Merge commit 'e3af174efe14ce76ebf557bf258e7139bb5a7f9c' into chunchun…

…/update-df-june-week-2-2

Cargo.toml

@@ -53,7 +53,7 @@ license = "Apache-2.0"
 readme = "README.md"
 repository = "https://github.com/apache/datafusion"
 rust-version = "1.73"
-version = "38.0.0"
+version = "39.0.0"
 
 [workspace.dependencies]
 # We turn off default-features for some dependencies here so the workspaces which inherit them can
@@ -86,23 +86,23 @@ bytes = "1.4"
 chrono = { version = "0.4.34", default-features = false }
 ctor = "0.2.0"
 dashmap = "5.5.0"
-datafusion = { path = "datafusion/core", version = "38.0.0", default-features = false }
-datafusion-common = { path = "datafusion/common", version = "38.0.0", default-features = false }
-datafusion-common-runtime = { path = "datafusion/common-runtime", version = "38.0.0" }
-datafusion-execution = { path = "datafusion/execution", version = "38.0.0" }
-datafusion-expr = { path = "datafusion/expr", version = "38.0.0" }
-datafusion-functions = { path = "datafusion/functions", version = "38.0.0" }
-datafusion-functions-aggregate = { path = "datafusion/functions-aggregate", version = "38.0.0" }
-datafusion-functions-array = { path = "datafusion/functions-array", version = "38.0.0" }
-datafusion-optimizer = { path = "datafusion/optimizer", version = "38.0.0", default-features = false }
-datafusion-physical-expr = { path = "datafusion/physical-expr", version = "38.0.0", default-features = false }
-datafusion-physical-expr-common = { path = "datafusion/physical-expr-common", version = "38.0.0", default-features = false }
-datafusion-physical-plan = { path = "datafusion/physical-plan", version = "38.0.0" }
-datafusion-proto = { path = "datafusion/proto", version = "38.0.0" }
-datafusion-proto-common = { path = "datafusion/proto-common", version = "38.0.0" }
-datafusion-sql = { path = "datafusion/sql", version = "38.0.0" }
-datafusion-sqllogictest = { path = "datafusion/sqllogictest", version = "38.0.0" }
-datafusion-substrait = { path = "datafusion/substrait", version = "38.0.0" }
+datafusion = { path = "datafusion/core", version = "39.0.0", default-features = false }
+datafusion-common = { path = "datafusion/common", version = "39.0.0", default-features = false }
+datafusion-common-runtime = { path = "datafusion/common-runtime", version = "39.0.0" }
+datafusion-execution = { path = "datafusion/execution", version = "39.0.0" }
+datafusion-expr = { path = "datafusion/expr", version = "39.0.0" }
+datafusion-functions = { path = "datafusion/functions", version = "39.0.0" }
+datafusion-functions-aggregate = { path = "datafusion/functions-aggregate", version = "39.0.0" }
+datafusion-functions-array = { path = "datafusion/functions-array", version = "39.0.0" }
+datafusion-optimizer = { path = "datafusion/optimizer", version = "39.0.0", default-features = false }
+datafusion-physical-expr = { path = "datafusion/physical-expr", version = "39.0.0", default-features = false }
+datafusion-physical-expr-common = { path = "datafusion/physical-expr-common", version = "39.0.0", default-features = false }
+datafusion-physical-plan = { path = "datafusion/physical-plan", version = "39.0.0" }
+datafusion-proto = { path = "datafusion/proto", version = "39.0.0" }
+datafusion-proto-common = { path = "datafusion/proto-common", version = "39.0.0" }
+datafusion-sql = { path = "datafusion/sql", version = "39.0.0" }
+datafusion-sqllogictest = { path = "datafusion/sqllogictest", version = "39.0.0" }
+datafusion-substrait = { path = "datafusion/substrait", version = "39.0.0" }
 doc-comment = "0.3"
 env_logger = "0.11"
 futures = "0.3"

datafusion-cli/Cargo.toml

@@ -18,7 +18,7 @@
 [package]
 name = "datafusion-cli"
 description = "Command Line Client for DataFusion query engine."
-version = "38.0.0"
+version = "39.0.0"
 authors = ["Apache DataFusion <[email protected]>"]
 edition = "2021"
 keywords = ["arrow", "datafusion", "query", "sql"]
@@ -35,7 +35,7 @@ async-trait = "0.1.41"
 aws-config = "0.55"
 aws-credential-types = "0.55"
 clap = { version = "3", features = ["derive", "cargo"] }
-datafusion = { path = "../datafusion/core", version = "38.0.0", features = [
+datafusion = { path = "../datafusion/core", version = "39.0.0", features = [
     "avro",
     "crypto_expressions",
     "datetime_expressions",

datafusion/CHANGELOG.md

@@ -19,41 +19,4 @@
 
 # Changelog
 
-- [38.0.0](../dev/changelog/38.0.0.md)
-- [37.1.0](../dev/changelog/37.1.0.md)
-- [37.0.0](../dev/changelog/37.0.0.md)
-- [36.0.0](../dev/changelog/36.0.0.md)
-- [35.0.0](../dev/changelog/35.0.0.md)
-- [34.0.0](../dev/changelog/34.0.0.md)
-- [33.0.0](../dev/changelog/33.0.0.md)
-- [32.0.0](../dev/changelog/32.0.0.md)
-- [31.0.0](../dev/changelog/31.0.0.md)
-- [30.0.0](../dev/changelog/30.0.0.md)
-- [29.0.0](../dev/changelog/29.0.0.md)
-- [28.0.0](../dev/changelog/28.0.0.md)
-- [27.0.0](../dev/changelog/27.0.0.md)
-- [26.0.0](../dev/changelog/26.0.0.md)
-- [25.0.0](../dev/changelog/25.0.0.md)
-- [24.0.0](../dev/changelog/24.0.0.md)
-- [23.0.0](../dev/changelog/23.0.0.md)
-- [22.0.0](../dev/changelog/22.0.0.md)
-- [21.1.0](../dev/changelog/21.1.0.md)
-- [21.0.0](../dev/changelog/21.0.0.md)
-- [20.0.0](../dev/changelog/20.0.0.md)
-- [19.0.0](../dev/changelog/19.0.0.md)
-- [18.0.0](../dev/changelog/18.0.0.md)
-- [17.0.0](../dev/changelog/17.0.0.md)
-- [16.1.0](../dev/changelog/16.1.0.md)
-- [16.0.0](../dev/changelog/16.0.0.md)
-- [15.0.0](../dev/changelog/15.0.0.md)
-- [14.0.0](../dev/changelog/14.0.0.md)
-- [13.0.0](../dev/changelog/13.0.0.md)
-- [12.0.0](../dev/changelog/12.0.0.md)
-- [11.0.0](../dev/changelog/11.0.0.md)
-- [10.0.0](../dev/changelog/10.0.0.md)
-- [9.0.0](../dev/changelog/9.0.0.md)
-- [8.0.0](../dev/changelog/8.0.0.md)
-- [7.1.0](../dev/changelog/7.1.0.md)
-- [7.0.0](../dev/changelog/7.0.0.md)
-- [6.0.0](../dev/changelog/6.0.0.md)
-- [5.0.0](../dev/changelog/5.0.0.md)
+Change logs for each release can be found [here](https://github.com/apache/datafusion/tree/main/dev/changelog).

datafusion/expr/src/expr_fn.rs

@@ -168,20 +168,6 @@ pub fn max(expr: Expr) -> Expr {
     ))
 }
 
-/// Create an expression to represent the sum() aggregate function
-///
-/// TODO: Remove this function and use `sum` from `datafusion_functions_aggregate::expr_fn` instead
-pub fn sum(expr: Expr) -> Expr {
-    Expr::AggregateFunction(AggregateFunction::new(
-        aggregate_function::AggregateFunction::Sum,
-        vec![expr],
-        false,
-        None,
-        None,
-        None,
-    ))
-}
-
 /// Create an expression to represent the array_agg() aggregate function
 pub fn array_agg(expr: Expr) -> Expr {
     Expr::AggregateFunction(AggregateFunction::new(

datafusion/expr/src/logical_plan/builder.rs

@@ -1719,7 +1719,7 @@ pub fn unnest_with_options(
 mod tests {
     use super::*;
     use crate::logical_plan::StringifiedPlan;
-    use crate::{col, expr, expr_fn::exists, in_subquery, lit, scalar_subquery, sum};
+    use crate::{col, expr, expr_fn::exists, in_subquery, lit, scalar_subquery};
 
     use datafusion_common::SchemaError;
 
@@ -1775,28 +1775,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn plan_builder_aggregate() -> Result<()> {
-        let plan =
-            table_scan(Some("employee_csv"), &employee_schema(), Some(vec![3, 4]))?
-                .aggregate(
-                    vec![col("state")],
-                    vec![sum(col("salary")).alias("total_salary")],
-                )?
-                .project(vec![col("state"), col("total_salary")])?
-                .limit(2, Some(10))?
-                .build()?;
-
-        let expected = "Limit: skip=2, fetch=10\
-                \n  Projection: employee_csv.state, total_salary\
-                \n    Aggregate: groupBy=[[employee_csv.state]], aggr=[[SUM(employee_csv.salary) AS total_salary]]\
-                \n      TableScan: employee_csv projection=[state, salary]";
-
-        assert_eq!(expected, format!("{plan:?}"));
-
-        Ok(())
-    }
-
     #[test]
     fn plan_builder_sort() -> Result<()> {
         let plan =
@@ -2037,36 +2015,6 @@ mod tests {
         }
     }
 
-    #[test]
-    fn aggregate_non_unique_names() -> Result<()> {
-        let plan = table_scan(
-            Some("employee_csv"),
-            &employee_schema(),
-            // project state and salary by column index
-            Some(vec![3, 4]),
-        )?
-        // two columns with the same name => error
-        .aggregate(vec![col("state")], vec![sum(col("salary")).alias("state")]);
-
-        match plan {
-            Err(DataFusionError::SchemaError(
-                SchemaError::AmbiguousReference {
-                    field:
-                        Column {
-                            relation: Some(TableReference::Bare { table }),
-                            name,
-                        },
-                },
-                _,
-            )) => {
-                assert_eq!(*"employee_csv", *table);
-                assert_eq!("state", &name);
-                Ok(())
-            }
-            _ => plan_err!("Plan should have returned an DataFusionError::SchemaError"),
-        }
-    }
-
     fn employee_schema() -> Schema {
         Schema::new(vec![
             Field::new("id", DataType::Int32, false),

datafusion/optimizer/Cargo.toml

@@ -50,6 +50,7 @@ hashbrown = { workspace = true }
 indexmap = { workspace = true }
 itertools = { workspace = true }
 log = { workspace = true }
+paste = "1.0.14"
 regex-syntax = "0.8.0"
 
 [dev-dependencies]