chore: fix typos

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

crates/aws/helpers.rs

@@ -39,7 +39,10 @@ pub async fn setup_s3_context() -> TestContext {
     config.insert("AWS_ACCESS_KEY_ID".to_owned(), "deltalake".to_owned());
     config.insert("AWS_SECRET_ACCESS_KEY".to_owned(), "weloverust".to_owned());
     config.insert("AWS_S3_LOCKING_PROVIDER".to_owned(), "dynamodb".to_owned());
-    config.insert(constants::LOCK_TABLE_KEY_NAME.to_owned(), lock_table.clone());
+    config.insert(
+        constants::LOCK_TABLE_KEY_NAME.to_owned(),
+        lock_table.clone(),
+    );
     config.insert("AWS_ALLOW_HTTP".to_owned(), "TRUE".to_string());
 
     TestContext {
@@ -72,7 +75,7 @@ impl S3Cli {
         child.wait().unwrap();
     }
 
-    pub fn rm_recurive(&self, prefix: &str, endpoint: &str) {
+    pub fn rm_recursive(&self, prefix: &str, endpoint: &str) {
         let mut child = Command::new("aws")
             .args([
                 "s3",
@@ -140,7 +143,7 @@ struct S3 {
 impl Drop for S3 {
     fn drop(&mut self) {
         let cli = S3Cli::default();
-        cli.rm_recurive(&self.uri, &self.endpoint);
+        cli.rm_recursive(&self.uri, &self.endpoint);
         cli.delete_table(&self.lock_table, &self.endpoint);
     }
 }

crates/aws/src/credentials.rs

@@ -211,7 +211,7 @@ mod options_tests {
 }
 
 /// Generate a random session name for assuming IAM roles
-fn assume_role_sessio_name() -> String {
+fn assume_role_session_name() -> String {
     let now = chrono::Utc::now();
 
     format!("delta-rs_{}", now.timestamp_millis())
@@ -256,7 +256,7 @@ fn assume_session_name(options: &StorageOptions) -> String {
         )
         .cloned();
 
-    assume_session.unwrap_or_else(assume_role_sessio_name)
+    assume_session.unwrap_or_else(assume_role_session_name)
 }
 
 /// Take a set of [StorageOptions] and produce an appropriate AWS SDK [SdkConfig]

crates/aws/src/errors.rs

@@ -128,7 +128,7 @@ impl From<PutItemError> for LockClientError {
     fn from(err: PutItemError) -> Self {
         match err {
             PutItemError::ConditionalCheckFailedException(_) => {
-                unreachable!("error must be handled explicitely")
+                unreachable!("error must be handled explicitly")
             }
             PutItemError::ProvisionedThroughputExceededException(_) => {
                 LockClientError::ProvisionedThroughputExceeded

crates/aws/src/lib.rs

@@ -249,7 +249,7 @@ impl DynamoDbLockClient {
     /// Transparently handles the case where that table already exists, so it's safe to call.
     /// After `create_table` operation is executed, the table state in DynamoDb is `creating`, and
     /// it's not immediately useable. This method does not wait for the table state to become
-    /// `active`, so transient failures might occurr when immediately using the lock client.
+    /// `active`, so transient failures might occur when immediately using the lock client.
     pub async fn try_create_lock_table(&self) -> Result<CreateLockTableResult, LockClientError> {
         let attribute_definitions = vec![
             AttributeDefinition::builder()

crates/aws/src/logstore/dynamodb_logstore.rs

@@ -329,7 +329,7 @@ pub enum RepairLogEntryResult {
     MovedFileAndFixedEntry,
     /// The database entry has been rewritten, but the file was already moved.
     FixedEntry,
-    /// Moved file, but the database entry was alrady updated.
+    /// Moved file, but the database entry was already updated.
     MovedFile,
     /// Both parts of the repair process where already carried.
     AlreadyCompleted,

crates/azure/src/config.rs

@@ -124,7 +124,7 @@ impl AzureConfigHelper {
             .all(|key| self.config.contains_key(key) || self.env_config.contains_key(key))
     }
 
-    /// Generate a cofiguration augmented with options from the environment
+    /// Generate a configuration augmented with options from the environment
     pub fn build(mut self) -> Result<HashMap<AzureConfigKey, String>> {
         let mut has_credential = false;
 
@@ -142,7 +142,7 @@ impl AzureConfigHelper {
             }
         }
 
-        // try partially avaialbe credentials augmented by environment
+        // try partially available credentials augmented by environment
         if !has_credential {
             for cred in &self.priority {
                 if self.has_any_config(cred) && self.has_full_config_with_env(cred) {

crates/core/src/delta_datafusion/mod.rs

@@ -118,7 +118,7 @@ impl From<DataFusionError> for DeltaTableError {
     }
 }
 
-/// Convience trait for calling common methods on snapshot heirarchies
+/// Convenience trait for calling common methods on snapshot hierarchies
 pub trait DataFusionMixins {
     /// The physical datafusion schema of a table
     fn arrow_schema(&self) -> DeltaResult<ArrowSchemaRef>;
@@ -2659,7 +2659,7 @@ mod tests {
     #[tokio::test]
     async fn passes_sanity_checker_when_all_files_filtered() {
         // Run a query that filters out all files and sorts.
-        // Verify that it returns an empty set of rows without panicing.
+        // Verify that it returns an empty set of rows without panicking.
         //
         // Historically, we had a bug that caused us to emit a query plan with 0 partitions, which
         // datafusion rejected.

crates/core/src/kernel/arrow/extract.rs

@@ -1,4 +1,4 @@
-//! Utilties to extract columns from a record batch or nested / complex arrays.
+//! Utilities to extract columns from a record batch or nested / complex arrays.
 
 use std::sync::Arc;
 
@@ -70,7 +70,7 @@ pub(crate) fn extract_column<'a>(
     if let Some(next_path_step) = remaining_path_steps.next() {
         match child.data_type() {
             DataType::Map(_, _) => {
-                // NOTE a map has exatly one child, but we wnat to be agnostic of its name.
+                // NOTE a map has exactly one child, but we want to be agnostic of its name.
                 // so we case the current array as map, and use the entries accessor.
                 let maparr = cast_column_as::<MapArray>(path_step, &Some(child))?;
                 if let Some(next_path) = remaining_path_steps.next() {

crates/core/src/kernel/models/actions.rs

@@ -188,19 +188,19 @@ impl Protocol {
         mut self,
         writer_features: impl IntoIterator<Item = impl Into<WriterFeatures>>,
     ) -> Self {
-        let all_writer_feautures = writer_features
+        let all_writer_features = writer_features
             .into_iter()
             .map(|c| c.into())
             .collect::<HashSet<_>>();
-        if !all_writer_feautures.is_empty() {
+        if !all_writer_features.is_empty() {
             self.min_writer_version = 7;
 
             match self.writer_features {
                 Some(mut features) => {
-                    features.extend(all_writer_feautures);
+                    features.extend(all_writer_features);
                     self.writer_features = Some(features);
                 }
-                None => self.writer_features = Some(all_writer_feautures),
+                None => self.writer_features = Some(all_writer_features),
             };
         }
         self

crates/core/src/kernel/models/schema.rs

@@ -46,7 +46,7 @@ impl DataCheck for Invariant {
     }
 }
 
-/// Trait to add convenince functions to struct type
+/// Trait to add convenience functions to struct type
 pub trait StructTypeExt {
     /// Get all invariants in the schemas
     fn get_invariants(&self) -> Result<Vec<Invariant>, Error>;

crates/core/src/kernel/snapshot/log_data.rs

@@ -158,7 +158,7 @@ impl LogicalFile<'_> {
     /// An object store [`Path`] to the file.
     ///
     /// this tries to parse the file string and if that fails, it will return the string as is.
-    // TODO assert consisent handling of the paths encoding when reading log data so this logic can be removed.
+    // TODO assert consistent handling of the paths encoding when reading log data so this logic can be removed.
     pub fn object_store_path(&self) -> Path {
         let path = self.path();
         // Try to preserve percent encoding if possible

crates/core/src/kernel/snapshot/log_segment.rs

@@ -136,7 +136,7 @@ impl LogSegment {
 
     /// Try to create a new [`LogSegment`] from a slice of the log.
     ///
-    /// Ths will create a new [`LogSegment`] from the log with all relevant log files
+    /// This will create a new [`LogSegment`] from the log with all relevant log files
     /// starting at `start_version` and ending at `end_version`.
     pub async fn try_new_slice(
         table_root: &Path,
@@ -190,7 +190,7 @@ impl LogSegment {
         Ok(())
     }
 
-    /// Returns the highes commit version number in the log segment
+    /// Returns the highest commit version number in the log segment
     pub fn file_version(&self) -> Option<i64> {
         self.commit_files
             .iter()
@@ -358,7 +358,7 @@ impl LogSegment {
     /// Advance the log segment with new commits
     ///
     /// Returns an iterator over record batches, as if the commits were read from the log.
-    /// The input commits should be in order in which they would be commited to the table.
+    /// The input commits should be in order in which they would be committed to the table.
     pub(super) fn advance<'a>(
         &mut self,
         commits: impl IntoIterator<Item = &'a CommitData>,

crates/core/src/kernel/snapshot/mod.rs

@@ -447,7 +447,7 @@ impl EagerSnapshot {
 
         schema_actions.insert(ActionType::Add);
         let checkpoint_stream = if new_slice.checkpoint_files.is_empty() {
-            // NOTE: we don't need to add the visitor relevant data here, as it is repüresented in teh state already
+            // NOTE: we don't need to add the visitor relevant data here, as it is repüresented in the state already
             futures::stream::iter(files.into_iter().map(Ok)).boxed()
         } else {
             let read_schema =

crates/core/src/kernel/snapshot/replay.rs

@@ -513,7 +513,7 @@ impl LogReplayScanner {
                         self.seen.insert(seen_key(&r));
                         keep.push(false);
                     }
-                    // NOTE: there sould always be only one action per row.
+                    // NOTE: there should always be only one action per row.
                     (None, None) => debug!("WARNING: no action found for row"),
                     (Some(a), Some(r)) => {
                         debug!(

crates/core/src/kernel/snapshot/visitors.rs

@@ -144,7 +144,7 @@ mod tests {
             Some(Some(123))
         );
 
-        // test that only the first encountered txn ist tacked for every app id.
+        // test that only the first encountered txn is tacked for every app id.
         data_app.extend([None, Some("my-app")]);
         data_version.extend([None, Some(2)]);
         data_last_updated.extend([None, Some(124)]);

crates/core/src/operations/cast/merge_schema.rs

@@ -336,9 +336,9 @@ fn merge_arrow_vec_fields(
                         // field.try_merge
                         f.set_metadata(right_field.metadata().clone());
 
-                        let mut field_matadata = f.metadata().clone();
-                        try_merge_metadata(&mut field_matadata, right_field.metadata())?;
-                        f.set_metadata(field_matadata);
+                        let mut field_metadata = f.metadata().clone();
+                        try_merge_metadata(&mut field_metadata, right_field.metadata())?;
+                        f.set_metadata(field_metadata);
                         Ok(f)
                     }
                 }

crates/core/src/operations/constraints.rs

@@ -121,7 +121,7 @@ impl std::future::IntoFuture for ConstraintBuilder {
 
             let expr = this
                 .expr
-                .ok_or_else(|| DeltaTableError::Generic("No Expresion provided".to_string()))?;
+                .ok_or_else(|| DeltaTableError::Generic("No Expression provided".to_string()))?;
 
             let mut metadata = this.snapshot.metadata().clone();
             let configuration_key = format!("delta.constraints.{}", name);

crates/core/src/operations/convert_to_delta.rs

@@ -75,7 +75,7 @@ impl From<Error> for DeltaTableError {
 }
 
 /// The partition strategy used by the Parquet table
-/// Currently only hive-partitioning is supproted for Parquet paths
+/// Currently only hive-partitioning is supported for Parquet paths
 #[non_exhaustive]
 #[derive(Default)]
 pub enum PartitionStrategy {
@@ -187,7 +187,7 @@ impl ConvertToDeltaBuilder {
     }
 
     /// Specify the partition strategy of the Parquet table
-    /// Currently only hive-partitioning is supproted for Parquet paths
+    /// Currently only hive-partitioning is supported for Parquet paths
     pub fn with_partition_strategy(mut self, strategy: PartitionStrategy) -> Self {
         self.partition_strategy = strategy;
         self
@@ -402,7 +402,7 @@ impl ConvertToDeltaBuilder {
 
             let mut arrow_schema = batch_builder.schema().as_ref().clone();
 
-            // Arrow schema of Parquet files may have conflicting metatdata
+            // Arrow schema of Parquet files may have conflicting metadata
             // Since Arrow schema metadata is not used to generate Delta table schema, we set the metadata field to an empty HashMap
             arrow_schema.metadata = HashMap::new();
             arrow_schemas.push(arrow_schema);

crates/core/src/operations/create.rs

@@ -224,7 +224,7 @@ impl CreateBuilder {
         self
     }
 
-    /// Specify whether to raise an error if the table properties in the configuration are not TablePropertys
+    /// Specify whether to raise an error if the table properties in the configuration are not TableProperties
     pub fn with_raise_if_key_not_exists(mut self, raise_if_key_not_exists: bool) -> Self {
         self.raise_if_key_not_exists = raise_if_key_not_exists;
         self

crates/core/src/operations/delete.rs

@@ -1,4 +1,4 @@
-//! Delete records from a Delta Table that statisfy a predicate
+//! Delete records from a Delta Table that satisfy a predicate
 //!
 //! When a predicate is not provided then all records are deleted from the Delta
 //! Table. Otherwise a scan of the Delta table is performed to mark any files
@@ -134,7 +134,7 @@ impl DeleteBuilder {
         self
     }
 
-    /// Additonal information to write to the commit
+    /// Additional information to write to the commit
     pub fn with_commit_properties(mut self, commit_properties: CommitProperties) -> Self {
         self.commit_properties = commit_properties;
         self
@@ -184,7 +184,7 @@ impl ExtensionPlanner for DeleteMetricExtensionPlanner {
 }
 
 #[allow(clippy::too_many_arguments)]
-async fn excute_non_empty_expr(
+async fn execute_non_empty_expr(
     snapshot: &DeltaTableState,
     log_store: LogStoreRef,
     state: &SessionState,
@@ -330,7 +330,7 @@ async fn execute(
 
     let mut actions = {
         let write_start = Instant::now();
-        let add = excute_non_empty_expr(
+        let add = execute_non_empty_expr(
             &snapshot,
             log_store.clone(),
             &state,

crates/core/src/operations/filesystem_check.rs

@@ -104,7 +104,7 @@ impl FileSystemCheckBuilder {
         self
     }
 
-    /// Additonal information to write to the commit
+    /// Additional information to write to the commit
     pub fn with_commit_properties(mut self, commit_properties: CommitProperties) -> Self {
         self.commit_properties = commit_properties;
         self

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

@@ -547,8 +547,8 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn test_barrier_changing_indicies() {
-        // Validate implementation can handle different dictionary indicies between batches
+    async fn test_barrier_changing_indices() {
+        // Validate implementation can handle different dictionary indices between batches
 
         let schema = get_schema();
         let mut batches = vec![];

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

@@ -1195,12 +1195,12 @@ async fn execute(
         LogicalPlanBuilder::from(plan).project(fields)?.build()?
     };
 
-    let distrbute_expr = col(file_column.as_str());
+    let distribute_expr = col(file_column.as_str());
 
     let merge_barrier = LogicalPlan::Extension(Extension {
         node: Arc::new(MergeBarrier {
             input: new_columns.clone(),
-            expr: distrbute_expr,
+            expr: distribute_expr,
             file_column,
         }),
     });

crates/core/src/operations/optimize.rs

@@ -267,7 +267,7 @@ impl<'a> OptimizeBuilder<'a> {
         self
     }
 
-    /// Additonal information to write to the commit
+    /// Additional information to write to the commit
     pub fn with_commit_properties(mut self, commit_properties: CommitProperties) -> Self {
         self.commit_properties = commit_properties;
         self

crates/core/src/operations/transaction/conflict_checker.rs

@@ -411,7 +411,7 @@ impl<'a> ConflictChecker<'a> {
             );
             if curr_read < win_read || win_write < curr_write {
                 return Err(CommitConflictError::ProtocolChanged(
-                    format!("reqired read/write {win_read}/{win_write}, current read/write {curr_read}/{curr_write}"),
+                    format!("required read/write {win_read}/{win_write}, current read/write {curr_read}/{curr_write}"),
                 ));
             };
         }
@@ -638,7 +638,7 @@ pub(super) fn can_downgrade_to_snapshot_isolation<'a>(
     match isolation_level {
         IsolationLevel::Serializable => !data_changed,
         IsolationLevel::WriteSerializable => !data_changed && !operation.changes_data(),
-        IsolationLevel::SnapshotIsolation => false, // this case should never happen, since spanpshot isolation canot be configured on table
+        IsolationLevel::SnapshotIsolation => false, // this case should never happen, since spanpshot isolation cannot be configured on table
     }
 }
 
@@ -857,7 +857,7 @@ mod tests {
         setup_actions.push(file_part1);
         let result = execute_test(
             Some(setup_actions),
-            // filter matches neither exisiting nor added files
+            // filter matches neither existing nor added files
             Some(col("value").lt(lit::<i32>(0))),
             vec![file_part2],
             vec![file_part3],