new blog linting rules

.github/workflows/pull-request.yml

@@ -19,12 +19,35 @@ jobs:
     environment: testing
     steps:
 
-      - uses: actions/checkout@v2
-
+      - uses: actions/checkout@v4
+        with:
+          # Only fetch PR branch
+          fetch-depth: 1
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Fetch base branch
+        run: |
+          # Fetch and create local master branch
+          git -c protocol.version=2 fetch --no-tags --prune --progress --no-recurse-submodules --depth=1 origin master:master
+          # Verify branches
+          echo "Local branches:"
+          git branch -v
+          echo "\nRemote branches:"
+          git branch -r
+
+      - name: Set base branch env
+        run: |
+          if [ "${{ github.event_name }}" = "pull_request" ]; then
+            echo "BASE_BRANCH=${{ github.event.pull_request.base.ref }}" >> $GITHUB_ENV
+          else
+            # This covers push scenario to master
+            # or any other scenario with no PR info
+            echo "BASE_BRANCH=" >> $GITHUB_ENV
+          fi
+          echo "Branch:${{ github.event.pull_request.base.ref }}"
       - uses: actions/setup-node@v1
         with:
           node-version: '18.x'
-
       - uses: peaceiris/actions-hugo@v2
         with:
           hugo-version: '0.135.0'
@@ -55,6 +78,7 @@ jobs:
           ALGOLIA_APP_SEARCH_KEY: ${{ vars.ALGOLIA_APP_SEARCH_KEY }}
           ALGOLIA_APP_ADMIN_KEY: ${{  secrets.ALGOLIA_APP_ADMIN_KEY }}
           NODE_OPTIONS: "--max_old_space_size=8192"
+          BASE_BRANCH: ${{ env.BASE_BRANCH }}
 
       - name: Archive test results
         uses: actions/upload-artifact@v4

Makefile

@@ -141,12 +141,11 @@ new-example-program:
 
 .PHONY: new-blog-post
 new-blog-post:
-	hugo new --kind blog-post --contentDir content \
-	"blog/$(shell bash -c 'read -p "Slug (e.g., 'my-new-post'): " slug; echo $$slug')"
+	./scripts/new-blog-post.sh
 
 .PHONY: lint
 lint:
-	./scripts/lint.sh
+	./scripts/lint/lint.sh
 
 .PHONY: format
 format:

archetypes/blog-post/index.md

@@ -7,7 +7,7 @@ title: "{{ replace .Name "-" " " | title }}"
 # published. To influence the ordering of posts published on the same date, use
 # the time portion of the date value; posts are sorted in descending order by
 # date/time.
-date: {{ .Date }}
+date: {{ now.Format "2006-01-02" }}
 
 # The draft setting determines whether a post is published. Set it to true if
 # you want to be able to merge the post without publishing it.

content/blog/sam-cogan-testing-best-practices/index.md

@@ -18,7 +18,7 @@ draft: true
 # of the content of the post, which is useful for targeting search results or
 # social-media previews. This field is required or the build will fail the
 # linter test. Max length is 160 characters.
-meta_desc:
+meta_desc: Infrastructure Testing Best Practices of Sam Cogan, Puluminary & Azure MVP
 
 # The meta_image appears in social-media previews and on the blog home page. A
 # placeholder image representing the recommended format, dimensions and aspect

content/events/build-dagger-module-pulumi-chainguard/index.md

@@ -1,7 +1,7 @@
 ---
 # Name of the event, <= 60 characters
 title: "Codefest: Build a Dagger Module with Pulumi & Chainguard"
-meta_desc: Join Pulumi, Dagger, and Chainguard for an evening of networking, coding, and talks. Learn basics with Dagger's tutorial, then showcase your module with lightning demos.
+meta_desc: Join Pulumi, Dagger, and Chainguard for an evening of networking, coding, and talks.
 meta_image:
 
 # A featured webinar will display first in the list.

content/events/connecting-securing-and-scaling-microservices-with-kubernetes/index.md

@@ -1,6 +1,7 @@
 ---
 # Name of the event, <= 60 characters
 title: Connecting, Securing and Scaling Microservices with Kubernetes
+allow_long_title: true
 meta_desc: Listen in and you will learn practical insights on how organizations can ease growing pains and successfully take Kubernetes from test to production.
 meta_image:
 

content/events/kubecon-meetup/index.md

@@ -1,6 +1,7 @@
 ---
 # Name of the event, <= 60 characters
 title: "RSVP to Meetup: Development & Data Productivity in the Age of AI"
+allow_long_title: true
 meta_desc: Join Docker, Pulumi, Tailscale, and New Relic for drinks, snacks, and casual conversations.
 meta_image:
 

package.json

@@ -5,7 +5,8 @@
   "license": "Apache-2.0",
   "scripts": {
     "minify-css": "node scripts/minify-css.js",
-    "prepare": "husky"
+    "prepare": "husky",
+    "ts-node": "ts-node"
   },
   "dependencies": {
     "@aws-sdk/client-s3": "^3.427.0",
@@ -36,10 +37,19 @@
     "turndown": "^7.2.0",
     "typedoc": "^0.25.11",
     "typedoc-plugin-script-inject": "^1.0.0",
-    "typescript": "^4.9.5"
+    "typescript": "^4.9.5",
+    "zod": "^3.24.1",
+    "zod-matter": "^0.1.1"
+  },
+  "resolutions": {
+    "@types/ms": "0.7.32"
   },
   "devDependencies": {
+    "@types/js-yaml": "^4.0.9",
+    "@types/markdownlint": "^0.18.0",
+    "@types/node": "^22.13.1",
     "husky": "^9.0.11",
-    "prettier": "^2.6.2"
+    "prettier": "^2.6.2",
+    "ts-node": "^10.9.2"
   }
 }

scripts/lint/find-markdown.ts

@@ -0,0 +1,212 @@
+import * as fs from 'fs';
+import * as path from 'path';
+import { execSync } from 'child_process';
+import { z } from 'zod';
+import { parse as parseMatter } from 'zod-matter';
+
+const frontMatterSchema = z.object({}).catchall(z.any());
+
+type FrontMatter = z.infer<typeof frontMatterSchema>;
+
+export interface MarkdownFile {
+    path: string;
+    isNew: boolean;
+    content: string;
+    // frontMatter can be anything that we parse out
+    frontMatter?: FrontMatter;
+  }
+
+/**
+ * Different modes for finding markdown files and determining if they're new
+ */
+export type FinderMode = 'git' | 'gha';
+
+const AUTO_GENERATED_HEADING_REGEX = /^> This page was automatically generated\./m;
+
+/**
+ * Parse front matter from a markdown file
+ */
+function parseFrontMatter(filePath: string): FrontMatter | undefined {
+    try {
+        const content = fs.readFileSync(filePath, 'utf8');
+
+        // Check for auto-generated heading in content
+        if (content.match(AUTO_GENERATED_HEADING_REGEX)) {
+            return { no_edit_this_page: true };
+        }
+
+        // Parse front matter with zod-matter
+        const { data } = parseMatter(content, frontMatterSchema);
+        return data;
+    } catch (e) {
+        // If there's no front matter or it's invalid, return null
+        return undefined;
+    }
+}
+
+/**
+ * Check if a file should be excluded based on its front matter
+ */
+function shouldExcludeByFrontMatter(frontMatter: FrontMatter | undefined): boolean {
+    if (!frontMatter) return false;
+
+    return frontMatter.no_edit_this_page === true ||
+           typeof frontMatter.redirect_to === 'string' ||
+           frontMatter.block_external_search_index === true ||
+           !!frontMatter.allow_long_title;
+}
+
+import { debug } from './utils';
+
+/**
+ * Get list of files that are newly added in the current branch compared to base branch,
+ * including staged and unstaged changes. Handles both local git and GitHub Actions environments.
+ */
+function getGitModifiedFiles(baseBranch?: string): Set<string> {
+    try {
+        debug('Getting git modified files...');
+        const newFiles = new Set<string>();
+
+        // In GitHub Actions, use FETCH_HEAD since we just fetched the base branch
+        const isGHA = process.env.GITHUB_ACTIONS === 'true';
+        const baseRef = isGHA ? 'FETCH_HEAD' : (baseBranch || process.env.BASE_BRANCH || 'master');
+        debug('Using base ref:', baseRef);
+
+        try {
+            // In GHA, we've just fetched the base branch to FETCH_HEAD, so this is safe
+            const diffOutput = execSync(`git diff --name-status ${baseRef} HEAD`, { encoding: 'utf8' });
+            debug('Got diff output');
+            diffOutput.split('\n')
+                .filter(line => line.startsWith('A\t'))
+                .map(line => line.split('\t')[1])
+                .forEach(file => newFiles.add(file));
+        } catch (error) {
+            debug('Diff failed:', error);
+            if (isGHA) {
+                // In GHA, if diff fails, something is wrong with our setup
+                throw error;
+            }
+            // In local dev, try to get staged/untracked files
+            debug('Falling back to staged/untracked files only');
+        }
+
+        // In local dev, also look for staged and untracked files
+        if (!isGHA) {
+            try {
+                // Get new files from staged changes
+                const stagedFiles = execSync('git diff --name-status --cached', { encoding: 'utf8' });
+                stagedFiles.split('\n')
+                    .filter(line => line.startsWith('A\t'))
+                    .map(line => line.split('\t')[1])
+                    .forEach(file => newFiles.add(file));
+
+                // Get untracked files
+                debug('Getting untracked files...');
+                const untrackedFiles = execSync('git ls-files --others --exclude-standard --full-name', { encoding: 'utf8' });
+                debug('Raw untracked files output:', untrackedFiles);
+                untrackedFiles.split('\n').filter(Boolean).forEach(file => newFiles.add(file));
+
+                // Also get untracked markdown files specifically
+                const untrackedMarkdown = execSync('git ls-files --others --exclude-standard --full-name "*.md"', { encoding: 'utf8' });
+                debug('Raw untracked markdown files:', untrackedMarkdown);
+                untrackedMarkdown.split('\n').filter(Boolean).forEach(file => newFiles.add(file));
+            } catch (error) {
+                debug('Failed to get staged/untracked files:', error);
+            }
+        }
+
+        debug('Found new files:', newFiles);
+        return newFiles;
+    } catch (error) {
+        console.warn('Failed to get git modified files:', error);
+        if (process.env.GITHUB_ACTIONS === 'true') {
+            console.warn('Running in GitHub Actions - treating all files as existing');
+        } else {
+            console.warn('Running locally - treating all files as existing');
+        }
+        return new Set<string>();
+    }
+}
+
+
+
+/**
+ * Find all markdown files in the given directory and its subdirectoriesA
+ * Optionally marks files as new based on git/GHA context.
+ */
+export function findMarkdownFiles(
+    rootDir: string,
+    mode: FinderMode = 'git',
+    excludePaths: string[] = ['/content/docs/reference/pkg', '/content/registry', '/node_modules']
+): MarkdownFile[] {
+    const files: MarkdownFile[] = [];
+
+    // Determine which files are considered new based on mode
+    let modifiedFiles = new Set<string>();
+    if (mode === 'git') {
+        modifiedFiles = getGitModifiedFiles();
+    } else if (mode === 'gha') {
+        const baseBranch = process.env.BASE_BRANCH;
+        debug('GHA mode using base branch:', baseBranch);
+        modifiedFiles = getGitModifiedFiles(baseBranch);
+    }
+
+    function isExcluded(filePath: string): boolean {
+        return excludePaths.some(excludePath => filePath.includes(excludePath));
+    }
+
+    function searchDirectory(dir: string) {
+        const entries = fs.readdirSync(dir);
+
+        for (const entry of entries) {
+            const fullPath = path.join(dir, entry);
+            const stat = fs.statSync(fullPath);
+
+            if (isExcluded(fullPath)) {
+                continue;
+            }
+
+            if (stat.isDirectory()) {
+                searchDirectory(fullPath);
+                continue;
+            }
+
+            if (path.extname(fullPath) === '.md') {
+                const content = fs.readFileSync(fullPath, 'utf8');
+                const frontMatter = parseFrontMatter(fullPath);
+                if (!shouldExcludeByFrontMatter(frontMatter)) {
+                    // Convert absolute path to relative for comparing with git modified files
+                    const relPath = path.relative(process.cwd(), fullPath);
+                    files.push({
+                        path: fullPath,
+                        isNew: modifiedFiles.has(relPath),
+                        content,
+                        frontMatter
+                    });
+                }
+            }
+        }
+    }
+
+    searchDirectory(path.resolve(rootDir));
+    return files;
+}
+
+// If run directly, output found files
+if (require.main === module) {
+    const mode = (process.argv[2] as FinderMode) || 'gha';
+    const showAll = process.argv.includes('--show-all');
+    debug('Running in mode:', mode, 'show all:', showAll);
+
+    // Find all markdown files
+    const files = findMarkdownFiles('.', mode);
+
+    if (showAll) {
+        console.log('All markdown files (new files marked with *):')
+        console.log(JSON.stringify(files.map(f => `${f.isNew ? '*' : ' '} ${f.path}`), null, 2));
+    } else {
+        const newFiles = files.filter(f => f.isNew).map(f => f.path);
+        console.log('New markdown files detected:');
+        console.log(JSON.stringify(newFiles, null, 2));
+    }
+}