add a ci job for typo checking (#17339)

* add a ci job for typo checking

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

* correct version number

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

* fix new occurs

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

* Update datafusion/core/tests/physical_optimizer/filter_pushdown/mod.rs

Co-authored-by: Jeffrey Vo <[email protected]>

---------

Signed-off-by: Ruihang Xia <[email protected]>
Co-authored-by: Jeffrey Vo <[email protected]>

Author: waynexia

.github/workflows/rust.yml

@@ -781,3 +781,11 @@ jobs:
       - name: Check datafusion-proto
         working-directory: datafusion/proto
         run: cargo msrv --output-format json --log-target stdout verify
+  typos:
+    name: Spell Check with Typos
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: false
+      - uses: crate-ci/typos@v1

datafusion/core/tests/physical_optimizer/filter_pushdown/mod.rs

@@ -1095,7 +1095,7 @@ async fn test_hashjoin_dynamic_filter_pushdown_partitioned() {
     // Top-level CoalesceBatchesExec
     let cb =
         Arc::new(CoalesceBatchesExec::new(hash_join, 8192)) as Arc<dyn ExecutionPlan>;
-    // Top-level CoalesceParititionsExec
+    // Top-level CoalescePartitionsExec
     let cp = Arc::new(CoalescePartitionsExec::new(cb)) as Arc<dyn ExecutionPlan>;
     // Add a sort for determistic output
     let plan = Arc::new(SortExec::new(

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

@@ -34,7 +34,7 @@ pub struct JoinFilter {
 }
 
 /// For display in `EXPLAIN` plans, only expression with column names is needed,
-/// it output expresion like `(col1 + col2) = 0`
+/// it output expression like `(col1 + col2) = 0`
 impl Display for JoinFilter {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         self.expression.fmt_sql(f)

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

@@ -827,7 +827,7 @@ impl Stream for NestedLoopJoinStream {
                 // side batch, before start joining.
                 NLJState::BufferingLeft => {
                     debug!("[NLJState] Entering: {:?}", self.state);
-                    // inside `collect_left_input` (the rountine to buffer build
+                    // inside `collect_left_input` (the routine to buffer build
                     // -side batches), related metrics except build time will be
                     // updated.
                     // stop on drop
@@ -1583,7 +1583,7 @@ fn apply_filter_to_row_join_batch(
 /// 30
 /// 40
 ///
-/// # After applying it, only index 1 and 3 elemnt in probe_side_batch will be
+/// # After applying it, only index 1 and 3 elements in probe_side_batch will be
 /// # kept
 /// probe_side_filter:
 /// false

typos.toml

@@ -0,0 +1,46 @@
+[default.extend-words]
+# random words from unit tests
+Pn = "Pn"
+fo = "fo"
+nd = "nd"
+Nd = "Nd"
+ba = "ba"
+ECT = "ECT"
+Ue = "Ue"
+Iy = "Iy"
+hte = "hte"
+numer = "numer"
+abd = "abd"
+aroun = "aroun"
+abov = "abov"
+Ois = "Ois"
+alo = "alo"
+
+# abbreviations, common words, etc.
+typ = "typ"
+datas = "datas"
+YOUY = "YOUY"
+lits = "lits"
+
+# exposed to public API
+Serializeable = "Serializeable"
+
+# from test cases like TPC-* or ClickBench
+carefull = "carefull"
+precentage = "precentage"
+flate = "flate"
+hom = "hom"
+alph = "alph"
+wih = "wih"
+Ded = "Ded"
+
+[files]
+extend-exclude = [
+    "*.slt",
+    "*.slt.part",
+    "*.svg",
+    "*.sql",
+    "dev/changelog/**",
+    "benchmarks/**",
+    "*.csv"
+]