Merge pull request #163 from fulldecent/copilot/fix-8abff14e-dfd9-486d-8463-8ab72a612a9b

Replace dirty words checker with allowed-links rule

Author: fulldecent

.github/workflows/build-test-deploy.yml

@@ -48,6 +48,10 @@ jobs:
         run: yarn install --immutable
 
       - name: Generate sitemap
+        env:
+          # For repository named username.github.io, use https://username.github.io
+          # For other repositories, use https://username.github.io/repository-name
+          SITE_URL: ${{ github.event.repository.name == format('{0}.github.io', github.repository_owner) && format('https://{0}.github.io', github.repository_owner) || format('https://{0}.github.io/{1}', github.repository_owner, github.event.repository.name) }}
         run: yarn run generate-sitemap
       - name: Upload build artifact, ready for GitHub Pages deployment
         uses: actions/upload-pages-artifact@v3

.htmlvalidate.mjs

@@ -4,6 +4,20 @@ export default defineConfig({
   plugins: ["<rootDir>/test/plugin.html-validate.mjs"],
   extends: ["html-validate:prettier", "<rootDir>/test/plugin.html-validate.mjs:recommended"],
   rules: {
+    "allowed-links": [
+      "error",
+      {
+        allowExternal: {
+          exclude: ["\\\\?utm_source=chatgpt.com", ".htm[l]?$"],
+        },
+        allowRelative: {
+          exclude: [".htm[l]?$"],
+        },
+        allowAbsolute: {
+          exclude: [".htm[l]?$"],
+        },
+      },
+    ],
     "pacific-medical-training/mailto-awesome": "error",
     "pacific-medical-training/external-links": "error",
     "pacific-medical-training/no-jquery": "error",

package.json

@@ -14,7 +14,7 @@
     "structured-data-testing-tool": "^4.5.0"
   },
   "scripts": {
-    "test": "yarn node test/fixtures-html-validate-should-fail.mjs && yarn node test/fixtures-structured-data-should-fail.mjs && yarn node test/build-html-validate.mjs && yarn node test/dirty-words-checker.mjs && yarn node test/dirty-file-paths-checker.mjs && yarn node test/build-structured-data-validate.mjs",
+    "test": "yarn node test/fixtures-html-validate-should-fail.mjs && yarn node test/fixtures-structured-data-should-fail.mjs && yarn node test/build-html-validate.mjs && yarn node test/dirty-file-paths-checker.mjs && yarn node test/build-structured-data-validate.mjs",
     "test-structured-data": "yarn node test/build-structured-data-validate.mjs",
     "lint": "yarn prettier-check && yarn markdownlint-check",
     "lint-fix": "yarn prettier-fix && yarn markdownlint-fix",

scripts/generate-sitemap.mjs

@@ -3,7 +3,9 @@ import path from "path";
 import https from "https";
 import { parseString } from "xml2js"; // Using xml2js for XML parsing
 
-const site = "https://www.acls.net";
+// Site URL configuration - can be overridden via SITE_URL environment variable
+// For GitHub Pages, this should typically be https://username.github.io/repository-name
+const site = process.env.SITE_URL || "https://www.acls.net";
 const buildFolderPath = path.join(process.cwd(), "build");
 const sitemapPath = path.join(buildFolderPath, "sitemap.xml");
 const daysThreshold = 30; // Number of days to compare for updating lastmod

test/dirty-words-checker.mjs

@@ -13,6 +13,18 @@
     }
   ],
   "test/fixtures/external-link-broken.html": [
+    {
+      "ruleId": "allowed-links",
+      "severity": 2,
+      "message": "External link to this destination is not allowed by current configuration",
+      "offset": 204,
+      "line": 9,
+      "column": 14,
+      "size": 66,
+      "selector": "html > body > a:nth-child(1)",
+      "ruleUrl": "https://html-validate.org/rules/allowed-links.html",
+      "context": "external"
+    },
     {
       "ruleId": "pacific-medical-training/external-links",
       "severity": 2,
@@ -59,6 +71,18 @@
     }
   ],
   "test/fixtures/internal-link-broken.html": [
+    {
+      "ruleId": "allowed-links",
+      "severity": 2,
+      "message": "Absolute link to this destination is not allowed by current configuration",
+      "offset": 204,
+      "line": 9,
+      "column": 14,
+      "size": 36,
+      "selector": "html > body > a",
+      "ruleUrl": "https://html-validate.org/rules/allowed-links.html",
+      "context": "absolute"
+    },
     {
       "ruleId": "pacific-medical-training/internal-links",
       "severity": 2,