PyHardLinkBackup 1.7.2__tar.gz → 1.8.0__tar.gz

{pyhardlinkbackup-1.7.2 → pyhardlinkbackup-1.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyHardLinkBackup
-Version: 1.7.2
+Version: 1.8.0
 Summary: HardLink/Deduplication Backups with Python
 Project-URL: Documentation, https://github.com/jedie/PyHardLinkBackup
 Project-URL: Source, https://github.com/jedie/PyHardLinkBackup
@@ -35,6 +35,8 @@ Some aspects:
 Limitations:
 
 - Requires a filesystem that supports hardlinks (e.g., btrfs, zfs, ext4, APFS, NTFS with limitations).
+- Empty directories are not backed up.
+
 
 ## installation
 
@@ -64,19 +66,23 @@ usage: phlb backup [-h] [BACKUP OPTIONS]
 
 Backup the source directory to the destination directory using hard links for deduplication.
 
-╭─ positional arguments ──────────────────────────────────────────────────────────────────────────────────────╮
-│ source       Source directory to back up. (required)                                                        │
-│ destination  Destination directory for the backup. (required)                                               │
-╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
-╭─ options ───────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ -h, --help   show this help message and exit                                                                │
-│ --excludes [STR [STR ...]]                                                                                  │
-│              List of directories to exclude from backup. (default: __pycache__ .cache .temp .tmp .tox .nox) │
-│ --verbosity {debug,info,warning,error}                                                                      │
-│              Log level for console logging. (default: warning)                                              │
-│ --log-file-level {debug,info,warning,error}                                                                 │
-│              Log level for the log file (default: info)                                                     │
-╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+╭─ positional arguments ───────────────────────────────────────────────────────────────────────────────────────────────╮
+│ source             Source directory to back up. (required)                                                           │
+│ destination        Destination directory for the backup. (required)                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+╭─ options ────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+│ -h, --help         show this help message and exit                                                                   │
+│ --name {None}|STR  Optional name for the backup (used to create a subdirectory in the backup destination). If not    │
+│                    provided, the name of the source directory is used. (default: None)                               │
+│ --one-file-system, --no-one-file-system                                                                              │
+│                    Do not cross filesystem boundaries. (default: True)                                               │
+│ --excludes [STR [STR ...]]                                                                                           │
+│                    List of directories to exclude from backup. (default: __pycache__ .cache .temp .tmp .tox .nox)    │
+│ --verbosity {debug,info,warning,error}                                                                               │
+│                    Log level for console logging. (default: warning)                                                 │
+│ --log-file-level {debug,info,warning,error}                                                                          │
+│                    Log level for the log file (default: info)                                                        │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
 ```
 [comment]: <> (✂✂✂ auto generated backup help end ✂✂✂)
 
@@ -283,10 +289,20 @@ Overview of main changes:
 
 [comment]: <> (✂✂✂ auto generated history start ✂✂✂)
 
+* [v1.8.0](https://github.com/jedie/PyHardLinkBackup/compare/v1.7.3...v1.8.0)
+  * 2026-01-22 - Add optional "--name" to enforce a name for the backup sub directory
+  * 2026-01-22 - Do not cross filesystem boundaries as default
+  * 2026-01-22 - Display progress also for large unique file copy
+  * 2026-01-22 - Optimize progress bars for smaller screens
+* [v1.7.3](https://github.com/jedie/PyHardLinkBackup/compare/v1.7.2...v1.7.3)
+  * 2026-01-21 - Handle directory symlinks correct
 * [v1.7.2](https://github.com/jedie/PyHardLinkBackup/compare/v1.7.1...v1.7.2)
   * 2026-01-21 - Display "Remaining time" to files and sizes, too.
 * [v1.7.1](https://github.com/jedie/PyHardLinkBackup/compare/v1.7.0...v1.7.1)
   * 2026-01-19 - Update requirements to fix problems under Windows
+
+<details><summary>Expand older history entries ...</summary>
+
 * [v1.7.0](https://github.com/jedie/PyHardLinkBackup/compare/v1.6.0...v1.7.0)
   * 2026-01-19 - Speedup and enhance unittest
   * 2026-01-17 - Remove unfinished copied files on errors
@@ -300,9 +316,6 @@ Overview of main changes:
   * 2026-01-17 - Fix flaky test, because of terminal size
   * 2026-01-17 - Bugfix: Don't hash new large files twice
   * 2026-01-17 - Use compare also in backup tests
-
-<details><summary>Expand older history entries ...</summary>
-
 * [v1.5.0](https://github.com/jedie/PyHardLinkBackup/compare/v1.4.1...v1.5.0)
   * 2026-01-17 - NEW: Compare command to verify source tree with last backup
 * [v1.4.1](https://github.com/jedie/PyHardLinkBackup/compare/v1.4.0...v1.4.1)

{pyhardlinkbackup-1.7.2 → pyhardlinkbackup-1.8.0}/PyHardLinkBackup/__init__.py

@@ -3,5 +3,5 @@
 """
 
 # See https://packaging.python.org/en/latest/specifications/version-specifiers/
-__version__ = '1.7.2'
+__version__ = '1.8.0'
 __author__ = 'Jens Diemer <PyHardLinkBackup@jensdiemer.de>'

{pyhardlinkbackup-1.7.2 → pyhardlinkbackup-1.8.0}/PyHardLinkBackup/backup.py

@@ -16,11 +16,13 @@ from PyHardLinkBackup.utilities.file_size_database import FileSizeDatabase
 from PyHardLinkBackup.utilities.filesystem import (
     RemoveFileOnError,
     copy_and_hash,
+    copy_with_progress,
     hash_file,
     humanized_fs_scan,
     iter_scandir_files,
     read_and_hash_file,
     supports_hardlinks,
+    verbose_path_stat,
 )
 from PyHardLinkBackup.utilities.humanize import PrintTimingContextManager, human_filesize
 from PyHardLinkBackup.utilities.rich_utils import DisplayFileTreeProgress
@@ -52,6 +54,16 @@ class BackupResult:
     error_count: int = 0
 
 
+def copy_symlink(src_path: Path, dst_path: Path) -> None:
+    """
+    Copy file and directory symlinks.
+    """
+    target_is_directory = src_path.is_dir()
+    logger.debug('Copy symlink: %s to %s (is directory: %r)', src_path, dst_path, target_is_directory)
+    target = os.readlink(src_path)
+    dst_path.symlink_to(target, target_is_directory=target_is_directory)
+
+
 def backup_one_file(
     *,
     src_root: Path,
@@ -74,8 +86,7 @@ def backup_one_file(
         size = entry.stat().st_size
     except FileNotFoundError as err:
         logger.warning(f'Broken symlink {src_path}: {err.__class__.__name__}: {err}')
-        target = os.readlink(src_path)
-        dst_path.symlink_to(target)
+        copy_symlink(src_path, dst_path)
         backup_result.symlink_files += 1
         return
 
@@ -88,9 +99,7 @@ def backup_one_file(
         return
 
     if entry.is_symlink():
-        logger.debug('Copy symlink: %s to %s', src_path, dst_path)
-        target = os.readlink(src_path)
-        dst_path.symlink_to(target)
+        copy_symlink(src_path, dst_path)
         backup_result.symlink_files += 1
         return
 
@@ -141,7 +150,7 @@ def backup_one_file(
                     backup_result.hardlinked_size += size
                 else:
                     logger.info('Copy unique file: %s to %s', src_path, dst_path)
-                    shutil.copyfile(src_path, dst_path)
+                    copy_with_progress(src_path, dst_path, progress=progress, total_size=size)
                     hash_db[file_hash] = dst_path
                     backup_result.copied_files += 1
                     backup_result.copied_size += size
@@ -163,6 +172,8 @@ def backup_tree(
     *,
     src_root: Path,
     backup_root: Path,
+    backup_name: str | None,
+    one_file_system: bool,
     excludes: tuple[str, ...],
     log_manager: LoggingManager,
 ) -> BackupResult:
@@ -172,12 +183,17 @@ def backup_tree(
         print(f'Please check source directory: "{src_root}"\n')
         sys.exit(1)
 
+    src_stat = verbose_path_stat(src_root)
+    src_device_id = src_stat.st_dev
+
     backup_root = backup_root.resolve()
     if not backup_root.is_dir():
         print('Error: Backup directory does not exist!')
         print(f'Please create "{backup_root}" directory first and start again!\n')
         sys.exit(1)
 
+    verbose_path_stat(backup_root)
+
     if not os.access(backup_root, os.W_OK):
         print('Error: No write access to backup directory!')
         print(f'Please check permissions for backup directory: "{backup_root}"\n')
@@ -191,13 +207,20 @@ def backup_tree(
     # Step 1: Scan source directory:
     excludes: set = set(excludes)
     with PrintTimingContextManager('Filesystem scan completed in'):
-        src_file_count, src_total_size = humanized_fs_scan(src_root, excludes=excludes)
+        src_file_count, src_total_size = humanized_fs_scan(
+            path=src_root,
+            one_file_system=one_file_system,
+            src_device_id=src_device_id,
+            excludes=excludes,
+        )
 
     phlb_conf_dir = backup_root / '.phlb'
     phlb_conf_dir.mkdir(parents=False, exist_ok=True)
 
     timestamp = datetime.datetime.now().strftime('%Y-%m-%d-%H%M%S')
-    backup_main_dir = backup_root / src_root.name
+    if not backup_name:
+        backup_name = src_root.name
+    backup_main_dir = backup_root / backup_name
     backup_dir = backup_main_dir / timestamp
     backup_dir.mkdir(parents=True, exist_ok=False)
 
@@ -220,7 +243,12 @@ def backup_tree(
         backup_result = BackupResult(backup_dir=backup_dir, log_file=log_file)
 
         next_update = 0
-        for entry in iter_scandir_files(src_root, excludes=excludes):
+        for entry in iter_scandir_files(
+            path=src_root,
+            one_file_system=one_file_system,
+            src_device_id=src_device_id,
+            excludes=excludes,
+        ):
             try:
                 backup_one_file(
                     src_root=src_root,

{pyhardlinkbackup-1.7.2 → pyhardlinkbackup-1.8.0}/PyHardLinkBackup/cli_app/phlb.py

@@ -17,7 +17,9 @@ from PyHardLinkBackup.logging_setup import (
 )
 from PyHardLinkBackup.utilities.tyro_cli_shared_args import (
     DEFAULT_EXCLUDE_DIRECTORIES,
+    TyroBackupNameArgType,
     TyroExcludeDirectoriesArgType,
+    TyroOneFileSystemArgType,
 )
 
 
@@ -41,6 +43,8 @@ def backup(
         ),
     ],
     /,
+    name: TyroBackupNameArgType = None,
+    one_file_system: TyroOneFileSystemArgType = True,
     excludes: TyroExcludeDirectoriesArgType = DEFAULT_EXCLUDE_DIRECTORIES,
     verbosity: TyroConsoleLogLevelArgType = DEFAULT_CONSOLE_LOG_LEVEL,
     log_file_level: TyroLogFileLevelArgType = DEFAULT_LOG_FILE_LEVEL,
@@ -55,6 +59,8 @@ def backup(
     backup_tree(
         src_root=src,
         backup_root=dst,
+        backup_name=name,
+        one_file_system=one_file_system,
         excludes=excludes,
         log_manager=log_manager,
     )
@@ -77,6 +83,7 @@ def compare(
         ),
     ],
     /,
+    one_file_system: TyroOneFileSystemArgType = True,
     excludes: TyroExcludeDirectoriesArgType = DEFAULT_EXCLUDE_DIRECTORIES,
     verbosity: TyroConsoleLogLevelArgType = DEFAULT_CONSOLE_LOG_LEVEL,
     log_file_level: TyroLogFileLevelArgType = DEFAULT_LOG_FILE_LEVEL,
@@ -91,6 +98,7 @@ def compare(
     compare_backup.compare_tree(
         src_root=src,
         backup_root=dst,
+        one_file_system=one_file_system,
         excludes=excludes,
         log_manager=log_manager,
     )

{pyhardlinkbackup-1.7.2 → pyhardlinkbackup-1.8.0}/PyHardLinkBackup/compare_backup.py

@@ -15,6 +15,7 @@ from PyHardLinkBackup.utilities.filesystem import (
     hash_file,
     humanized_fs_scan,
     iter_scandir_files,
+    verbose_path_stat,
 )
 from PyHardLinkBackup.utilities.humanize import PrintTimingContextManager, human_filesize
 from PyHardLinkBackup.utilities.rich_utils import DisplayFileTreeProgress
@@ -55,13 +56,21 @@ def compare_one_file(
     compare_result: CompareResult,
     progress: DisplayFileTreeProgress,
 ) -> None:
-    src_size = entry.stat().st_size
+    if entry.is_file():
+        # For the progress bars:
+        compare_result.total_file_count += 1
+
+    try:
+        src_size = entry.stat().st_size
+    except FileNotFoundError as err:
+        logger.warning(f'Broken symlink {entry.path}: {err.__class__.__name__}: {err}')
+        return
 
     # For the progress bars:
-    compare_result.total_file_count += 1
     compare_result.total_size += src_size
 
     src_path = Path(entry.path)
+
     dst_path = compare_dir / src_path.relative_to(src_root)
 
     if not dst_path.exists():
@@ -69,6 +78,24 @@ def compare_one_file(
         compare_result.src_file_new_count += 1
         return
 
+    if src_path.is_dir():
+        if not src_path.is_symlink():
+            raise RuntimeError(f'Internal error - Directory found: {src_path=}')
+
+        # compare directory symlink targets:
+        src_target = src_path.readlink()
+        dst_target = dst_path.readlink()
+        if src_target != dst_target:
+            logger.warning(
+                'Source directory symlink %s target %s differs from compare symlink %s target %s',
+                src_path,
+                src_target,
+                dst_path,
+                dst_target,
+            )
+            compare_result.error_count += 1
+        return
+
     dst_size = dst_path.stat().st_size
     if src_size != dst_size:
         logger.warning(
@@ -123,6 +150,7 @@ def compare_tree(
     *,
     src_root: Path,
     backup_root: Path,
+    one_file_system: bool,
     excludes: tuple[str, ...],
     log_manager: LoggingManager,
 ) -> CompareResult:
@@ -155,9 +183,16 @@ def compare_tree(
     log_file = compare_main_dir / f'{now_timestamp}-compare.log'
     log_manager.start_file_logging(log_file)
 
+    src_device_id = verbose_path_stat(src_root).st_dev
+
     excludes: set = set(excludes)
     with PrintTimingContextManager('Filesystem scan completed in'):
-        src_file_count, src_total_size = humanized_fs_scan(src_root, excludes=excludes)
+        src_file_count, src_total_size = humanized_fs_scan(
+            path=src_root,
+            one_file_system=one_file_system,
+            src_device_id=src_device_id,
+            excludes=excludes,
+        )
 
     with DisplayFileTreeProgress(
         description=f'Compare {src_root}...',
@@ -171,7 +206,12 @@ def compare_tree(
         compare_result = CompareResult(last_timestamp=last_timestamp, compare_dir=compare_dir, log_file=log_file)
 
         next_update = 0
-        for entry in iter_scandir_files(src_root, excludes=excludes):
+        for entry in iter_scandir_files(
+            path=src_root,
+            one_file_system=one_file_system,
+            src_device_id=src_device_id,
+            excludes=excludes,
+        ):
             try:
                 compare_one_file(
                     src_root=src_root,

{pyhardlinkbackup-1.7.2 → pyhardlinkbackup-1.8.0}/PyHardLinkBackup/rebuild_databases.py

@@ -113,7 +113,12 @@ def rebuild(
     log_manager.start_file_logging(log_file=backup_root / f'{timestamp}-rebuild.log')
 
     with PrintTimingContextManager('Filesystem scan completed in'):
-        file_count, total_size = humanized_fs_scan(backup_root, excludes={'.phlb'})
+        file_count, total_size = humanized_fs_scan(
+            path=backup_root,
+            one_file_system=False,
+            src_device_id=None,
+            excludes={'.phlb'},
+        )
 
         # We should ignore all files in the root backup directory itself
         # e.g.: Our *-summary.txt and *.log files
@@ -134,7 +139,12 @@ def rebuild(
         rebuild_result = RebuildResult()
 
         next_update = 0
-        for entry in iter_scandir_files(backup_root, excludes={'.phlb'}):
+        for entry in iter_scandir_files(
+            path=backup_root,
+            one_file_system=False,
+            src_device_id=None,
+            excludes={'.phlb'},
+        ):
             try:
                 rebuild_one_file(
                     backup_root=backup_root,