_more_rows=has_more_rows,
-            results_queue=queue,
             has_been_closed_server_side=False,
             lz4_compressed=lz4_compressed,
             is_staging_operation=is_staging_operation,
+            arrow_schema_bytes=schema_bytes,
+            result_format=t_result_set_metadata_resp.resultFormat,
         )
 
         return ThriftResultSet(
@@ -887,7 +860,10 @@ def get_execution_result(
             buffer_size_bytes=cursor.buffer_size_bytes,
             arraysize=cursor.arraysize,
             use_cloud_fetch=cursor.connection.use_cloud_fetch,
-            arrow_schema_bytes=schema_bytes,
+            t_row_set=resp.results,
+            max_download_threads=self.max_download_threads,
+            ssl_options=self._ssl_options,
+            is_direct_results=is_direct_results,
         )
 
     def _wait_until_command_done(self, op_handle, initial_operation_status_resp):
@@ -918,7 +894,7 @@ def get_query_state(self, command_id: CommandId) -> CommandState:
         self._check_command_not_in_error_or_closed_state(thrift_handle, poll_resp)
         state = CommandState.from_thrift_state(operation_state)
         if state is None:
-            raise ValueError(f"Invalid operation state: {operation_state}")
+            raise ValueError(f"Unknown command state: {operation_state}")
         return state
 
     @staticmethod
@@ -1000,18 +976,25 @@ def execute_command(
             self._handle_execute_response_async(resp, cursor)
             return None
         else:
-            execute_response, arrow_schema_bytes = self._handle_execute_response(
+            execute_response, is_direct_results = self._handle_execute_response(
                 resp, cursor
             )
 
+            t_row_set = None
+            if resp.directResults and resp.directResults.resultSet:
+                t_row_set = resp.directResults.resultSet.results
+
             return ThriftResultSet(
                 connection=cursor.connection,
                 execute_response=execute_response,
                 thrift_client=self,
                 buffer_size_bytes=max_bytes,
                 arraysize=max_rows,
                 use_cloud_fetch=use_cloud_fetch,
-                arrow_schema_bytes=arrow_schema_bytes,
+                t_row_set=t_row_set,
+                max_download_threads=self.max_download_threads,
+                ssl_options=self._ssl_options,
+                is_direct_results=is_direct_results,
             )
 
     def get_catalogs(
@@ -1033,18 +1016,25 @@ def get_catalogs(
         )
         resp = self.make_request(self._client.GetCatalogs, req)
 
-        execute_response, arrow_schema_bytes = self._handle_execute_response(
+        execute_response, is_direct_results = self._handle_execute_response(
             resp, cursor
         )
 
+        t_row_set = None
+        if resp.directResults and resp.directResults.resultSet:
+            t_row_set = resp.directResults.resultSet.results
+
         return ThriftResultSet(
             connection=cursor.connection,
             execute_response=execute_response,
             thrift_client=self,
             buffer_size_bytes=max_bytes,
             arraysize=max_rows,
             use_cloud_fetch=cursor.connection.use_cloud_fetch,
-            arrow_schema_bytes=arrow_schema_bytes,
+            t_row_set=t_row_set,
+            max_download_threads=self.max_download_threads,
+            ssl_options=self._ssl_options,
+            is_direct_results=is_direct_results,
         )
 
     def get_schemas(
@@ -1070,18 +1060,25 @@ def get_schemas(
         )
         resp = self.make_request(self._client.GetSchemas, req)
 
-        execute_response, arrow_schema_bytes = self._handle_execute_response(
+        execute_response, is_direct_results = self._handle_execute_response(
             resp, cursor
         )
 
+        t_row_set = None
+        if resp.directResults and resp.directResults.resultSet:
+            t_row_set = resp.directResults.resultSet.results
+
         return ThriftResultSet(
             connection=cursor.connection,
             execute_response=execute_response,
             thrift_client=self,
             buffer_size_bytes=max_bytes,
             arraysize=max_rows,
             use_cloud_fetch=cursor.connection.use_cloud_fetch,
-            arrow_schema_bytes=arrow_schema_bytes,
+            t_row_set=t_row_set,
+            max_download_threads=self.max_download_threads,
+            ssl_options=self._ssl_options,
+            is_direct_results=is_direct_results,
         )
 
     def get_tables(
@@ -1111,18 +1108,25 @@ def get_tables(
         )
         resp = self.make_request(self._client.GetTables, req)
 
-        execute_response, arrow_schema_bytes = self._handle_execute_response(
+        execute_response, is_direct_results = self._handle_execute_response(
             resp, cursor
         )
 
+        t_row_set = None
+        if resp.directResults and resp.directResults.resultSet:
+            t_row_set = resp.directResults.resultSet.results
+
         return ThriftResultSet(
             connection=cursor.connection,
             execute_response=execute_response,
             thrift_client=self,
             buffer_size_bytes=max_bytes,
             arraysize=max_rows,
             use_cloud_fetch=cursor.connection.use_cloud_fetch,
-            arrow_schema_bytes=arrow_schema_bytes,
+            t_row_set=t_row_set,
+            max_download_threads=self.max_download_threads,
+            ssl_options=self._ssl_options,
+            is_direct_results=is_direct_results,
         )
 
     def get_columns(
@@ -1152,18 +1156,25 @@ def get_columns(
         )
         resp = self.make_request(self._client.GetColumns, req)
 
-        execute_response, arrow_schema_bytes = self._handle_execute_response(
+        execute_response, is_direct_results = self._handle_execute_response(
             resp, cursor
         )
 
+        t_row_set = None
+        if resp.directResults and resp.directResults.resultSet:
+            t_row_set = resp.directResults.resultSet.results
+
         return ThriftResultSet(
             connection=cursor.connection,
             execute_response=execute_response,
             thrift_client=self,
             buffer_size_bytes=max_bytes,
             arraysize=max_rows,
             use_cloud_fetch=cursor.connection.use_cloud_fetch,
-            arrow_schema_bytes=arrow_schema_bytes,
+            t_row_set=t_row_set,
+            max_download_threads=self.max_download_threads,
+            ssl_options=self._ssl_options,
+            is_direct_results=is_direct_results,
         )
 
     def _handle_execute_response(self, resp, cursor):
@@ -1177,11 +1188,7 @@ def _handle_execute_response(self, resp, cursor):
             resp.directResults and resp.directResults.operationStatus,
         )
 
-        (
-            execute_response,
-            arrow_schema_bytes,
-        ) = self._results_message_to_execute_response(resp, final_operation_state)
-        return execute_response, arrow_schema_bytes
+        return self._results_message_to_execute_response(resp, final_operation_state)
 
     def _handle_execute_response_async(self, resp, cursor):
         command_id = CommandId.from_thrift_handle(resp.operationHandle)

src/databricks/sql/backend/types.py

@@ -423,11 +423,9 @@ class ExecuteResponse:
 
     command_id: CommandId
     status: CommandState
-    description: Optional[
-        List[Tuple[str, str, None, None, Optional[int], Optional[int], bool]]
-    ] = None
-    has_more_rows: bool = False
-    results_queue: Optional[Any] = None
+    description: Optional[List[Tuple]] = None
     has_been_closed_server_side: bool = False
     lz4_compressed: bool = True
     is_staging_operation: bool = False
+    arrow_schema_bytes: Optional[bytes] = None
+    result_format: Optional[Any] = None