ChatApp/scripts/migrate/04-restore-storage-xattrs.py

#!/usr/bin/env python3
# Incident fix (2026-06-02): after the netralax.cloud -> netralax.de move, every
# storage object GET returned HTTP 500 with:
#     { "code": "ENODATA", "errno": 61, "message": "The extended attribute does not exist." }
#
# Root cause: the OBJECT BYTES were copied to the new server, but Supabase
# Storage (supabase/storage-api:v1.48.26, file backend) keeps each object's
# response metadata in Linux extended attributes (xattrs) on the version file:
#     user.supabase.content-type
#     user.supabase.cache-control
#     user.supabase.etag
# The migration copy did not preserve xattrs, so storage's getObject() throws
# ENODATA when it reads them. The OLD server is gone, so we cannot re-copy —
# but every value we need is still in the database column storage.objects.metadata
# (mimetype / cacheControl / eTag). This script reconstructs the missing xattrs
# from that column. It is idempotent and only ADDS metadata xattrs; it never
# touches object bytes.
#
# RUN ON THE NEW SERVER (needs /opt/supabase, docker, and root for setxattr):
#     sudo python3 04-restore-storage-xattrs.py            # all buckets
#     sudo python3 04-restore-storage-xattrs.py --dry-run  # show, change nothing
#     sudo python3 04-restore-storage-xattrs.py --bucket profile-avatars
# After it finishes, no storage restart is needed (xattrs are read per request).

import argparse
import json
import os
import subprocess
import sys

SUPABASE_DIR = "/opt/supabase"
# Single-tenant self-hosted layout: <volume>/stub/stub/<bucket>/<name>/<version-file>
STORAGE_ROOT = os.path.join(SUPABASE_DIR, "volumes/storage/stub/stub")

# DB metadata field  ->  (xattr name, default when the field is absent)
XATTRS = [
    ("mimetype", "user.supabase.content-type", "application/octet-stream"),
    ("cacheControl", "user.supabase.cache-control", "no-cache"),
    ("eTag", "user.supabase.etag", None),  # None default => skip if missing
]


def fetch_objects():
    """Return [(bucket_id, name, metadata_dict), ...] from storage.objects."""
    # Tab-separate so object names containing '|' can't break parsing.
    query = (
        "select bucket_id||chr(9)||name||chr(9)||coalesce(metadata::text,'{}') "
        "from storage.objects"
    )
    raw = subprocess.check_output(
        [
            "docker", "compose", "exec", "-T", "db",
            "psql", "-U", "postgres", "-d", "postgres", "-tAc", query,
        ],
        cwd=SUPABASE_DIR,
    ).decode()
    rows = []
    for line in raw.splitlines():
        line = line.rstrip("\r")
        if not line.strip():
            continue
        parts = line.split("\t", 2)
        if len(parts) < 3:
            continue
        bucket, name, meta = parts
        try:
            md = json.loads(meta) if meta else {}
        except json.JSONDecodeError:
            md = {}
        rows.append((bucket, name, md))
    return rows


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--bucket", help="only this bucket (e.g. profile-avatars)")
    ap.add_argument("--dry-run", action="store_true", help="print, change nothing")
    args = ap.parse_args()

    objects = fetch_objects()
    fixed = missing_dir = missing_file = 0

    for bucket, name, md in objects:
        if args.bucket and bucket != args.bucket:
            continue
        objdir = os.path.join(STORAGE_ROOT, bucket, name)
        if not os.path.isdir(objdir):
            print("NO_DIR  ", bucket, name)
            missing_dir += 1
            continue
        version_files = [
            os.path.join(objdir, f)
            for f in os.listdir(objdir)
            if os.path.isfile(os.path.join(objdir, f))
        ]
        if not version_files:
            print("NO_FILE ", bucket, name)
            missing_file += 1
            continue
        for path in version_files:
            for field, xattr, default in XATTRS:
                value = md.get(field, default)
                if value is None:
                    continue
                if args.dry_run:
                    print(f"  would set {xattr}={value!r} on {path}")
                else:
                    os.setxattr(path, xattr, str(value).encode())
            fixed += 1
        print("OK      ", bucket, name)

    print(
        f"\n{'DRY-RUN: would fix' if args.dry_run else 'fixed'} {fixed} file(s); "
        f"{missing_dir} missing dir(s), {missing_file} empty object dir(s)."
    )
    if missing_dir or missing_file:
        print(
            "NOTE: objects with a missing dir/file have lost their bytes and "
            "cannot be recovered from xattrs — those are genuinely gone."
        )


if __name__ == "__main__":
    if os.geteuid() != 0 and "--dry-run" not in sys.argv:
        print("Re-run with sudo (setxattr needs root).", file=sys.stderr)
        sys.exit(1)
    main()