[text] reject long filename extensions (#8491)

fixes regression introduced in 3252ead7c7
ref bc868e7bb8

gallery_dl/text.py

@@ -125,7 +125,7 @@ def nameext_from_name(filename, data=None):
         data = {}
 
     name, _, ext = filename.rpartition(".")
-    if name:
+    if name and len(ext) <= 16:
         data["filename"] = name
         data["extension"] = ext.lower()
     else:

test/results/kemono.py

@@ -549,6 +549,17 @@ __tests__ = (
     "username"    : util.NONE,
 },
 
+{
+    "#url"     : "https://kemono.cr/patreon/user/2570882/post/79311665",
+    "#comment" : "patreon file URL as 'name' / long 'extension' (#8491)",
+    "#category": ("", "kemono", "patreon"),
+    "#class"   : kemono.KemonoPostExtractor,
+
+    "name"     : "https://www.patreon.com/media-u/Z0FBQUFBQmpfWFNLWHpRakFlYjVNeWpuTlRuRnJBdHY3VVA2UmRhVHFpOFBHMW9QZUdVOHQ3b2pXSV9XMkJlaHFuN2JyVk5VNDBqdV9lZVRLR2NkUXUwSjgwdndDQlk3VzBCUXI5TW5iejlVWVZaUmJoTktIX3B5aGVCS3dUQk11a2hxajd4TUx2MFN2UHpKa0pfOWZQeS1UeDlzNEhpbG9pRzJsZE54MG5OcnZDOUllTGhyY01rNjVRaGgyaVFycjFSUUFIaV92OU9wdktuVjlMeFJNLXhYejdDNWZTVXZEc2l0TVZCR1A0YXM3RVMzbmsxSjh2ND0=#190833153_",
+    "filename" : "https://www.patreon.com/media-u/Z0FBQUFBQmpfWFNLWHpRakFlYjVNeWpuTlRuRnJBdHY3VVA2UmRhVHFpOFBHMW9QZUdVOHQ3b2pXSV9XMkJlaHFuN2JyVk5VNDBqdV9lZVRLR2NkUXUwSjgwdndDQlk3VzBCUXI5TW5iejlVWVZaUmJoTktIX3B5aGVCS3dUQk11a2hxajd4TUx2MFN2UHpKa0pfOWZQeS1UeDlzNEhpbG9pRzJsZE54MG5OcnZDOUllTGhyY01rNjVRaGgyaVFycjFSUUFIaV92OU9wdktuVjlMeFJNLXhYejdDNWZTVXZEc2l0TVZCR1A0YXM3RVMzbmsxSjh2ND0=#190833153_",
+    "extension": "jpg",
+},
+
 {
     "#url"     : "https://kemono.cr/discord/server/488668827274444803/608504710906904576",
     "#category": ("", "kemono", "discord"),

test/test_text.py

@@ -228,6 +228,10 @@ class TestText(unittest.TestCase):
             {"filename": "foo%202?bar&<>", "extension": "ext"},
         )
 
+        # long "extension"
+        fn = "httpswww.example.orgpath-path-path-path-path-path-path-path"
+        self.assertEqual(f(fn), {"filename": fn, "extension": ""})
+
     def test_extract(self, f=text.extract):
         txt = "<a><b>"
         self.assertEqual(f(txt, "<", ">"), ("a" , 3))