chore: remove repetitive words (#9673)

Signed-off-by: InventiveCoder <liucongcong@outlook.com>

datafusion/common/src/stats.rs

@@ -221,7 +221,7 @@ pub struct Statistics {
     /// Total bytes of the table rows.
     pub total_byte_size: Precision<usize>,
     /// Statistics on a column level. It contains a [`ColumnStatistics`] for
-    /// each field in the schema of the the table to which the [`Statistics`] refer.
+    /// each field in the schema of the table to which the [`Statistics`] refer.
     pub column_statistics: Vec<ColumnStatistics>,
 }
 

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

@@ -49,7 +49,7 @@ use object_store::{ObjectMeta, ObjectStore};
 
 /// This trait abstracts all the file format specific implementations
 /// from the [`TableProvider`]. This helps code re-utilization across
-/// providers that support the the same file formats.
+/// providers that support the same file formats.
 ///
 /// [`TableProvider`]: crate::datasource::provider::TableProvider
 #[async_trait]

datafusion/core/src/physical_optimizer/enforce_distribution.rs

@@ -392,7 +392,7 @@ fn adjust_input_keys_ordering(
         let expr = proj.expr();
         // For Projection, we need to transform the requirements to the columns before the Projection
         // And then to push down the requirements
-        // Construct a mapping from new name to the the orginal Column
+        // Construct a mapping from new name to the orginal Column
         let new_required = map_columns_before_projection(&requirements.data, expr);
         if new_required.len() == requirements.data.len() {
             requirements.children[0].data = new_required;

datafusion/core/src/physical_optimizer/output_requirements.rs

@@ -216,7 +216,7 @@ impl PhysicalOptimizerRule for OutputRequirements {
     }
 }
 
-/// This functions adds ancillary `OutputRequirementExec` to the the physical plan, so that
+/// This functions adds ancillary `OutputRequirementExec` to the physical plan, so that
 /// global requirements are not lost during optimization.
 fn require_top_ordering(plan: Arc<dyn ExecutionPlan>) -> Result<Arc<dyn ExecutionPlan>> {
     let (new_plan, is_changed) = require_top_ordering_helper(plan)?;

datafusion/core/src/physical_optimizer/projection_pushdown.rs

@@ -322,7 +322,7 @@ fn try_swapping_with_output_req(
     projection: &ProjectionExec,
     output_req: &OutputRequirementExec,
 ) -> Result<Option<Arc<dyn ExecutionPlan>>> {
-    // If the projection does not narrow the the schema, we should not try to push it down:
+    // If the projection does not narrow the schema, we should not try to push it down:
     if projection.expr().len() >= projection.input().schema().fields().len() {
         return Ok(None);
     }
@@ -372,7 +372,7 @@ fn try_swapping_with_output_req(
 fn try_swapping_with_coalesce_partitions(
     projection: &ProjectionExec,
 ) -> Result<Option<Arc<dyn ExecutionPlan>>> {
-    // If the projection does not narrow the the schema, we should not try to push it down:
+    // If the projection does not narrow the schema, we should not try to push it down:
     if projection.expr().len() >= projection.input().schema().fields().len() {
         return Ok(None);
     }
@@ -387,7 +387,7 @@ fn try_swapping_with_filter(
     projection: &ProjectionExec,
     filter: &FilterExec,
 ) -> Result<Option<Arc<dyn ExecutionPlan>>> {
-    // If the projection does not narrow the the schema, we should not try to push it down:
+    // If the projection does not narrow the schema, we should not try to push it down:
     if projection.expr().len() >= projection.input().schema().fields().len() {
         return Ok(None);
     }
@@ -412,7 +412,7 @@ fn try_swapping_with_repartition(
     projection: &ProjectionExec,
     repartition: &RepartitionExec,
 ) -> Result<Option<Arc<dyn ExecutionPlan>>> {
-    // If the projection does not narrow the the schema, we should not try to push it down.
+    // If the projection does not narrow the schema, we should not try to push it down.
     if projection.expr().len() >= projection.input().schema().fields().len() {
         return Ok(None);
     }
@@ -454,7 +454,7 @@ fn try_swapping_with_sort(
     projection: &ProjectionExec,
     sort: &SortExec,
 ) -> Result<Option<Arc<dyn ExecutionPlan>>> {
-    // If the projection does not narrow the the schema, we should not try to push it down.
+    // If the projection does not narrow the schema, we should not try to push it down.
     if projection.expr().len() >= projection.input().schema().fields().len() {
         return Ok(None);
     }
@@ -1082,7 +1082,7 @@ fn join_table_borders(
     (far_right_left_col_ind, far_left_right_col_ind)
 }
 
-/// Tries to update the equi-join `Column`'s of a join as if the the input of
+/// Tries to update the equi-join `Column`'s of a join as if the input of
 /// the join was replaced by a projection.
 fn update_join_on(
     proj_left_exprs: &[(Column, String)],
@@ -1152,7 +1152,7 @@ fn new_columns_for_join_on(
     (new_columns.len() == hash_join_on.len()).then_some(new_columns)
 }
 
-/// Tries to update the column indices of a [`JoinFilter`] as if the the input of
+/// Tries to update the column indices of a [`JoinFilter`] as if the input of
 /// the join was replaced by a projection.
 fn update_join_filter(
     projection_left_exprs: &[(Column, String)],

datafusion/physical-expr/src/binary_map.rs

@@ -280,7 +280,7 @@ where
     /// # Returns
     ///
     /// The payload value for the entry, either the existing value or
-    /// the the newly inserted value
+    /// the newly inserted value
     ///
     /// # Safety:
     ///

datafusion/physical-plan/src/aggregates/order/mod.rs

@@ -40,7 +40,7 @@ pub(crate) enum GroupOrdering {
 }
 
 impl GroupOrdering {
-    /// Create a `GroupOrdering` for the the specified ordering
+    /// Create a `GroupOrdering` for the specified ordering
     pub fn try_new(
         input_schema: &Schema,
         mode: &InputOrderMode,

datafusion/sql/src/expr/arrow_cast.rs

@@ -76,7 +76,7 @@ pub fn create_arrow_cast(mut args: Vec<Expr>, schema: &DFSchema) -> Result<Expr>
 
 /// Parses `str` into a `DataType`.
 ///
-/// `parse_data_type` is the the reverse of [`DataType`]'s `Display`
+/// `parse_data_type` is the reverse of [`DataType`]'s `Display`
 /// impl, and maintains the invariant that
 /// `parse_data_type(data_type.to_string()) == data_type`
 ///

datafusion/sqllogictest/test_files/create_function.slt

@@ -47,7 +47,7 @@ select abs(-1);
 statement ok
 DROP FUNCTION abs;
 
-# now the the query errors
+# now the query errors
 query error Invalid function 'abs'.
 select abs(-1);
 

datafusion/sqllogictest/test_files/limit.slt

@@ -320,7 +320,7 @@ SELECT COUNT(*) FROM (SELECT a FROM t1 LIMIT 3 OFFSET 11);
 0
 
 # The aggregate does not need to be computed because the input statistics are exact and
-# the number of rows is less than or equal to the the "fetch+skip" value (LIMIT+OFFSET).
+# the number of rows is less than or equal to the "fetch+skip" value (LIMIT+OFFSET).
 query TT
 EXPLAIN SELECT COUNT(*) FROM (SELECT a FROM t1 LIMIT 3 OFFSET 8);
 ----

dev/changelog/13.0.0.md

@@ -87,7 +87,7 @@
 - Optimizer rule 'projection_push_down' failed due to unexpected error: Error during planning: Aggregate schema has wrong number of fields. Expected 3 got 8 [\#3704](https://github.com/apache/arrow-datafusion/issues/3704)
 - Optimizer regressions in `unwrap_cast_in_comparison` [\#3690](https://github.com/apache/arrow-datafusion/issues/3690)
 - Internal error when evaluating a predicate = "The type of Dictionary\(Int16, Utf8\) = Int64 of binary physical should be same" [\#3685](https://github.com/apache/arrow-datafusion/issues/3685)
-- Specialized regexp_replace should early-abort when the the input arrays are empty [\#3647](https://github.com/apache/arrow-datafusion/issues/3647)
+- Specialized regexp_replace should early-abort when the input arrays are empty [\#3647](https://github.com/apache/arrow-datafusion/issues/3647)
 - Internal error: Failed to coerce types Decimal128\(10, 2\) and Boolean in BETWEEN expression [\#3646](https://github.com/apache/arrow-datafusion/issues/3646)
 - Internal error: Failed to coerce types Decimal128\(10, 2\) and Boolean in BETWEEN expression [\#3645](https://github.com/apache/arrow-datafusion/issues/3645)
 - Type coercion error: The type of Boolean AND Decimal128\(10, 2\) of binary physical should be same [\#3644](https://github.com/apache/arrow-datafusion/issues/3644)

dev/changelog/7.0.0.md

@@ -56,7 +56,7 @@
 - Keep all datafusion's packages up to date with Dependabot [\#1472](https://github.com/apache/arrow-datafusion/issues/1472)
 - ExecutionContext support init ExecutionContextState with `new(state: Arc<Mutex<ExecutionContextState>>)` method [\#1439](https://github.com/apache/arrow-datafusion/issues/1439)
 - support the decimal scalar value [\#1393](https://github.com/apache/arrow-datafusion/issues/1393)
-- Documentation for using scalar functions with the the DataFrame API [\#1364](https://github.com/apache/arrow-datafusion/issues/1364)
+- Documentation for using scalar functions with the DataFrame API [\#1364](https://github.com/apache/arrow-datafusion/issues/1364)
 - Support `boolean == boolean` and `boolean != boolean` operators [\#1159](https://github.com/apache/arrow-datafusion/issues/1159)
 - Support DataType::Decimal\(15, 2\) in TPC-H benchmark [\#174](https://github.com/apache/arrow-datafusion/issues/174)
 - Make `MemoryStream` public [\#150](https://github.com/apache/arrow-datafusion/issues/150)

docs/source/contributor-guide/communication.md

@@ -44,7 +44,7 @@ request one in the `Arrow Rust` channel of the [Arrow Rust Discord server](https
 ## Mailing list
 
 We also use arrow.apache.org's `dev@` mailing list for release coordination and occasional design discussions. Other
-than the the release process, most DataFusion mailing list traffic will link to a GitHub issue or PR for discussion.
+than the release process, most DataFusion mailing list traffic will link to a GitHub issue or PR for discussion.
 ([subscribe](mailto:dev-subscribe@arrow.apache.org),
 [unsubscribe](mailto:dev-unsubscribe@arrow.apache.org),
 [archives](https://lists.apache.org/list.html?dev@arrow.apache.org)).

docs/source/library-user-guide/adding-udfs.md

@@ -204,7 +204,7 @@ let df = ctx.sql(&sql).await.unwrap();
 
 ## Adding a Window UDF
 
-Scalar UDFs are functions that take a row of data and return a single value. Window UDFs are similar, but they also have access to the rows around them. Access to the the proximal rows is helpful, but adds some complexity to the implementation.
+Scalar UDFs are functions that take a row of data and return a single value. Window UDFs are similar, but they also have access to the rows around them. Access to the proximal rows is helpful, but adds some complexity to the implementation.
 
 For example, we will declare a user defined window function that computes a moving average.