trivial typo fix

Signed-off-by: Ruihang Xia <[email protected]>

Author: waynexia

benchmarks/src/bin/external_aggr.rs

@@ -113,7 +113,7 @@ impl ExternalAggrConfig {
         "#,
     ];
 
-    /// If `--query` and `--memory-limit` is not speicified, run all queries
+    /// If `--query` and `--memory-limit` is not specified, run all queries
     /// with pre-configured memory limits
     /// If only `--query` is specified, run the query with all memory limits
     /// for this query

datafusion-cli/tests/cli_integration.rs

@@ -64,7 +64,7 @@ async fn setup_minio_container() -> ContainerAsync<minio::MinIO> {
 
     match container {
         Ok(container) => {
-            // We wait for MinIO to be healthy and preprare test files. We do it via CLI to avoid s3 dependency
+            // We wait for MinIO to be healthy and prepare test files. We do it via CLI to avoid s3 dependency
             let commands = [
                 ExecCommand::new(["/usr/bin/mc", "ready", "local"]),
                 ExecCommand::new([

datafusion-examples/examples/custom_file_casts.rs

@@ -41,7 +41,7 @@ use object_store::path::Path;
 use object_store::{ObjectStore, PutPayload};
 
 // Example showing how to implement custom casting rules to adapt file schemas.
-// This example enforces that casts must be stricly widening: if the file type is Int64 and the table type is Int32, it will error
+// This example enforces that casts must be strictly widening: if the file type is Int64 and the table type is Int32, it will error
 // before even reading the data.
 // Without this custom cast rule DataFusion would happily do the narrowing cast, potentially erroring only if it found a row with data it could not cast.
 

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

@@ -215,16 +215,16 @@ impl ListingTableConfig {
     ) -> Result<(String, Option<String>)> {
         let mut exts = path.rsplit('.');
 
-        let splitted = exts.next().unwrap_or("");
+        let split = exts.next().unwrap_or("");
 
-        let file_compression_type = FileCompressionType::from_str(splitted)
+        let file_compression_type = FileCompressionType::from_str(split)
             .unwrap_or(FileCompressionType::UNCOMPRESSED);
 
         if file_compression_type.is_compressed() {
             let splitted2 = exts.next().unwrap_or("");
-            Ok((splitted2.to_string(), Some(splitted.to_string())))
+            Ok((splitted2.to_string(), Some(split.to_string())))
         } else {
-            Ok((splitted.to_string(), None))
+            Ok((split.to_string(), None))
         }
     }
 

datafusion/core/tests/memory_limit/memory_limit_validation/sort_mem_validation.rs

@@ -31,7 +31,7 @@ static INIT: Once = Once::new();
 
 // ===========================================================================
 // Test runners:
-// Runners are splitted into multiple tests to run in parallel
+// Runners are split into multiple tests to run in parallel
 // ===========================================================================
 
 #[test]

datafusion/core/tests/memory_limit/mod.rs

@@ -546,7 +546,7 @@ async fn test_external_sort_zero_merge_reservation() {
 // Tests for disk limit (`max_temp_directory_size` in `DiskManager`)
 // ------------------------------------------------------------------
 
-// Create a new `SessionContext` with speicified disk limit, memory pool limit, and spill compression codec
+// Create a new `SessionContext` with specified disk limit, memory pool limit, and spill compression codec
 async fn setup_context(
     disk_limit: u64,
     memory_pool_limit: usize,

datafusion/core/tests/physical_optimizer/enforce_distribution.rs

@@ -2610,7 +2610,7 @@ fn parallelization_two_partitions_into_four() -> Result<()> {
         "AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[]",
         "  RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4",
         "    AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[]",
-        // Multiple source files splitted across partitions
+        // Multiple source files split across partitions
         "      DataSourceExec: file_groups={4 groups: [[x:0..50], [x:50..100], [y:0..50], [y:50..100]]}, projection=[a, b, c, d, e], file_type=parquet",
     ];
     test_config.run(
@@ -2625,7 +2625,7 @@ fn parallelization_two_partitions_into_four() -> Result<()> {
         "AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[]",
         "  RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4",
         "    AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[]",
-        // Multiple source files splitted across partitions
+        // Multiple source files split across partitions
         "      DataSourceExec: file_groups={4 groups: [[x:0..50], [x:50..100], [y:0..50], [y:50..100]]}, projection=[a, b, c, d, e], file_type=csv, has_header=false",
     ];
     test_config.run(&expected_csv, plan_csv.clone(), &DISTRIB_DISTRIB_SORT)?;

datafusion/datasource-parquet/src/opener.rs

@@ -186,7 +186,7 @@ impl FileOpener for ParquetOpener {
 
             // Don't load the page index yet. Since it is not stored inline in
             // the footer, loading the page index if it is not needed will do
-            // unecessary I/O. We decide later if it is needed to evaluate the
+            // unnecessary I/O. We decide later if it is needed to evaluate the
             // pruning predicates. Thus default to not requesting if from the
             // underlying reader.
             let mut options = ArrowReaderOptions::new().with_page_index(false);

datafusion/expr/src/logical_plan/builder.rs

@@ -1520,7 +1520,7 @@ impl ValuesFields {
 // `name_map` tracks a mapping between a field name and the number of appearances of that field.
 //
 // Some field names might already come to this function with the count (number of times it appeared)
-// as a sufix e.g. id:1, so there's still a chance of name collisions, for example,
+// as a suffix e.g. id:1, so there's still a chance of name collisions, for example,
 // if these three fields passed to this function: "col:1", "col" and "col", the function
 // would rename them to -> col:1, col, col:1 causing a posteriror error when building the DFSchema.
 // that's why we need the `seen` set, so the fields are always unique.

datafusion/expr/src/logical_plan/invariants.rs

@@ -102,7 +102,7 @@ fn assert_unique_field_names(plan: &LogicalPlan) -> Result<()> {
     plan.schema().check_names()
 }
 
-/// Returns an error if the plan is not sematically valid.
+/// Returns an error if the plan is not semantically valid.
 fn assert_valid_semantic_plan(plan: &LogicalPlan) -> Result<()> {
     assert_subqueries_are_valid(plan)?;