fix(og): brandable static title + wider crawler UA coverage (#521)
@Rekoo-PS reported that gallery URLs sent via the WhatsApp Business API render an unbranded "PicPeak - Photo Sharing Platform" preview even though manual link sends from the WhatsApp app pick up the per-event rich preview correctly. Two root causes, two fixes: 1. WhatsApp Business and 3rd-party preview services (Twilio, LinkPreview.net, etc.) don't always crawl with the recognisable "WhatsApp/X.Y.Z" UA we matched in nginx + galleryOgService. Extend the regex (both copies) to also catch WhatsAppBot, wa-bot, LinkPreview, and Slack-ImgProxy. 2. Even with broader UA coverage, some senders cache metadata with no UA at all and fetch the static SPA shell. That shell's <title> was hard-coded to "PicPeak - Photo Sharing Platform" — embarrassingly generic for any self-hosted brand. Switch to Vite's %VITE_DEFAULT_TITLE% / %VITE_DEFAULT_DESCRIPTION% HTML substitution so self-hosters can bake their brand into the fallback at build time. Defaults stay "PicPeak" so the upstream image doesn't change behaviour for anyone. The per-event rich preview path (handleGalleryOgRequest, fired on matched crawler UAs) is unchanged — this only improves the fallback for unrecognised UAs and for the SPA-shell title that humans see in their browser tab. Adds a vite.config plugin to provide the defaults when env vars aren't set, so unsubstituted "%VITE_..." literals never reach the built HTML. Adds .env.example entries explaining the override. Tests: extend galleryOgService.shareImage.test.js with an isSocialCrawler suite that pins every documented UA (incl. the new ones) plus three browser UAs (negative) and null/empty edge cases. Verified locally: `vite build` with VITE_DEFAULT_TITLE="MyBrand" produces <title>MyBrand</title> + og:title="MyBrand"; without the env var falls back to "PicPeak". Refs: #521
This commit is contained in:
@@ -35,6 +35,7 @@ const { getStorage } = require('../services/storage');
|
||||
const {
|
||||
buildOgMetadata,
|
||||
handleGalleryOgCover,
|
||||
isSocialCrawler,
|
||||
} = require('../services/galleryOgService');
|
||||
|
||||
// The service hits two tables in sequence:
|
||||
@@ -237,3 +238,52 @@ describe('handleGalleryOgCover — 404 unless explicitly opted in', () => {
|
||||
expect(ensureThumbnail).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
|
||||
// Regression for #521 — WhatsApp Business API + 3rd-party preview
|
||||
// services use UAs that aren't "WhatsApp/X.Y.Z". If isSocialCrawler
|
||||
// misses them, those requests fall through to the static SPA shell
|
||||
// and the link preview ends up unbranded.
|
||||
describe('isSocialCrawler — extended bot coverage (#521)', () => {
|
||||
it('matches every UA the README/changelog claims to support', () => {
|
||||
// Pin the contract: each listed UA must hit the crawler path so the
|
||||
// nginx rewrite + backend OG handler stay in sync. Adding a new UA
|
||||
// here without also adding it to nginx.conf would silently regress.
|
||||
const knownBots = [
|
||||
// Main WhatsApp app
|
||||
'WhatsApp/2.23.20.0',
|
||||
// WhatsApp Business / Cloud API variants
|
||||
'WhatsAppBot/1.0',
|
||||
'wa-bot/2.0',
|
||||
// Other messaging app crawlers
|
||||
'facebookexternalhit/1.1',
|
||||
'Twitterbot/1.0',
|
||||
'Slackbot-LinkExpanding 1.0',
|
||||
'TelegramBot (like TwitterBot)',
|
||||
// 3rd-party preview services used by business-messaging stacks
|
||||
'LinkPreview/1.0',
|
||||
'Slack-ImgProxy/1.0',
|
||||
];
|
||||
for (const ua of knownBots) {
|
||||
expect(isSocialCrawler(ua)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('does not match a regular browser UA', () => {
|
||||
const browsers = [
|
||||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0 Safari/537.36',
|
||||
'Mozilla/5.0 (iPhone; CPU iPhone OS 17_2 like Mac OS X) AppleWebKit/605.1.15',
|
||||
// Browser UA that happens to contain "Mobile" — guard against an
|
||||
// over-broad regex landing on it.
|
||||
'Mozilla/5.0 (Linux; Android 14; Pixel 7) AppleWebKit/537.36 Chrome/120.0 Mobile Safari/537.36',
|
||||
];
|
||||
for (const ua of browsers) {
|
||||
expect(isSocialCrawler(ua)).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
it('returns false for null/empty/undefined UAs', () => {
|
||||
expect(isSocialCrawler(null)).toBe(false);
|
||||
expect(isSocialCrawler(undefined)).toBe(false);
|
||||
expect(isSocialCrawler('')).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -7,7 +7,12 @@ const SOCIAL_CRAWLER_PATTERNS = [
|
||||
/facebookexternalhit/i,
|
||||
/facebot/i,
|
||||
/Twitterbot/i,
|
||||
// WhatsApp's main app crawler is "WhatsApp/X.Y.Z"; the Business
|
||||
// API and some Cloud API senders use "WhatsAppBot" or "wa-bot/" —
|
||||
// detect both so API-driven sends get the rich preview too (#521).
|
||||
/WhatsApp/i,
|
||||
/WhatsAppBot/i,
|
||||
/wa-bot/i,
|
||||
/Slackbot/i,
|
||||
/TelegramBot/i,
|
||||
/SkypeUriPreview/i,
|
||||
@@ -24,7 +29,12 @@ const SOCIAL_CRAWLER_PATTERNS = [
|
||||
/Mastodon/i,
|
||||
/Bluesky/i,
|
||||
/OpenGraph/i,
|
||||
/opengraph/i
|
||||
/opengraph/i,
|
||||
// Generic preview/scrape services commonly used in business
|
||||
// messaging stacks (Twilio, LinkPreview.net, etc.). Match the
|
||||
// canonical lowercase substring; the /i flag handles case.
|
||||
/LinkPreview/i,
|
||||
/Slack-ImgProxy/i
|
||||
];
|
||||
|
||||
function isSocialCrawler(userAgent) {
|
||||
|
||||
Reference in New Issue
Block a user