fix(seed): handle empty databases.csv and add unit tests

- Gracefully handle empty databases.csv by creating header columns and emitting a warning
- Add _empty_df() helper for consistent DataFrame initialization
- Add unit tests for baudolo-seed including empty-file regression case
- Apply minor formatting fixes across backup and e2e test files

https://chatgpt.com/share/69628f0b-8744-800f-b08d-2633e05167da

src/baudolo/backup/app.py

@@ -72,6 +72,7 @@ def requires_stop(containers: list[str], images_no_stop_required: list[str]) ->
             return True
     return False
 
+
 def backup_mariadb_or_postgres(
     *,
     container: str,

src/baudolo/backup/cli.py

@@ -68,7 +68,7 @@ def parse_args() -> argparse.Namespace:
         action="store_true",
         help="Do not restart containers after backup",
     )
-    
+
     p.add_argument(
         "--dump-only-sql",
         action="store_true",

src/baudolo/backup/db.py

@@ -52,7 +52,9 @@ def _atomic_write_cmd(cmd: str, out_file: str) -> None:
     execute_shell_command(f"mv {tmp} {out_file}")
 
 
-def fallback_pg_dumpall(container: str, username: str, password: str, out_file: str) -> None:
+def fallback_pg_dumpall(
+    container: str, username: str, password: str, out_file: str
+) -> None:
     """
     Perform a full Postgres cluster dump using pg_dumpall.
     """
@@ -103,9 +105,7 @@ def backup_database(
                     "'*' is currently only supported for Postgres."
                 )
 
-            cluster_file = os.path.join(
-                out_dir, f"{instance_name}.cluster.backup.sql"
-            )
+            cluster_file = os.path.join(out_dir, f"{instance_name}.cluster.backup.sql")
             fallback_pg_dumpall(container, user, password, cluster_file)
             produced = True
             continue

src/baudolo/seed/__main__.py

@@ -7,10 +7,11 @@ import re
 import sys
 import pandas as pd
 from typing import Optional
-
+from pandas.errors import EmptyDataError
 
 DB_NAME_RE = re.compile(r"^[a-zA-Z0-9_][a-zA-Z0-9_-]*$")
 
+
 def _validate_database_value(value: Optional[str], *, instance: str) -> str:
     v = (value or "").strip()
     if v == "":
@@ -31,6 +32,11 @@ def _validate_database_value(value: Optional[str], *, instance: str) -> str:
         )
     return v
 
+
+def _empty_df() -> pd.DataFrame:
+    return pd.DataFrame(columns=["instance", "database", "username", "password"])
+
+
 def check_and_add_entry(
     file_path: str,
     instance: str,
@@ -48,17 +54,21 @@ def check_and_add_entry(
     database = _validate_database_value(database, instance=instance)
 
     if os.path.exists(file_path):
-        df = pd.read_csv(
-            file_path,
-            sep=";",
-            dtype=str,
-            keep_default_na=False,
-        )
+        try:
+            df = pd.read_csv(
+                file_path,
+                sep=";",
+                dtype=str,
+                keep_default_na=False,
+            )
+        except EmptyDataError:
+            print(
+                f"WARNING: databases.csv exists but is empty: {file_path}. Creating header columns.",
+                file=sys.stderr,
+            )
+            df = _empty_df()
     else:
-        df = pd.DataFrame(
-            columns=["instance", "database", "username", "password"]
-        )
-
+        df = _empty_df()
     mask = (df["instance"] == instance) & (df["database"] == database)
 
     if mask.any():