Merge branch 'main' of github.com:apache/datafusion into dev/xinli/im…

…prov-args

.github/workflows/rust.yml

@@ -234,7 +234,7 @@ jobs:
           rust-version: stable
       - name: Run cargo doc
         run: |
-          export RUSTDOCFLAGS="-D warnings -A rustdoc::private-intra-doc-links"
+          export RUSTDOCFLAGS="-D warnings"
           cargo doc --document-private-items --no-deps --workspace
           cd datafusion-cli
           cargo doc --document-private-items --no-deps

benchmarks/queries/clickbench/README.md

@@ -14,7 +14,7 @@ ClickBench is focused on aggregation and filtering performance (though it has no
 
 The "extended" queries are not part of the official ClickBench benchmark.
 Instead they are used to test other DataFusion features that are not covered by
-the standard benchmark  Each description below is for the corresponding line in
+the standard benchmark. Each description below is for the corresponding line in
 `extended.sql` (line 1 is `Q0`, line 2 is `Q1`, etc.)
 
 ### Q0: Data Exploration

datafusion-examples/examples/dataframe_subquery.rs

@@ -20,6 +20,7 @@ use std::sync::Arc;
 
 use datafusion::error::Result;
 use datafusion::functions_aggregate::average::avg;
+use datafusion::functions_aggregate::min_max::max;
 use datafusion::prelude::*;
 use datafusion::test_util::arrow_test_data;
 use datafusion_common::ScalarValue;

datafusion-examples/examples/parquet_index.rs

@@ -25,12 +25,10 @@ use arrow_schema::SchemaRef;
 use async_trait::async_trait;
 use datafusion::catalog::Session;
 use datafusion::datasource::listing::PartitionedFile;
-use datafusion::datasource::physical_plan::{
-    parquet::StatisticsConverter,
-    {FileScanConfig, ParquetExec},
-};
+use datafusion::datasource::physical_plan::{FileScanConfig, ParquetExec};
 use datafusion::datasource::TableProvider;
 use datafusion::execution::object_store::ObjectStoreUrl;
+use datafusion::parquet::arrow::arrow_reader::statistics::StatisticsConverter;
 use datafusion::parquet::arrow::{
     arrow_reader::ParquetRecordBatchReaderBuilder, ArrowWriter,
 };

datafusion/common/src/error.rs

@@ -321,7 +321,8 @@ impl From<DataFusionError> for io::Error {
 }
 
 impl DataFusionError {
-    const BACK_TRACE_SEP: &'static str = "\n\nbacktrace: ";
+    /// The separator between the error message and the backtrace
+    pub const BACK_TRACE_SEP: &'static str = "\n\nbacktrace: ";
 
     /// Get deepest underlying [`DataFusionError`]
     ///

datafusion/core/Cargo.toml

@@ -217,10 +217,6 @@ name = "sort"
 harness = false
 name = "topk_aggregate"
 
-[[bench]]
-harness = false
-name = "parquet_statistic"
-
 [[bench]]
 harness = false
 name = "map_query_sql"

datafusion/core/src/dataframe/mod.rs

@@ -53,9 +53,11 @@ use datafusion_common::{
 };
 use datafusion_expr::{case, is_null, lit};
 use datafusion_expr::{
-    max, min, utils::COUNT_STAR_EXPANSION, TableProviderFilterPushDown, UNNAMED_TABLE,
+    utils::COUNT_STAR_EXPANSION, TableProviderFilterPushDown, UNNAMED_TABLE,
+};
+use datafusion_functions_aggregate::expr_fn::{
+    avg, count, max, median, min, stddev, sum,
 };
-use datafusion_functions_aggregate::expr_fn::{avg, count, median, stddev, sum};
 
 use async_trait::async_trait;
 use datafusion_catalog::Session;
@@ -144,6 +146,7 @@ impl Default for DataFrameWriteOptions {
 /// ```
 /// # use datafusion::prelude::*;
 /// # use datafusion::error::Result;
+/// # use datafusion::functions_aggregate::expr_fn::min;
 /// # #[tokio::main]
 /// # async fn main() -> Result<()> {
 /// let ctx = SessionContext::new();
@@ -407,6 +410,7 @@ impl DataFrame {
     /// ```
     /// # use datafusion::prelude::*;
     /// # use datafusion::error::Result;
+    /// # use datafusion::functions_aggregate::expr_fn::min;
     /// # #[tokio::main]
     /// # async fn main() -> Result<()> {
     /// let ctx = SessionContext::new();