Merge remote-tracking branch 'apache/main' into alamb/move_partition_evaluator

Author: alamb

benchmarks/src/bin/tpch.rs

@@ -303,14 +303,14 @@ async fn execute_query(
     if debug {
         println!(
             "=== Physical plan ===\n{}\n",
-            displayable(physical_plan.as_ref()).indent()
+            displayable(physical_plan.as_ref()).indent(true)
         );
     }
     let result = collect(physical_plan.clone(), state.task_ctx()).await?;
     if debug {
         println!(
             "=== Physical plan with metrics ===\n{}\n",
-            DisplayableExecutionPlan::with_metrics(physical_plan.as_ref()).indent()
+            DisplayableExecutionPlan::with_metrics(physical_plan.as_ref()).indent(true)
         );
         if !result.is_empty() {
             // do not call print_batches if there are no batches as the result is confusing

datafusion-cli/Cargo.lock

@@ -18,6 +18,7 @@
 use std::sync::atomic::{AtomicUsize, Ordering};
 
 /// A utility struct that can be used to generate unique aliases when optimizing queries
+#[derive(Debug)]
 pub struct AliasGenerator {
     next_id: AtomicUsize,
 }

datafusion/optimizer/src/alias.rs renamed to datafusion/common/src/alias.rs

@@ -15,6 +15,7 @@
 // specific language governing permissions and limitations
 // under the License.
 
+pub mod alias;
 pub mod cast;
 mod column;
 pub mod config;

datafusion/common/src/lib.rs

@@ -20,7 +20,7 @@
 use std::any::Any;
 use std::collections::HashSet;
 use std::fmt;
-use std::fmt::{Debug, Display};
+use std::fmt::Debug;
 use std::sync::Arc;
 
 use arrow::csv::WriterBuilder;
@@ -51,7 +51,7 @@ use crate::datasource::physical_plan::{
 use crate::error::Result;
 use crate::execution::context::SessionState;
 use crate::physical_plan::insert::{DataSink, InsertExec};
-use crate::physical_plan::Statistics;
+use crate::physical_plan::{DisplayAs, DisplayFormatType, Statistics};
 use crate::physical_plan::{ExecutionPlan, SendableRecordBatchStream};
 
 /// The default file extension of csv files
@@ -443,14 +443,19 @@ impl Debug for CsvSink {
     }
 }
 
-impl Display for CsvSink {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "CsvSink(writer_mode={:?}, file_groups={})",
-            self.config.writer_mode,
-            FileGroupDisplay(&self.config.file_groups),
-        )
+impl DisplayAs for CsvSink {
+    fn fmt_as(&self, t: DisplayFormatType, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match t {
+            DisplayFormatType::Default | DisplayFormatType::Verbose => {
+                write!(
+                    f,
+                    "CsvSink(writer_mode={:?}, file_groups=",
+                    self.config.writer_mode
+                )?;
+                FileGroupDisplay(&self.config.file_groups).fmt_as(t, f)?;
+                write!(f, ")")
+            }
+        }
     }
 }
 

datafusion/core/src/datasource/file_format/csv.rs

@@ -50,7 +50,6 @@ pub struct FileRange {
 
 #[derive(Debug, Clone)]
 /// A single file or part of a file that should be read, along with its schema, statistics
-/// A single file that should be read, along with its schema, statistics
 /// and partition column values that need to be appended to each row.
 pub struct PartitionedFile {
     /// Path for the file (e.g. URL, filesystem path, etc)

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

@@ -28,7 +28,7 @@ use url::Url;
 
 /// A parsed URL identifying files for a listing table, see [`ListingTableUrl::parse`]
 /// for more information on the supported expressions
-#[derive(Debug, Clone)]
+#[derive(Debug, Clone, Eq, PartialEq, Hash)]
 pub struct ListingTableUrl {
     /// A URL that identifies a file or directory to list files from
     url: Url,