add typos spell checker to pre-commit (#2568)

Co-authored-by: Michał Krassowski <5832902+krassowski@users.noreply.github.com>

.github/workflows/test_azure_integration.yaml

@@ -1,4 +1,4 @@
-name: Azure Delpoyment
+name: Azure Deployment
 
 on:
   schedule:

.github/workflows/test_helm_charts.yaml

@@ -1,5 +1,5 @@
 # Right now the trigger is set to run on every Monday at 13:00 UTC,
-# or when the workflow file is modified. An aditional manual trigger
+# or when the workflow file is modified. An additional manual trigger
 # is also available.
 name: "Validate Helm Charts downloads"
 

.pre-commit-config.yaml

@@ -36,6 +36,11 @@ repos:
       - id: check-executables-have-shebangs
         exclude: "^src/_nebari/template/"
 
+  - repo: https://github.com/crate-ci/typos
+    rev: v1.23.2
+    hooks:
+      - id: typos
+
   - repo: https://github.com/codespell-project/codespell
     rev: v2.3.0
     hooks:

RELEASE.md

@@ -285,7 +285,7 @@ command and follow the instructions
 * paginator for boto3 ec2 instance types by @sblair-metrostar in https://github.com/nebari-dev/nebari/pull/1923
 * Update README.md -- fix typo. by @teoliphant in https://github.com/nebari-dev/nebari/pull/1925
 * Add more unit tests, add cleanup step for Digital Ocean integration test by @iameskild in https://github.com/nebari-dev/nebari/pull/1910
-* Add cleanup step for AWS integration test, ensure diable_prompt is passed through by @iameskild in https://github.com/nebari-dev/nebari/pull/1921
+* Add cleanup step for AWS integration test, ensure disable_prompt is passed through by @iameskild in https://github.com/nebari-dev/nebari/pull/1921
 * K8s 1.25 + More Improvements by @Adam-D-Lewis in https://github.com/nebari-dev/nebari/pull/1856
 * adding lifecycle ignore to eks node group by @sblair-metrostar in https://github.com/nebari-dev/nebari/pull/1905
 * nebari init unit tests by @sblair-metrostar in https://github.com/nebari-dev/nebari/pull/1931

pyproject.toml

@@ -177,3 +177,9 @@ exclude_also = [
     "@(abc\\.)?abstractmethod",
     ]
 ignore_errors = false
+
+[tool.typos]
+files.extend-exclude = ["_build", "*/build/*", "*/node_modules/*", "nebari.egg-info", "*.git", "*.js", "*.json", "*.yaml", "*.yml", "pre-commit-config.yaml"]
+default.extend-ignore-re = ["(?Rm)^.*(#|//)\\s*typos: ignore$"]
+default.extend-ignore-words-re = ["aks", "AKS"]
+default.check-filename = false  # Turn off initially, enable once https://github.com/nebari-dev/nebari/issues/2598 is addressed

pytest.ini

@@ -1,6 +1,6 @@
 [pytest]
 addopts =
-    # show tests that (f)ailed, (E)rror, or (X)passed in the summary
+    # show tests that (f)ailed, (E)rror, or (X)passed in the summary  # typos: ignore
     -rfEX
     # Make tracebacks shorter
     --tb=native

src/_nebari/stages/infrastructure/__init__.py

@@ -340,10 +340,10 @@ class GoogleCloudPlatformProvider(schema.Base):
     @classmethod
     def _check_input(cls, data: Any) -> Any:
         google_cloud.check_credentials()
-        avaliable_regions = google_cloud.regions()
-        if data["region"] not in avaliable_regions:
+        available_regions = google_cloud.regions()
+        if data["region"] not in available_regions:
             raise ValueError(
-                f"Google Cloud region={data['region']} is not one of {avaliable_regions}"
+                f"Google Cloud region={data['region']} is not one of {available_regions}"
             )
 
         available_kubernetes_versions = google_cloud.kubernetes_versions(data["region"])
@@ -584,16 +584,16 @@ def check_provider(cls, data: Any) -> Any:
                     f"'{provider}' is not a valid enumeration member; permitted: local, existing, do, aws, gcp, azure"
                 )
         else:
-            setted_providers = [
+            set_providers = [
                 provider
                 for provider in provider_name_abbreviation_map.keys()
                 if provider in data
             ]
-            num_providers = len(setted_providers)
+            num_providers = len(set_providers)
             if num_providers > 1:
-                raise ValueError(f"Multiple providers set: {setted_providers}")
+                raise ValueError(f"Multiple providers set: {set_providers}")
             elif num_providers == 1:
-                data["provider"] = provider_name_abbreviation_map[setted_providers[0]]
+                data["provider"] = provider_name_abbreviation_map[set_providers[0]]
             elif num_providers == 0:
                 data["provider"] = schema.ProviderEnum.local.value
         return data
@@ -606,7 +606,7 @@ class NodeSelectorKeyValue(schema.Base):
 
 class KubernetesCredentials(schema.Base):
     host: str
-    cluster_ca_certifiate: str
+    cluster_ca_certifiate: str  # ignored for now.  More info in https://github.com/nebari-dev/nebari/issues/2597. # typos: ignore
     token: Optional[str] = None
     username: Optional[str] = None
     password: Optional[str] = None

src/_nebari/stages/infrastructure/template/aws/variables.tf

@@ -47,7 +47,7 @@ variable "availability_zones" {
 }
 
 variable "vpc_cidr_block" {
-  description = "VPC cidr block for infastructure"
+  description = "VPC cidr block for infrastructure"
   type        = string
 }
 

src/_nebari/stages/infrastructure/template/gcp/modules/kubernetes/outputs.tf

@@ -1,5 +1,5 @@
 output "credentials" {
-  description = "Credentials required for connecting to kubernets cluster"
+  description = "Credentials required for connecting to kubernetes cluster"
   sensitive   = true
   value = {
     endpoint = "https://${google_container_cluster.main.endpoint}"

src/_nebari/stages/kubernetes_services/template/modules/kubernetes/services/dask-gateway/files/gateway_config.py

@@ -129,7 +129,7 @@ def base_node_group(options):
         default_node_group if worker_node_group is None else worker_node_group
     )
 
-    # check `schduler_extra_pod_config` first
+    # check `scheduler_extra_pod_config` first
     scheduler_node_group = (
         config["profiles"][options.profile]
         .get("scheduler_extra_pod_config", {})

tests/common/run_notebook.py

@@ -20,7 +20,7 @@ def run(
         expected_outputs: List[str],
         conda_env: str,
         timeout: float = 1000,
-        complition_wait_time: float = 2,
+        completion_wait_time: float = 2,
         retry: int = 2,
         retry_wait_time: float = 5,
         exact_match: bool = True,
@@ -47,7 +47,7 @@ def run(
         timeout: float
             Time in seconds to wait for the expected output text to appear.
             default: 1000
-        complition_wait_time: float
+        completion_wait_time: float
             Time in seconds to wait between checking for expected output text.
             default: 2
         retry: int
@@ -77,7 +77,7 @@ def run(
             self._restart_run_all()
             # Wait for a couple of seconds to make sure it's re-started
             time.sleep(retry_wait_time)
-            self._wait_for_commands_completion(timeout, complition_wait_time)
+            self._wait_for_commands_completion(timeout, completion_wait_time)
             all_outputs = self._get_outputs()
             assert_match_all_outputs(expected_outputs, all_outputs, exact_match)
 
@@ -126,7 +126,7 @@ def assert_code_output(
         code: str,
         expected_output: str,
         timeout: float = 1000,
-        complition_wait_time: float = 2,
+        completion_wait_time: float = 2,
         exact_match: bool = True,
     ):
         """
@@ -143,11 +143,11 @@ def assert_code_output(
         timeout: float
             Time in seconds to wait for the expected output text to appear.
             default: 1000
-        complition_wait_time: float
+        completion_wait_time: float
             Time in seconds to wait between checking for expected output text.
         """
         self.run_in_last_cell(code)
-        self._wait_for_commands_completion(timeout, complition_wait_time)
+        self._wait_for_commands_completion(timeout, completion_wait_time)
         outputs = self._get_outputs()
         actual_output = outputs[-1] if outputs else ""
         assert_match_output(expected_output, actual_output, exact_match)
@@ -177,7 +177,7 @@ def _get_last_cell(self):
         raise ValueError("Unable to get last cell")
 
     def _wait_for_commands_completion(
-        self, timeout: float, complition_wait_time: float
+        self, timeout: float, completion_wait_time: float
     ):
         """
         Wait for commands to finish running
@@ -186,7 +186,7 @@ def _wait_for_commands_completion(
         ----------
         timeout: float
             Time in seconds to wait for the expected output text to appear.
-        complition_wait_time: float
+        completion_wait_time: float
         Time in seconds to wait between checking for expected output text.
         """
         elapsed_time = 0.0
@@ -198,7 +198,7 @@ def _wait_for_commands_completion(
             if not still_visible:
                 break
             elapsed_time = time.time() - start_time
-            time.sleep(complition_wait_time)
+            time.sleep(completion_wait_time)
         if still_visible:
             raise ValueError(
                 f"Timeout Waited for commands to finish, "

tests/tests_unit/test_schema.py

@@ -139,7 +139,7 @@ def test_multiple_providers(config_schema):
         config_schema(**config_dict)
 
 
-def test_aws_premissions_boundary(config_schema):
+def test_aws_permissions_boundary(config_schema):
     permissions_boundary = "arn:aws:iam::123456789012:policy/MyBoundaryPolicy"
     config_dict = {
         "project_name": "test",
@@ -156,7 +156,7 @@ def test_aws_premissions_boundary(config_schema):
 
 
 @pytest.mark.parametrize("provider", ["local", "existing"])
-def test_setted_provider(config_schema, provider):
+def test_set_provider(config_schema, provider):
     config_dict = {
         "project_name": "test",
         "provider": provider,