add vale linting to docs as ci check (#5623)

.github/workflows/vale.yml

@@ -0,0 +1,80 @@
+name: Vale linting
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths:
+      - 'website/docs/**/*'
+      - 'website/blog/**/*'
+      - 'website/**/*'
+
+jobs:
+  vale:
+    name: Vale linting
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 1
+
+      - name: List repository contents
+        run: |
+          pwd
+          ls -R
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.x'
+
+      - name: Install Vale
+        run: pip install vale==2.27.0  # Install a stable version of Vale
+
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v34
+        with:
+          files: |
+            website/**/*.md
+          separator: ' '
+
+      - name: Debugging - Print changed files
+        if: ${{ steps.changed-files.outputs.any_changed == 'true' }}
+        run: |
+          echo "Changed files:"
+          echo "${{ steps.changed-files.outputs.all_changed_and_modified_files }}"
+
+      - name: Confirm files exist
+        if: ${{ steps.changed-files.outputs.any_changed == 'true' }}
+        run: |
+          echo "Checking if files exist..."
+          for file in ${{ steps.changed-files.outputs.all_changed_and_modified_files }}; do
+            if [ -f "$file" ]; then
+              echo "Found: $file"
+            else
+              echo "File not found: $file"
+              exit 1
+            fi
+          done
+
+      - name: Run vale
+        if: ${{ steps.changed-files.outputs.any_changed == 'true' }}
+        uses: errata-ai/vale-action@reviewdog
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          reporter: github-check
+          files: ${{ steps.changed-files.outputs.all_changed_and_modified_files }}
+          separator: ' '
+          version: '2.27.0'
+
+      - name: Post summary comment
+        if: ${{ steps.changed-files.outputs.any_changed == 'true' }}
+        run: |
+          COMMENT="❗️Oh no, some Vale linting found issues! Please check the **Files change** tab for detailed results and make the necessary updates."
+          COMMENT+=$'\n'
+          COMMENT+=$'\n\n'
+          COMMENT+="➡️ Link to detailed report: [Files changed](${{ github.event.pull_request.html_url }}/files)"
+          gh pr comment ${{ github.event.pull_request.number }} --body "$COMMENT"
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.hyperlint/config.yaml

@@ -0,0 +1,10 @@
+content_dir: /docs
+authorized_users:
+  - mirnawong1
+  - matthewshaver
+  - nghi-ly
+  - runleonarun
+  - nataliefiann
+
+vale:
+  enabled: true

.vale.ini

@@ -0,0 +1,7 @@
+StylesPath = styles
+MinAlertLevel = warning
+
+Vocab = EN
+
+[*.md]
+BasedOnStyles = custom

styles/Vocab/EN/accept.txt

@@ -0,0 +1,67 @@
+dbt Cloud
+dbt Core
+dbt Semantic Layer
+dbt Explorer
+dbt
+dbt-tonic
+dbtonic
+IDE
+CLI
+Config  
+info
+docs
+yaml
+YAML
+SQL
+bash
+shell
+MetricFlow
+jinja
+jinja2
+sqlmesh
+Snowflake
+Databricks
+Fabric
+Redshift
+Azure
+DevOps
+Athena
+Amazon
+UI
+CSV
+S3
+SCD
+repo
+dbt_project.yml
+boolean
+defaultValue=
+DWH
+DWUs
+shoutout
+ADF
+BQ
+gcloud
+MSFT
+DDL
+APIs
+API
+SSIS
+PBI
+PowerBI
+datetime
+PySpark
+:::caution
+:::note
+:::info
+:::tip
+:::warning
+\<[^>]+\>        
+\b[A-Z]{2,}(?:/[A-Z]{2,})?\b
+\w+-\w+          
+\w+/\w+          
+n/a
+N/A
+\<Tabs
+pseudocolumn
+yml
+values=

styles/Vocab/EN/reject.txt

@@ -0,0 +1,9 @@
+DBT Cloud
+DBT Core
+DBT Semantic Layer
+DBT Explorer
+DBT
+DBT-tonic
+DBTonic
+DBT Mesh
+\b\w+\s{2,}\w+\b <!-- catches extra spaces -->

styles/custom/LatinAbbreviations.yml

@@ -0,0 +1,21 @@
+extends: substitution
+message: "Avoid latin abbreviations: '%s'. Consider using '%s' instead."
+level: warning
+ignorecase: false
+
+swap:
+  - e.g.: for example
+  - eg: for example
+  - e.g: for example
+  - i.e.: for example
+  - i.e.: that is
+  - etc.: and so on
+  - N.B.: Note
+
+action:
+  name: replace
+  params:
+    - for example
+    - that is
+    - and so on
+    - Note

styles/custom/Metrics.yml

@@ -0,0 +1,8 @@
+extends: metric
+message: "Try to keep the Flesch-Kincaid grade level (%s) below 8."
+link: https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readability_tests
+
+formula: |
+    (0.39 * (words / sentences)) + (11.8 * (syllables / words)) - 15.59
+
+condition: "> 8.0"

styles/custom/Repitition.yml

@@ -0,0 +1,6 @@
+extends: repetition
+message: "'%s' is repeated!"
+level: warning
+alpha: true
+tokens:
+  - '[^\s]+'

styles/custom/SentenceCaseHeaders.yml

@@ -0,0 +1,34 @@
+extends: capitalization
+message: "'%s' should use sentence-style capitalization. Try '%s' instead."
+level: warning
+scope: heading
+match: $sentence  # Enforces sentence-style capitalization
+indicators:
+  - ":"
+exceptions:
+  - '\bdbt\b'
+  - '\bdbt\s+Cloud\b'
+  - '\bdbt\s+Core\b'
+  - '\bdbt\s+Cloud\s+CLI\b'
+  - Snowflake
+  - Databricks
+  - Azure
+  - GCP
+  - AWS
+  - SQL
+  - CLI
+  - API
+  - YAML
+  - JSON
+  - HTML
+  - Redshift
+  - Google
+  - BigQuery
+  - SnowSQL
+  - Snowsight
+  - Snowpark
+  - Fabric
+  - Microsoft
+  - Postgres
+  - Explorer
+  - IDE

styles/custom/Typos.yml

@@ -0,0 +1,39 @@
+extends: spelling
+
+message: "Oops there's a typo -- did you really mean '%s'? "
+level: warning
+
+action:
+  name: suggest
+  params:
+    - spellings
+
+custom: true
+filters:
+  - '\bdbt\b'
+  - '\bdbt\s+Cloud\b'
+  - '\bdbt\s+Core\b'
+  - '\bdbt\s+Cloud\s+CLI\b'
+  - '\bdbt\s+.*?\b'
+  - '<[^>]+>' # Ignore all HTML-like components starting with < and ending with >
+  - '<[^>]+>.*<\/[^>]+>'
+
+---
+
+extends: existence
+
+message: "Ignore specific patterns"
+level: skip
+tokens:
+  - '\bdbt\b'
+  - '\bdbt\s+Cloud\b'
+  - '\bdbt\s+Core\b'
+  - '\bdbt\s+Cloud\s+CLI\b'
+  - '\bdbt\s+.*?\b'
+  - '<[^>]+>' # Ignore all HTML-like components starting with < and ending with >
+  - '<[^>]+>.*<\/[^>]+>'
+  - '\w+-\w+'
+  - '\w+/\w+'
+  - '\w+/\w+|\w+-\w+|n/a'
+  - 'n/a' 
+  - 'N/A'

styles/custom/UIElements.yml

@@ -0,0 +1,17 @@
+# styles/custom/BoldUIElements.yml
+extends: existence
+message: "UI elements like '%s' should be bold."
+level: warning
+tokens:
+  # Match UI elements that are not bolded (i.e., not within **), but exclude those starting a sentence or following a list number
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bSave\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bSave as\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bCancel\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bSubmit\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bEdit\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bAccount settings\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bProject details\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bProfile settings\b'
+  - '(?<!^)(?<![.!?]\s)(?<!\d\.\s)\bPersonal profile\b'
+
+scope: raw  # Ensure the rule is applied before formatting