Update remaining crates to rust 2024 edition (apache#19361)

## Which issue does this PR close?

Closes apache#15804 

## Rationale for this change

Now that we are on MSRV 1.88 we can use rust edition 2024, which brings
let chains and other nice features. It also improves `unsafe` checking.
In order to introduce these changes in slower way instead of one massive
PR that is too difficult to manage we are updating a few crates at a
time.

## What changes are included in this PR?

Updates these crates to 2024.

- datafusion-benchmarks
- datafusion-ffi
- datafusion-sqllogictest
- datafusion-examples

## Are these changes tested?

Existing unit tests. There are no functional code changes.

## Are there any user-facing changes?

None.

## Note

It is recommended to review with the ignore whitespace setting:
https://github.com/apache/datafusion/pull/19361/files?w=1

Author: timsaucer

Cargo.toml

@@ -71,7 +71,7 @@ resolver = "2"
 
 [workspace.package]
 authors = ["Apache DataFusion <[email protected]>"]
-edition = "2021"
+edition = "2024"
 homepage = "https://datafusion.apache.org"
 license = "Apache-2.0"
 readme = "README.md"

benchmarks/src/bin/external_aggr.rs

@@ -33,16 +33,16 @@ use datafusion::datasource::listing::{
 };
 use datafusion::datasource::{MemTable, TableProvider};
 use datafusion::error::Result;
+use datafusion::execution::SessionStateBuilder;
 use datafusion::execution::memory_pool::FairSpillPool;
 use datafusion::execution::runtime_env::RuntimeEnvBuilder;
-use datafusion::execution::SessionStateBuilder;
 use datafusion::physical_plan::display::DisplayableExecutionPlan;
 use datafusion::physical_plan::{collect, displayable};
 use datafusion::prelude::*;
 use datafusion_benchmarks::util::{BenchmarkRun, CommonOpt, QueryResult};
 use datafusion_common::instant::Instant;
 use datafusion_common::utils::get_available_parallelism;
-use datafusion_common::{exec_err, DEFAULT_PARQUET_EXTENSION};
+use datafusion_common::{DEFAULT_PARQUET_EXTENSION, exec_err};
 use datafusion_common::{human_readable_size, units};
 
 #[derive(Debug, StructOpt)]

benchmarks/src/bin/mem_profile.rs

@@ -199,21 +199,18 @@ fn run_query(args: &[String], results: &mut Vec<QueryResult>) -> Result<()> {
 
     // Look for lines that contain execution time / memory stats
     while let Some(line) = iter.next() {
-        if let Some((query, duration_ms)) = parse_query_time(line) {
-            if let Some(next_line) = iter.peek() {
-                if let Some((peak_rss, peak_commit, page_faults)) =
-                    parse_vm_line(next_line)
-                {
-                    results.push(QueryResult {
-                        query,
-                        duration_ms,
-                        peak_rss,
-                        peak_commit,
-                        page_faults,
-                    });
-                    break;
-                }
-            }
+        if let Some((query, duration_ms)) = parse_query_time(line)
+            && let Some(next_line) = iter.peek()
+            && let Some((peak_rss, peak_commit, page_faults)) = parse_vm_line(next_line)
+        {
+            results.push(QueryResult {
+                query,
+                duration_ms,
+                peak_rss,
+                peak_commit,
+                page_faults,
+            });
+            break;
         }
     }
 

benchmarks/src/cancellation.rs

@@ -25,22 +25,22 @@ use arrow::array::Array;
 use arrow::datatypes::DataType;
 use arrow::record_batch::RecordBatch;
 use datafusion::common::{Result, ScalarValue};
-use datafusion::datasource::file_format::parquet::ParquetFormat;
 use datafusion::datasource::file_format::FileFormat;
+use datafusion::datasource::file_format::parquet::ParquetFormat;
 use datafusion::datasource::listing::{ListingOptions, ListingTableUrl};
-use datafusion::execution::object_store::ObjectStoreUrl;
 use datafusion::execution::TaskContext;
-use datafusion::physical_plan::coalesce_partitions::CoalescePartitionsExec;
+use datafusion::execution::object_store::ObjectStoreUrl;
 use datafusion::physical_plan::ExecutionPlan;
+use datafusion::physical_plan::coalesce_partitions::CoalescePartitionsExec;
 use datafusion::prelude::*;
 use datafusion_common::instant::Instant;
 use futures::TryStreamExt;
 use object_store::ObjectStore;
-use parquet::arrow::async_writer::ParquetObjectWriter;
 use parquet::arrow::AsyncArrowWriter;
+use parquet::arrow::async_writer::ParquetObjectWriter;
+use rand::Rng;
 use rand::distr::Alphanumeric;
 use rand::rngs::ThreadRng;
-use rand::Rng;
 use structopt::StructOpt;
 use tokio::runtime::Runtime;
 use tokio_util::sync::CancellationToken;

benchmarks/src/clickbench.rs

@@ -19,7 +19,7 @@ use std::fs;
 use std::io::ErrorKind;
 use std::path::{Path, PathBuf};
 
-use crate::util::{print_memory_stats, BenchmarkRun, CommonOpt, QueryResult};
+use crate::util::{BenchmarkRun, CommonOpt, QueryResult, print_memory_stats};
 use datafusion::logical_expr::{ExplainFormat, ExplainOption};
 use datafusion::{
     error::{DataFusionError, Result},
@@ -156,7 +156,9 @@ impl RunOpt {
                 .any(|opt| opt.contains("prefer_existing_sort=true"));
 
             if !has_prefer_sort {
-                println!("ℹ️  Consider using -c datafusion.optimizer.prefer_existing_sort=true");
+                println!(
+                    "ℹ️  Consider using -c datafusion.optimizer.prefer_existing_sort=true"
+                );
                 println!("ℹ️  to optimize queries while maintaining parallelism");
             }
         }

benchmarks/src/h2o.rs

@@ -20,11 +20,11 @@
 //! - [H2O AI Benchmark](https://duckdb.org/2023/04/14/h2oai.html)
 //! - [Extended window function benchmark](https://duckdb.org/2024/06/26/benchmarks-over-time.html#window-functions-benchmark)
 
-use crate::util::{print_memory_stats, BenchmarkRun, CommonOpt};
+use crate::util::{BenchmarkRun, CommonOpt, print_memory_stats};
 use datafusion::logical_expr::{ExplainFormat, ExplainOption};
 use datafusion::{error::Result, prelude::SessionContext};
 use datafusion_common::{
-    exec_datafusion_err, instant::Instant, internal_err, DataFusionError, TableReference,
+    DataFusionError, TableReference, exec_datafusion_err, instant::Instant, internal_err,
 };
 use std::path::{Path, PathBuf};
 use structopt::StructOpt;

benchmarks/src/hj.rs

@@ -19,7 +19,7 @@ use crate::util::{BenchmarkRun, CommonOpt, QueryResult};
 use datafusion::physical_plan::execute_stream;
 use datafusion::{error::Result, prelude::SessionContext};
 use datafusion_common::instant::Instant;
-use datafusion_common::{exec_datafusion_err, exec_err, DataFusionError};
+use datafusion_common::{DataFusionError, exec_datafusion_err, exec_err};
 use structopt::StructOpt;
 
 use futures::StreamExt;

benchmarks/src/imdb/convert.rs

@@ -26,8 +26,8 @@ use structopt::StructOpt;
 
 use datafusion::common::not_impl_err;
 
-use super::get_imdb_table_schema;
 use super::IMDB_TABLES;
+use super::get_imdb_table_schema;
 
 #[derive(Debug, StructOpt)]
 pub struct ConvertOpt {

benchmarks/src/imdb/run.rs

@@ -19,16 +19,16 @@ use std::path::PathBuf;
 use std::sync::Arc;
 
 use super::{
-    get_imdb_table_schema, get_query_sql, IMDB_QUERY_END_ID, IMDB_QUERY_START_ID,
-    IMDB_TABLES,
+    IMDB_QUERY_END_ID, IMDB_QUERY_START_ID, IMDB_TABLES, get_imdb_table_schema,
+    get_query_sql,
 };
-use crate::util::{print_memory_stats, BenchmarkRun, CommonOpt, QueryResult};
+use crate::util::{BenchmarkRun, CommonOpt, QueryResult, print_memory_stats};
 
 use arrow::record_batch::RecordBatch;
 use arrow::util::pretty::{self, pretty_format_batches};
+use datafusion::datasource::file_format::FileFormat;
 use datafusion::datasource::file_format::csv::CsvFormat;
 use datafusion::datasource::file_format::parquet::ParquetFormat;
-use datafusion::datasource::file_format::FileFormat;
 use datafusion::datasource::listing::{
     ListingOptions, ListingTable, ListingTableConfig, ListingTableUrl,
 };

benchmarks/src/nlj.rs

@@ -19,7 +19,7 @@ use crate::util::{BenchmarkRun, CommonOpt, QueryResult};
 use datafusion::physical_plan::execute_stream;
 use datafusion::{error::Result, prelude::SessionContext};
 use datafusion_common::instant::Instant;
-use datafusion_common::{exec_datafusion_err, exec_err, DataFusionError};
+use datafusion_common::{DataFusionError, exec_datafusion_err, exec_err};
 use structopt::StructOpt;
 
 use futures::StreamExt;
@@ -268,8 +268,8 @@ impl RunOpt {
             let elapsed = start.elapsed();
 
             println!(
-                    "Query {query_name} iteration {i} returned {row_count} rows in {elapsed:?}"
-                );
+                "Query {query_name} iteration {i} returned {row_count} rows in {elapsed:?}"
+            );
 
             query_results.push(QueryResult { elapsed, row_count });
         }