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,
             ))

tests/test_importer_attachments.py

@@ -59,3 +59,25 @@ def test_json_sidecar_is_not_attached(importer, import_layout):
         select(func.count()).select_from(PostAttachment)
     ).scalar_one()
     assert n == 0
+
+
+def test_mangled_filename_extension_is_sanitized(importer, import_layout):
+    """gallery-dl sometimes URL-encodes a query string into the basename
+    (`...https___www.patreon.com_media-u_Z0F...`). Python's Path.suffix
+    returns 50+ chars of base64-ish junk for those, which blows the
+    PostAttachment.ext varchar(32) column. Operator-flagged 2026-05-25.
+    The importer should record an empty ext rather than crash."""
+    import_root, _ = import_layout
+    f = (
+        import_root / "Alice"
+        / "79507046_media_https___www.patreon.com_media-u_Z0FBQUFBQm5q"
+    )
+    f.parent.mkdir(parents=True, exist_ok=True)
+    f.write_bytes(b"binary blob")
+    r = importer.import_one(f)
+    assert r.status == "attached"
+    att = importer.session.execute(select(PostAttachment)).scalar_one()
+    # Junk "extension" -> stored as empty string (not the 50-char garbage).
+    assert att.ext == ""
+    # original_filename is Text-typed so the full name survives intact.
+    assert att.original_filename.endswith("_Z0FBQUFBQm5q")