[pull] main from apache:main

benchmarks/bench.sh

@@ -900,7 +900,7 @@ data_imdb() {
                 if [ "${DOWNLOADED_SIZE}" != "${expected_size}" ]; then
                     echo "Error: Download size mismatch"
                     echo "Expected: ${expected_size}"
-                    echo "Got: ${DOWNLADED_SIZE}"
+                    echo "Got: ${DOWNLOADED_SIZE}"
                     echo "Please re-initiate the download"
                     return 1
                 fi

benchmarks/lineprotocol.py

@@ -164,12 +164,12 @@ def lineformat(
 ) -> None:
     baseline = BenchmarkRun.load_from_file(baseline)
     context = baseline.context
-    benchamrk_str = f"benchmark,name={context.name},version={context.benchmark_version},datafusion_version={context.datafusion_version},num_cpus={context.num_cpus}"
+    benchmark_str = f"benchmark,name={context.name},version={context.benchmark_version},datafusion_version={context.datafusion_version},num_cpus={context.num_cpus}"
     for query in baseline.queries:
         query_str = f"query=\"{query.query}\""
         timestamp = f"{query.start_time*10**9}"
         for iter_num, result in enumerate(query.iterations):
-            print(f"{benchamrk_str} {query_str},iteration={iter_num},row_count={result.row_count},elapsed_ms={result.elapsed*1000:.0f} {timestamp}\n")
+            print(f"{benchmark_str} {query_str},iteration={iter_num},row_count={result.row_count},elapsed_ms={result.elapsed*1000:.0f} {timestamp}\n")
 
 def main() -> None:
     parser = ArgumentParser()

datafusion/core/src/execution/context/mod.rs

@@ -254,7 +254,7 @@ where
 /// let state = SessionStateBuilder::new()
 ///     .with_config(config)
 ///     .with_runtime_env(runtime_env)
-///     // include support for built in functions and configurations
+///     // include support for built-in functions and configurations
 ///     .with_default_features()
 ///     .build();
 ///
@@ -1087,8 +1087,8 @@ impl SessionContext {
         }
     }
 
-    fn schema_doesnt_exist_err(&self, schemaref: &SchemaReference) -> Result<DataFrame> {
-        exec_err!("Schema '{schemaref}' doesn't exist.")
+    fn schema_doesnt_exist_err(&self, schema_ref: &SchemaReference) -> Result<DataFrame> {
+        exec_err!("Schema '{schema_ref}' doesn't exist.")
     }
 
     async fn set_variable(&self, stmt: SetVariable) -> Result<()> {

datafusion/expr/src/udf.rs

@@ -587,7 +587,7 @@ pub trait ScalarUDFImpl: Debug + DynEq + DynHash + Send + Sync + Any {
     ///
     /// If you provide an implementation for [`Self::return_field_from_args`],
     /// DataFusion will not call `return_type` (this function). While it is
-    /// valid to to put [`unimplemented!()`] or [`unreachable!()`], it is
+    /// valid to put [`unimplemented!()`] or [`unreachable!()`], it is
     /// recommended to return [`DataFusionError::Internal`] instead, which
     /// reduces the severity of symptoms if bugs occur (an error rather than a
     /// panic).