[Improvement] Spell check only PR-changed files and added manual dispatch for full check (#693)

* spell check only PR changed files

* Update .github/workflows/spell-check.yaml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update scripts/spell_check/check_spelling.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix:reqs

---------

Co-authored-by: Lukas Wallrich <lukas.wallrich@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Author: 3 people

.github/workflows/spell-check.yaml

@@ -4,12 +4,19 @@ name: Spell Check
 # Automated Spell Checking
 # =======================
 # Purpose: Checks for spelling errors in pull requests using codespell
-# Triggers: PR opened, synchronized, or reopened
+# Triggers: PR opened, synchronized, or reopened; manual dispatch for full check
 # Reports: Comments on PR with potential typos and suggestions
 
 on:
   pull_request:
     types: [opened, synchronize, reopened]
+  workflow_dispatch:
+    inputs:
+      check_all:
+        description: 'Check all website content (not just changed files)'
+        required: false
+        default: true
+        type: boolean
 
 permissions:
   contents: read
@@ -23,6 +30,18 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Get changed files (PR only)
+        id: changed_files
+        if: github.event_name == 'pull_request'
+        run: |
+          # Get list of changed files in the PR
+          CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.sha }} | grep -E '\.(md|txt|html|yaml|yml|py|js|json|toml)$' || true)
+          echo "files<<EOF" >> $GITHUB_OUTPUT
+          echo "$CHANGED_FILES" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
 
       - name: Set up Python
         uses: actions/setup-python@v5
@@ -36,18 +55,23 @@ jobs:
 
       - name: Run Spell Check Script
         id: spell_check
+        env:
+          CHECK_ALL: ${{ github.event_name == 'workflow_dispatch' && inputs.check_all == true }}
+          CHANGED_FILES: ${{ steps.changed_files.outputs.files }}
         run: |
           python scripts/spell_check/check_spelling.py
 
       - name: Find Comment
+        if: github.event_name == 'pull_request'
         uses: peter-evans/find-comment@v3
         id: fc
         with:
           issue-number: ${{ github.event.pull_request.number }}
           comment-author: 'github-actions[bot]'
-          body-includes: Spell Check Results
+          body-includes: Spell Check
 
       - name: Create or update comment
+        if: github.event_name == 'pull_request'
         uses: peter-evans/create-or-update-comment@v4
         with:
           comment-id: ${{ steps.fc.outputs.comment-id }}

scripts/spell_check/check_spelling.py

@@ -2,6 +2,10 @@
 """
 Spell-check script for FORRT repository using codespell.
 Checks for typos in pull requests and generates a formatted comment.
+
+Modes:
+- PR mode: Only checks files changed in the pull request (CHANGED_FILES env var)
+- Full mode: Checks the default set of paths (content, scripts, .github, CONTRIBUTING.md, README.md) (CHECK_ALL=true env var)
 """
 
 import os
@@ -10,12 +14,61 @@
 import json
 from pathlib import Path
 
-def run_codespell():
+# Default paths to check in full mode
+DEFAULT_PATHS = ['content', 'scripts', 'data', '.github', 'CONTRIBUTING.md', 'README.md']
+
+# File extensions to check
+ALLOWED_EXTENSIONS = {'.md', '.txt', '.html', '.yaml', '.yml', '.py', '.js', '.json', '.toml'}
+
+
+def get_files_to_check():
+    """Determine which files to check based on environment variables.
+
+    Returns a tuple of (paths, is_full_mode).
+    """
+    check_all = os.environ.get('CHECK_ALL', 'false').lower() == 'true'
+    changed_files_env = os.environ.get('CHANGED_FILES')
+
+    # If CHECK_ALL is explicitly requested, always run in full mode.
+    if check_all:
+        print("Running in full mode: checking default paths...", file=sys.stderr)
+        return DEFAULT_PATHS, True
+
+    # If CHANGED_FILES is not provided at all, fall back to full mode
+    # (e.g., local runs or legacy workflows).
+    if changed_files_env is None:
+        print("Running in full mode: checking default paths (no CHANGED_FILES provided)...", file=sys.stderr)
+        return DEFAULT_PATHS, True
+
+    # CHANGED_FILES is provided but may be empty (no matching files).
+    changed_files = changed_files_env.strip()
+    if not changed_files:
+        print("No spell-checkable files changed in this PR.", file=sys.stderr)
+        return [], False
+
+    # PR mode: only check changed files
+    files = [f.strip() for f in changed_files.split('\n') if f.strip()]
+
+    # Filter to only existing files with allowed extensions
+    valid_files = []
+    for f in files:
+        path = Path(f)
+        if path.exists() and path.suffix.lower() in ALLOWED_EXTENSIONS:
+            valid_files.append(f)
+
+    if not valid_files:
+        print("No spell-checkable files changed in this PR.", file=sys.stderr)
+        return [], False
+    print(f"Running in PR mode: checking {len(valid_files)} changed file(s)...", file=sys.stderr)
+    return valid_files, False
+
+
+def run_codespell(paths):
     """Run codespell and capture output."""
+    if not paths:
+        return "", 0
+    
     try:
-        # Run codespell on specific directories to avoid themes and other large dirs
-        # Focus on content, scripts, and GitHub workflows
-        paths = ['content', 'scripts', '.github', 'CONTRIBUTING.md', 'README.md']
 
         # Use repo root - GitHub Actions path or repo root directory
         repo_root = os.environ.get('GITHUB_WORKSPACE')
@@ -69,15 +122,20 @@ def parse_codespell_output(output):
 
     return typos
 
-def format_comment(typos):
+def format_comment(typos, is_full_mode=False, files_checked=None):
     """Format typos as a GitHub comment."""
+    mode_info = "all content" if is_full_mode else f"{files_checked} changed file(s)"
+    
     if not typos:
         comment = "## ✅ Spell Check Passed\n\n"
-        comment += "No spelling issues found in this PR! 🎉"
+        if files_checked == 0:
+            comment += "No spell-checkable files were changed in this PR."
+        else:
+            comment += f"No spelling issues found when checking {mode_info}! 🎉"
         return comment
 
     comment = "## 📝 Spell Check Results\n\n"
-    comment += f"Found {len(typos)} potential spelling issue(s) in this PR:\n\n"
+    comment += f"Found {len(typos)} potential spelling issue(s) when checking {mode_info}:\n\n"
 
     # Group typos by file
     typos_by_file = {}
@@ -111,14 +169,17 @@ def main():
     """Main function to run spell check and output comment."""
     print("Running spell check...", file=sys.stderr)
 
+    # Determine which files to check
+    paths, is_full_mode = get_files_to_check()
+    
     # Run codespell
-    output, returncode = run_codespell()
+    output, returncode = run_codespell(paths)
 
     # Parse output
     typos = parse_codespell_output(output)
 
     # Format comment
-    comment = format_comment(typos)
+    comment = format_comment(typos, is_full_mode, len(paths) if not is_full_mode else None)
 
     # Output comment for GitHub Actions
     # Escape special characters for GitHub Actions output