Fix instances of "the the" to be "the" in comments/docs (#18478)

## Which issue does this PR close?

<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->

There's no issue for this, just some simple text fixes.

## Rationale for this change

<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->

While "the the" *can* be grammatically correct, in these instances it
was not.

## What changes are included in this PR?

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

"the the" -> "the"

## Are these changes tested?

<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->

Not at as such, no.

## Are there any user-facing changes?

<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

Yes, in both code docs and in the website.

Author: corasaurus-hex

datafusion/datasource-parquet/src/source.rs

@@ -504,7 +504,7 @@ impl FileSource for ParquetSource {
         ) {
             (Some(expr_adapter_factory), Some(schema_adapter_factory)) => {
                 // Use both the schema adapter factory and the expr adapter factory.
-                // This results in the the SchemaAdapter being used for projections (e.g. a column was selected that is a UInt32 in the file and a UInt64 in the table schema)
+                // This results in the SchemaAdapter being used for projections (e.g. a column was selected that is a UInt32 in the file and a UInt64 in the table schema)
                 // but the PhysicalExprAdapterFactory being used for predicate pushdown and stats pruning.
                 (
                     Some(Arc::clone(expr_adapter_factory)),

datafusion/expr/src/expr.rs

@@ -100,7 +100,7 @@ impl From<sqlparser::ast::NullTreatment> for NullTreatment {
 ///
 /// # Printing Expressions
 ///
-/// You can print `Expr`s using the the `Debug` trait, `Display` trait, or
+/// You can print `Expr`s using the `Debug` trait, `Display` trait, or
 /// [`Self::human_display`]. See the [examples](#examples-displaying-exprs) below.
 ///
 /// If you need  SQL to pass to other systems, consider using [`Unparser`].
@@ -990,7 +990,7 @@ impl WindowFunctionDefinition {
         }
     }
 
-    /// Return the the inner window simplification function, if any
+    /// Return the inner window simplification function, if any
     ///
     /// See [`WindowFunctionSimplification`] for more information
     pub fn simplify(&self) -> Option<WindowFunctionSimplification> {
@@ -1077,7 +1077,7 @@ impl WindowFunction {
         }
     }
 
-    /// Return the the inner window simplification function, if any
+    /// Return the inner window simplification function, if any
     ///
     /// See [`WindowFunctionSimplification`] for more information
     pub fn simplify(&self) -> Option<WindowFunctionSimplification> {

datafusion/physical-plan/src/execution_plan.rs

@@ -797,7 +797,7 @@ impl ExecutionPlanProperties for &dyn ExecutionPlan {
 /// For unbounded streams, it also tracks whether the operator requires finite memory
 /// to process the stream or if memory usage could grow unbounded.
 ///
-/// Boundedness of the output stream is based on the the boundedness of the input stream and the nature of
+/// Boundedness of the output stream is based on the boundedness of the input stream and the nature of
 /// the operator. For example, limit or topk with fetch operator can convert an unbounded stream to a bounded stream.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub enum Boundedness {

datafusion/physical-plan/src/joins/cross_join.rs

@@ -627,7 +627,7 @@ impl<T: BatchTransformer> CrossJoinStream<T> {
         Poll::Ready(Ok(StatefulStreamResult::Continue))
     }
 
-    /// Joins the the indexed row of left data with the current probe batch.
+    /// Joins the indexed row of left data with the current probe batch.
     /// If all the results are produced, the state is set to fetch new probe batch.
     fn build_batches(&mut self) -> Result<StatefulStreamResult<Option<RecordBatch>>> {
         let right_batch = self.state.try_as_record_batch()?;

datafusion/physical-plan/src/joins/sort_merge_join/stream.rs

@@ -1031,7 +1031,7 @@ impl SortMergeJoinStream {
         let mut join_streamed = false;
         // Whether to join buffered rows
         let mut join_buffered = false;
-        // For Mark join we store a dummy id to indicate the the row has a match
+        // For Mark join we store a dummy id to indicate the row has a match
         let mut mark_row_as_match = false;
 
         // determine whether we need to join streamed/buffered rows
@@ -1140,7 +1140,7 @@ impl SortMergeJoinStream {
             } else {
                 Some(self.buffered_data.scanning_batch_idx)
             };
-            // For Mark join we store a dummy id to indicate the the row has a match
+            // For Mark join we store a dummy id to indicate the row has a match
             let scanning_idx = mark_row_as_match.then_some(0);
 
             self.streamed_batch

datafusion/physical-plan/src/repartition/distributor_channels.rs

@@ -151,7 +151,7 @@ impl<T> Clone for DistributionSender<T> {
 impl<T> Drop for DistributionSender<T> {
     fn drop(&mut self) {
         let n_senders_pre = self.channel.n_senders.fetch_sub(1, Ordering::SeqCst);
-        // is the the last copy of the sender side?
+        // is the last copy of the sender side?
         if n_senders_pre > 1 {
             return;
         }

datafusion/sqllogictest/test_files/select.slt

@@ -1912,7 +1912,7 @@ select * from t_with_user where user = 'foo';
 statement count 0
 create table t_with_current_time(a int, current_time text) as values (1,'now'), (2,null), (3,'later');
 
-# here it's clear the the column was meant
+# here it's clear the column was meant
 query B
 select t_with_current_time.current_time is not null from t_with_current_time;
 ----

docs/source/user-guide/sql/dml.md

@@ -88,7 +88,7 @@ of hive-style partitioned parquet files:
 +-------+
 ```
 
-If the the data contains values of `x` and `y` in column1 and only `a` in
+If the data contains values of `x` and `y` in column1 and only `a` in
 column2, output files will appear in the following directory structure:
 
 ```text

docs/source/user-guide/sql/subqueries.md

@@ -183,7 +183,7 @@ FROM
 and return _true_ or _false_.
 Rows that evaluate to _false_ or NULL are filtered from results.
 The `WHERE` clause supports correlated and non-correlated subqueries
-as well as scalar and non-scalar subqueries (depending on the the operator used
+as well as scalar and non-scalar subqueries (depending on the operator used
 in the predicate expression).
 
 ```sql
@@ -293,7 +293,7 @@ returned by aggregate functions in the `SELECT` clause to the result of the
 subquery and return _true_ or _false_.
 Rows that evaluate to _false_ are filtered from results.
 The `HAVING` clause supports correlated and non-correlated subqueries
-as well as scalar and non-scalar subqueries (depending on the the operator used
+as well as scalar and non-scalar subqueries (depending on the operator used
 in the predicate expression).
 
 ```sql