From 476c1bf413225a80e34f7269cc9e09342cb91411 Mon Sep 17 00:00:00 2001
From: para <157126561+mdegallaix@users.noreply.github.com>
Date: Sat, 26 Sep 2026 00:23:02 +0200
Subject: [PATCH] Fix W3C validator errors in the Facebook feed proxy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

FetchRSS's raw feed fails validation: entry <id> is a bare Facebook post
ID rather than a full URI, and <link rel="self"> points at the FetchRSS
URL instead of where we actually serve it. Parse the fetched XML with
DOMDocument and fix both before caching/serving: reuse each entry's own
alternate link (already a full post URL) as its id, and rewrite the self
link to our own facebook.php URL.

Requires the php-xml extension (ext-dom) — near-universal on shared
hosting, but worth checking if this breaks on deploy.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---
 php/facebook.php | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/php/facebook.php b/php/facebook.php
index f594560..42b9b70 100644
--- a/php/facebook.php
+++ b/php/facebook.php
@@ -10,10 +10,46 @@ require __DIR__ . '/common.php';
  * notre propre domaine pour avoir une URL stable a partager.
  */
 const FETCHRSS_URL = 'https://fetchrss.com/feed/1xABzW0ZB9CM1xAByX0rYAhW.atom';
+const SELF_URL = 'https://sillycone-village.be/silly-rss/facebook.php';
 
+/**
+ * Le flux FetchRSS brut ne passe pas le validateur W3C :
+ * - <id> de chaque <entry> est l'identifiant numerique brut du post
+ *   Facebook, alors que la spec Atom exige une URI complete. On reutilise
+ *   le <link rel="alternate"> de l'entree (deja une URL complete vers le
+ *   post) a la place.
+ * - Le <link rel="self"> pointe vers l'URL FetchRSS d'origine au lieu de
+ *   celle ou ce flux est reellement servi.
+ */
 function fetch_facebook_feed(): string
 {
-    return http_get(FETCHRSS_URL, ['Accept: application/atom+xml, application/xml']);
+    $raw = http_get(FETCHRSS_URL, ['Accept: application/atom+xml, application/xml']);
+
+    $doc = new DOMDocument();
+    if (!$doc->loadXML($raw)) {
+        return $raw; // XML illisible : on sert quand meme le brut plutot que de casser le flux
+    }
+
+    $atomNs = 'http://www.w3.org/2005/Atom';
+    $xpath = new DOMXPath($doc);
+    $xpath->registerNamespace('a', $atomNs);
+
+    foreach ($xpath->query('/a:feed/a:link[@rel="self"]') as $selfLink) {
+        $selfLink->setAttribute('href', SELF_URL);
+    }
+
+    foreach ($xpath->query('/a:feed/a:entry') as $entry) {
+        $idNode = $xpath->query('a:id', $entry)->item(0);
+        $linkNode = $xpath->query('a:link[@rel="alternate"]', $entry)->item(0);
+        if ($idNode && $linkNode) {
+            $href = $linkNode->getAttribute('href');
+            if ($href && !preg_match('#^https?://#', $idNode->textContent)) {
+                $idNode->textContent = $href;
+            }
+        }
+    }
+
+    return $doc->saveXML();
 }
 
 // text/xml plutot que application/atom+xml : voir la note dans common.php