feat(backup)!: exact --images-* matching and --hard-restart-projects

Match --images-no-stop-required and --images-no-backup-required against
the container's exact .Config.Image instead of a substring, so callers
pass full repo:tag references (registry prefix included) and near-miss
image names no longer flip the stop/skip decision. Rename the opt-in
--hard-compose-restart flag to --hard-restart-projects.

The e2e suite pins a SPOT for the DB images and in-container data dirs
(postgres:alpine at /var/lib/postgresql, mariadb:latest at
/var/lib/mysql) and passes exact image refs to the --images-* flags.

BREAKING CHANGE: --images-* now require exact image references, not
substrings; --hard-compose-restart is renamed to --hard-restart-projects.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/baudolo/backup/app.py

@@ -52,7 +52,7 @@ def is_image_ignored(container: str, images_no_backup_required: list[str]) -> bo
     if not images_no_backup_required:
         return False
     img = get_image_info(container)
-    return any(pat in img for pat in images_no_backup_required)
+    return img in images_no_backup_required
 
 
 def volume_is_fully_ignored(
@@ -68,15 +68,15 @@ def volume_is_fully_ignored(
 
 def requires_stop(containers: list[str], images_no_stop_required: list[str]) -> bool:
     """
-    Stop is required if ANY stoppable container image is NOT in the
+    Stop is required if ANY stoppable container image is NOT in the exact
-    whitelist patterns. Swarm task containers never count: baudolo must
+    image whitelist. Swarm task containers never count: baudolo must
     not cycle them (see docker.is_swarm_task).
     """
     for c in containers:
         if is_swarm_task(c):
             continue
         img = get_image_info(c)
-        if not any(pat in img for pat in images_no_stop_required):
+        if img not in images_no_stop_required:
             return True
     return False
 
@@ -247,6 +247,6 @@ def main() -> int:
     print("Finished volume backups.", flush=True)
 
     print("Handling Docker Compose services...", flush=True)
-    handle_docker_compose_services(args.compose_dir, args.hard_compose_restart)
+    handle_docker_compose_services(args.compose_dir, args.hard_restart_projects)
 
     return 0

src/baudolo/backup/cli.py

@@ -17,7 +17,7 @@ def parse_args() -> argparse.Namespace:
         help="Path to the parent directory containing docker-compose setups",
     )
     p.add_argument(
-        "--hard-compose-restart",
+        "--hard-restart-projects",
         nargs="*",
         default=[],
         help="Compose dir names that require 'docker-compose down && up -d' (default: none; pass e.g. 'mailu' under compose where the DB cannot be backed up hot)",
@@ -49,13 +49,13 @@ def parse_args() -> argparse.Namespace:
         "--images-no-stop-required",
         nargs="+",
         required=True,
-        help="Image name patterns for which containers should not be stopped during file backup",
+        help="Exact image references (repo:tag, incl. any registry prefix) whose containers must not be stopped during file backup",
     )
     p.add_argument(
         "--images-no-backup-required",
         nargs="+",
         default=[],
-        help="Image name patterns for which no backup should be performed",
+        help="Exact image references (repo:tag, incl. any registry prefix) for which no backup should be performed",
     )
 
     p.add_argument(

tests/e2e/helpers.py

@@ -7,6 +7,14 @@ import time
 import uuid
 from pathlib import Path
 
+# SPOT for the database images and their in-container data dirs the e2e
+# suite runs against. postgres:alpine tracks latest (18+), which mounts at
+# /var/lib/postgresql (not /var/lib/postgresql/data); bump here only.
+POSTGRES_IMAGE = "postgres:alpine"
+POSTGRES_DATA_DIR = "/var/lib/postgresql"
+MARIADB_IMAGE = "mariadb:latest"
+MARIADB_DATA_DIR = "/var/lib/mysql"
+
 
 def run(
     cmd: list[str],
@@ -172,7 +180,7 @@ def backup_run(
         "baudolo",
         "--compose-dir",
         compose_dir,
-        "--docker-compose-hard-restart-required",
+        "--hard-restart-projects",
         "mailu",
         "--repo-name",
         repo_name,

tests/e2e/test_e2e_dump_only_fallback_to_files.py

@@ -2,6 +2,8 @@
 import unittest
 
 from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
     backup_path,
     cleanup_docker,
     create_minimal_compose_dir,
@@ -50,8 +52,8 @@ class TestE2EDumpOnlyFallbackToFiles(unittest.TestCase):
                 "-e",
                 "POSTGRES_USER=postgres",
                 "-v",
-                f"{cls.pg_volume}:/var/lib/postgresql/data",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
-                "postgres:16",
+                POSTGRES_IMAGE,
             ]
         )
         wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
@@ -65,7 +67,7 @@ class TestE2EDumpOnlyFallbackToFiles(unittest.TestCase):
                 cls.pg_container,
                 "sh",
                 "-lc",
-                f"echo '{cls.marker}' > /var/lib/postgresql/data/marker.txt",
+                f"echo '{cls.marker}' > {POSTGRES_DATA_DIR}/marker.txt",
             ]
         )
 
@@ -79,7 +81,7 @@ class TestE2EDumpOnlyFallbackToFiles(unittest.TestCase):
             "baudolo",
             "--compose-dir",
             cls.compose_dir,
-            "--docker-compose-hard-restart-required",
+            "--hard-restart-projects",
             "mailu",
             "--repo-name",
             cls.repo_name,
@@ -90,10 +92,7 @@ class TestE2EDumpOnlyFallbackToFiles(unittest.TestCase):
             "--database-containers",
             cls.pg_container,
             "--images-no-stop-required",
-            "postgres",
+            POSTGRES_IMAGE,
-            "mariadb",
-            "mysql",
-            "alpine",
             "--dump-only-sql",
         ]
         cp = run(cmd, capture=True, check=True)
@@ -116,8 +115,6 @@ class TestE2EDumpOnlyFallbackToFiles(unittest.TestCase):
                 cls.repo_name,
                 "--source-volume",
                 cls.pg_volume,
-                "--rsync-image",
-                "ghcr.io/kevinveenbirkenbach/alpine-rsync",
             ]
         )
 

tests/e2e/test_e2e_dump_only_sql_mixed_run.py

@@ -1,6 +1,8 @@
 import unittest
 
 from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
     backup_path,
     cleanup_docker,
     create_minimal_compose_dir,
@@ -70,8 +72,8 @@ class TestE2EDumpOnlySqlMixedRun(unittest.TestCase):
                 "-e",
                 f"POSTGRES_PASSWORD={cls.pg_password}",
                 "-v",
-                f"{cls.db_volume}:/var/lib/postgresql/data",
+                f"{cls.db_volume}:{POSTGRES_DATA_DIR}",
-                "postgres:16-alpine",
+                POSTGRES_IMAGE,
             ]
         )
         wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
@@ -122,10 +124,7 @@ class TestE2EDumpOnlySqlMixedRun(unittest.TestCase):
             "--database-containers",
             cls.pg_container,
             "--images-no-stop-required",
-            "alpine",
+            POSTGRES_IMAGE,
-            "postgres",
-            "mariadb",
-            "mysql",
             "--dump-only-sql",
             "--backups-dir",
             cls.backups_dir,

tests/e2e/test_e2e_files_full.py

@@ -57,7 +57,7 @@ class TestE2EFilesFull(unittest.TestCase):
             compose_dir=cls.compose_dir,
             databases_csv=cls.databases_csv,
             database_containers=["dummy-db"],
-            images_no_stop_required=["alpine", "postgres", "mariadb", "mysql"],
+            images_no_stop_required=["alpine:3.20"],
         )
 
         cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
@@ -94,8 +94,6 @@ class TestE2EFilesFull(unittest.TestCase):
                 self.repo_name,
                 "--source-volume",
                 self.volume_src,
-                "--rsync-image",
-                "ghcr.io/kevinveenbirkenbach/alpine-rsync",
             ]
         )
 

tests/e2e/test_e2e_files_no_copy.py

@@ -55,7 +55,7 @@ class TestE2EFilesNoCopy(unittest.TestCase):
             compose_dir=cls.compose_dir,
             databases_csv=cls.databases_csv,
             database_containers=["dummy-db"],
-            images_no_stop_required=["alpine", "postgres", "mariadb", "mysql"],
+            images_no_stop_required=["alpine:3.20"],
             dump_only_sql=True,
         )
 

tests/e2e/test_e2e_images_no_backup_required_early_skip.py

@@ -76,7 +76,7 @@ class TestE2EImagesNoBackupRequiredEarlySkip(unittest.TestCase):
             "baudolo",
             "--compose-dir",
             cls.compose_dir,
-            "--docker-compose-hard-restart-required",
+            "--hard-restart-projects",
             "mailu",
             "--repo-name",
             cls.repo_name,
@@ -87,13 +87,9 @@ class TestE2EImagesNoBackupRequiredEarlySkip(unittest.TestCase):
             "--database-containers",
             "dummy-db",
             "--images-no-stop-required",
-            "alpine",
+            "redis:alpine",
-            "redis",
-            "postgres",
-            "mariadb",
-            "mysql",
             "--images-no-backup-required",
-            "redis",
+            "redis:alpine",
         ]
         cp = run(cmd, capture=True, check=True)
         cls.stdout = cp.stdout or ""

tests/e2e/test_e2e_mariadb_anonymous_preemption.py

@@ -30,6 +30,8 @@ import pandas
 from baudolo.backup import db as db_mod
 
 from .helpers import (
+    MARIADB_IMAGE,
+    MARIADB_DATA_DIR,
     cleanup_docker,
     require_docker,
     run,
@@ -69,8 +71,8 @@ class TestE2EMariaDBAnonymousPreemption(unittest.TestCase):
                 "-e",
                 f"MARIADB_ROOT_PASSWORD={cls.root_password}",
                 "-v",
-                f"{cls.db_volume}:/var/lib/mysql",
+                f"{cls.db_volume}:{MARIADB_DATA_DIR}",
-                "mariadb:12.2",
+                MARIADB_IMAGE,
             ]
         )
 

tests/e2e/test_e2e_mariadb_full.py

@@ -2,6 +2,8 @@
 import unittest
 
 from .helpers import (
+    MARIADB_IMAGE,
+    MARIADB_DATA_DIR,
     backup_run,
     backup_path,
     cleanup_docker,
@@ -56,8 +58,8 @@ class TestE2EMariaDBFull(unittest.TestCase):
                 "-e",
                 f"MARIADB_PASSWORD={cls.db_password}",
                 "-v",
-                f"{cls.db_volume}:/var/lib/mysql",
+                f"{cls.db_volume}:{MARIADB_DATA_DIR}",
-                "mariadb:11",
+                MARIADB_IMAGE,
             ]
         )
 
@@ -97,7 +99,7 @@ class TestE2EMariaDBFull(unittest.TestCase):
             compose_dir=cls.compose_dir,
             databases_csv=cls.databases_csv,
             database_containers=[cls.db_container],
-            images_no_stop_required=["mariadb", "mysql", "alpine", "postgres"],
+            images_no_stop_required=[MARIADB_IMAGE],
         )
 
         cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)

tests/e2e/test_e2e_mariadb_no_copy.py

@@ -2,6 +2,8 @@
 import unittest
 
 from .helpers import (
+    MARIADB_IMAGE,
+    MARIADB_DATA_DIR,
     backup_run,
     backup_path,
     cleanup_docker,
@@ -55,8 +57,8 @@ class TestE2EMariaDBNoCopy(unittest.TestCase):
                 "-e",
                 f"MARIADB_PASSWORD={cls.db_password}",
                 "-v",
-                f"{cls.db_volume}:/var/lib/mysql",
+                f"{cls.db_volume}:{MARIADB_DATA_DIR}",
-                "mariadb:11",
+                MARIADB_IMAGE,
             ]
         )
 
@@ -94,7 +96,7 @@ class TestE2EMariaDBNoCopy(unittest.TestCase):
             compose_dir=cls.compose_dir,
             databases_csv=cls.databases_csv,
             database_containers=[cls.db_container],
-            images_no_stop_required=["mariadb", "mysql", "alpine", "postgres"],
+            images_no_stop_required=[MARIADB_IMAGE],
             dump_only_sql=True,
         )
 

tests/e2e/test_e2e_postgres_full.py

@@ -2,6 +2,8 @@
 import unittest
 
 from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
     backup_run,
     backup_path,
     cleanup_docker,
@@ -47,8 +49,8 @@ class TestE2EPostgresFull(unittest.TestCase):
                 "-e",
                 "POSTGRES_USER=postgres",
                 "-v",
-                f"{cls.pg_volume}:/var/lib/postgresql/data",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
-                "postgres:16",
+                POSTGRES_IMAGE,
             ]
         )
         wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
@@ -76,7 +78,7 @@ class TestE2EPostgresFull(unittest.TestCase):
             compose_dir=cls.compose_dir,
             databases_csv=cls.databases_csv,
             database_containers=[cls.pg_container],
-            images_no_stop_required=["postgres", "mariadb", "mysql", "alpine"],
+            images_no_stop_required=[POSTGRES_IMAGE],
         )
 
         cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)

tests/e2e/test_e2e_postgres_no_copy.py

@@ -2,6 +2,8 @@
 import unittest
 
 from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
     backup_run,
     backup_path,
     cleanup_docker,
@@ -46,8 +48,8 @@ class TestE2EPostgresNoCopy(unittest.TestCase):
                 "-e",
                 "POSTGRES_USER=postgres",
                 "-v",
-                f"{cls.pg_volume}:/var/lib/postgresql/data",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
-                "postgres:16",
+                POSTGRES_IMAGE,
             ]
         )
         wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
@@ -74,7 +76,7 @@ class TestE2EPostgresNoCopy(unittest.TestCase):
             compose_dir=cls.compose_dir,
             databases_csv=cls.databases_csv,
             database_containers=[cls.pg_container],
-            images_no_stop_required=["postgres", "mariadb", "mysql", "alpine"],
+            images_no_stop_required=[POSTGRES_IMAGE],
             dump_only_sql=True,
         )
 

tests/e2e/test_e2e_seed_star_and_db_entries_backup_postgres.py

@@ -1,6 +1,8 @@
 import unittest
 
 from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
     backup_path,
     cleanup_docker,
     create_minimal_compose_dir,
@@ -66,8 +68,8 @@ class TestE2ESeedStarAndDbEntriesBackupPostgres(unittest.TestCase):
                 "-e",
                 f"POSTGRES_PASSWORD={cls.pg_password}",
                 "-v",
-                f"{cls.db_volume}:/var/lib/postgresql/data",
+                f"{cls.db_volume}:{POSTGRES_DATA_DIR}",
-                "postgres:16-alpine",
+                POSTGRES_IMAGE,
             ]
         )
         wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
@@ -165,10 +167,7 @@ class TestE2ESeedStarAndDbEntriesBackupPostgres(unittest.TestCase):
             "--database-containers",
             cls.pg_container,
             "--images-no-stop-required",
-            "alpine",
+            POSTGRES_IMAGE,
-            "postgres",
-            "mariadb",
-            "mysql",
             "--dump-only-sql",
             "--backups-dir",
             cls.backups_dir,

tests/unit/backup/test_compose.py

@@ -279,15 +279,15 @@ class HardRestartArgTests(unittest.TestCase):
 
     def test_default_is_empty(self) -> None:
         args = self._parse([])
-        self.assertEqual(args.hard_compose_restart, [])
+        self.assertEqual(args.hard_restart_projects, [])
 
     def test_empty_flag_stays_empty(self) -> None:
-        args = self._parse(["--hard-compose-restart"])
+        args = self._parse(["--hard-restart-projects"])
-        self.assertEqual(args.hard_compose_restart, [])
+        self.assertEqual(args.hard_restart_projects, [])
 
     def test_explicit_names_preserved(self) -> None:
-        args = self._parse(["--hard-compose-restart", "mailu", "foo"])
+        args = self._parse(["--hard-restart-projects", "mailu", "foo"])
-        self.assertEqual(args.hard_compose_restart, ["mailu", "foo"])
+        self.assertEqual(args.hard_restart_projects, ["mailu", "foo"])
 
     def test_backups_dir_is_required(self) -> None:
         import sys

tests/unit/test_backup.py

@@ -10,13 +10,12 @@ class TestRequiresStop(unittest.TestCase):
     def test_requires_stop_false_when_all_images_are_whitelisted(
         self, mock_get_image_info, _mock_is_swarm_task
     ):
-        # All containers use images containing allowed substrings
         mock_get_image_info.side_effect = [
             "repo/mastodon:v4",
             "repo/wordpress:latest",
         ]
         containers = ["c1", "c2"]
-        whitelist = ["mastodon", "wordpress"]
+        whitelist = ["repo/mastodon:v4", "repo/wordpress:latest"]
         self.assertFalse(requires_stop(containers, whitelist))
 
     @patch("baudolo.backup.app.get_image_info")
@@ -28,9 +27,17 @@ class TestRequiresStop(unittest.TestCase):
             "repo/nginx:latest",
         ]
         containers = ["c1", "c2"]
-        whitelist = ["mastodon", "wordpress"]
+        whitelist = ["repo/mastodon:v4", "repo/wordpress:latest"]
         self.assertTrue(requires_stop(containers, whitelist))
 
+    @patch("baudolo.backup.app.get_image_info")
+    def test_requires_stop_true_on_substring_only_match(
+        self, mock_get_image_info, _mock_is_swarm_task
+    ):
+        mock_get_image_info.return_value = "reg:5000/repo/mastodon:v4"
+        self.assertTrue(requires_stop(["c1"], ["mastodon"]))
+        self.assertTrue(requires_stop(["c1"], ["repo/mastodon:v4"]))
+
     @patch("baudolo.backup.app.get_image_info")
     def test_requires_stop_true_when_whitelist_empty(
         self, mock_get_image_info, _mock_is_swarm_task