Add heading order check to site lint

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: Jubayeromi

.github/workflows/site_lint.yml

@@ -1,4 +1,4 @@
-name: Site Lint / Heading ID check
+name: Site Lint / Heading checks
 
 on:
   push:
@@ -17,6 +17,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
       - name: Use Node.js 20.x
         uses: actions/setup-node@v4
         with:
@@ -35,3 +37,8 @@ jobs:
 
       - name: Lint codebase
         run: yarn ci-check
+
+      - name: Check heading order
+        env:
+          HEADING_ORDER_BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.before }}
+        run: yarn lint-heading-order "$HEADING_ORDER_BASE_SHA"

package.json

@@ -15,6 +15,7 @@
     "prettier": "yarn format:source",
     "prettier:diff": "yarn nit:source",
     "lint-heading-ids": "node scripts/headingIdLinter.js",
+    "lint-heading-order": "node scripts/headingOrderLinter.js",
     "fix-headings": "node scripts/headingIdLinter.js --fix",
     "ci-check": "npm-run-all prettier:diff --parallel lint test:eslint-local-rules tsc lint-heading-ids rss deadlinks",
     "tsc": "tsc --noEmit",

scripts/headingOrderLinter.js

@@ -0,0 +1,157 @@
+/**
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ *
+ * This source code is licensed under the MIT license found in the
+ * LICENSE file in the root directory of this source tree.
+ */
+
+const fs = require('fs');
+const path = require('path');
+const {execFileSync} = require('child_process');
+
+const contentDirectory = 'src/content';
+const baseSha = process.argv[2];
+
+if (!baseSha) {
+  console.error(
+    'Pass the base commit SHA to compare heading-order violations.'
+  );
+  process.exit(1);
+}
+
+function walk(directory) {
+  return fs.readdirSync(directory, {withFileTypes: true}).flatMap((entry) => {
+    const entryPath = path.join(directory, entry.name);
+    if (entry.isDirectory()) {
+      return walk(entryPath);
+    }
+    return entry.name.endsWith('.md') || entry.name.endsWith('.mdx')
+      ? [entryPath]
+      : [];
+  });
+}
+
+function findHeadingOrderViolations(content, file) {
+  const violations = [];
+  const lines = content.split(/\r?\n/);
+  let previousLevel = 1;
+  let codeFence = null;
+
+  lines.forEach((line, index) => {
+    const fence = /^\s{0,3}(`{3,}|~{3,})/.exec(line);
+    if (fence) {
+      const marker = fence[1][0];
+      if (!codeFence) {
+        codeFence = {marker, length: fence[1].length};
+      } else if (
+        marker === codeFence.marker &&
+        fence[1].length >= codeFence.length
+      ) {
+        codeFence = null;
+      }
+      return;
+    }
+    if (codeFence) {
+      return;
+    }
+
+    const heading = /^(#{1,6})[ \t]+(.+?)\s*$/.exec(line);
+    if (!heading) {
+      return;
+    }
+
+    const level = heading[1].length;
+    if (level > previousLevel + 1) {
+      const text = heading[2].replace(/\s+\{\/\*.*?\*\/}\s*$/, '').trim();
+      violations.push({
+        file,
+        line: index + 1,
+        previousLevel,
+        level,
+        text,
+      });
+    }
+    previousLevel = level;
+  });
+
+  return violations;
+}
+
+function violationKey(violation) {
+  return JSON.stringify([
+    violation.file,
+    violation.previousLevel,
+    violation.level,
+    violation.text,
+  ]);
+}
+
+function readBaseContent(revision, file) {
+  try {
+    return execFileSync('git', ['show', `${revision}:${file}`], {
+      encoding: 'utf8',
+      stdio: ['ignore', 'pipe', 'ignore'],
+    });
+  } catch (error) {
+    if (error.status === 128) {
+      return null;
+    }
+    throw error;
+  }
+}
+
+try {
+  execFileSync('git', ['rev-parse', '--verify', `${baseSha}^{commit}`], {
+    stdio: 'ignore',
+  });
+
+  const currentViolations = walk(contentDirectory).flatMap((filePath) => {
+    const file = path
+      .relative(process.cwd(), filePath)
+      .split(path.sep)
+      .join('/');
+    return findHeadingOrderViolations(fs.readFileSync(filePath, 'utf8'), file);
+  });
+  const filesWithViolations = [
+    ...new Set(currentViolations.map((violation) => violation.file)),
+  ];
+  const baselineCounts = new Map();
+
+  filesWithViolations.forEach((file) => {
+    const content = readBaseContent(baseSha, file);
+    const violations = content ? findHeadingOrderViolations(content, file) : [];
+    violations.forEach((violation) => {
+      const key = violationKey(violation);
+      baselineCounts.set(key, (baselineCounts.get(key) || 0) + 1);
+    });
+  });
+
+  const newViolations = [];
+  currentViolations.forEach((violation) => {
+    const key = violationKey(violation);
+    const count = baselineCounts.get(key) || 0;
+    if (count > 0) {
+      baselineCounts.set(key, count - 1);
+    } else {
+      newViolations.push(violation);
+    }
+  });
+
+  if (newViolations.length > 0) {
+    console.error('New heading-order skips found:');
+    newViolations.forEach(({file, line, previousLevel, level, text}) => {
+      console.error(
+        `  ${file}:${line}: h${previousLevel} to h${level}: ${text}`
+      );
+    });
+    process.exitCode = 1;
+  } else {
+    console.log('No new heading-order skips found.');
+  }
+} catch (error) {
+  console.error(
+    'Unable to check heading order against the base commit:',
+    error.message
+  );
+  process.exitCode = 1;
+}