@adobe/helix-html-pipeline 3.7.6 → 3.7.8

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+## [3.7.8](https://github.com/adobe/helix-html-pipeline/compare/v3.7.7...v3.7.8) (2022-12-09)
+
+
+### Bug Fixes
+
+* handle cloudflare url error gracefully (issue [#216](https://github.com/adobe/helix-html-pipeline/issues/216)) ([3d7e5fb](https://github.com/adobe/helix-html-pipeline/commit/3d7e5fb6dea06737c3d4f70b816c8bf70df8b2cd))
+
+## [3.7.7](https://github.com/adobe/helix-html-pipeline/compare/v3.7.6...v3.7.7) (2022-12-08)
+
+
+### Bug Fixes
+
+* remove og:url meta tag if overridden with ""  ([d605625](https://github.com/adobe/helix-html-pipeline/commit/d6056258ab5188362cd6afd94cd860a5dca6880a)), closes [#214](https://github.com/adobe/helix-html-pipeline/issues/214)
+
 ## [3.7.6](https://github.com/adobe/helix-html-pipeline/compare/v3.7.5...v3.7.6) (2022-11-29)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adobe/helix-html-pipeline",
-  "version": "3.7.6",
+  "version": "3.7.8",
   "description": "Helix HTML Pipeline",
   "main": "src/index.js",
   "types": "src/index.d.ts",
@@ -79,15 +79,15 @@
   "devDependencies": {
     "@adobe/eslint-config-helix": "1.3.2",
     "@markedjs/html-differ": "4.0.2",
-    "@semantic-release/changelog": "6.0.1",
+    "@semantic-release/changelog": "6.0.2",
     "@semantic-release/git": "10.0.1",
     "@semantic-release/npm": "9.0.1",
     "c8": "7.12.0",
-    "eslint": "8.28.0",
+    "eslint": "8.29.0",
     "eslint-import-resolver-exports": "1.0.0-beta.3",
     "eslint-plugin-header": "3.1.1",
     "eslint-plugin-import": "2.26.0",
-    "esmock": "2.0.9",
+    "esmock": "2.1.0",
     "husky": "8.0.2",
     "js-yaml": "4.1.0",
     "jsdom": "20.0.3",

package/src/html-pipe.js

@@ -144,7 +144,9 @@ export async function htmlPipe(state, req) {
 
     // turn any URL errors into a 400, since they are user input
     // see https://github.com/adobe/helix-pipeline-service/issues/346
-    if (e.code === 'ERR_INVALID_URL') {
+    if (e.code === 'ERR_INVALID_URL' // node runtime
+      /* c8 ignore next */
+      || (e instanceof TypeError && e.message === 'Invalid URL string.')) { // cloudflare runtime
       res.status = 400;
       res.headers.set('x-error', cleanupHeaderValue(`invalid url: ${e.input}`));
     }

package/src/steps/extract-metadata.js

@@ -161,8 +161,6 @@ export default function extractMetaData(state, req) {
     getLocalMetadata(hast),
   );
 
-  const IGNORED_CUSTOM_META = ['twitter:card'];
-
   // first process supported metadata properties
   [
     'title',
@@ -179,19 +177,12 @@ export default function extractMetaData(state, req) {
       delete metaConfig[name];
     }
   });
-  if (Object.keys(metaConfig).length > 0) {
-    // add rest to meta.custom
-    meta.custom = Object.entries(metaConfig)
-      .filter(([name]) => !IGNORED_CUSTOM_META.includes(name))
-      .map(([name, value]) => ({
-        name,
-        value,
-        property: name.includes(':'),
-      }));
-  }
-
   // default value for twitter:card (mandatory for rendering URLs as cards in tweets)
   meta['twitter:card'] = metaConfig['twitter:card'] || 'summary_large_image';
+  delete metaConfig['twitter:card'];
+
+  // add rest to meta.custom
+  meta.custom = metaConfig;
 
   if (meta.keywords) {
     meta.keywords = toList(meta.keywords).join(', ');

package/src/steps/render.js

@@ -55,29 +55,51 @@ export default async function render(state, req, res) {
   ]);
 
   // add meta
+  // (this is so complicated to keep the order backward compatible to make the diff tests happy)
+  const metadata = {
+    'og:title': meta.title,
+    'og:description': meta.description,
+    'og:url': meta.url,
+    'og:image': meta.image,
+    'og:image:secure_url': meta.image,
+    'og:image:alt': meta.imageAlt,
+    'og:updated_time': meta.modified_time,
+    'article:tag': meta.tags || [],
+    'article:section': meta.section,
+    'article:published_time': meta.published_time,
+    'article:modified_time': meta.modified_time,
+    'twitter:card': meta['twitter:card'],
+    'twitter:title': meta.title,
+    'twitter:description': meta.description,
+    'twitter:image': meta.image,
+  };
+  // remove meta with no values
+  for (const name of Object.keys(metadata)) {
+    if (!metadata[name]) {
+      delete metadata[name];
+    }
+  }
+  // append custom metadata
+  Object.assign(metadata, meta.custom);
+
+  // remove og:url with explicit removal marker
+  if (metadata['og:url'] === '""') {
+    delete metadata['og:url'];
+  }
+
   appendElement($head, createElement('link', 'rel', 'canonical', 'href', content.meta.canonical));
   appendElement($head, createElement('meta', 'name', 'description', 'content', content.meta.description));
   appendElement($head, createElement('meta', 'name', 'keywords', 'content', content.meta.keywords));
-  appendElement($head, createElement('meta', 'property', 'og:title', 'content', content.meta.title));
-  appendElement($head, createElement('meta', 'property', 'og:description', 'content', content.meta.description));
-  appendElement($head, createElement('meta', 'property', 'og:url', 'content', content.meta.url));
-  appendElement($head, createElement('meta', 'property', 'og:image', 'content', content.meta.image));
-  appendElement($head, createElement('meta', 'property', 'og:image:secure_url', 'content', content.meta.image));
-  appendElement($head, createElement('meta', 'property', 'og:image:alt', 'content', content.meta.imageAlt));
-  appendElement($head, createElement('meta', 'property', 'og:updated_time', 'content', content.meta.modified_time));
-  for (const tag of (meta.tags || [])) {
-    appendElement($head, createElement('meta', 'property', 'article:tag', 'content', tag));
-  }
-  appendElement($head, createElement('meta', 'property', 'article:section', 'content', content.meta.section));
-  appendElement($head, createElement('meta', 'property', 'article:published_time', 'content', content.meta.published_time));
-  appendElement($head, createElement('meta', 'property', 'article:modified_time', 'content', content.meta.modified_time));
-  appendElement($head, createElement('meta', 'name', 'twitter:card', 'content', content.meta['twitter:card']));
-  appendElement($head, createElement('meta', 'name', 'twitter:title', 'content', content.meta.title));
-  appendElement($head, createElement('meta', 'name', 'twitter:description', 'content', content.meta.description));
-  appendElement($head, createElement('meta', 'name', 'twitter:image', 'content', content.meta.image));
 
-  for (const custom of (meta.custom || [])) {
-    appendElement($head, createElement('meta', custom.property ? 'property' : 'name', custom.name, 'content', custom.value));
+  for (const [name, value] of Object.entries(metadata)) {
+    const attr = name.includes(':') && !name.startsWith('twitter:') ? 'property' : 'name';
+    if (Array.isArray(value)) {
+      for (const v of value) {
+        appendElement($head, createElement('meta', attr, name, 'content', v));
+      }
+    } else {
+      appendElement($head, createElement('meta', attr, name, 'content', value));
+    }
   }
   appendElement($head, createElement('link', 'rel', 'alternate', 'type', 'application/xml+atom', 'href', meta.feed, 'title', `${meta.title} feed`));