ci: add spellchecker to pr tests

Signed-off-by: Robert Pack <[email protected]>

Author: roeap

.github/workflows/dev_pr.yml

@@ -82,3 +82,11 @@ jobs:
               body: message
             })
             core.setFailed(message)
+
+  typos:
+    name: Spell Check
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Check spelling
+        uses: crate-ci/typos@v1

Cargo.toml

@@ -26,10 +26,7 @@ debug = true
 debug = "line-tables-only"
 
 [workspace.dependencies]
-delta_kernel = { version = "0.10.0", features = [
-    "arrow-55",
-    "internal-api",
-] }
+delta_kernel = { version = "0.10.0", features = ["arrow-55", "internal-api"] }
 
 # arrow
 arrow = { version = "=55.0.0" }
@@ -78,3 +75,6 @@ async-trait = { version = "0.1" }
 futures = { version = "0.3" }
 tokio = { version = "1" }
 num_cpus = { version = "1" }
+
+[workspace.metadata.typos]
+default.extend-ignore-re = ["(?Rm)^.*(#|//)\\s*spellchecker:disable-line$"]

crates/core/src/logstore/mod.rs

@@ -646,7 +646,7 @@ pub async fn get_latest_version(
             let part_count = location_path.prefix_match(prefix).unwrap().count();
             if part_count > 1 {
                 // Per the spec, ignore any files in subdirectories.
-                // Spark may create these as uncommited transactions which we don't want
+                // Spark may create these as uncommitted transactions which we don't want
                 //
                 // https://github.com/delta-io/delta/blob/master/PROTOCOL.md#delta-log-entries
                 // "Delta files are stored as JSON in a directory at the *root* of the table

crates/core/src/operations/constraints.rs

@@ -367,7 +367,7 @@ mod tests {
     async fn test_constraint_case_sensitive() -> DeltaResult<()> {
         let arrow_schema = Arc::new(ArrowSchema::new(vec![
             Field::new("Id", ArrowDataType::Utf8, true),
-            Field::new("vAlue", ArrowDataType::Int32, true),
+            Field::new("vAlue", ArrowDataType::Int32, true), // spellchecker:disable-line
             Field::new("mOdifieD", ArrowDataType::Utf8, true),
         ]));
 
@@ -389,12 +389,12 @@ mod tests {
 
         let mut table = DeltaOps(table)
             .add_constraint()
-            .with_constraint("valid_values", "vAlue < 1000")
+            .with_constraint("valid_values", "vAlue < 1000") // spellchecker:disable-line
             .await?;
         let version = table.version();
         assert_eq!(version, 1);
 
-        let expected_expr = "vAlue < 1000";
+        let expected_expr = "vAlue < 1000"; // spellchecker:disable-line
         assert_eq!(get_constraint_op_params(&mut table).await, expected_expr);
         assert_eq!(
             get_constraint(&table, "delta.constraints.valid_values"),

crates/core/src/operations/merge/mod.rs

@@ -3324,7 +3324,7 @@ mod tests {
                 true,
             ),
             StructField::new(
-                "vAlue".to_string(),
+                "vAlue".to_string(), // spellchecker:disable-line
                 DataType::Primitive(PrimitiveType::Integer),
                 true,
             ),
@@ -3337,7 +3337,7 @@ mod tests {
 
         let arrow_schema = Arc::new(ArrowSchema::new(vec![
             Field::new("Id", ArrowDataType::Utf8, true),
-            Field::new("vAlue", ArrowDataType::Int32, true),
+            Field::new("vAlue", ArrowDataType::Int32, true), // spellchecker:disable-line
             Field::new("mOdifieD", ArrowDataType::Utf8, true),
         ]));
 
@@ -3374,7 +3374,7 @@ mod tests {
             .when_not_matched_insert(|insert| {
                 insert
                     .set("Id", "source.Id")
-                    .set("vAlue", "source.vAlue + 1")
+                    .set("vAlue", "source.vAlue + 1") // spellchecker:disable-line
                     .set("mOdifieD", "source.mOdifieD")
             })
             .unwrap()
@@ -3383,7 +3383,7 @@ mod tests {
 
         let expected = vec![
             "+----+-------+------------+",
-            "| Id | vAlue | mOdifieD   |",
+            "| Id | vAlue | mOdifieD   |", // spellchecker:disable-line
             "+----+-------+------------+",
             "| A  | 1     | 2021-02-01 |",
             "| B  | 10    | 2021-02-01 |",

crates/core/src/operations/update.rs

@@ -863,7 +863,7 @@ mod tests {
                 true,
             ),
             StructField::new(
-                "ValUe".to_string(),
+                "ValUe".to_string(), // spellchecker:disable-line
                 DeltaDataType::Primitive(PrimitiveType::Integer),
                 true,
             ),
@@ -876,7 +876,7 @@ mod tests {
 
         let arrow_schema = Arc::new(ArrowSchema::new(vec![
             Field::new("Id", DataType::Utf8, true),
-            Field::new("ValUe", DataType::Int32, true),
+            Field::new("ValUe", DataType::Int32, true), // spellchecker:disable-line
             Field::new("mOdified", DataType::Utf8, true),
         ]));
 
@@ -912,7 +912,7 @@ mod tests {
 
         let expected = vec![
             "+----+-------+------------+",
-            "| Id | ValUe | mOdified   |",
+            "| Id | ValUe | mOdified   |", // spellchecker:disable-line
             "+----+-------+------------+",
             "| A  | 1     | 2021-02-02 |",
             "| B  | 10    | 2021-02-02 |",

crates/core/src/table/mod.rs

@@ -388,7 +388,7 @@ impl DeltaTable {
             let part_count = location_path.prefix_match(prefix).unwrap().count();
             if part_count > 1 {
                 // Per the spec, ignore any files in subdirectories.
-                // Spark may create these as uncommited transactions which we don't want
+                // Spark may create these as uncommitted transactions which we don't want
                 //
                 // https://github.com/delta-io/delta/blob/master/PROTOCOL.md#delta-log-entries
                 // "Delta files are stored as JSON in a directory at the *root* of the table