feat(backup): stricter databases.csv semantics + atomic SQL dumps

- read databases.csv with stable types (dtype=str, keep_default_na=False)
- validate database field: require '*' or concrete name (no empty/NaN)
- support Postgres cluster dumps via '*' entries (pg_dumpall)
- write SQL dumps atomically to avoid partial/empty files
- early-skip fully ignored volumes before creating backup directories
- update seed CLI to enforce new contract and update by (instance,database)
- adjust tests: sql dir naming + add E2E coverage for early-skip and '*' seeding

src/baudolo/seed/__main__.py

@@ -1,67 +1,106 @@
-import pandas as pd
+#!/usr/bin/env python3
+from __future__ import annotations
+
 import argparse
 import os
+import re
+import sys
+import pandas as pd
+from typing import Optional
 
 
-def check_and_add_entry(file_path, instance, database, username, password):
-    # Check if the file exists and is not empty
-    if os.path.exists(file_path) and os.path.getsize(file_path) > 0:
-        # Read the existing CSV file with header
-        df = pd.read_csv(file_path, sep=";")
-    else:
-        # Create a new DataFrame with columns if file does not exist
-        df = pd.DataFrame(columns=["instance", "database", "username", "password"])
+DB_NAME_RE = re.compile(r"^[a-zA-Z0-9_][a-zA-Z0-9_-]*$")
 
-    # Check if the entry exists and remove it
-    mask = (
-        (df["instance"] == instance)
-        & (
-            (df["database"] == database)
-            | (((df["database"].isna()) | (df["database"] == "")) & (database == ""))
+def _validate_database_value(value: Optional[str], *, instance: str) -> str:
+    v = (value or "").strip()
+    if v == "":
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': "
+            "column 'database' must be '*' or a concrete database name (not empty)."
         )
-        & (df["username"] == username)
-    )
+    if v == "*":
+        return "*"
+    if v.lower() == "nan":
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': database must not be 'nan'."
+        )
+    if not DB_NAME_RE.match(v):
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': "
+            f"invalid database name '{v}'. Allowed: letters, numbers, '_' and '-'."
+        )
+    return v
 
-    if not df[mask].empty:
-        print("Replacing existing entry.")
-        df = df[~mask]
+def check_and_add_entry(
+    file_path: str,
+    instance: str,
+    database: Optional[str],
+    username: str,
+    password: str,
+) -> None:
+    """
+    Add or update an entry in databases.csv.
+
+    The function enforces strict validation:
+    - database MUST be set
+    - database MUST be '*' or a valid database name
+    """
+    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,
+        )
+    else:
+        df = pd.DataFrame(
+            columns=["instance", "database", "username", "password"]
+        )
+
+    mask = (df["instance"] == instance) & (df["database"] == database)
+
+    if mask.any():
+        print("Updating existing entry.")
+        df.loc[mask, ["username", "password"]] = [username, password]
     else:
         print("Adding new entry.")
+        new_entry = pd.DataFrame(
+            [[instance, database, username, password]],
+            columns=["instance", "database", "username", "password"],
+        )
+        df = pd.concat([df, new_entry], ignore_index=True)
 
-    # Create a new DataFrame for the new entry
-    new_entry = pd.DataFrame(
-        [
-            {
-                "instance": instance,
-                "database": database,
-                "username": username,
-                "password": password,
-            }
-        ]
-    )
-
-    # Add (or replace) the entry using concat
-    df = pd.concat([df, new_entry], ignore_index=True)
-
-    # Save the updated CSV file
     df.to_csv(file_path, sep=";", index=False)
 
 
-def main():
+def main() -> None:
     parser = argparse.ArgumentParser(
-        description="Check and replace (or add) a database entry in a CSV file."
+        description="Seed or update databases.csv for backup configuration."
     )
-    parser.add_argument("file_path", help="Path to the CSV file")
-    parser.add_argument("instance", help="Database instance")
-    parser.add_argument("database", help="Database name")
-    parser.add_argument("username", help="Username")
-    parser.add_argument("password", nargs="?", default="", help="Password (optional)")
+    parser.add_argument("file", help="Path to databases.csv")
+    parser.add_argument("instance", help="Instance name (e.g. bigbluebutton)")
+    parser.add_argument(
+        "database",
+        help="Database name or '*' to dump all databases",
+    )
+    parser.add_argument("username", help="Database username")
+    parser.add_argument("password", help="Database password")
 
     args = parser.parse_args()
 
-    check_and_add_entry(
-        args.file_path, args.instance, args.database, args.username, args.password
-    )
+    try:
+        check_and_add_entry(
+            file_path=args.file,
+            instance=args.instance,
+            database=args.database,
+            username=args.username,
+            password=args.password,
+        )
+    except Exception as exc:
+        print(f"ERROR: {exc}", file=sys.stderr)
+        sys.exit(1)
 
 
 if __name__ == "__main__":