fix(importer): sanitize PostAttachment.ext to skip mangled gallery-dl URL-encoded basenames (varchar(32) overrun) — Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/app/services/importer.py

@@ -71,6 +71,31 @@ def is_video(path: Path) -> bool:
     return path.suffix.lower() in VIDEO_EXTS
 
 
+def _safe_ext(path: Path) -> str:
+    """Conservatively extract a file extension for PostAttachment.ext
+    (varchar(32)).
+
+    gallery-dl produces some filenames with URL-encoded query-string
+    artifacts embedded into the basename (e.g.
+    `79507046_media_..._https___www.patreon.com_media-u_Z0FBQUFBQm5q...`).
+    `Path.suffix` finds the LAST dot and returns everything after, which
+    in those cases yields a 50+ char "extension" of mostly base64-ish
+    junk. That blows the column. Operator-flagged 2026-05-25.
+
+    Real extensions are short and alphanumeric. We accept anything ≤ 16
+    chars where every post-dot character is alphanumeric; anything else
+    means the input wasn't a real extension and we return the empty
+    string. ext is nullable-ish (empty string still satisfies NOT NULL)
+    and consumers should treat "" as "no known extension".
+    """
+    suffix = path.suffix.lower()
+    if not suffix or len(suffix) > 16:
+        return ""
+    if not all(c.isalnum() for c in suffix[1:]):
+        return ""
+    return suffix
+
+
 def _mime_for(path: Path) -> str:
     suffix = path.suffix.lower()
     image_mimes = {
@@ -209,7 +234,7 @@ class Importer:
                 sha256=sha,
                 path=stored,
                 original_filename=source.name,
-                ext=source.suffix.lower(),
+                ext=_safe_ext(source),
                 mime=_mime_for(source),
                 size_bytes=source.stat().st_size,
             ))