feat: customize column default values for external tables

datafusion/core/src/catalog/listing_schema.rs

@@ -149,6 +149,7 @@ impl ListingSchemaProvider {
                             unbounded: false,
                             options: Default::default(),
                             constraints: Constraints::empty(),
+                            column_defaults: Default::default(),
                         },
                     )
                     .await?;

datafusion/core/src/datasource/listing/table.rs

@@ -17,6 +17,7 @@
 
 //! The table implementation.
 
+use std::collections::HashMap;
 use std::str::FromStr;
 use std::{any::Any, sync::Arc};
 
@@ -558,6 +559,7 @@ pub struct ListingTable {
     collected_statistics: FileStatisticsCache,
     infinite_source: bool,
     constraints: Constraints,
+    column_defaults: HashMap<String, Expr>,
 }
 
 impl ListingTable {
@@ -596,6 +598,7 @@ impl ListingTable {
             collected_statistics: Arc::new(DefaultFileStatisticsCache::default()),
             infinite_source,
             constraints: Constraints::empty(),
+            column_defaults: HashMap::new(),
         };
 
         Ok(table)
@@ -607,6 +610,15 @@ impl ListingTable {
         self
     }
 
+    /// Assign column defaults
+    pub fn with_column_defaults(
+        mut self,
+        column_defaults: HashMap<String, Expr>,
+    ) -> Self {
+        self.column_defaults = column_defaults;
+        self
+    }
+
     /// Set the [`FileStatisticsCache`] used to cache parquet file statistics.
     ///
     /// Setting a statistics cache on the `SessionContext` can avoid refetching statistics
@@ -844,6 +856,10 @@ impl TableProvider for ListingTable {
             .create_writer_physical_plan(input, state, config, order_requirements)
             .await
     }
+
+    fn get_column_default(&self, column: &str) -> Option<&Expr> {
+        self.column_defaults.get(column)
+    }
 }
 
 impl ListingTable {

datafusion/core/src/datasource/listing_table_factory.rs

@@ -228,7 +228,8 @@ impl TableProviderFactory for ListingTableFactory {
             .with_cache(state.runtime_env().cache_manager.get_file_statistic_cache());
         let table = provider
             .with_definition(cmd.definition.clone())
-            .with_constraints(cmd.constraints.clone());
+            .with_constraints(cmd.constraints.clone())
+            .with_column_defaults(cmd.column_defaults.clone());
         Ok(Arc::new(table))
     }
 }
@@ -279,6 +280,7 @@ mod tests {
             unbounded: false,
             options: HashMap::new(),
             constraints: Constraints::empty(),
+            column_defaults: HashMap::new(),
         };
         let table_provider = factory.create(&state, &cmd).await.unwrap();
         let listing_table = table_provider

datafusion/core/src/datasource/memory.rs

@@ -19,9 +19,9 @@
 
 use datafusion_physical_plan::metrics::MetricsSet;
 use futures::StreamExt;
-use hashbrown::HashMap;
 use log::debug;
 use std::any::Any;
+use std::collections::HashMap;
 use std::fmt::{self, Debug};
 use std::sync::Arc;
 

datafusion/expr/src/logical_plan/ddl.rs

@@ -194,6 +194,8 @@ pub struct CreateExternalTable {
     pub options: HashMap<String, String>,
     /// The list of constraints in the schema, such as primary key, unique, etc.
     pub constraints: Constraints,
+    /// Default values for columns
+    pub column_defaults: HashMap<String, Expr>,
 }
 
 // Hashing refers to a subset of fields considered in PartialEq.

datafusion/proto/proto/datafusion.proto

@@ -216,6 +216,7 @@ message CreateExternalTableNode {
   bool unbounded = 14;
   map<string, string> options = 11;
   Constraints constraints = 15;
+  map<string, LogicalExprNode> column_defaults = 16;
 }
 
 message PrepareNode {

datafusion/proto/src/logical_plan/mod.rs

@@ -15,6 +15,7 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use std::collections::HashMap;
 use std::fmt::Debug;
 use std::str::FromStr;
 use std::sync::Arc;
@@ -521,6 +522,13 @@ impl AsLogicalPlan for LogicalPlanNode {
                     order_exprs.push(order_expr)
                 }
 
+                let mut column_defaults =
+                    HashMap::with_capacity(create_extern_table.column_defaults.len());
+                for (col_name, expr) in &create_extern_table.column_defaults {
+                    let expr = from_proto::parse_expr(expr, ctx)?;
+                    column_defaults.insert(col_name.clone(), expr);
+                }
+
                 Ok(LogicalPlan::Ddl(DdlStatement::CreateExternalTable(CreateExternalTable {
                     schema: pb_schema.try_into()?,
                     name: from_owned_table_reference(create_extern_table.name.as_ref(), "CreateExternalTable")?,
@@ -540,6 +548,7 @@ impl AsLogicalPlan for LogicalPlanNode {
                     unbounded: create_extern_table.unbounded,
                     options: create_extern_table.options.clone(),
                     constraints: constraints.into(),
+                    column_defaults,
                 })))
             }
             LogicalPlanType::CreateView(create_view) => {
@@ -1298,6 +1307,7 @@ impl AsLogicalPlan for LogicalPlanNode {
                     unbounded,
                     options,
                     constraints,
+                    column_defaults,
                 },
             )) => {
                 let mut converted_order_exprs: Vec<LogicalExprNodeCollection> = vec![];
@@ -1312,6 +1322,12 @@ impl AsLogicalPlan for LogicalPlanNode {
                     converted_order_exprs.push(temp);
                 }
 
+                let mut converted_column_defaults =
+                    HashMap::with_capacity(column_defaults.len());
+                for (col_name, expr) in column_defaults {
+                    converted_column_defaults.insert(col_name.clone(), expr.try_into()?);
+                }
+
                 Ok(protobuf::LogicalPlanNode {
                     logical_plan_type: Some(LogicalPlanType::CreateExternalTable(
                         protobuf::CreateExternalTableNode {
@@ -1329,6 +1345,7 @@ impl AsLogicalPlan for LogicalPlanNode {
                             unbounded: *unbounded,
                             options: options.clone(),
                             constraints: Some(constraints.clone().into()),
+                            column_defaults: converted_column_defaults,
                         },
                     )),
                 })

datafusion/proto/tests/cases/roundtrip_logical_plan.rs

@@ -220,8 +220,8 @@ async fn roundtrip_custom_listing_tables() -> Result<()> {
     // Make sure during round-trip, constraint information is preserved
     let query = "CREATE EXTERNAL TABLE multiple_ordered_table_with_pk (
               a0 INTEGER,
-              a INTEGER,
-              b INTEGER,
+              a INTEGER DEFAULT 1*2 + 3,
+              b INTEGER DEFAULT NULL,
               c INTEGER,
               d INTEGER,
               primary key(c)
@@ -232,11 +232,12 @@ async fn roundtrip_custom_listing_tables() -> Result<()> {
             WITH ORDER (c ASC)
             LOCATION '../core/tests/data/window_2.csv';";
 
-    let plan = ctx.sql(query).await?.into_optimized_plan()?;
+    let plan = ctx.state().create_logical_plan(query).await?;
 
     let bytes = logical_plan_to_bytes(&plan)?;
     let logical_round_trip = logical_plan_from_bytes(&bytes, &ctx)?;
-    assert_eq!(format!("{plan:?}"), format!("{logical_round_trip:?}"));
+    // Use exact matching to verify everything, such as column defaults
+    assert_eq!(plan, logical_round_trip);
 
     Ok(())
 }

datafusion/sql/src/statement.rs

@@ -755,11 +755,18 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
             )?;
         }
 
+        let mut planner_context = PlannerContext::new();
+
+        let column_defaults = self
+            .build_column_defaults(&columns, &mut planner_context)?
+            .into_iter()
+            .collect();
+
         let schema = self.build_schema(columns)?;
         let df_schema = schema.to_dfschema_ref()?;
 
         let ordered_exprs =
-            self.build_order_by(order_exprs, &df_schema, &mut PlannerContext::new())?;
+            self.build_order_by(order_exprs, &df_schema, &mut planner_context)?;
 
         // External tables do not support schemas at the moment, so the name is just a table name
         let name = OwnedTableReference::bare(name);
@@ -781,6 +788,7 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
                 unbounded,
                 options,
                 constraints,
+                column_defaults,
             },
         )))
     }

datafusion/sqllogictest/test_files/insert_to_external.slt

@@ -543,3 +543,48 @@ select * from table_without_values;
 
 statement ok
 drop table table_without_values;
+
+
+### Test for specifying column's default value
+
+statement ok
+CREATE EXTERNAL TABLE test_column_defaults(
+  a int,
+  b int not null default null,
+  c int default 100*2+300,
+  d text default lower('DEFAULT_TEXT'),
+  e timestamp default now()
+) STORED AS parquet
+LOCATION 'test_files/scratch/insert_to_external/external_parquet_table_q6'
+OPTIONS (create_local_path 'true');
+
+query IIITP
+insert into test_column_defaults values(1, 10, 100, 'ABC', now())
+----
+1
+
+statement error DataFusion error: Execution error: Invalid batch column at '1' has null but schema specifies non-nullable
+insert into test_column_defaults(a) values(2)
+
+query IIITP
+insert into test_column_defaults(b) values(20)
+----
+1
+
+query IIIT rowsort
+select a,b,c,d from test_column_defaults
+----
+1 10 100 ABC
+NULL 20 500 default_text
+
+statement ok
+drop table test_column_defaults
+
+# test invalid default value
+statement error DataFusion error: Error during planning: Column reference is not allowed in the DEFAULT expression : Schema error: No field named a.
+CREATE EXTERNAL TABLE test_column_defaults(
+  a int,
+  b int default a+1
+) STORED AS parquet
+LOCATION 'test_files/scratch/insert_to_external/external_parquet_table_q7'
+OPTIONS (create_local_path 'true');