feat: Add codespell config, pre-commit and dedicated workflow (to cat…

…ch new typos) and get typos fixed
awslabs · Dec 13, 2023 · 30ad93b · 30ad93b
2 parents 241a241 + 8d35cdc
commit 30ad93b
Show file tree

Hide file tree

Showing 54 changed files with 106 additions and 74 deletions.
diff --git a/.codespellrc b/.codespellrc
@@ -0,0 +1,6 @@
+[codespell]
+skip = .git,*.pdf,*.svg,go.sum,package-lock.json,*.css,.codespellrc,*.sql,website/package-lock.json
+check-hidden = true
+# some embedded images and known typoed outputs
+ignore-regex = ^\s*"image/\S+": ".*|.*loopback adddress.*
+# ignore-words-list = 
diff --git a/.github/workflows/codespell.yml b/.github/workflows/codespell.yml
@@ -0,0 +1,22 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -33,3 +33,7 @@ repos:
           - '--args=--only=terraform_workspace_remote'
       - id: terraform_validate
         exclude: docs
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.6
+    hooks:
+    - id: codespell
diff --git a/ai-ml/emr-spark-rapids/addons.tf b/ai-ml/emr-spark-rapids/addons.tf
@@ -158,7 +158,7 @@ module "eks_data_addons" {
   #---------------------------------------------------------------
   # Kubecost Add-on
   #---------------------------------------------------------------
-  # Note: Kubecost add-on depdends on Kube Prometheus Stack add-on for storing the metrics
+  # Note: Kubecost add-on depends on Kube Prometheus Stack add-on for storing the metrics
   enable_kubecost = var.enable_kubecost
   kubecost_helm_config = {
     values              = [templatefile("${path.module}/helm-values/kubecost-values.yaml", {})]

diff --git a/ai-ml/emr-spark-rapids/eks.tf b/ai-ml/emr-spark-rapids/eks.tf
@@ -141,7 +141,7 @@ module "eks" {
       instance_types       = ["m5.xlarge"] # 4 vCPU and 16GB
 
       ebs_optimized = true
-      # This bloc device is used only for root volume. Adjust volume according to your size.
+      # This block device is used only for root volume. Adjust volume according to your size.
       # NOTE: Dont use this volume for Spark workloads
       block_device_mappings = {
         xvda = {

diff --git a/ai-ml/emr-spark-rapids/helm-values/aws-for-fluentbit-values.yaml b/ai-ml/emr-spark-rapids/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/ai-ml/jark-stack/terraform/eks.tf b/ai-ml/jark-stack/terraform/eks.tf
@@ -84,7 +84,7 @@ module "eks" {
 
   eks_managed_node_groups = {
     #  It's recommended to have a Managed Node group for hosting critical add-ons
-    #  It's recommeded to use Karpenter to place your workloads instead of using Managed Node groups
+    #  It's recommended to use Karpenter to place your workloads instead of using Managed Node groups
     #  You can leverage nodeSelector and Taints/tolerations to distribute workloads across Managed Node group or Karpenter nodes.
     core_node_group = {
       name        = "core-node-group"

diff --git a/ai-ml/jupyterhub/helm/aws-for-fluentbit/values.yaml b/ai-ml/jupyterhub/helm/aws-for-fluentbit/values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/ai-ml/jupyterhub/helm/jupyterhub/jupyterhub-values-cognito.yaml b/ai-ml/jupyterhub/helm/jupyterhub/jupyterhub-values-cognito.yaml
@@ -79,7 +79,7 @@ proxy:
       service.beta.kubernetes.io/aws-load-balancer-ip-address-type: ipv4
 
 singleuser:
-  startTimeout: 1200 # 20 mins to spin up a notebook server for GPU inlcuding the image pull
+  startTimeout: 1200 # 20 mins to spin up a notebook server for GPU including the image pull
   profileList:
     - display_name: Data Engineering (CPU)
       description: "PySpark Notebooks | Karpenter AutoScaling"

diff --git a/ai-ml/jupyterhub/main.tf b/ai-ml/jupyterhub/main.tf
@@ -88,7 +88,7 @@ module "eks" {
 
   eks_managed_node_groups = {
     #  It's recommended to have a Managed Node group for hosting critical add-ons
-    #  It's recommeded to use Karpenter to place your workloads instead of using Managed Node groups
+    #  It's recommended to use Karpenter to place your workloads instead of using Managed Node groups
     #  You can leverage nodeSelector and Taints/tolerations to distribute workloads across Managed Node group or Karpenter nodes.
     core_node_group = {
       name        = "jupyterhub-node-group"

diff --git a/ai-ml/trainium-inferentia/addons.tf b/ai-ml/trainium-inferentia/addons.tf
@@ -155,7 +155,7 @@ module "eks_blueprints_addons" {
   #---------------------------------------
   enable_aws_fsx_csi_driver = true
   aws_fsx_csi_driver = {
-    # INFO: fsx node daemonset wont be placed on Karpenter nodes with taints without the following toleration
+    # INFO: fsx node daemonset won't be placed on Karpenter nodes with taints without the following toleration
     values = [
       <<-EOT
         node:
@@ -440,7 +440,7 @@ resource "aws_launch_template" "trn1_lt" {
     name = module.eks_blueprints_addons.karpenter.node_instance_profile_name
   }
 
-  # Commented for visiblity to implement this feature in the future
+  # Commented for visibility to implement this feature in the future
   #  placement {
   #   tenancy = "default"
   #   availability_zone = "${local.region}d"

diff --git a/ai-ml/trainium-inferentia/eks.tf b/ai-ml/trainium-inferentia/eks.tf
@@ -45,7 +45,7 @@ module "eks" {
 
   # security group rule from all ipv4 to nodes for port 22
   node_security_group_additional_rules = {
-    # Critical Secruity group rule for EFA enabled nodes
+    # Critical Security group rule for EFA enabled nodes
     ingress_efa_self_enabled = {
       description = "EFA-enabled self-referencing security group Ingress"
       protocol    = "-1"
@@ -55,7 +55,7 @@ module "eks" {
       self        = true
     }
 
-    # Critical Secruity group rule for EFA enabled nodes
+    # Critical Security group rule for EFA enabled nodes
     egress_efa_self_enabled = {
       description = "EFA-enabled self-referencing security group Egress"
       protocol    = "-1"
@@ -248,7 +248,7 @@ module "eks" {
         }
       ]
 
-      # Commented to investigate further as the node group creation is failing with palcement group
+      # Commented to investigate further as the node group creation is failing with placement group
       # placement = {
       #   spread_domain = "cluster"
       #   groupName     = "trn1-32xl-ng1"
@@ -458,7 +458,7 @@ module "eks" {
         },
       ]
 
-      # Commented to investigate further as the node group creation is failing with palcement group
+      # Commented to investigate further as the node group creation is failing with placement group
       # placement = {
       #   spread_domain = "cluster"
       #   groupName     = "trn1-32xl-ng1"

diff --git a/ai-ml/trainium-inferentia/examples/ray-serve/llama2-inf2/README.md b/ai-ml/trainium-inferentia/examples/ray-serve/llama2-inf2/README.md
@@ -33,14 +33,14 @@ Now, you can access the Ray Dashboard from the URL Below
 To test the Llama2 model, you can use the following command with a query added at the end of the URL.
 This uses the GET method to get the response:
 
-    http://<NLB_DNS_NAME>/serve/infer?sentence=what is data parallelism and tensor parallelisma and the diffrences
+    http://<NLB_DNS_NAME>/serve/infer?sentence=what is data parallelism and tensor parallelisma and the differences
 
 
 You will see an output like this in your browser:
 
 ```text
 [
-"what is data parallelism and tensor parallelisma and the diffrences between them?
+"what is data parallelism and tensor parallelisma and the differences between them?
 
 Data parallelism and tensor parallelism are both techniques used to speed up machine learning training on large datasets using multiple GPUs or other parallel processing units. However, there are some key differences between them:
 

diff --git a/ai-ml/trainium-inferentia/fsx-for-lustre.tf b/ai-ml/trainium-inferentia/fsx-for-lustre.tf
@@ -61,7 +61,7 @@ YAML
 
 #---------------------------------------------------------------
 # Static PV for FSx for Lustre
-# Don't change the metdata.name `fsx-claim` as this is referenced in lib/trn1_dist_ddp.py script
+# Don't change the metadata.name `fsx-claim` as this is referenced in lib/trn1_dist_ddp.py script
 #---------------------------------------------------------------
 resource "kubectl_manifest" "static_pv" {
   yaml_body = <<YAML

diff --git a/ai-ml/trainium-inferentia/helm-values/aws-for-fluentbit-values.yaml b/ai-ml/trainium-inferentia/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/ai-ml/trainium-inferentia/helm-values/jupyterhub-values.yaml b/ai-ml/trainium-inferentia/helm-values/jupyterhub-values.yaml
@@ -10,7 +10,7 @@ proxy:
   service:
     type: ClusterIP
 singleuser:
-  startTimeout: 1200 # 20 mins to spin up a notebook server for GPU inlcuding the image pull
+  startTimeout: 1200 # 20 mins to spin up a notebook server for GPU including the image pull
   profileList:
     - display_name: Trainium (trn1)
       description: "Trainium | Karpenter AutoScaling"

diff --git a/analytics/cdk/stream-emr-on-eks/README.md b/analytics/cdk/stream-emr-on-eks/README.md
@@ -72,7 +72,7 @@ echo -e "\nIn web browser, paste the URL to launch the template: https://console
 ### CDK Deployment
 
 #### Prerequisites
-Install the folowing tools:
+Install the following tools:
 1. [Python 3.6 +](https://www.python.org/downloads/).
 2. [Node.js 10.3.0 +](https://nodejs.org/en/)
 3. [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/install-macos.html#install-macosos-bundled). Configure the CLI by `aws configure`.
@@ -113,12 +113,12 @@ rm -vf ${HOME}/.aws/credentials
 curl https://raw.githubusercontent.com/aws-samples/stream-emr-on-eks/main/deployment/app_code/post-deployment.sh | bash
 ```
 5. Wait for 5 mins, then check the [MSK cluster](https://console.aws.amazon.com/msk/) status. Make sure it is `active` before sending data to the cluster.
-6. Launching a new termnial window in Cloud9, send the sample data to MSK:
+6. Launching a new terminal window in Cloud9, send the sample data to MSK:
 ```bash
 wget https://github.com/xuite627/workshop_flink1015-1/raw/master/dataset/nycTaxiRides.gz
 zcat nycTaxiRides.gz | split -l 10000 --filter="kafka_2.12-2.8.1/bin/kafka-console-producer.sh --broker-list ${MSK_SERVER} --topic taxirides ; sleep 0.2"  > /dev/null
 ```
-6. Launching the 3rd termnial window and monitor the source MSK topic:
+6. Launching the 3rd terminal window and monitor the source MSK topic:
 ```bash
 kafka_2.12-2.8.1/bin/kafka-console-consumer.sh \
 --bootstrap-server ${MSK_SERVER} \
@@ -172,7 +172,7 @@ aws emr-containers cancel-job-run --virtual-cluster-id $VIRTUAL_CLUSTER_ID  --id
 ### 2. EMR on EKS with Fargate
 Run the [same job](deployment/app_code/job/msk_consumer.py) on the same EKS cluster, but with the serverless option - Fargate compute choice.
 
-To ensure it is picked up by Fargate not by the managed nodegroup on EC2, we will tag the Spark job by a `serverless` label, which has setup in a Fargate profile prevously:
+To ensure it is picked up by Fargate not by the managed nodegroup on EC2, we will tag the Spark job by a `serverless` label, which has setup in a Fargate profile previously:
 ```yaml
 --conf spark.kubernetes.driver.label.type=serverless
 --conf spark.kubernetes.executor.label.type=serverless

diff --git a/analytics/cdk/stream-emr-on-eks/deployment/build-s3-dist.sh b/analytics/cdk/stream-emr-on-eks/deployment/build-s3-dist.sh
@@ -166,7 +166,7 @@ for d in `find . -mindepth 1 -maxdepth 1 -type d`; do
     mv $d $fname
     cd $staging_dist_dir/$fname
 
-    # Build the artifcats
+    # Build the artifacts
     if ls *.py 1> /dev/null 2>&1; then
         echo "===================================="
         echo "This is Python runtime"

diff --git a/analytics/cdk/stream-emr-on-eks/source/lib/cdk_infra/eks_cluster.py b/analytics/cdk/stream-emr-on-eks/source/lib/cdk_infra/eks_cluster.py
@@ -54,7 +54,7 @@ def __init__(self, scope: Construct, id:str,
         )
 
 
-        # 3. Add Spot managed NodeGroup to EKS (Run Spark exectutor on spot)
+        # 3. Add Spot managed NodeGroup to EKS (Run Spark executor on spot)
         self._my_cluster.add_nodegroup_capacity('spot-mn',
             nodegroup_name = 'etl-spot',
             node_role = noderole,

diff --git a/analytics/terraform/datahub-on-eks/helm-values/aws-for-fluentbit-values.yaml b/analytics/terraform/datahub-on-eks/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/analytics/terraform/emr-eks-ack/helm-values/aws-for-fluentbit-values.yaml b/analytics/terraform/emr-eks-ack/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/analytics/terraform/emr-eks-fargate/addons.tf b/analytics/terraform/emr-eks-fargate/addons.tf
@@ -27,13 +27,13 @@ module "eks_blueprints_addons" {
         resources = {
           limits = {
             cpu = "0.25"
-            # We are targetting the smallest Task size of 512Mb, so we subtract 256Mb from the
+            # We are targeting the smallest Task size of 512Mb, so we subtract 256Mb from the
             # request/limit to ensure we can fit within that task
             memory = "256M"
           }
           requests = {
             cpu = "0.25"
-            # We are targetting the smallest Task size of 512Mb, so we subtract 256Mb from the
+            # We are targeting the smallest Task size of 512Mb, so we subtract 256Mb from the
             # request/limit to ensure we can fit within that task
             memory = "256M"
           }

diff --git a/analytics/terraform/emr-eks-karpenter/addons.tf b/analytics/terraform/emr-eks-karpenter/addons.tf
@@ -114,7 +114,7 @@ module "eks_blueprints_addons" {
   #---------------------------------------
   enable_aws_fsx_csi_driver = var.enable_fsx_for_lustre
   aws_fsx_csi_driver = {
-    # INFO: fsx node daemonset wont be placed on Karpenter nodes with taints without the following toleration
+    # INFO: fsx node daemonset won't be placed on Karpenter nodes with taints without the following toleration
     values = [
       <<-EOT
         node:
@@ -201,7 +201,7 @@ module "eks_data_addons" {
   #---------------------------------------------------------------
   # Kubecost Add-on
   #---------------------------------------------------------------
-  # Note: Kubecost add-on depdends on Kube Prometheus Stack add-on for storing the metrics
+  # Note: Kubecost add-on depends on Kube Prometheus Stack add-on for storing the metrics
   enable_kubecost = var.enable_kubecost
   kubecost_helm_config = {
     values              = [templatefile("${path.module}/helm-values/kubecost-values.yaml", {})]

diff --git a/analytics/terraform/emr-eks-karpenter/examples/emr-spark-operator/pyspark-pi.yml b/analytics/terraform/emr-eks-karpenter/examples/emr-spark-operator/pyspark-pi.yml
@@ -49,7 +49,7 @@ spec:
     spark.driver.extraLibraryPath: /usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native:/docker/usr/lib/hadoop/lib/native:/docker/usr/lib/hadoop-lzo/lib/native
     spark.executor.extraClassPath: /usr/lib/hadoop-lzo/lib/*:/usr/lib/hadoop/hadoop-aws.jar:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*:/usr/share/aws/emr/security/conf:/usr/share/aws/emr/security/lib/*:/usr/share/aws/hmclient/lib/aws-glue-datacatalog-spark-client.jar:/usr/share/java/Hive-JSON-Serde/hive-openx-serde.jar:/usr/share/aws/sagemaker-spark-sdk/lib/sagemaker-spark-sdk.jar:/home/hadoop/extrajars/*
     spark.executor.extraLibraryPath: /usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native:/docker/usr/lib/hadoop/lib/native:/docker/usr/lib/hadoop-lzo/lib/native
-    # EMRFS commiter
+    # EMRFS committer
     spark.sql.parquet.output.committer.class: com.amazon.emr.committer.EmrOptimizedSparkSqlParquetOutputCommitter
     spark.sql.parquet.fs.optimized.committer.optimization-enabled: "true"
     spark.sql.emr.internal.extensions: com.amazonaws.emr.spark.EmrSparkSessionExtensions

diff --git a/analytics/terraform/emr-eks-karpenter/helm-values/aws-for-fluentbit-values.yaml b/analytics/terraform/emr-eks-karpenter/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/analytics/terraform/spark-k8s-operator/addons.tf b/analytics/terraform/spark-k8s-operator/addons.tf
@@ -192,7 +192,7 @@ module "eks_data_addons" {
   #---------------------------------------------------------------
   # Spark History Server Add-on
   #---------------------------------------------------------------
-  # Spark hsitory server is required only when EMR Spark Operator is enabled
+  # Spark history server is required only when EMR Spark Operator is enabled
   enable_spark_history_server = true
   spark_history_server_helm_config = {
     values = [

diff --git a/analytics/terraform/spark-k8s-operator/helm-values/aws-for-fluentbit-values.yaml b/analytics/terraform/spark-k8s-operator/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false
 

diff --git a/analytics/terraform/spark-k8s-operator/main.tf b/analytics/terraform/spark-k8s-operator/main.tf
@@ -104,7 +104,7 @@ module "eks" {
     EOT
 
     ebs_optimized = true
-    # This bloc device is used only for root volume. Adjust volume according to your size.
+    # This block device is used only for root volume. Adjust volume according to your size.
     # NOTE: Don't use this volume for Spark workloads
     block_device_mappings = {
       xvda = {

diff --git a/distributed-databases/cloudnative-postgres/examples/cluster-prod.yaml b/distributed-databases/cloudnative-postgres/examples/cluster-prod.yaml
@@ -50,7 +50,7 @@ spec:
         name: app-auth
   backup:
     barmanObjectStore:
-    # For backup, we S3 backet to store data.
+    # For backup, we S3 bucket to store data.
     # On this Blueprint, we create an S3 check the terraform output for it.
       destinationPath: s3://<your-s3-barman-bucket> # ie: s3://xxxx-cnpg-barman-bucket
       s3Credentials:

diff --git a/distributed-databases/cloudnative-postgres/helm-files/values.yaml b/distributed-databases/cloudnative-postgres/helm-files/values.yaml
@@ -63,7 +63,7 @@ config:
   # INHERITED_LABELS: environment, workload, app
   # WATCH_NAMESPACE: namespace-a,namespace-b
 
-# -- Additinal arguments to be added to the operator's args list.
+# -- Additional arguments to be added to the operator's args list.
 additionalArgs: []
 
 serviceAccount:

diff --git a/schedulers/terraform/argo-workflow/README.md b/schedulers/terraform/argo-workflow/README.md
@@ -1,4 +1,4 @@
-# Argo Worklfows on EKS
+# Argo Workflows on EKS
 Checkout the [documentation website](https://awslabs.github.io/data-on-eks/docs/job-schedulers/argo-workflows-eks) to deploy this pattern and run sample tests.
 
 <!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->

diff --git a/schedulers/terraform/argo-workflow/addons.tf b/schedulers/terraform/argo-workflow/addons.tf
@@ -224,7 +224,7 @@ module "eks_data_addons" {
   #---------------------------------------------------------------
   # Spark History Server Add-on
   #---------------------------------------------------------------
-  # Spark hsitory server is required only when EMR Spark Operator is enabled
+  # Spark history server is required only when EMR Spark Operator is enabled
   enable_spark_history_server = true
   spark_history_server_helm_config = {
     values = [

diff --git a/schedulers/terraform/argo-workflow/eks.tf b/schedulers/terraform/argo-workflow/eks.tf
@@ -75,7 +75,7 @@ module "eks" {
     }
 
     ebs_optimized = true
-    # This bloc device is used only for root volume. Adjust volume according to your size.
+    # This block device is used only for root volume. Adjust volume according to your size.
     # NOTE: Don't use this volume for Spark workloads
     block_device_mappings = {
       xvda = {

diff --git a/schedulers/terraform/argo-workflow/helm-values/aws-for-fluentbit-values.yaml b/schedulers/terraform/argo-workflow/helm-values/aws-for-fluentbit-values.yaml
@@ -49,7 +49,7 @@ filter:
     Kube_CA_File        /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
     Kube_Token_File     /var/run/secrets/kubernetes.io/serviceaccount/token
 
-# CATION: Donot use `cloudwatch` plugin. This Golang Plugin is not recommnded by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
+# CATION: Do not use `cloudwatch` plugin. This Golang Plugin is not recommended by AWS anymore instead use C plugin(`cloudWatchLogs`) for better performance.
 # cloudWatch:
 #   enabled: false