jayzhan211 commented on code in PR #11403:
URL: https://github.com/apache/datafusion/pull/11403#discussion_r1676066827
##########
datafusion/core/src/execution/session_state.rs:
##########
@@ -195,122 +196,10 @@ impl SessionState {
runtime: Arc<RuntimeEnv>,
catalog_list: Arc<dyn CatalogProviderList>,
) -> Self {
- let session_id = Uuid::new_v4().to_string();
-
- // Create table_factories for all default formats
- let mut table_factories: HashMap<String, Arc<dyn
TableProviderFactory>> =
- HashMap::new();
- #[cfg(feature = "parquet")]
- table_factories.insert("PARQUET".into(),
Arc::new(DefaultTableFactory::new()));
- table_factories.insert("CSV".into(),
Arc::new(DefaultTableFactory::new()));
- table_factories.insert("JSON".into(),
Arc::new(DefaultTableFactory::new()));
- table_factories.insert("NDJSON".into(),
Arc::new(DefaultTableFactory::new()));
- table_factories.insert("AVRO".into(),
Arc::new(DefaultTableFactory::new()));
- table_factories.insert("ARROW".into(),
Arc::new(DefaultTableFactory::new()));
-
- if config.create_default_catalog_and_schema() {
- let default_catalog = MemoryCatalogProvider::new();
-
- default_catalog
- .register_schema(
- &config.options().catalog.default_schema,
- Arc::new(MemorySchemaProvider::new()),
- )
- .expect("memory catalog provider can register schema");
-
- Self::register_default_schema(
- &config,
- &table_factories,
- &runtime,
- &default_catalog,
- );
-
- catalog_list.register_catalog(
- config.options().catalog.default_catalog.clone(),
- Arc::new(default_catalog),
- );
- }
-
- let expr_planners: Vec<Arc<dyn ExprPlanner>> = vec![
- Arc::new(functions::core::planner::CoreFunctionPlanner::default()),
- // register crate of array expressions (if enabled)
- #[cfg(feature = "array_expressions")]
- Arc::new(functions_array::planner::ArrayFunctionPlanner),
- #[cfg(feature = "array_expressions")]
- Arc::new(functions_array::planner::FieldAccessPlanner),
- #[cfg(any(
- feature = "datetime_expressions",
- feature = "unicode_expressions"
- ))]
- Arc::new(functions::planner::UserDefinedFunctionPlanner),
- ];
-
- let mut new_self = SessionState {
- session_id,
- analyzer: Analyzer::new(),
- expr_planners,
- optimizer: Optimizer::new(),
- physical_optimizers: PhysicalOptimizer::new(),
- query_planner: Arc::new(DefaultQueryPlanner {}),
- catalog_list,
- table_functions: HashMap::new(),
- scalar_functions: HashMap::new(),
- aggregate_functions: HashMap::new(),
- window_functions: HashMap::new(),
- serializer_registry: Arc::new(EmptySerializerRegistry),
- file_formats: HashMap::new(),
- table_options:
TableOptions::default_from_session_config(config.options()),
- config,
- execution_props: ExecutionProps::new(),
- runtime_env: runtime,
- table_factories,
- function_factory: None,
- };
-
- #[cfg(feature = "parquet")]
- if let Err(e) =
-
new_self.register_file_format(Arc::new(ParquetFormatFactory::new()), false)
- {
- log::info!("Unable to register default ParquetFormat: {e}")
- };
-
- if let Err(e) =
- new_self.register_file_format(Arc::new(JsonFormatFactory::new()),
false)
- {
- log::info!("Unable to register default JsonFormat: {e}")
- };
-
- if let Err(e) =
- new_self.register_file_format(Arc::new(CsvFormatFactory::new()),
false)
- {
- log::info!("Unable to register default CsvFormat: {e}")
- };
-
- if let Err(e) =
- new_self.register_file_format(Arc::new(ArrowFormatFactory::new()),
false)
- {
- log::info!("Unable to register default ArrowFormat: {e}")
- };
-
- if let Err(e) =
- new_self.register_file_format(Arc::new(AvroFormatFactory::new()),
false)
- {
- log::info!("Unable to register default AvroFormat: {e}")
- };
-
- // register built in functions
- functions::register_all(&mut new_self)
- .expect("can not register built in functions");
-
- // register crate of array expressions (if enabled)
- #[cfg(feature = "array_expressions")]
- functions_array::register_all(&mut new_self)
- .expect("can not register array expressions");
-
- functions_aggregate::register_all(&mut new_self)
- .expect("can not register aggregate functions");
-
- new_self
+ SessionStateBuilder::new_with_config_rt(config, runtime)
+ .with_defaults(true)
Review Comment:
I think we need either session state with default or not. If we have builder
that has `default: true` , we need another function `disable_default()` or
something similar to get the plain session state. If we have builder that has
`default: false`, we need function like `with_default` to get the session state
with builtin. Both are fine to me, as long as builtin is optional
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
