Fix typos in datafusion-examples/datafusion-cli/docs (apache#11259)

* Add typos check in ci workflow

* typos.toml

* exclude more

* typos autofix

* remove typos ci

.github/workflows/rust.yml

@@ -581,4 +581,4 @@ jobs:
         run: cargo msrv verify
       - name: Check datafusion-cli
         working-directory: datafusion-cli
-        run: cargo msrv verify
+        run: cargo msrv verify

datafusion-cli/src/helper.rs

@@ -252,7 +252,7 @@ mod tests {
     fn unescape_readline_input() -> Result<()> {
         let validator = CliHelper::default();
 
-        // shoule be valid
+        // should be valid
         let result = readline_direct(
              Cursor::new(
                  r"create external table test stored as csv location 'data.csv' options ('format.delimiter' ',');"
@@ -326,7 +326,7 @@ mod tests {
     fn sql_dialect() -> Result<()> {
         let mut validator = CliHelper::default();
 
-        // shoule be invalid in generic dialect
+        // should be invalid in generic dialect
         let result =
             readline_direct(Cursor::new(r"select 1 # 2;".as_bytes()), &validator)?;
         assert!(

datafusion-examples/examples/advanced_udaf.rs

@@ -339,7 +339,7 @@ impl GroupsAccumulator for GeometricMeanGroupsAccumulator {
         Ok(())
     }
 
-    /// Generate output, as specififed by `emit_to` and update the intermediate state
+    /// Generate output, as specified by `emit_to` and update the intermediate state
     fn evaluate(&mut self, emit_to: datafusion_expr::EmitTo) -> Result<ArrayRef> {
         let counts = emit_to.take_needed(&mut self.counts);
         let prods = emit_to.take_needed(&mut self.prods);

datafusion-examples/examples/advanced_udwf.rs

@@ -75,7 +75,7 @@ impl WindowUDFImpl for SmoothItUdf {
         Ok(DataType::Float64)
     }
 
-    /// Create a `PartitionEvalutor` to evaluate this function on a new
+    /// Create a `PartitionEvaluator` to evaluate this function on a new
     /// partition.
     fn partition_evaluator(&self) -> Result<Box<dyn PartitionEvaluator>> {
         Ok(Box::new(MyPartitionEvaluator::new()))

datafusion-examples/examples/catalog.rs

@@ -83,7 +83,7 @@ async fn main() -> Result<()> {
     // register our catalog in the context
     ctx.register_catalog("dircat", Arc::new(catalog));
     {
-        // catalog was passed down into our custom catalog list since we overide the ctx's default
+        // catalog was passed down into our custom catalog list since we override the ctx's default
         let catalogs = catlist.catalogs.read().unwrap();
         assert!(catalogs.contains_key("dircat"));
     };

datafusion-examples/examples/expr_api.rs

@@ -46,7 +46,7 @@ use datafusion_expr::{AggregateExt, ColumnarValue, ExprSchemable, Operator};
 ///
 /// The code in this example shows how to:
 /// 1. Create [`Expr`]s using different APIs: [`main`]`
-/// 2. Use the fluent API to easly create complex [`Expr`]s:  [`expr_fn_demo`]
+/// 2. Use the fluent API to easily create complex [`Expr`]s:  [`expr_fn_demo`]
 /// 3. Evaluate [`Expr`]s against data: [`evaluate_demo`]
 /// 4. Simplify expressions: [`simplify_demo`]
 /// 5. Analyze predicates for boundary ranges: [`range_analysis_demo`]

datafusion-examples/examples/parse_sql_expr.rs

@@ -113,7 +113,7 @@ async fn query_parquet_demo() -> Result<()> {
             vec![df.parse_sql_expr("SUM(int_col) as sum_int_col")?],
         )?
         // Directly parsing the SQL text into a sort expression is not supported yet, so
-        // construct it programatically
+        // construct it programmatically
         .sort(vec![col("double_col").sort(false, false)])?
         .limit(0, Some(1))?;
 

datafusion-examples/examples/simple_udwf.rs

@@ -132,7 +132,7 @@ async fn main() -> Result<()> {
     Ok(())
 }
 
-/// Create a `PartitionEvalutor` to evaluate this function on a new
+/// Create a `PartitionEvaluator` to evaluate this function on a new
 /// partition.
 fn make_partition_evaluator() -> Result<Box<dyn PartitionEvaluator>> {
     Ok(Box::new(MyPartitionEvaluator::new()))

datafusion-examples/examples/sql_analysis.rs

@@ -87,7 +87,7 @@ fn count_trees(plan: &LogicalPlan) -> (usize, Vec<usize>) {
     let mut groups = vec![];
 
     while let Some(node) = to_visit.pop() {
-        // if we encouter a join, we know were at the root of the tree
+        // if we encounter a join, we know were at the root of the tree
         // count this tree and recurse on it's inputs
         if matches!(node, LogicalPlan::Join(_) | LogicalPlan::CrossJoin(_)) {
             let (group_count, inputs) = count_tree(node);

docs/source/contributor-guide/inviting.md

@@ -294,7 +294,7 @@ Subject: [DISCUSS] $NEW_PMC_MEMBER for PMC
 
 I would like to propose adding $NEW_PMC_MEMBER[1] to the DataFusion PMC.
 
-$NEW_PMC_MEMBMER has been a committer since $COMMITER_MONTH [2], has a
+$NEW_PMC_MEMBMER has been a committer since $COMMITTER_MONTH [2], has a
 strong and sustained contribution record for more than a year, and focused on
 helping the community and the project grow[3].
 

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

@@ -268,7 +268,7 @@ impl PartitionEvaluator for MyPartitionEvaluator {
     }
 }
 
-/// Create a `PartitionEvalutor` to evaluate this function on a new
+/// Create a `PartitionEvaluator` to evaluate this function on a new
 /// partition.
 fn make_partition_evaluator() -> Result<Box<dyn PartitionEvaluator>> {
     Ok(Box::new(MyPartitionEvaluator::new()))
@@ -474,7 +474,7 @@ impl Accumulator for GeometricMean {
 
 ### registering an Aggregate UDF
 
-To register a Aggreate UDF, you need to wrap the function implementation in a [`AggregateUDF`] struct and then register it with the `SessionContext`. DataFusion provides the [`create_udaf`] helper functions to make this easier.
+To register a Aggregate UDF, you need to wrap the function implementation in a [`AggregateUDF`] struct and then register it with the `SessionContext`. DataFusion provides the [`create_udaf`] helper functions to make this easier.
 There is a lower level API with more functionality but is more complex, that is documented in [`advanced_udaf.rs`].
 
 ```rust

docs/source/user-guide/example-usage.md

@@ -264,8 +264,8 @@ Set environment [variables](https://doc.rust-lang.org/std/backtrace/index.html#e
 ```bash
 RUST_BACKTRACE=1 ./target/debug/datafusion-cli
 DataFusion CLI v31.0.0
-> select row_numer() over (partition by a order by a) from (select 1 a);
-Error during planning: Invalid function 'row_numer'.
+> select row_number() over (partition by a order by a) from (select 1 a);
+Error during planning: Invalid function 'row_number'.
 Did you mean 'ROW_NUMBER'?
 
 backtrace:    0: std::backtrace_rs::backtrace::libunwind::trace
@@ -290,7 +290,7 @@ async fn test_get_backtrace_for_failed_code() -> Result<()> {
     let ctx = SessionContext::new();
 
     let sql = "
-    select row_numer() over (partition by a order by a) from (select 1 a);
+    select row_number() over (partition by a order by a) from (select 1 a);
     ";
 
     let _ = ctx.sql(sql).await?.collect().await?;