Big changes

scripts/db/backup_full.sh

@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+project_root="$(cd "${script_dir}/../.." && pwd)"
+
+usage() {
+  cat <<'USAGE'
+Usage: scripts/db/backup_full.sh [--plain]
+
+Creates a PostgreSQL logical backup from the running `db` compose service.
+
+Options:
+  --plain    Write a plain SQL dump instead of custom-format dump.
+  -h, --help Show this help.
+
+Environment:
+  BACKUP_DIR         Destination directory (default: <repo>/backups)
+  BACKUP_PREFIX      File prefix (default: scholarr)
+  USE_DEV_COMPOSE    Set to 1 to include docker-compose.dev.yml
+USAGE
+}
+
+format="custom"
+while (($#)); do
+  case "$1" in
+    --plain)
+      format="plain"
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage >&2
+      exit 2
+      ;;
+  esac
+done
+
+compose_cmd=(docker compose -f "${project_root}/docker-compose.yml")
+if [[ "${USE_DEV_COMPOSE:-0}" == "1" && -f "${project_root}/docker-compose.dev.yml" ]]; then
+  compose_cmd+=(-f "${project_root}/docker-compose.dev.yml")
+fi
+
+backup_dir="${BACKUP_DIR:-${project_root}/backups}"
+backup_prefix="${BACKUP_PREFIX:-scholarr}"
+mkdir -p "${backup_dir}"
+
+timestamp="$(date -u +"%Y%m%dT%H%M%SZ")"
+if [[ "${format}" == "plain" ]]; then
+  backup_file="${backup_dir}/${backup_prefix}_${timestamp}.sql"
+  dump_cmd='pg_dump --no-owner --no-acl -U "$POSTGRES_USER" "$POSTGRES_DB"'
+else
+  backup_file="${backup_dir}/${backup_prefix}_${timestamp}.dump"
+  dump_cmd='pg_dump --format=custom --no-owner --no-acl -U "$POSTGRES_USER" "$POSTGRES_DB"'
+fi
+
+"${compose_cmd[@]}" exec -T db sh -lc "${dump_cmd}" > "${backup_file}"
+
+echo "Backup created: ${backup_file}"

scripts/db/check_integrity.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import asyncio
+import json
+
+from app.db.session import get_session_factory
+from app.services.domains.dbops import collect_integrity_report
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description="Run database integrity checks.")
+    parser.add_argument(
+        "--strict-warnings",
+        action="store_true",
+        help="Return non-zero exit code if any warning is present.",
+    )
+    return parser
+
+
+async def _run() -> dict:
+    session_factory = get_session_factory()
+    async with session_factory() as db_session:
+        return await collect_integrity_report(db_session)
+
+
+def _exit_code(report: dict, *, strict_warnings: bool) -> int:
+    if report.get("status") == "failed":
+        return 1
+    if strict_warnings and report.get("warnings"):
+        return 2
+    return 0
+
+
+def main() -> int:
+    args = build_parser().parse_args()
+
+    try:
+        report = asyncio.run(_run())
+    except Exception as exc:
+        print(json.dumps({"status": "failed", "error": str(exc)}, indent=2))
+        return 1
+
+    print(json.dumps(report, indent=2))
+    return _exit_code(report, strict_warnings=args.strict_warnings)
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

scripts/db/repair_publication_links.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import asyncio
+import json
+
+from app.db.session import get_session_factory
+from app.services.domains.dbops import run_publication_link_repair
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description="Repair scholar-publication links for a user with audit logging.",
+    )
+    parser.add_argument("--user-id", type=int, required=True, help="Target user ID.")
+    parser.add_argument(
+        "--scholar-profile-id",
+        type=int,
+        action="append",
+        default=[],
+        help="Optional scholar_profile_id filter. Repeat for multiple values.",
+    )
+    parser.add_argument("--apply", action="store_true", help="Apply changes. Default is dry-run.")
+    parser.add_argument(
+        "--gc-orphan-publications",
+        action="store_true",
+        help="Delete publications with zero links after cleanup.",
+    )
+    parser.add_argument(
+        "--requested-by",
+        default="",
+        help="Operator identifier for audit logs (email/name/ticket).",
+    )
+    return parser
+
+
+async def _run(args: argparse.Namespace) -> dict:
+    session_factory = get_session_factory()
+    async with session_factory() as db_session:
+        return await run_publication_link_repair(
+            db_session,
+            user_id=args.user_id,
+            scholar_profile_ids=args.scholar_profile_id,
+            dry_run=not args.apply,
+            gc_orphan_publications=args.gc_orphan_publications,
+            requested_by=args.requested_by,
+        )
+
+
+def main() -> int:
+    parser = build_parser()
+    args = parser.parse_args()
+
+    try:
+        result = asyncio.run(_run(args))
+    except Exception as exc:
+        print(json.dumps({"status": "failed", "error": str(exc)}, indent=2))
+        return 1
+
+    print(json.dumps(result, indent=2))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

scripts/db/restore_dump.sh

@@ -0,0 +1,79 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+project_root="$(cd "${script_dir}/../.." && pwd)"
+
+usage() {
+  cat <<'USAGE'
+Usage: scripts/db/restore_dump.sh --file <path> [--wipe-public]
+
+Restores a PostgreSQL dump into the running `db` compose service.
+
+Options:
+  --file <path>   Required. Backup file (.dump custom format or .sql plain).
+  --wipe-public   Drop and recreate public schema before restore.
+  -h, --help      Show this help.
+
+Environment:
+  USE_DEV_COMPOSE   Set to 1 to include docker-compose.dev.yml
+USAGE
+}
+
+dump_file=""
+wipe_public="0"
+while (($#)); do
+  case "$1" in
+    --file)
+      dump_file="${2:-}"
+      shift 2
+      ;;
+    --wipe-public)
+      wipe_public="1"
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage >&2
+      exit 2
+      ;;
+  esac
+done
+
+if [[ -z "${dump_file}" ]]; then
+  echo "--file is required" >&2
+  usage >&2
+  exit 2
+fi
+if [[ ! -f "${dump_file}" ]]; then
+  echo "Dump file not found: ${dump_file}" >&2
+  exit 2
+fi
+
+compose_cmd=(docker compose -f "${project_root}/docker-compose.yml")
+if [[ "${USE_DEV_COMPOSE:-0}" == "1" && -f "${project_root}/docker-compose.dev.yml" ]]; then
+  compose_cmd+=(-f "${project_root}/docker-compose.dev.yml")
+fi
+
+if [[ "${wipe_public}" == "1" ]]; then
+  "${compose_cmd[@]}" exec -T db sh -lc 'psql -v ON_ERROR_STOP=1 -U "$POSTGRES_USER" "$POSTGRES_DB" -c "DROP SCHEMA public CASCADE; CREATE SCHEMA public;"'
+fi
+
+case "${dump_file}" in
+  *.dump)
+    cat "${dump_file}" | "${compose_cmd[@]}" exec -T db sh -lc 'pg_restore --no-owner --no-acl -U "$POSTGRES_USER" -d "$POSTGRES_DB" -'
+    ;;
+  *.sql)
+    cat "${dump_file}" | "${compose_cmd[@]}" exec -T db sh -lc 'psql -v ON_ERROR_STOP=1 -U "$POSTGRES_USER" "$POSTGRES_DB"'
+    ;;
+  *)
+    echo "Unsupported file extension. Expected .dump or .sql" >&2
+    exit 2
+    ;;
+esac
+
+echo "Restore completed: ${dump_file}"