SeaDatabricksClient: Add Metadata Commands

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

@@ -10,6 +10,7 @@
     ResultDisposition,
     ResultCompression,
     WaitTimeout,
+    MetadataCommands,
 )
 
 if TYPE_CHECKING:
@@ -627,9 +628,22 @@ def get_catalogs(
         max_rows: int,
         max_bytes: int,
         cursor: "Cursor",
-    ):
-        """Not implemented yet."""
-        raise NotImplementedError("get_catalogs is not yet implemented for SEA backend")
+    ) -> "ResultSet":
+        """Get available catalogs by executing 'SHOW CATALOGS'."""
+        result = self.execute_command(
+            operation=MetadataCommands.SHOW_CATALOGS.value,
+            session_id=session_id,
+            max_rows=max_rows,
+            max_bytes=max_bytes,
+            lz4_compression=False,
+            cursor=cursor,
+            use_cloud_fetch=False,
+            parameters=[],
+            async_op=False,
+            enforce_embedded_schema_correctness=False,
+        )
+        assert result is not None, "execute_command returned None in synchronous mode"
+        return result
 
     def get_schemas(
         self,
@@ -639,9 +653,30 @@ def get_schemas(
         cursor: "Cursor",
         catalog_name: Optional[str] = None,
         schema_name: Optional[str] = None,
-    ):
-        """Not implemented yet."""
-        raise NotImplementedError("get_schemas is not yet implemented for SEA backend")
+    ) -> "ResultSet":
+        """Get schemas by executing 'SHOW SCHEMAS IN catalog [LIKE pattern]'."""
+        if not catalog_name:
+            raise ValueError("Catalog name is required for get_schemas")
+
+        operation = MetadataCommands.SHOW_SCHEMAS.value.format(catalog_name)
+
+        if schema_name:
+            operation += MetadataCommands.LIKE_PATTERN.value.format(schema_name)
+
+        result = self.execute_command(
+            operation=operation,
+            session_id=session_id,
+            max_rows=max_rows,
+            max_bytes=max_bytes,
+            lz4_compression=False,
+            cursor=cursor,
+            use_cloud_fetch=False,
+            parameters=[],
+            async_op=False,
+            enforce_embedded_schema_correctness=False,
+        )
+        assert result is not None, "execute_command returned None in synchronous mode"
+        return result
 
     def get_tables(
         self,
@@ -653,9 +688,48 @@ def get_tables(
         schema_name: Optional[str] = None,
         table_name: Optional[str] = None,
         table_types: Optional[List[str]] = None,
-    ):
-        """Not implemented yet."""
-        raise NotImplementedError("get_tables is not yet implemented for SEA backend")
+    ) -> "ResultSet":
+        """Get tables by executing 'SHOW TABLES IN catalog [SCHEMA LIKE pattern] [LIKE pattern]'."""
+        operation = (
+            MetadataCommands.SHOW_TABLES_ALL_CATALOGS.value
+            if catalog_name in [None, "*", "%"]
+            else MetadataCommands.SHOW_TABLES.value.format(
+                MetadataCommands.CATALOG_SPECIFIC.value.format(catalog_name)
+            )
+        )
+
+        if schema_name:
+            operation += MetadataCommands.SCHEMA_LIKE_PATTERN.value.format(schema_name)
+
+        if table_name:
+            operation += MetadataCommands.LIKE_PATTERN.value.format(table_name)
+
+        result = self.execute_command(
+            operation=operation,
+            session_id=session_id,
+            max_rows=max_rows,
+            max_bytes=max_bytes,
+            lz4_compression=False,
+            cursor=cursor,
+            use_cloud_fetch=False,
+            parameters=[],
+            async_op=False,
+            enforce_embedded_schema_correctness=False,
+        )
+        assert result is not None, "execute_command returned None in synchronous mode"
+
+        from databricks.sql.result_set import SeaResultSet
+
+        assert isinstance(
+            result, SeaResultSet
+        ), "execute_command returned a non-SeaResultSet"
+
+        # Apply client-side filtering by table_types
+        from databricks.sql.backend.sea.utils.filters import ResultSetFilter
+
+        result = ResultSetFilter.filter_tables_by_type(result, table_types)
+
+        return result
 
     def get_columns(
         self,
@@ -667,6 +741,33 @@ def get_columns(
         schema_name: Optional[str] = None,
         table_name: Optional[str] = None,
         column_name: Optional[str] = None,
-    ):
-        """Not implemented yet."""
-        raise NotImplementedError("get_columns is not yet implemented for SEA backend")
+    ) -> "ResultSet":
+        """Get columns by executing 'SHOW COLUMNS IN CATALOG catalog [SCHEMA LIKE pattern] [TABLE LIKE pattern] [LIKE pattern]'."""
+        if not catalog_name:
+            raise ValueError("Catalog name is required for get_columns")
+
+        operation = MetadataCommands.SHOW_COLUMNS.value.format(catalog_name)
+
+        if schema_name:
+            operation += MetadataCommands.SCHEMA_LIKE_PATTERN.value.format(schema_name)
+
+        if table_name:
+            operation += MetadataCommands.TABLE_LIKE_PATTERN.value.format(table_name)
+
+        if column_name:
+            operation += MetadataCommands.LIKE_PATTERN.value.format(column_name)
+
+        result = self.execute_command(
+            operation=operation,
+            session_id=session_id,
+            max_rows=max_rows,
+            max_bytes=max_bytes,
+            lz4_compression=False,
+            cursor=cursor,
+            use_cloud_fetch=False,
+            parameters=[],
+            async_op=False,
+            enforce_embedded_schema_correctness=False,
+        )
+        assert result is not None, "execute_command returned None in synchronous mode"
+        return result

src/databricks/sql/backend/sea/utils/constants.py

@@ -45,3 +45,23 @@ class WaitTimeout(Enum):
 
     ASYNC = "0s"
     SYNC = "10s"
+
+
+class MetadataCommands(Enum):
+    """SQL commands used in the SEA backend.
+
+    These constants are used for metadata operations and other SQL queries
+    to ensure consistency and avoid string literal duplication.
+    """
+
+    SHOW_CATALOGS = "SHOW CATALOGS"
+    SHOW_SCHEMAS = "SHOW SCHEMAS IN {}"
+    SHOW_TABLES = "SHOW TABLES IN {}"
+    SHOW_TABLES_ALL_CATALOGS = "SHOW TABLES IN ALL CATALOGS"
+    SHOW_COLUMNS = "SHOW COLUMNS IN CATALOG {}"
+
+    LIKE_PATTERN = " LIKE '{}'"
+    SCHEMA_LIKE_PATTERN = " SCHEMA" + LIKE_PATTERN
+    TABLE_LIKE_PATTERN = " TABLE" + LIKE_PATTERN
+
+    CATALOG_SPECIFIC = "CATALOG {}"

src/databricks/sql/backend/sea/utils/filters.py

@@ -0,0 +1,153 @@
+"""
+Client-side filtering utilities for Databricks SQL connector.
+
+This module provides filtering capabilities for result sets returned by different backends.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import (
+    List,
+    Optional,
+    Any,
+    Callable,
+    cast,
+    TYPE_CHECKING,
+)
+
+if TYPE_CHECKING:
+    from databricks.sql.result_set import SeaResultSet
+
+from databricks.sql.backend.types import ExecuteResponse
+
+logger = logging.getLogger(__name__)
+
+
+class ResultSetFilter:
+    """
+    A general-purpose filter for result sets.
+    """
+
+    @staticmethod
+    def _filter_sea_result_set(
+        result_set: SeaResultSet, filter_func: Callable[[List[Any]], bool]
+    ) -> SeaResultSet:
+        """
+        Filter a SEA result set using the provided filter function.
+
+        Args:
+            result_set: The SEA result set to filter
+            filter_func: Function that takes a row and returns True if the row should be included
+
+        Returns:
+            A filtered SEA result set
+        """
+
+        # Get all remaining rows
+        all_rows = result_set.results.remaining_rows()
+
+        # Filter rows
+        filtered_rows = [row for row in all_rows if filter_func(row)]
+
+        # Reuse the command_id from the original result set
+        command_id = result_set.command_id
+
+        # Create an ExecuteResponse with the filtered data
+        execute_response = ExecuteResponse(
+            command_id=command_id,
+            status=result_set.status,
+            description=result_set.description,
+            has_been_closed_server_side=result_set.has_been_closed_server_side,
+            lz4_compressed=result_set.lz4_compressed,
+            arrow_schema_bytes=result_set._arrow_schema_bytes,
+            is_staging_operation=False,
+        )
+
+        # Create a new ResultData object with filtered data
+        from databricks.sql.backend.sea.models.base import ResultData
+
+        result_data = ResultData(data=filtered_rows, external_links=None)
+
+        from databricks.sql.backend.sea.backend import SeaDatabricksClient
+        from databricks.sql.result_set import SeaResultSet
+
+        # Create a new SeaResultSet with the filtered data
+        filtered_result_set = SeaResultSet(
+            connection=result_set.connection,
+            execute_response=execute_response,
+            sea_client=cast(SeaDatabricksClient, result_set.backend),
+            buffer_size_bytes=result_set.buffer_size_bytes,
+            arraysize=result_set.arraysize,
+            result_data=result_data,
+        )
+
+        return filtered_result_set
+
+    @staticmethod
+    def filter_by_column_values(
+        result_set: SeaResultSet,
+        column_index: int,
+        allowed_values: List[str],
+        case_sensitive: bool = False,
+    ) -> SeaResultSet:
+        """
+        Filter a result set by values in a specific column.
+
+        Args:
+            result_set: The result set to filter
+            column_index: The index of the column to filter on
+            allowed_values: List of allowed values for the column
+            case_sensitive: Whether to perform case-sensitive comparison
+
+        Returns:
+            A filtered result set
+        """
+
+        # Convert to uppercase for case-insensitive comparison if needed
+        if not case_sensitive:
+            allowed_values = [v.upper() for v in allowed_values]
+
+        return ResultSetFilter._filter_sea_result_set(
+            result_set,
+            lambda row: (
+                len(row) > column_index
+                and isinstance(row[column_index], str)
+                and (
+                    row[column_index].upper()
+                    if not case_sensitive
+                    else row[column_index]
+                )
+                in allowed_values
+            ),
+        )
+
+    @staticmethod
+    def filter_tables_by_type(
+        result_set: SeaResultSet, table_types: Optional[List[str]] = None
+    ) -> SeaResultSet:
+        """
+        Filter a result set of tables by the specified table types.
+
+        This is a client-side filter that processes the result set after it has been
+        retrieved from the server. It filters out tables whose type does not match
+        any of the types in the table_types list.
+
+        Args:
+            result_set: The original result set containing tables
+            table_types: List of table types to include (e.g., ["TABLE", "VIEW"])
+
+        Returns:
+            A filtered result set containing only tables of the specified types
+        """
+
+        # Default table types if none specified
+        DEFAULT_TABLE_TYPES = ["TABLE", "VIEW", "SYSTEM TABLE"]
+        valid_types = (
+            table_types if table_types and len(table_types) > 0 else DEFAULT_TABLE_TYPES
+        )
+
+        # Table type is the 6th column (index 5)
+        return ResultSetFilter.filter_by_column_values(
+            result_set, 5, valid_types, case_sensitive=True
+        )