From 85a37ca039e982f465d6ca77f176dcce479fafd9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Thu, 12 Dec 2024 20:20:30 +0100
Subject: [PATCH] [facebook] decode surrogate pairs in metadata values (#6599)

---
 gallery_dl/extractor/facebook.py | 3 ++-
 test/results/facebook.py         | 9 +++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/gallery_dl/extractor/facebook.py b/gallery_dl/extractor/facebook.py
index 04acfc52..2f3fdbf3 100644
--- a/gallery_dl/extractor/facebook.py
+++ b/gallery_dl/extractor/facebook.py
@@ -40,7 +40,8 @@ class FacebookExtractor(Extractor):
     @staticmethod
     def decode_all(txt):
         return text.unescape(
-            txt.encode("utf-8").decode("unicode_escape")
+            txt.encode().decode("unicode_escape")
+            .encode("utf_16", "surrogatepass").decode("utf_16")
         ).replace("\\/", "/")
 
     @staticmethod
diff --git a/test/results/facebook.py b/test/results/facebook.py
index 7b34a248..165a2239 100644
--- a/test/results/facebook.py
+++ b/test/results/facebook.py
@@ -113,6 +113,15 @@ __tests__ = (
     "username" : "Facebook",
 },
 
+{
+    "#url"     : "https://www.facebook.com/photo.php?fbid=1156625586261770",
+    "#comment" : "surrogate pair in 'caption' data (#6599)",
+    "#category": ("", "facebook", "photo"),
+    "#class"   : facebook.FacebookPhotoExtractor,
+
+    "caption"  : "A century of innovation parked side by side.\n\n📸: Vocabutesla via X",
+},
+
 {
     "#url"     : "https://www.facebook.com/watch/?v=1165557851291824",
     "#category": ("", "facebook", "video"),