Apache DataFusion SQL Query Engine
chore: Fix duplicated word typos in comments (#23662)
jackyleebf948c924598
diff --git a/datafusion-examples/examples/data_io/parquet_embedded_index.rs b/datafusion-examples/examples/data_io/parquet_embedded_index.rsindex 40b5b468ff..a8a3c97fa1 100644--- a/datafusion-examples/examples/data_io/parquet_embedded_index.rs+++ b/datafusion-examples/examples/data_io/parquet_embedded_index.rs@@ -87,7 +87,7 @@//! 2. Read and deserialize the index.//!//! 3. Create a `TableProvider` that knows how to use the index to quickly find-//! the relevant files, row groups, data pages or rows based on on pushed down+//! the relevant files, row groups, data pages or rows based on pushed down//! filters.//!//! # FAQ: Why do other Parquet readers skip over the custom index?diff --git a/datafusion/common/src/pruning.rs b/datafusion/common/src/pruning.rsindex ebae23f072..a36ac9f795 100644--- a/datafusion/common/src/pruning.rs+++ b/datafusion/common/src/pruning.rs@@ -305,7 +305,7 @@ impl PruningStatistics for PartitionPruningStatistics {/// that has statistics of its columns.////// It is up to the caller to decide what each container represents. For-/// example, they can come from a file (e.g. [`PartitionedFile`]) or a set of of+/// example, they can come from a file (e.g. [`PartitionedFile`]) or a set of/// files (e.g. [`FileGroup`])////// [`PartitionedFile`]: https://docs.rs/datafusion/latest/datafusion/datasource/listing/struct.PartitionedFile.htmldiff --git a/datafusion/common/src/test_util.rs b/datafusion/common/src/test_util.rsindex 8ad1e086bc..3d645c4254 100644--- a/datafusion/common/src/test_util.rs+++ b/datafusion/common/src/test_util.rs@@ -174,7 +174,7 @@ macro_rules! assert_contains {}/// A macro to assert that one string is NOT contained within another with-/// a nice error message if they are are.+/// a nice error message if they are.////// Usage: `assert_not_contains!(actual, unexpected)`///diff --git a/datafusion/core/tests/user_defined/user_defined_plan.rs b/datafusion/core/tests/user_defined/user_defined_plan.rsindex b837373632..75738bcfe1 100644--- a/datafusion/core/tests/user_defined/user_defined_plan.rs+++ b/datafusion/core/tests/user_defined/user_defined_plan.rs@@ -518,7 +518,7 @@ impl OptimizerRule for TopKOptimizerRule {if let LogicalPlan::Sort(Sort { expr, input, .. }) = limit.input.as_ref()&& expr.len() == 1{- // we found a sort with a single sort expr, replace with a a TopK+ // we found a sort with a single sort expr, replace with a TopKreturn Ok(Transformed::yes(LogicalPlan::Extension(Extension {node: Arc::new(TopKPlanNode {k: fetch,diff --git a/datafusion/datasource-arrow/src/source.rs b/datafusion/datasource-arrow/src/source.rsindex 59c020c779..27533052ce 100644--- a/datafusion/datasource-arrow/src/source.rs+++ b/datafusion/datasource-arrow/src/source.rs@@ -340,7 +340,7 @@ impl FileSource for ArrowSource {// The Arrow IPC stream format doesn't support range-based parallel reading// because it lacks a footer with the information that would be needed to// make range-based parallel reading practical. Without the data in the- // footer you would either need to read the the entire file and record the+ // footer you would either need to read the entire file and record the// offsets of the record batches and dictionaries, essentially recreating// the footer's contents, or else each partition would need to read the// entire file up to the correct offset which is a lot of duplicate I/O.diff --git a/datafusion/datasource-csv/src/file_format.rs b/datafusion/datasource-csv/src/file_format.rsindex 6b131f2bee..89c3d374e6 100644--- a/datafusion/datasource-csv/src/file_format.rs+++ b/datafusion/datasource-csv/src/file_format.rs@@ -168,7 +168,7 @@ impl CsvFormat {stream.boxed()}- /// Convert a stream of bytes into a stream of of [`Bytes`] containing newline+ /// Convert a stream of bytes into a stream of [`Bytes`] containing newline/// delimited CSV records, while accounting for `\` and `"`.pub async fn read_to_delimited_chunks_from_stream<'a>(&self,diff --git a/datafusion/expr/src/logical_plan/plan.rs b/datafusion/expr/src/logical_plan/plan.rsindex b6e6cc7683..9cfab21a03 100644--- a/datafusion/expr/src/logical_plan/plan.rs+++ b/datafusion/expr/src/logical_plan/plan.rs@@ -1733,7 +1733,7 @@ impl LogicalPlan {/// ```pub fn display_indent(&self) -> impl Display + '_ {// Boilerplate structure to wrap LogicalPlan with something- // that that can be formatted+ // that can be formattedstruct Wrapper<'a>(&'a LogicalPlan);impl Display for Wrapper<'_> {fn fmt(&self, f: &mut Formatter) -> fmt::Result {@@ -1779,7 +1779,7 @@ impl LogicalPlan {/// ```pub fn display_indent_schema(&self) -> impl Display + '_ {// Boilerplate structure to wrap LogicalPlan with something- // that that can be formatted+ // that can be formattedstruct Wrapper<'a>(&'a LogicalPlan);impl Display for Wrapper<'_> {fn fmt(&self, f: &mut Formatter) -> fmt::Result {@@ -1799,7 +1799,7 @@ impl LogicalPlan {/// Users can use this format to visualize the plan in existing plan visualization tools, for example [dalibo](https://explain.dalibo.com/)pub fn display_pg_json(&self) -> impl Display + '_ {// Boilerplate structure to wrap LogicalPlan with something- // that that can be formatted+ // that can be formattedstruct Wrapper<'a>(&'a LogicalPlan);impl Display for Wrapper<'_> {fn fmt(&self, f: &mut Formatter) -> fmt::Result {@@ -1845,7 +1845,7 @@ impl LogicalPlan {/// ```pub fn display_graphviz(&self) -> impl Display + '_ {// Boilerplate structure to wrap LogicalPlan with something- // that that can be formatted+ // that can be formattedstruct Wrapper<'a>(&'a LogicalPlan);impl Display for Wrapper<'_> {fn fmt(&self, f: &mut Formatter) -> fmt::Result {@@ -1896,7 +1896,7 @@ impl LogicalPlan {/// ```pub fn display(&self) -> impl Display + '_ {// Boilerplate structure to wrap LogicalPlan with something- // that that can be formatted+ // that can be formattedstruct Wrapper<'a>(&'a LogicalPlan);impl Display for Wrapper<'_> {fn fmt(&self, f: &mut Formatter) -> fmt::Result {diff --git a/datafusion/physical-expr/src/aggregate.rs b/datafusion/physical-expr/src/aggregate.rsindex e5d55aba4f..b774658679 100644--- a/datafusion/physical-expr/src/aggregate.rs+++ b/datafusion/physical-expr/src/aggregate.rs@@ -858,7 +858,7 @@ impl AggregateFunctionExpr {// `retract_batch` method will not be called. In this case// having retract_batch is not a requirement.//- // This approach is a a bit different than window function+ // This approach is a bit different than window function// approach. In window function (when they use a window frame)// they get all the desired range during evaluation.if !accumulator.supports_retract_batch() {diff --git a/datafusion/physical-expr/src/window/standard.rs b/datafusion/physical-expr/src/window/standard.rsindex 46f3cabbad..6f61174ee0 100644--- a/datafusion/physical-expr/src/window/standard.rs+++ b/datafusion/physical-expr/src/window/standard.rs@@ -128,7 +128,7 @@ impl WindowExpr for StandardWindowExpr {let mut window_frame_ctx =WindowFrameContext::new(Arc::clone(&self.window_frame), sort_options);let mut last_range = Range { start: 0, end: 0 };- // We iterate on each row to calculate window frame range and and window function result+ // We iterate on each row to calculate window frame range and window function resultfor idx in 0..num_rows {let range = window_frame_ctx.calculate_range(order_bys_ref,diff --git a/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs b/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rsindex 36a043cc7d..50ef78f18b 100644--- a/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs+++ b/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs@@ -125,7 +125,7 @@ impl RecordBatchStream for ClassicPWMJStream {// Classic Joins// 1. `WaitBufferedSide` - Load in the buffered side data into memory.// 2. `FetchStreamBatch` - Fetch + sort incoming stream batches. We switch the state to-// `Completed` if there are are still remaining partitions to process. It is only switched to+// `Completed` if there are still remaining partitions to process. It is only switched to// `ExhaustedStreamBatch` if all partitions have been processed.// 3. `ProcessStreamBatch` - Compare stream batch row values against the buffered side data.// 4. `ExhaustedStreamBatch` - If the join type is Left or Inner we will return state as