feat: Add Markdown parser and CI validation workflow

.github/workflows/generate-schema.yml

@@ -0,0 +1,112 @@
+name: Generate and Validate Schema
+
+on:
+  push:
+    branches: [ main, schema-for-programmatic-consumption ]
+    paths:
+      - 'techniques/**/*.md'
+      - 'mitigations/**/*.md'
+      - 'README.md'
+      - 'scripts/**/*.py'
+      - 'schemas/**/*.json'
+  pull_request:
+    branches: [ main ]
+    paths:
+      - 'techniques/**/*.md'
+      - 'mitigations/**/*.md'
+      - 'README.md'
+      - 'scripts/**/*.py'
+      - 'schemas/**/*.json'
+  workflow_dispatch:
+
+jobs:
+  generate-and-validate:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+        cache: 'pip'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install jsonschema pyyaml
+
+    - name: Parse markdown files to JSON
+      run: |
+        python3 scripts/parse_markdown.py --root-dir . --output data/safe-mcp-index.json
+
+    - name: Validate schema (non-blocking)
+      id: validate
+      continue-on-error: true
+      run: |
+        python3 scripts/validate_schema.py --root-dir . --data-file data/safe-mcp-index.json
+
+    - name: Check if data files changed
+      id: check_changes
+      run: |
+        git diff --quiet data/ || echo "changed=true" >> $GITHUB_OUTPUT
+
+    - name: Upload generated files as artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: generated-schema-files
+        path: |
+          data/safe-mcp-index.json
+        retention-days: 90
+
+    - name: Create Release with Data Files
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      uses: softprops/action-gh-release@v1
+      with:
+        tag_name: latest-data
+        name: Latest Generated Data
+        body: |
+          Auto-generated SAFE-MCP data files from markdown sources.
+
+          **Files:**
+          - `safe-mcp-index.json` - Complete JSON index
+
+          **Generated:** ${{ github.event.head_commit.timestamp }}
+          **Commit:** ${{ github.sha }}
+        files: |
+          data/safe-mcp-index.json
+        prerelease: true
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Create comment on PR with statistics
+      if: github.event_name == 'pull_request'
+      uses: actions/github-script@v7
+      with:
+        script: |
+          const fs = require('fs');
+          const data = JSON.parse(fs.readFileSync('data/safe-mcp-index.json', 'utf8'));
+          const jsonSize = fs.statSync('data/safe-mcp-index.json').size;
+
+          const body = `## Schema Generation Results
+
+          ✅ Successfully generated schema files from markdown sources.
+
+          ### Statistics
+          - **Tactics**: ${data.metadata.total_tactics}
+          - **Techniques**: ${data.metadata.total_techniques}
+          - **Mitigations**: ${data.metadata.total_mitigations}
+
+          ### File Size
+          - **JSON**: ${(jsonSize / 1024).toFixed(1)} KB
+
+          The generated files are available as workflow artifacts.`;
+
+          github.rest.issues.createComment({
+            issue_number: context.issue.number,
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            body: body
+          });

.gitignore

@@ -71,4 +71,23 @@ local_settings.py
 *.pem
 *.p12
 secrets/
-credentials/
+credentials/
+# Python
+__pycache__/
+*.py[cod]
+*.class
+.Python
+*.so
+
+# Virtual environments
+venv/
+ENV/
+env/
+
+# Generated data files (recreated by CI)
+data/*.json
+data/*.toon
+
+# Keep directory structure
+!data/.gitkeep
+