Apply snapshot path rewriting to excludes and patterns, not just source directories (#962).

Reviewed-on: https://projects.torsion.org/borgmatic-collective/borgmatic/pulls/964

NEWS

@@ -4,9 +4,15 @@
  * #960: Fix for archives storing relative source directory paths such that they contain the working
    directory.
  * #960: Fix the "spot" check to support relative source directory paths.
+ * #962: For the ZFS, Btrfs, and LVM hooks, perform path rewriting for excludes and patterns in
+   addition to the existing source directories rewriting.
+ * #962: Under the hood, merge all configured source directories, excludes, and patterns into a
+   unified temporary patterns file for passing to Borg. The borgmatic configuration options remain
+   unchanged.
  * #965: Fix a borgmatic runtime directory error when running the "spot" check with a database hook
    enabled.
  * Fix the "spot" check to no longer consider pipe files within an archive for file comparisons.
+ * Fix the "spot" check to have a nicer error when there are no source paths to compare.
  * Fix auto-excluding of special files (when databases are configured) to support relative source
    directory paths.
  * Drop support for Python 3.8, which has been end-of-lifed.

borgmatic/actions/check.py

@@ -367,14 +367,16 @@ def collect_spot_check_source_paths(
             borgmatic.hooks.dispatch.Hook_type.DATA_SOURCE,
         ).values()
     )
+    working_directory = borgmatic.config.paths.get_working_directory(config)
 
-    (create_flags, create_positional_arguments, pattern_file, exclude_file) = (
+    (create_flags, create_positional_arguments, pattern_file) = (
         borgmatic.borg.create.make_base_create_command(
             dry_run=True,
             repository_path=repository['path'],
             config=config,
-            source_directories=borgmatic.actions.create.process_source_directories(
-                config,
+            patterns=borgmatic.actions.create.process_patterns(
+                borgmatic.actions.create.collect_patterns(config),
+                working_directory,
             ),
             local_borg_version=local_borg_version,
             global_arguments=global_arguments,
@@ -627,6 +629,14 @@ def spot_check(
     )
     logger.debug(f'{log_prefix}: {len(archive_paths)} total archive paths for spot check')
 
+    if len(source_paths) == 0:
+        logger.debug(
+            f'{log_prefix}: Paths in latest archive but not source paths: {", ".join(set(archive_paths)) or "none"}'
+        )
+        raise ValueError(
+            'Spot check failed: There are no source paths to compare against the archive'
+        )
+
     # Calculate the percentage delta between the source paths count and the archive paths count, and
     # compare that delta to the configured count tolerance percentage.
     count_delta_percentage = abs(len(source_paths) - len(archive_paths)) / len(source_paths) * 100

borgmatic/actions/create.py

@@ -6,6 +6,7 @@ import pathlib
 
 import borgmatic.actions.json
 import borgmatic.borg.create
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 import borgmatic.config.validate
 import borgmatic.hooks.command
@@ -14,6 +15,80 @@ import borgmatic.hooks.dispatch
 logger = logging.getLogger(__name__)
 
 
+def parse_pattern(pattern_line):
+    '''
+    Given a Borg pattern as a string, parse it into a borgmatic.borg.pattern.Pattern instance and
+    return it.
+    '''
+    try:
+        (pattern_type, remainder) = pattern_line.split(' ', maxsplit=1)
+    except ValueError:
+        raise ValueError('Invalid pattern:', pattern_line)
+
+    try:
+        (pattern_style, path) = remainder.split(':', maxsplit=1)
+    except ValueError:
+        pattern_style = ''
+        path = remainder
+
+    return borgmatic.borg.pattern.Pattern(
+        path,
+        borgmatic.borg.pattern.Pattern_type(pattern_type),
+        borgmatic.borg.pattern.Pattern_style(pattern_style),
+    )
+
+
+def collect_patterns(config):
+    '''
+    Given a configuration dict, produce a single sequence of patterns comprised of the configured
+    source directories, patterns, excludes, pattern files, and exclude files.
+
+    The idea is that Borg has all these different ways of specifying includes, excludes, source
+    directories, etc., but we'd like to collapse them all down to one common format (patterns) for
+    ease of manipulation within borgmatic.
+    '''
+    try:
+        return (
+            tuple(
+                borgmatic.borg.pattern.Pattern(source_directory)
+                for source_directory in config.get('source_directories', ())
+            )
+            + tuple(
+                parse_pattern(pattern_line.strip())
+                for pattern_line in config.get('patterns', ())
+                if not pattern_line.lstrip().startswith('#')
+            )
+            + tuple(
+                borgmatic.borg.pattern.Pattern(
+                    exclude_line.strip(),
+                    borgmatic.borg.pattern.Pattern_type.EXCLUDE,
+                    borgmatic.borg.pattern.Pattern_style.FNMATCH,
+                )
+                for exclude_line in config.get('exclude_patterns', ())
+            )
+            + tuple(
+                parse_pattern(pattern_line.strip())
+                for filename in config.get('patterns_from', ())
+                for pattern_line in open(filename).readlines()
+                if not pattern_line.lstrip().startswith('#')
+            )
+            + tuple(
+                borgmatic.borg.pattern.Pattern(
+                    exclude_line.strip(),
+                    borgmatic.borg.pattern.Pattern_type.EXCLUDE,
+                    borgmatic.borg.pattern.Pattern_style.FNMATCH,
+                )
+                for filename in config.get('excludes_from', ())
+                for exclude_line in open(filename).readlines()
+                if not exclude_line.lstrip().startswith('#')
+            )
+        )
+    except (FileNotFoundError, OSError) as error:
+        logger.debug(error)
+
+        raise ValueError(f'Cannot read patterns_from/excludes_from file: {error.filename}')
+
+
 def expand_directory(directory, working_directory):
     '''
     Given a directory path, expand any tilde (representing a user's home directory) and any globs
@@ -25,141 +100,152 @@ def expand_directory(directory, working_directory):
 
     # This would be a lot easier to do with glob(..., root_dir=working_directory), but root_dir is
     # only available in Python 3.10+.
-    glob_paths = glob.glob(os.path.join(working_directory or '', expanded_directory))
+    normalized_directory = os.path.join(working_directory or '', expanded_directory)
+    glob_paths = glob.glob(normalized_directory)
 
     if not glob_paths:
         return [expanded_directory]
 
     working_directory_prefix = os.path.join(working_directory or '', '')
 
-    # Remove the working directory prefix that we added above in order to make glob() work.
     return [
-        # os.path.relpath() won't work here because it collapses any usage of Borg's slashdot hack.
-        glob_path.removeprefix(working_directory_prefix)
+        (
+            glob_path
+            # If these are equal, that means we didn't add any working directory prefix above.
+            if normalized_directory == expanded_directory
+            # Remove the working directory prefix that we added above in order to make glob() work.
+            # We can't use os.path.relpath() here because it collapses any use of Borg's slashdot
+            # hack.
+            else glob_path.removeprefix(working_directory_prefix)
+        )
         for glob_path in glob_paths
     ]
 
 
-def expand_directories(directories, working_directory=None):
+def expand_patterns(patterns, working_directory=None, skip_paths=None):
     '''
-    Given a sequence of directory paths and an optional working directory, expand tildes and globs
-    in each one. Return all the resulting directories as a single flattened tuple.
+    Given a sequence of borgmatic.borg.pattern.Pattern instances and an optional working directory,
+    expand tildes and globs in each root pattern. Return all the resulting patterns (not just the
+    root patterns) as a tuple.
+
+    If a set of paths are given to skip, then don't expand any patterns matching them.
     '''
-    if directories is None:
+    if patterns is None:
         return ()
 
     return tuple(
         itertools.chain.from_iterable(
-            expand_directory(directory, working_directory) for directory in directories
+            (
+                (
+                    borgmatic.borg.pattern.Pattern(
+                        expanded_path,
+                        pattern.type,
+                        pattern.style,
+                        pattern.device,
+                    )
+                    for expanded_path in expand_directory(pattern.path, working_directory)
+                )
+                if pattern.type == borgmatic.borg.pattern.Pattern_type.ROOT
+                and pattern.path not in (skip_paths or ())
+                else (pattern,)
+            )
+            for pattern in patterns
         )
     )
 
 
-def map_directories_to_devices(directories, working_directory=None):
+def device_map_patterns(patterns, working_directory=None):
     '''
-    Given a sequence of directories and an optional working directory, return a map from directory
-    to an identifier for the device on which that directory resides or None if the path doesn't
-    exist.
+    Given a sequence of borgmatic.borg.pattern.Pattern instances and an optional working directory,
+    determine the identifier for the device on which the pattern's path resides—or None if the path
+    doesn't exist or is from a non-root pattern. Return an updated sequence of patterns with the
+    device field populated. But if the device field is already set, don't bother setting it again.
 
-    This is handy for determining whether two different directories are on the same filesystem (have
-    the same device identifier).
+    This is handy for determining whether two different pattern paths are on the same filesystem
+    (have the same device identifier).
     '''
-    return {
-        directory: os.stat(full_directory).st_dev if os.path.exists(full_directory) else None
-        for directory in directories
-        for full_directory in (os.path.join(working_directory or '', directory),)
-    }
+    return tuple(
+        borgmatic.borg.pattern.Pattern(
+            pattern.path,
+            pattern.type,
+            pattern.style,
+            device=pattern.device
+            or (
+                os.stat(full_path).st_dev
+                if pattern.type == borgmatic.borg.pattern.Pattern_type.ROOT
+                and os.path.exists(full_path)
+                else None
+            ),
+        )
+        for pattern in patterns
+        for full_path in (os.path.join(working_directory or '', pattern.path),)
+    )
 
 
-def deduplicate_directories(directory_devices, additional_directory_devices):
+def deduplicate_patterns(patterns):
     '''
-    Given a map from directory to the identifier for the device on which that directory resides,
-    return the directories as a sorted sequence with all duplicate child directories removed. For
-    instance, if paths is ['/foo', '/foo/bar'], return just: ['/foo']
+    Given a sequence of borgmatic.borg.pattern.Pattern instances, return them with all duplicate
+    root child patterns removed. For instance, if two root patterns are given with paths "/foo" and
+    "/foo/bar", return just the one with "/foo". Non-root patterns are passed through without
+    modification.
 
-    The one exception to this rule is if two paths are on different filesystems (devices). In that
-    case, they won't get de-duplicated in case they both need to be passed to Borg (e.g. the
-    location.one_file_system option is true).
+    The one exception to deduplication is two paths are on different filesystems (devices). In that
+    case, they won't get deduplicated, in case they both need to be passed to Borg (e.g. the
+    one_file_system option is true).
 
-    The idea is that if Borg is given a parent directory, then it doesn't also need to be given
-    child directories, because it will naturally spider the contents of the parent directory. And
+    The idea is that if Borg is given a root parent pattern, then it doesn't also need to be given
+    child patterns, because it will naturally spider the contents of the parent pattern's path. And
     there are cases where Borg coming across the same file twice will result in duplicate reads and
     even hangs, e.g. when a database hook is using a named pipe for streaming database dumps to
     Borg.
-
-    If any additional directory devices are given, also deduplicate against them, but don't include
-    them in the returned directories.
     '''
-    deduplicated = set()
-    directories = sorted(directory_devices.keys())
-    additional_directories = sorted(additional_directory_devices.keys())
-    all_devices = {**directory_devices, **additional_directory_devices}
+    deduplicated = {}  # Use just the keys as an ordered set.
 
-    for directory in directories:
-        deduplicated.add(directory)
-        parents = pathlib.PurePath(directory).parents
+    for pattern in patterns:
+        if pattern.type != borgmatic.borg.pattern.Pattern_type.ROOT:
+            deduplicated[pattern] = True
+            continue
 
-        # If another directory in the given list (or the additional list) is a parent of current
-        # directory (even n levels up) and both are on the same filesystem, then the current
-        # directory is a duplicate.
-        for other_directory in directories + additional_directories:
-            for parent in parents:
-                if (
-                    pathlib.PurePath(other_directory) == parent
-                    and all_devices[directory] is not None
-                    and all_devices[other_directory] == all_devices[directory]
-                ):
-                    if directory in deduplicated:
-                        deduplicated.remove(directory)
-                    break
+        parents = pathlib.PurePath(pattern.path).parents
 
-    return sorted(deduplicated)
+        # If another directory in the given list is a parent of current directory (even n levels up)
+        # and both are on the same filesystem, then the current directory is a duplicate.
+        for other_pattern in patterns:
+            if other_pattern.type != borgmatic.borg.pattern.Pattern_type.ROOT:
+                continue
 
+            if any(
+                pathlib.PurePath(other_pattern.path) == parent
+                and pattern.device is not None
+                and other_pattern.device == pattern.device
+                for parent in parents
+            ):
+                break
+        else:
+            deduplicated[pattern] = True
 
-ROOT_PATTERN_PREFIX = 'R '
+    return tuple(deduplicated.keys())
 
 
-def pattern_root_directories(patterns=None):
+def process_patterns(patterns, working_directory, skip_expand_paths=None):
     '''
-    Given a sequence of patterns, parse out and return just the root directories.
-    '''
-    if not patterns:
-        return []
-
-    return [
-        pattern.split(ROOT_PATTERN_PREFIX, maxsplit=1)[1]
-        for pattern in patterns
-        if pattern.startswith(ROOT_PATTERN_PREFIX)
-    ]
-
-
-def process_source_directories(config, source_directories=None, skip_expand_paths=None):
-    '''
-    Given a sequence of source directories (either in the source_directories argument or, lacking
-    that, from config), expand and deduplicate the source directories, returning the result.
+    Given a sequence of Borg patterns and a configured working directory, expand and deduplicate any
+    "root" patterns, returning the resulting root and non-root patterns as a list.
 
     If any paths are given to skip, don't expand them.
     '''
-    working_directory = borgmatic.config.paths.get_working_directory(config)
     skip_paths = set(skip_expand_paths or ())
 
-    if source_directories is None:
-        source_directories = tuple(config.get('source_directories', ()))
-
-    return deduplicate_directories(
-        map_directories_to_devices(
-            expand_directories(
-                tuple(source for source in source_directories if source not in skip_paths),
-                working_directory=working_directory,
+    return list(
+        deduplicate_patterns(
+            device_map_patterns(
+                expand_patterns(
+                    patterns,
+                    working_directory=working_directory,
+                    skip_paths=skip_paths,
+                )
             )
-            + tuple(skip_paths)
-        ),
-        additional_directory_devices=map_directories_to_devices(
-            expand_directories(
-                pattern_root_directories(config.get('patterns')),
-                working_directory=working_directory,
-            )
-        ),
+        )
     )
 
 
@@ -197,6 +283,7 @@ def run_create(
 
     log_prefix = repository.get('label', repository['path'])
     logger.info(f'{log_prefix}: Creating archive{dry_run_label}')
+    working_directory = borgmatic.config.paths.get_working_directory(config)
 
     with borgmatic.config.paths.Runtime_directory(
         config, log_prefix
@@ -209,7 +296,7 @@ def run_create(
             borgmatic_runtime_directory,
             global_arguments.dry_run,
         )
-        source_directories = process_source_directories(config)
+        patterns = process_patterns(collect_patterns(config), working_directory)
         active_dumps = borgmatic.hooks.dispatch.call_hooks(
             'dump_data_sources',
             config,
@@ -217,23 +304,21 @@ def run_create(
             borgmatic.hooks.dispatch.Hook_type.DATA_SOURCE,
             config_paths,
             borgmatic_runtime_directory,
-            source_directories,
+            patterns,
             global_arguments.dry_run,
         )
 
-        # Process source directories again in case any data source hooks updated them. Without this
-        # step, we could end up with duplicate paths that cause Borg to hang when it tries to read
-        # from the same named pipe twice.
-        source_directories = process_source_directories(
-            config, source_directories, skip_expand_paths=config_paths
-        )
+        # Process the patterns again in case any data source hooks updated them. Without this step,
+        # we could end up with duplicate paths that cause Borg to hang when it tries to read from
+        # the same named pipe twice.
+        patterns = process_patterns(patterns, working_directory, skip_expand_paths=config_paths)
         stream_processes = [process for processes in active_dumps.values() for process in processes]
 
         json_output = borgmatic.borg.create.create_archive(
             global_arguments.dry_run,
             repository['path'],
             config,
-            source_directories,
+            patterns,
             local_borg_version,
             global_arguments,
             borgmatic_runtime_directory,

borgmatic/borg/create.py

@@ -6,6 +6,7 @@ import stat
 import tempfile
 import textwrap
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 import borgmatic.logger
 from borgmatic.borg import environment, feature, flags
@@ -19,81 +20,42 @@ from borgmatic.execute import (
 logger = logging.getLogger(__name__)
 
 
-def expand_home_directories(directories):
+def write_patterns_file(patterns, borgmatic_runtime_directory, log_prefix, patterns_file=None):
     '''
-    Given a sequence of directory paths, expand tildes in each one. Do not perform any globbing.
-    Return the results as a tuple.
-    '''
-    if directories is None:
-        return ()
-
-    return tuple(os.path.expanduser(directory) for directory in directories)
+    Given a sequence of patterns as borgmatic.borg.pattern.Pattern instances, write them to a named
+    temporary file in the given borgmatic runtime directory and return the file object so it can
+    continue to exist on disk as long as the caller needs it.
 
+    Use the given log prefix in any logging.
 
-def write_pattern_file(patterns=None, sources=None, pattern_file=None):
-    '''
-    Given a sequence of patterns and an optional sequence of source directories, write them to a
-    named temporary file (with the source directories as additional roots) and return the file.
-    If an optional open pattern file is given, overwrite it instead of making a new temporary file.
+    If an optional open pattern file is given, append to it instead of making a new temporary file.
     Return None if no patterns are provided.
     '''
-    if not patterns and not sources:
+    if not patterns:
         return None
 
-    if pattern_file is None:
-        pattern_file = tempfile.NamedTemporaryFile('w')
+    if patterns_file is None:
+        patterns_file = tempfile.NamedTemporaryFile('w', dir=borgmatic_runtime_directory)
     else:
-        pattern_file.seek(0)
+        patterns_file.write('\n')
 
-    pattern_file.write(
-        '\n'.join(tuple(patterns or ()) + tuple(f'R {source}' for source in (sources or [])))
+    patterns_output = '\n'.join(
+        f'{pattern.type.value} {pattern.style.value}{":" if pattern.style.value else ""}{pattern.path}'
+        for pattern in patterns
     )
-    pattern_file.flush()
-
-    return pattern_file
-
-
-def ensure_files_readable(*filename_lists):
-    '''
-    Given a sequence of filename sequences, ensure that each filename is openable. This prevents
-    unreadable files from being passed to Borg, which in certain situations only warns instead of
-    erroring.
-    '''
-    for file_object in itertools.chain.from_iterable(
-        filename_list for filename_list in filename_lists if filename_list
-    ):
-        open(file_object).close()
+    logger.debug(f'{log_prefix}: Writing patterns to {patterns_file.name}:\n{patterns_output}')
 
+    patterns_file.write(patterns_output)
+    patterns_file.flush()
 
-def make_pattern_flags(config, pattern_filename=None):
-    '''
-    Given a configuration dict with a potential patterns_from option, and a filename containing any
-    additional patterns, return the corresponding Borg flags for those files as a tuple.
-    '''
-    pattern_filenames = tuple(config.get('patterns_from') or ()) + (
-        (pattern_filename,) if pattern_filename else ()
-    )
-
-    return tuple(
-        itertools.chain.from_iterable(
-            ('--patterns-from', pattern_filename) for pattern_filename in pattern_filenames
-        )
-    )
+    return patterns_file
 
 
-def make_exclude_flags(config, exclude_filename=None):
+def make_exclude_flags(config):
     '''
-    Given a configuration dict with various exclude options, and a filename containing any exclude
-    patterns, return the corresponding Borg flags as a tuple.
+    Given a configuration dict with various exclude options, return the corresponding Borg flags as
+    a tuple.
     '''
-    exclude_filenames = tuple(config.get('exclude_from') or ()) + (
-        (exclude_filename,) if exclude_filename else ()
-    )
-    exclude_from_flags = tuple(
-        itertools.chain.from_iterable(
-            ('--exclude-from', exclude_filename) for exclude_filename in exclude_filenames
-        )
-    )
     caches_flag = ('--exclude-caches',) if config.get('exclude_caches') else ()
     if_present_flags = tuple(
         itertools.chain.from_iterable(
@@ -104,13 +66,7 @@ def make_exclude_flags(config, exclude_filename=None):
     keep_exclude_tags_flags = ('--keep-exclude-tags',) if config.get('keep_exclude_tags') else ()
     exclude_nodump_flags = ('--exclude-nodump',) if config.get('exclude_nodump') else ()
 
-    return (
-        exclude_from_flags
-        + caches_flag
-        + if_present_flags
-        + keep_exclude_tags_flags
-        + exclude_nodump_flags
-    )
+    return caches_flag + if_present_flags + keep_exclude_tags_flags + exclude_nodump_flags
 
 
 def make_list_filter_flags(local_borg_version, dry_run):
@@ -215,18 +171,22 @@ def collect_special_file_paths(
     )
 
 
-def check_all_source_directories_exist(source_directories):
+def check_all_root_patterns_exist(patterns):
     '''
-    Given a sequence of source directories, check that the source directories all exist. If any do
-    not, raise an exception.
+    Given a sequence of borgmatic.borg.pattern.Pattern instances, check that all root pattern
+    paths exist. If any don't, raise an exception.
     '''
-    missing_directories = [
-        source_directory
-        for source_directory in source_directories
-        if not os.path.exists(source_directory)
+    missing_paths = [
+        pattern.path
+        for pattern in patterns
+        if pattern.type == borgmatic.borg.pattern.Pattern_type.ROOT
+        if not os.path.exists(pattern.path)
     ]
-    if missing_directories:
-        raise ValueError(f"Source directories do not exist: {', '.join(missing_directories)}")
+
+    if missing_paths:
+        raise ValueError(
+            f"Source directories / root pattern paths do not exist: {', '.join(missing_paths)}"
+        )
 
 
 MAX_SPECIAL_FILE_PATHS_LENGTH = 1000
@@ -236,7 +196,7 @@ def make_base_create_command(
     dry_run,
     repository_path,
     config,
-    source_directories,
+    patterns,
     local_borg_version,
     global_arguments,
     borgmatic_runtime_directory,
@@ -248,23 +208,18 @@ def make_base_create_command(
     stream_processes=None,
 ):
     '''
-    Given vebosity/dry-run flags, a local or remote repository path, a configuration dict, a
-    sequence of loaded configuration paths, the local Borg version, global arguments as an
-    argparse.Namespace instance, and a sequence of borgmatic source directories, return a tuple of
-    (base Borg create command flags, Borg create command positional arguments, open pattern file
-    handle, open exclude file handle).
+    Given verbosity/dry-run flags, a local or remote repository path, a configuration dict, a
+    sequence of patterns as borgmatic.borg.pattern.Pattern instances, the local Borg version,
+    global arguments as an argparse.Namespace instance, and a sequence of borgmatic source
+    directories, return a tuple of (base Borg create command flags, Borg create command positional
+    arguments, open pattern file handle).
     '''
     if config.get('source_directories_must_exist', False):
-        check_all_source_directories_exist(source_directories)
-
-    ensure_files_readable(config.get('patterns_from'), config.get('exclude_from'))
+        check_all_root_patterns_exist(patterns)
 
-    pattern_file = (
-        write_pattern_file(config.get('patterns'), source_directories)
-        if config.get('patterns') or config.get('patterns_from')
-        else None
+    patterns_file = write_patterns_file(
+        patterns, borgmatic_runtime_directory, log_prefix=repository_path
     )
-    exclude_file = write_pattern_file(expand_home_directories(config.get('exclude_patterns')))
     checkpoint_interval = config.get('checkpoint_interval', None)
     checkpoint_volume = config.get('checkpoint_volume', None)
     chunker_params = config.get('chunker_params', None)
@@ -307,8 +262,8 @@ def make_base_create_command(
     create_flags = (
         tuple(local_path.split(' '))
         + ('create',)
-        + make_pattern_flags(config, pattern_file.name if pattern_file else None)
-        + make_exclude_flags(config, exclude_file.name if exclude_file else None)
+        + (('--patterns-from', patterns_file.name) if patterns_file else ())
+        + make_exclude_flags(config)
         + (('--checkpoint-interval', str(checkpoint_interval)) if checkpoint_interval else ())
         + (('--checkpoint-volume', str(checkpoint_volume)) if checkpoint_volume else ())
         + (('--chunker-params', chunker_params) if chunker_params else ())
@@ -338,7 +293,7 @@ def make_base_create_command(
 
     create_positional_arguments = flags.make_repository_archive_flags(
         repository_path, archive_name_format, local_borg_version
-    ) + (tuple(source_directories) if not pattern_file else ())
+    )
 
     # If database hooks are enabled (as indicated by streaming processes), exclude files that might
     # cause Borg to hang. But skip this if the user has explicitly set the "read_special" to True.
@@ -369,22 +324,31 @@ def make_base_create_command(
             logger.warning(
                 f'{repository_path}: Excluding special files to prevent Borg from hanging: {truncated_special_file_paths}'
             )
-            exclude_file = write_pattern_file(
-                expand_home_directories(
-                    tuple(config.get('exclude_patterns') or ()) + special_file_paths
+            patterns_file = write_patterns_file(
+                tuple(
+                    borgmatic.borg.pattern.Pattern(
+                        special_file_path,
+                        borgmatic.borg.pattern.Pattern_type.EXCLUDE,
+                        borgmatic.borg.pattern.Pattern_style.FNMATCH,
+                    )
+                    for special_file_path in special_file_paths
                 ),
-                pattern_file=exclude_file,
+                borgmatic_runtime_directory,
+                log_prefix=repository_path,
+                patterns_file=patterns_file,
             )
-            create_flags += make_exclude_flags(config, exclude_file.name)
 
-    return (create_flags, create_positional_arguments, pattern_file, exclude_file)
+            if '--patterns-from' not in create_flags:
+                create_flags += ('--patterns-from', patterns_file.name)
+
+    return (create_flags, create_positional_arguments, patterns_file)
 
 
 def create_archive(
     dry_run,
     repository_path,
     config,
-    source_directories,
+    patterns,
     local_borg_version,
     global_arguments,
     borgmatic_runtime_directory,
@@ -397,7 +361,7 @@ def create_archive(
     stream_processes=None,
 ):
     '''
-    Given vebosity/dry-run flags, a local or remote repository path, a configuration dict, a
+    Given verbosity/dry-run flags, a local or remote repository path, a configuration dict, a
     sequence of loaded configuration paths, the local Borg version, and global arguments as an
     argparse.Namespace instance, create a Borg archive and return Borg's JSON output (if any).
 
@@ -408,22 +372,20 @@ def create_archive(
 
     working_directory = borgmatic.config.paths.get_working_directory(config)
 
-    (create_flags, create_positional_arguments, pattern_file, exclude_file) = (
-        make_base_create_command(
-            dry_run,
-            repository_path,
-            config,
-            source_directories,
-            local_borg_version,
-            global_arguments,
-            borgmatic_runtime_directory,
-            local_path,
-            remote_path,
-            progress,
-            json,
-            list_files,
-            stream_processes,
-        )
+    (create_flags, create_positional_arguments, patterns_file) = make_base_create_command(
+        dry_run,
+        repository_path,
+        config,
+        patterns,
+        local_borg_version,
+        global_arguments,
+        borgmatic_runtime_directory,
+        local_path,
+        remote_path,
+        progress,
+        json,
+        list_files,
+        stream_processes,
     )
 
     if json:

borgmatic/borg/pattern.py

@@ -0,0 +1,31 @@
+import collections
+import enum
+
+
+# See https://borgbackup.readthedocs.io/en/stable/usage/help.html#borg-help-patterns
+class Pattern_type(enum.Enum):
+    ROOT = 'R'  # A ROOT pattern always has a NONE pattern style.
+    PATTERN_STYLE = 'P'
+    EXCLUDE = '-'
+    NO_RECURSE = '!'
+    INCLUDE = '+'
+
+
+class Pattern_style(enum.Enum):
+    NONE = ''
+    FNMATCH = 'fm'
+    SHELL = 'sh'
+    REGULAR_EXPRESSION = 're'
+    PATH_PREFIX = 'pp'
+    PATH_FULL_MATCH = 'pf'
+
+
+Pattern = collections.namedtuple(
+    'Pattern',
+    ('path', 'type', 'style', 'device'),
+    defaults=(
+        Pattern_type.ROOT,
+        Pattern_style.NONE,
+        None,
+    ),
+)

borgmatic/config/schema.yaml

@@ -131,8 +131,7 @@ properties:
             Any paths matching these patterns are included/excluded from
             backups. Globs are expanded. (Tildes are not.) See the output of
             "borg help patterns" for more details. Quote any value if it
-            contains leading punctuation, so it parses correctly. Note that only
-            one of "patterns" and "source_directories" may be used.
+            contains leading punctuation, so it parses correctly.
         example:
             - 'R /'
             - '- /home/*/.cache'
@@ -144,9 +143,8 @@ properties:
             type: string
         description: |
             Read include/exclude patterns from one or more separate named files,
-            one pattern per line. Note that Borg considers this option
-            experimental. See the output of "borg help patterns" for more
-            details.
+            one pattern per line. See the output of "borg help patterns" for
+            more details.
         example:
             - /etc/borgmatic/patterns
     exclude_patterns:
@@ -230,8 +228,8 @@ properties:
     source_directories_must_exist:
         type: boolean
         description: |
-            If true, then source directories must exist, otherwise an error is
-            raised. Defaults to false.
+            If true, then source directories (and root pattern paths) must
+            exist. If they don't, an error is raised. Defaults to false.
         example: true
     encryption_passcommand:
         type: string

borgmatic/hooks/data_source/bootstrap.py

@@ -4,6 +4,7 @@ import json
 import logging
 import os
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 
 logger = logging.getLogger(__name__)
@@ -22,15 +23,15 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
     Given a bootstrap configuration dict, a configuration dict, a log prefix, the borgmatic
-    configuration file paths, the borgmatic runtime directory, the configured source directories,
-    and whether this is a dry run, create a borgmatic manifest file to store the paths of the
-    configuration files used to create the archive. But skip this if the bootstrap
-    store_config_files option is False or if this is a dry run.
+    configuration file paths, the borgmatic runtime directory, the configured patterns, and whether
+    this is a dry run, create a borgmatic manifest file to store the paths of the configuration
+    files used to create the archive. But skip this if the bootstrap store_config_files option is
+    False or if this is a dry run.
 
     Return an empty sequence, since there are no ongoing dump processes from this hook.
     '''
@@ -55,8 +56,10 @@ def dump_data_sources(
             manifest_file,
         )
 
-    source_directories.extend(config_paths)
-    source_directories.append(os.path.join(borgmatic_runtime_directory, 'bootstrap'))
+    patterns.extend(borgmatic.borg.pattern.Pattern(config_path) for config_path in config_paths)
+    patterns.append(
+        borgmatic.borg.pattern.Pattern(os.path.join(borgmatic_runtime_directory, 'bootstrap'))
+    )
 
     return []
 

borgmatic/hooks/data_source/btrfs.py

@@ -6,6 +6,7 @@ import os
 import shutil
 import subprocess
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 import borgmatic.execute
 import borgmatic.hooks.data_source.snapshot
@@ -72,41 +73,39 @@ def get_subvolumes_for_filesystem(btrfs_command, filesystem_mount_point):
     )
 
 
-Subvolume = collections.namedtuple(
-    'Subvolume', ('path', 'contained_source_directories'), defaults=((),)
-)
+Subvolume = collections.namedtuple('Subvolume', ('path', 'contained_patterns'), defaults=((),))
 
 
-def get_subvolumes(btrfs_command, findmnt_command, source_directories=None):
+def get_subvolumes(btrfs_command, findmnt_command, patterns=None):
     '''
-    Given a Btrfs command to run and a sequence of configured source directories, find the
-    intersection between the current Btrfs filesystem and subvolume mount points and the configured
-    borgmatic source directories. The idea is that these are the requested subvolumes to snapshot.
+    Given a Btrfs command to run and a sequence of configured patterns, find the intersection
+    between the current Btrfs filesystem and subvolume mount points and the paths of any patterns.
+    The idea is that these pattern paths represent the requested subvolumes to snapshot.
 
-    If the source directories is None, then return all subvolumes, sorted by path.
+    If patterns is None, then return all subvolumes, sorted by path.
 
     Return the result as a sequence of matching subvolume mount points.
     '''
-    candidate_source_directories = set(source_directories or ())
+    candidate_patterns = set(patterns or ())
     subvolumes = []
 
-    # For each filesystem mount point, find its subvolumes and match them against the given source
-    # directories to find the subvolumes to backup. And within this loop, sort the subvolumes from
-    # longest to shortest mount points, so longer mount points get a whack at the candidate source
-    # directory piñata before their parents do. (Source directories are consumed during this
-    # process, so no two datasets get the same contained source directories.)
+    # For each filesystem mount point, find its subvolumes and match them against the given patterns
+    # to find the subvolumes to backup. And within this loop, sort the subvolumes from longest to
+    # shortest mount points, so longer mount points get a whack at the candidate pattern piñata
+    # before their parents do. (Patterns are consumed during this process, so no two subvolumes end
+    # up with the same contained patterns.)
     for mount_point in get_filesystem_mount_points(findmnt_command):
         subvolumes.extend(
-            Subvolume(subvolume_path, contained_source_directories)
+            Subvolume(subvolume_path, contained_patterns)
             for subvolume_path in reversed(
                 get_subvolumes_for_filesystem(btrfs_command, mount_point)
             )
-            for contained_source_directories in (
-                borgmatic.hooks.data_source.snapshot.get_contained_directories(
-                    subvolume_path, candidate_source_directories
+            for contained_patterns in (
+                borgmatic.hooks.data_source.snapshot.get_contained_patterns(
+                    subvolume_path, candidate_patterns
                 ),
             )
-            if source_directories is None or contained_source_directories
+            if patterns is None or contained_patterns
         )
 
     return tuple(sorted(subvolumes, key=lambda subvolume: subvolume.path))
@@ -126,13 +125,13 @@ def make_snapshot_path(subvolume_path):
     ) + subvolume_path.rstrip(os.path.sep)
 
 
-def make_snapshot_exclude_path(subvolume_path):  # pragma: no cover
+def make_snapshot_exclude_pattern(subvolume_path):  # pragma: no cover
     '''
-    Given the path to a subvolume, make a corresponding exclude path for its embedded snapshot path.
-    This is to work around a quirk of Btrfs: If you make a snapshot path as a child directory of a
-    subvolume, then the snapshot's own initial directory component shows up as an empty directory
-    within the snapshot itself. For instance, if you have a Btrfs subvolume at /mnt and make a
-    snapshot of it at:
+    Given the path to a subvolume, make a corresponding exclude pattern for its embedded snapshot
+    path. This is to work around a quirk of Btrfs: If you make a snapshot path as a child directory
+    of a subvolume, then the snapshot's own initial directory component shows up as an empty
+    directory within the snapshot itself. For instance, if you have a Btrfs subvolume at /mnt and
+    make a snapshot of it at:
 
         /mnt/.borgmatic-snapshot-1234/mnt
 
@@ -140,30 +139,52 @@ def make_snapshot_exclude_path(subvolume_path):  # pragma: no cover
 
         /mnt/.borgmatic-snapshot-1234/mnt/.borgmatic-snapshot-1234
 
-    So to prevent that from ending up in the Borg archive, this function produces its path for
-    exclusion.
+    So to prevent that from ending up in the Borg archive, this function produces an exclude pattern
+    to exclude that path.
     '''
     snapshot_directory = f'{BORGMATIC_SNAPSHOT_PREFIX}{os.getpid()}'
 
-    return os.path.join(
-        subvolume_path,
-        snapshot_directory,
-        subvolume_path.lstrip(os.path.sep),
-        snapshot_directory,
+    return borgmatic.borg.pattern.Pattern(
+        os.path.join(
+            subvolume_path,
+            snapshot_directory,
+            subvolume_path.lstrip(os.path.sep),
+            snapshot_directory,
+        ),
+        borgmatic.borg.pattern.Pattern_type.EXCLUDE,
+        borgmatic.borg.pattern.Pattern_style.FNMATCH,
     )
 
 
-def make_borg_source_directory_path(subvolume_path, source_directory):
+def make_borg_snapshot_pattern(subvolume_path, pattern):
     '''
-    Given the path to a subvolume and a source directory inside it, make a corresponding path for
-    the source directory within a snapshot path intended for giving to Borg.
+    Given the path to a subvolume and a pattern as a borgmatic.borg.pattern.Pattern instance whose
+    path is inside the subvolume, return a new Pattern with its path rewritten to be in a snapshot
+    path intended for giving to Borg.
+
+    Move any initial caret in a regular expression pattern path to the beginning, so as not to break
+    the regular expression.
     '''
-    return os.path.join(
+    initial_caret = (
+        '^'
+        if pattern.style == borgmatic.borg.pattern.Pattern_style.REGULAR_EXPRESSION
+        and pattern.path.startswith('^')
+        else ''
+    )
+
+    rewritten_path = initial_caret + os.path.join(
         subvolume_path,
         f'{BORGMATIC_SNAPSHOT_PREFIX}{os.getpid()}',
         '.',  # Borg 1.4+ "slashdot" hack.
         # Included so that the source directory ends up in the Borg archive at its "original" path.
-        source_directory.lstrip(os.path.sep),
+        pattern.path.lstrip('^').lstrip(os.path.sep),
+    )
+
+    return borgmatic.borg.pattern.Pattern(
+        rewritten_path,
+        pattern.type,
+        pattern.style,
+        pattern.device,
     )
 
 
@@ -193,16 +214,16 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
     Given a Btrfs configuration dict, a configuration dict, a log prefix, the borgmatic
-    configuration file paths, the borgmatic runtime directory, the configured source directories,
-    and whether this is a dry run, auto-detect and snapshot any Btrfs subvolume mount points listed
-    in the given source directories. Also update those source directories, replacing subvolume mount
-    points with corresponding snapshot directories so they get stored in the Borg archive instead.
-    Use the log prefix in any log entries.
+    configuration file paths, the borgmatic runtime directory, the configured patterns, and whether
+    this is a dry run, auto-detect and snapshot any Btrfs subvolume mount points listed in the given
+    patterns. Also update those patterns, replacing subvolume mount points with corresponding
+    snapshot directories so they get stored in the Borg archive instead. Use the log prefix in any
+    log entries.
 
     Return an empty sequence, since there are no ongoing dump processes from this hook.
 
@@ -211,15 +232,15 @@ def dump_data_sources(
     dry_run_label = ' (dry run; not actually snapshotting anything)' if dry_run else ''
     logger.info(f'{log_prefix}: Snapshotting Btrfs subvolumes{dry_run_label}')
 
-    # Based on the configured source directories, determine Btrfs subvolumes to backup.
+    # Based on the configured patterns, determine Btrfs subvolumes to backup.
     btrfs_command = hook_config.get('btrfs_command', 'btrfs')
     findmnt_command = hook_config.get('findmnt_command', 'findmnt')
-    subvolumes = get_subvolumes(btrfs_command, findmnt_command, source_directories)
+    subvolumes = get_subvolumes(btrfs_command, findmnt_command, patterns)
 
     if not subvolumes:
         logger.warning(f'{log_prefix}: No Btrfs subvolumes found to snapshot{dry_run_label}')
 
-    # Snapshot each subvolume, rewriting source directories to use their snapshot paths.
+    # Snapshot each subvolume, rewriting patterns to use their snapshot paths.
     for subvolume in subvolumes:
         logger.debug(f'{log_prefix}: Creating Btrfs snapshot for {subvolume.path} subvolume')
 
@@ -230,17 +251,16 @@ def dump_data_sources(
 
         snapshot_subvolume(btrfs_command, subvolume.path, snapshot_path)
 
-        for source_directory in subvolume.contained_source_directories:
+        for pattern in subvolume.contained_patterns:
+            snapshot_pattern = make_borg_snapshot_pattern(subvolume.path, pattern)
+
+            # Attempt to update the pattern in place, since pattern order matters to Borg.
             try:
-                source_directories.remove(source_directory)
+                patterns[patterns.index(pattern)] = snapshot_pattern
             except ValueError:
-                pass
-
-            source_directories.append(
-                make_borg_source_directory_path(subvolume.path, source_directory)
-            )
+                patterns.append(snapshot_pattern)
 
-        config.setdefault('exclude_patterns', []).append(make_snapshot_exclude_path(subvolume.path))
+        patterns.append(make_snapshot_exclude_pattern(subvolume.path))
 
     return []
 

borgmatic/hooks/data_source/lvm.py

@@ -6,6 +6,7 @@ import os
 import shutil
 import subprocess
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 import borgmatic.execute
 import borgmatic.hooks.data_source.snapshot
@@ -22,18 +23,17 @@ def use_streaming(hook_config, config, log_prefix):  # pragma: no cover
 
 BORGMATIC_SNAPSHOT_PREFIX = 'borgmatic-'
 Logical_volume = collections.namedtuple(
-    'Logical_volume', ('name', 'device_path', 'mount_point', 'contained_source_directories')
+    'Logical_volume', ('name', 'device_path', 'mount_point', 'contained_patterns')
 )
 
 
-def get_logical_volumes(lsblk_command, source_directories=None):
+def get_logical_volumes(lsblk_command, patterns=None):
     '''
-    Given an lsblk command to run and a sequence of configured source directories, find the
-    intersection between the current LVM logical volume mount points and the configured borgmatic
-    source directories. The idea is that these are the requested logical volumes to snapshot.
+    Given an lsblk command to run and a sequence of configured patterns, find the intersection
+    between the current LVM logical volume mount points and the paths of any patterns. The idea is
+    that these pattern paths represent the requested logical volumes to snapshot.
 
-    If source directories is None, include all logical volume mounts points, not just those in
-    source directories.
+    If patterns is None, include all logical volume mounts points, not just those in patterns.
 
     Return the result as a sequence of Logical_volume instances.
     '''
@@ -53,21 +53,19 @@ def get_logical_volumes(lsblk_command, source_directories=None):
     except json.JSONDecodeError as error:
         raise ValueError(f'Invalid {lsblk_command} JSON output: {error}')
 
-    candidate_source_directories = set(source_directories or ())
+    candidate_patterns = set(patterns or ())
 
     try:
         return tuple(
-            Logical_volume(
-                device['name'], device['path'], device['mountpoint'], contained_source_directories
-            )
+            Logical_volume(device['name'], device['path'], device['mountpoint'], contained_patterns)
             for device in devices_info['blockdevices']
             if device['mountpoint'] and device['type'] == 'lvm'
-            for contained_source_directories in (
-                borgmatic.hooks.data_source.snapshot.get_contained_directories(
-                    device['mountpoint'], candidate_source_directories
+            for contained_patterns in (
+                borgmatic.hooks.data_source.snapshot.get_contained_patterns(
+                    device['mountpoint'], candidate_patterns
                 ),
             )
-            if not source_directories or contained_source_directories
+            if not patterns or contained_patterns
         )
     except KeyError as error:
         raise ValueError(f'Invalid {lsblk_command} output: Missing key "{error}"')
@@ -119,6 +117,37 @@ def mount_snapshot(mount_command, snapshot_device, snapshot_mount_path):  # prag
     )
 
 
+def make_borg_snapshot_pattern(pattern, normalized_runtime_directory):
+    '''
+    Given a Borg pattern as a borgmatic.borg.pattern.Pattern instance, return a new Pattern with its
+    path rewritten to be in a snapshot directory based on the given runtime directory.
+
+    Move any initial caret in a regular expression pattern path to the beginning, so as not to break
+    the regular expression.
+    '''
+    initial_caret = (
+        '^'
+        if pattern.style == borgmatic.borg.pattern.Pattern_style.REGULAR_EXPRESSION
+        and pattern.path.startswith('^')
+        else ''
+    )
+
+    rewritten_path = initial_caret + os.path.join(
+        normalized_runtime_directory,
+        'lvm_snapshots',
+        '.',  # Borg 1.4+ "slashdot" hack.
+        # Included so that the source directory ends up in the Borg archive at its "original" path.
+        pattern.path.lstrip('^').lstrip(os.path.sep),
+    )
+
+    return borgmatic.borg.pattern.Pattern(
+        rewritten_path,
+        pattern.type,
+        pattern.style,
+        pattern.device,
+    )
+
+
 DEFAULT_SNAPSHOT_SIZE = '10%ORIGIN'
 
 
@@ -128,16 +157,16 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
     Given an LVM configuration dict, a configuration dict, a log prefix, the borgmatic configuration
-    file paths, the borgmatic runtime directory, the configured source directories, and whether this
-    is a dry run, auto-detect and snapshot any LVM logical volume mount points listed in the given
-    source directories. Also update those source directories, replacing logical volume mount points
-    with corresponding snapshot directories so they get stored in the Borg archive instead. Use the
-    log prefix in any log entries.
+    file paths, the borgmatic runtime directory, the configured patterns, and whether this is a dry
+    run, auto-detect and snapshot any LVM logical volume mount points listed in the given patterns.
+    Also update those patterns, replacing logical volume mount points with corresponding snapshot
+    directories so they get stored in the Borg archive instead. Use the log prefix in any log
+    entries.
 
     Return an empty sequence, since there are no ongoing dump processes from this hook.
 
@@ -148,7 +177,7 @@ def dump_data_sources(
 
     # List logical volumes to get their mount points.
     lsblk_command = hook_config.get('lsblk_command', 'lsblk')
-    requested_logical_volumes = get_logical_volumes(lsblk_command, source_directories)
+    requested_logical_volumes = get_logical_volumes(lsblk_command, patterns)
 
     # Snapshot each logical volume, rewriting source directories to use the snapshot paths.
     snapshot_suffix = f'{BORGMATIC_SNAPSHOT_PREFIX}{os.getpid()}'
@@ -198,22 +227,14 @@ def dump_data_sources(
             hook_config.get('mount_command', 'mount'), snapshot.device_path, snapshot_mount_path
         )
 
-        # Update the path for each contained source directory, so Borg sees it within the
-        # mounted snapshot.
-        for source_directory in logical_volume.contained_source_directories:
+        for pattern in logical_volume.contained_patterns:
+            snapshot_pattern = make_borg_snapshot_pattern(pattern, normalized_runtime_directory)
+
+            # Attempt to update the pattern in place, since pattern order matters to Borg.
             try:
-                source_directories.remove(source_directory)
+                patterns[patterns.index(pattern)] = snapshot_pattern
             except ValueError:
-                pass
-
-            source_directories.append(
-                os.path.join(
-                    normalized_runtime_directory,
-                    'lvm_snapshots',
-                    '.',  # Borg 1.4+ "slashdot" hack.
-                    source_directory.lstrip(os.path.sep),
-                )
-            )
+                patterns.append(snapshot_pattern)
 
     return []
 

borgmatic/hooks/data_source/mariadb.py

@@ -3,6 +3,7 @@ import logging
 import os
 import shlex
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 from borgmatic.execute import (
     execute_command,
@@ -131,7 +132,7 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
@@ -142,7 +143,8 @@ def dump_data_sources(
 
     Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
     pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
-    Also append the given source directories with the parent directory of the database dumps.
+    Also append the the parent directory of the database dumps to the given patterns list, so the
+    dumps actually get backed up.
     '''
     dry_run_label = ' (dry run; not actually dumping anything)' if dry_run else ''
     processes = []
@@ -191,7 +193,11 @@ def dump_data_sources(
             )
 
     if not dry_run:
-        source_directories.append(os.path.join(borgmatic_runtime_directory, 'mariadb_databases'))
+        patterns.append(
+            borgmatic.borg.pattern.Pattern(
+                os.path.join(borgmatic_runtime_directory, 'mariadb_databases')
+            )
+        )
 
     return [process for process in processes if process]
 

borgmatic/hooks/data_source/mongodb.py

@@ -2,6 +2,7 @@ import logging
 import os
 import shlex
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 from borgmatic.execute import execute_command, execute_command_with_processes
 from borgmatic.hooks.data_source import dump
@@ -30,7 +31,7 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
@@ -41,7 +42,8 @@ def dump_data_sources(
 
     Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
     pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
-    Also append the given source directories with the parent directory of the database dumps.
+    Also append the the parent directory of the database dumps to the given patterns list, so the
+    dumps actually get backed up.
     '''
     dry_run_label = ' (dry run; not actually dumping anything)' if dry_run else ''
 
@@ -74,7 +76,11 @@ def dump_data_sources(
             processes.append(execute_command(command, shell=True, run_to_completion=False))
 
     if not dry_run:
-        source_directories.append(os.path.join(borgmatic_runtime_directory, 'mongodb_databases'))
+        patterns.append(
+            borgmatic.borg.pattern.Pattern(
+                os.path.join(borgmatic_runtime_directory, 'mongodb_databases')
+            )
+        )
 
     return processes
 

borgmatic/hooks/data_source/mysql.py

@@ -3,6 +3,7 @@ import logging
 import os
 import shlex
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 from borgmatic.execute import (
     execute_command,
@@ -130,7 +131,7 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
@@ -141,7 +142,8 @@ def dump_data_sources(
 
     Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
     pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
-    Also append the given source directories with the parent directory of the database dumps.
+    Also append the the parent directory of the database dumps to the given patterns list, so the
+    dumps actually get backed up.
     '''
     dry_run_label = ' (dry run; not actually dumping anything)' if dry_run else ''
     processes = []
@@ -190,7 +192,11 @@ def dump_data_sources(
             )
 
     if not dry_run:
-        source_directories.append(os.path.join(borgmatic_runtime_directory, 'mysql_databases'))
+        patterns.append(
+            borgmatic.borg.pattern.Pattern(
+                os.path.join(borgmatic_runtime_directory, 'mysql_databases')
+            )
+        )
 
     return [process for process in processes if process]
 

borgmatic/hooks/data_source/postgresql.py

@@ -5,6 +5,7 @@ import os
 import pathlib
 import shlex
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 from borgmatic.execute import (
     execute_command,
@@ -110,7 +111,7 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
@@ -121,7 +122,8 @@ def dump_data_sources(
 
     Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
     pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
-    Also append the given source directories with the parent directory of the database dumps.
+    Also append the the parent directory of the database dumps to the given patterns list, so the
+    dumps actually get backed up.
 
     Raise ValueError if the databases to dump cannot be determined.
     '''
@@ -216,7 +218,11 @@ def dump_data_sources(
                 )
 
     if not dry_run:
-        source_directories.append(os.path.join(borgmatic_runtime_directory, 'postgresql_databases'))
+        patterns.append(
+            borgmatic.borg.pattern.Pattern(
+                os.path.join(borgmatic_runtime_directory, 'postgresql_databases')
+            )
+        )
 
     return processes
 

borgmatic/hooks/data_source/snapshot.py

@@ -3,28 +3,37 @@ import pathlib
 IS_A_HOOK = False
 
 
-def get_contained_directories(parent_directory, candidate_contained_directories):
+def get_contained_patterns(parent_directory, candidate_patterns):
     '''
-    Given a parent directory and a set of candidate directories potentially inside it, get the
-    subset of contained directories for which the parent directory is actually the parent, a
-    grandparent, the very same directory, etc. The idea is if, say, /var/log and /var/lib are
-    candidate contained directories, but there's a parent directory (logical volume, dataset,
-    subvolume, etc.) at /var, then /var is what we want to snapshot.
-
-    Also mutate the given set of candidate contained directories to remove any actually contained
-    directories from it. That way, this function can be called multiple times, successively
-    processing candidate directories until none are left—and avoiding assigning any candidate
-    directory to more than one parent directory.
+    Given a parent directory and a set of candidate patterns potentially inside it, get the subset
+    of contained patterns for which the parent directory is actually the parent, a grandparent, the
+    very same directory, etc. The idea is if, say, /var/log and /var/lib are candidate pattern
+    paths, but there's a parent directory (logical volume, dataset, subvolume, etc.) at /var, then
+    /var is what we want to snapshot.
+
+    For this to work, a candidate pattern path can't have any globs or other non-literal characters
+    in the initial portion of the path that matches the parent directory. For instance, a parent
+    directory of /var would match a candidate pattern path of /var/log/*/data, but not a pattern
+    path like /v*/log/*/data.
+
+    The one exception is that if a regular expression pattern path starts with "^", that will get
+    stripped off for purposes of matching against a parent directory.
+
+    As part of this, also mutate the given set of candidate patterns to remove any actually
+    contained patterns from it. That way, this function can be called multiple times, successively
+    processing candidate patterns until none are left—and avoiding assigning any candidate pattern
+    to more than one parent directory.
     '''
-    if not candidate_contained_directories:
+    if not candidate_patterns:
         return ()
 
-    contained = tuple(
+    contained_patterns = tuple(
         candidate
-        for candidate in candidate_contained_directories
-        if pathlib.PurePath(parent_directory) == pathlib.PurePath(candidate)
-        or pathlib.PurePath(parent_directory) in pathlib.PurePath(candidate).parents
+        for candidate in candidate_patterns
+        for candidate_path in (pathlib.PurePath(candidate.path.lstrip('^')),)
+        if pathlib.PurePath(parent_directory) == candidate_path
+        or pathlib.PurePath(parent_directory) in candidate_path.parents
     )
-    candidate_contained_directories -= set(contained)
+    candidate_patterns -= set(contained_patterns)
 
-    return contained
+    return contained_patterns

borgmatic/hooks/data_source/sqlite.py

@@ -2,6 +2,7 @@ import logging
 import os
 import shlex
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 from borgmatic.execute import execute_command, execute_command_with_processes
 from borgmatic.hooks.data_source import dump
@@ -30,7 +31,7 @@ def dump_data_sources(
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
@@ -40,7 +41,8 @@ def dump_data_sources(
 
     Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
     pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
-    Also append the given source directories with the parent directory of the database dumps.
+    Also append the the parent directory of the database dumps to the given patterns list, so the
+    dumps actually get backed up.
     '''
     dry_run_label = ' (dry run; not actually dumping anything)' if dry_run else ''
     processes = []
@@ -83,7 +85,11 @@ def dump_data_sources(
         processes.append(execute_command(command, shell=True, run_to_completion=False))
 
     if not dry_run:
-        source_directories.append(os.path.join(borgmatic_runtime_directory, 'sqlite_databases'))
+        patterns.append(
+            borgmatic.borg.pattern.Pattern(
+                os.path.join(borgmatic_runtime_directory, 'sqlite_databases')
+            )
+        )
 
     return processes
 

borgmatic/hooks/data_source/zfs.py

@@ -5,6 +5,7 @@ import os
 import shutil
 import subprocess
 
+import borgmatic.borg.pattern
 import borgmatic.config.paths
 import borgmatic.execute
 import borgmatic.hooks.data_source.snapshot
@@ -25,18 +26,17 @@ BORGMATIC_USER_PROPERTY = 'org.torsion.borgmatic:backup'
 
 Dataset = collections.namedtuple(
     'Dataset',
-    ('name', 'mount_point', 'auto_backup', 'contained_source_directories'),
+    ('name', 'mount_point', 'auto_backup', 'contained_patterns'),
     defaults=(False, ()),
 )
 
 
-def get_datasets_to_backup(zfs_command, source_directories):
+def get_datasets_to_backup(zfs_command, patterns):
     '''
-    Given a ZFS command to run and a sequence of configured source directories, find the
-    intersection between the current ZFS dataset mount points and the configured borgmatic source
-    directories. The idea is that these are the requested datasets to snapshot. But also include any
-    datasets tagged with a borgmatic-specific user property, whether or not they appear in source
-    directories.
+    Given a ZFS command to run and a sequence of configured patterns, find the intersection between
+    the current ZFS dataset mount points and the paths of any patterns. The idea is that these
+    pattern paths represent the requested datasets to snapshot. But also include any datasets tagged
+    with a borgmatic-specific user property, whether or not they appear in the patterns.
 
     Return the result as a sequence of Dataset instances, sorted by mount point.
     '''
@@ -54,9 +54,8 @@ def get_datasets_to_backup(zfs_command, source_directories):
 
     try:
         # Sort from longest to shortest mount points, so longer mount points get a whack at the
-        # candidate source directory piñata before their parents do. (Source directories are
-        # consumed during the second loop below, so no two datasets get the same contained source
-        # directories.)
+        # candidate pattern piñata before their parents do. (Patterns are consumed during the second
+        # loop below, so no two datasets end up with the same contained patterns.)
         datasets = sorted(
             (
                 Dataset(dataset_name, mount_point, (user_property_value == 'auto'), ())
@@ -69,7 +68,7 @@ def get_datasets_to_backup(zfs_command, source_directories):
     except ValueError:
         raise ValueError(f'Invalid {zfs_command} list output')
 
-    candidate_source_directories = set(source_directories)
+    candidate_patterns = set(patterns)
 
     return tuple(
         sorted(
@@ -78,19 +77,22 @@ def get_datasets_to_backup(zfs_command, source_directories):
                     dataset.name,
                     dataset.mount_point,
                     dataset.auto_backup,
-                    contained_source_directories,
+                    contained_patterns,
                 )
                 for dataset in datasets
-                for contained_source_directories in (
+                for contained_patterns in (
                     (
-                        (dataset.mount_point,)
-                        if dataset.auto_backup
-                        else borgmatic.hooks.data_source.snapshot.get_contained_directories(
-                            dataset.mount_point, candidate_source_directories
+                        (
+                            (borgmatic.borg.pattern.Pattern(dataset.mount_point),)
+                            if dataset.auto_backup
+                            else ()
+                        )
+                        + borgmatic.hooks.data_source.snapshot.get_contained_patterns(
+                            dataset.mount_point, candidate_patterns
                         )
                     ),
                 )
-                if contained_source_directories
+                if contained_patterns
             ),
             key=lambda dataset: dataset.mount_point,
         )
@@ -153,22 +155,53 @@ def mount_snapshot(mount_command, full_snapshot_name, snapshot_mount_path):  # p
     )
 
 
+def make_borg_snapshot_pattern(pattern, normalized_runtime_directory):
+    '''
+    Given a Borg pattern as a borgmatic.borg.pattern.Pattern instance, return a new Pattern with its
+    path rewritten to be in a snapshot directory based on the given runtime directory.
+
+    Move any initial caret in a regular expression pattern path to the beginning, so as not to break
+    the regular expression.
+    '''
+    initial_caret = (
+        '^'
+        if pattern.style == borgmatic.borg.pattern.Pattern_style.REGULAR_EXPRESSION
+        and pattern.path.startswith('^')
+        else ''
+    )
+
+    rewritten_path = initial_caret + os.path.join(
+        normalized_runtime_directory,
+        'zfs_snapshots',
+        '.',  # Borg 1.4+ "slashdot" hack.
+        # Included so that the source directory ends up in the Borg archive at its "original" path.
+        pattern.path.lstrip('^').lstrip(os.path.sep),
+    )
+
+    return borgmatic.borg.pattern.Pattern(
+        rewritten_path,
+        pattern.type,
+        pattern.style,
+        pattern.device,
+    )
+
+
 def dump_data_sources(
     hook_config,
     config,
     log_prefix,
     config_paths,
     borgmatic_runtime_directory,
-    source_directories,
+    patterns,
     dry_run,
 ):
     '''
     Given a ZFS configuration dict, a configuration dict, a log prefix, the borgmatic configuration
-    file paths, the borgmatic runtime directory, the configured source directories, and whether this
-    is a dry run, auto-detect and snapshot any ZFS dataset mount points listed in the given source
-    directories and any dataset with a borgmatic-specific user property. Also update those source
-    directories, replacing dataset mount points with corresponding snapshot directories so they get
-    stored in the Borg archive instead. Use the log prefix in any log entries.
+    file paths, the borgmatic runtime directory, the configured patterns, and whether this is a dry
+    run, auto-detect and snapshot any ZFS dataset mount points listed in the given patterns and any
+    dataset with a borgmatic-specific user property. Also update those patterns, replacing dataset
+    mount points with corresponding snapshot directories so they get stored in the Borg archive
+    instead. Use the log prefix in any log entries.
 
     Return an empty sequence, since there are no ongoing dump processes from this hook.
 
@@ -179,9 +212,9 @@ def dump_data_sources(
 
     # List ZFS datasets to get their mount points.
     zfs_command = hook_config.get('zfs_command', 'zfs')
-    requested_datasets = get_datasets_to_backup(zfs_command, source_directories)
+    requested_datasets = get_datasets_to_backup(zfs_command, patterns)
 
-    # Snapshot each dataset, rewriting source directories to use the snapshot paths.
+    # Snapshot each dataset, rewriting patterns to use the snapshot paths.
     snapshot_name = f'{BORGMATIC_SNAPSHOT_PREFIX}{os.getpid()}'
     normalized_runtime_directory = os.path.normpath(borgmatic_runtime_directory)
 
@@ -216,20 +249,14 @@ def dump_data_sources(
             hook_config.get('mount_command', 'mount'), full_snapshot_name, snapshot_mount_path
         )
 
-        for source_directory in dataset.contained_source_directories:
+        for pattern in dataset.contained_patterns:
+            snapshot_pattern = make_borg_snapshot_pattern(pattern, normalized_runtime_directory)
+
+            # Attempt to update the pattern in place, since pattern order matters to Borg.
             try:
-                source_directories.remove(source_directory)
+                patterns[patterns.index(pattern)] = snapshot_pattern
             except ValueError:
-                pass
-
-            source_directories.append(
-                os.path.join(
-                    normalized_runtime_directory,
-                    'zfs_snapshots',
-                    '.',  # Borg 1.4+ "slashdot" hack.
-                    source_directory.lstrip(os.path.sep),
-                )
-            )
+                patterns.append(snapshot_pattern)
 
     return []
 

docs/how-to/snapshot-your-filesystems.md

@@ -53,6 +53,9 @@ You have a couple of options for borgmatic to find and backup your ZFS datasets:
 
  * For any dataset you'd like backed up, add its mount point to borgmatic's
    `source_directories` option.
+ * <span class="minilink minilink-addedin">New in version 1.9.6</span> Or
+   include the mount point with borgmatic's `patterns` or `patterns_from`
+   options.
  * Or set the borgmatic-specific user property
    `org.torsion.borgmatic:backup=auto` onto your dataset, e.g. by running `zfs
    set org.torsion.borgmatic:backup=auto datasetname`. Then borgmatic can find
@@ -84,6 +87,14 @@ let's say you add `/var/log` and `/var/lib` to your source directories, but
 accordingly. This also works even with nested datasets; borgmatic selects
 the dataset that's the "closest" parent to your source directories.
 
+<span class="minilink minilink-addedin">New in version 1.9.6</span> When using
+[patterns](https://borgbackup.readthedocs.io/en/stable/usage/help.html#borg-help-patterns),
+the initial portion of a pattern's path that you intend borgmatic to match
+against a dataset can't have globs or other non-literal characters in it—or it
+won't actually match. For instance, a mount point of `/var` would match a
+pattern of `+ fm:/var/*/data`, but borgmatic isn't currently smart enough to
+match `/var` to a pattern like `+ fm:/v*/lib/data`.
+
 <span class="minilink minilink-addedin">With Borg version 1.2 and
 earlier</span>Snapshotted files are instead stored at a path dependent on the
 [runtime
@@ -133,10 +144,14 @@ feedback](https://torsion.org/borgmatic/#issues) you have on this feature.
 #### Subvolume discovery
 
 For any subvolume you'd like backed up, add its path to borgmatic's
-`source_directories` option. During a backup, borgmatic snapshots these
-subvolumes (non-recursively) and includes the snapshotted files in the paths
-sent to Borg. borgmatic is also responsible for cleaning up (deleting) these
-snapshots after a backup completes.
+`source_directories` option.
+
+<span class="minilink minilink-addedin">New in version 1.9.6</span> Or include
+the mount point with borgmatic's `patterns` or `patterns_from` options.
+
+During a backup, borgmatic snapshots these subvolumes (non-recursively) and
+includes the snapshotted files in the paths sent to Borg. borgmatic is also
+responsible for cleaning up (deleting) these snapshots after a backup completes.
 
 borgmatic is smart enough to look at the parent (and grandparent, etc.)
 directories of each of your `source_directories` to discover any subvolumes.
@@ -146,6 +161,14 @@ snapshot `/var` accordingly. This also works even with nested subvolumes;
 borgmatic selects the subvolume that's the "closest" parent to your source
 directories.
 
+<span class="minilink minilink-addedin">New in version 1.9.6</span> When using
+[patterns](https://borgbackup.readthedocs.io/en/stable/usage/help.html#borg-help-patterns),
+the initial portion of a pattern's path that you intend borgmatic to match
+against a subvolume can't have globs or other non-literal characters in it—or it
+won't actually match. For instance, a subvolume of `/var` would match a pattern
+of `+ fm:/var/*/data`, but borgmatic isn't currently smart enough to match
+`/var` to a pattern like `+ fm:/v*/lib/data`.
+
 Additionally, borgmatic rewrites the snapshot file paths so that they appear
 at their original subvolume locations in a Borg archive. For instance, if your
 subvolume exists at `/var/subvolume`, then the snapshotted files will appear
@@ -228,6 +251,9 @@ more information about possible values here. (Under the hood, borgmatic uses
 For any logical volume you'd like backed up, add its mount point to
 borgmatic's `source_directories` option.
 
+<span class="minilink minilink-addedin">New in version 1.9.6</span> Or include
+the mount point with borgmatic's `patterns` or `patterns_from` options.
+
 During a backup, borgmatic automatically snapshots these discovered logical volumes, temporarily
 mounts the snapshots within its [runtime
 directory](https://torsion.org/borgmatic/docs/how-to/backup-your-databases/#runtime-directory), and
@@ -240,6 +266,14 @@ volumes. For instance, let's say you add `/var/log` and `/var/lib` to your
 source directories, but `/var` is a logical volume. borgmatic will discover
 that and snapshot `/var` accordingly.
 
+<span class="minilink minilink-addedin">New in version 1.9.6</span> When using
+[patterns](https://borgbackup.readthedocs.io/en/stable/usage/help.html#borg-help-patterns),
+the initial portion of a pattern's path that you intend borgmatic to match
+against a logical volume can't have globs or other non-literal characters in
+it—or it won't actually match. For instance, a logical volume of `/var` would
+match a pattern of `+ fm:/var/*/data`, but borgmatic isn't currently smart
+enough to match `/var` to a pattern like `+ fm:/v*/lib/data`.
+
 Additionally, borgmatic rewrites the snapshot file paths so that they appear
 at their original logical volume locations in a Borg archive. For instance, if
 your logical volume is mounted at `/var/lvolume`, then the snapshotted files

tests/unit/actions/test_check.py

@@ -2,6 +2,7 @@ import pytest
 from flexmock import flexmock
 
 from borgmatic.actions import check as module
+from borgmatic.borg.pattern import Pattern
 
 
 def test_parse_checks_returns_them_as_tuple():
@@ -557,14 +558,20 @@ def test_collect_spot_check_source_paths_parses_borg_output():
     flexmock(module.borgmatic.hooks.dispatch).should_receive('call_hooks').and_return(
         {'hook1': False, 'hook2': True}
     )
-    flexmock(module.borgmatic.actions.create).should_receive(
-        'process_source_directories'
-    ).and_return(['foo', 'bar'])
+    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('collect_patterns').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('process_patterns').and_return(
+        [Pattern('foo'), Pattern('bar')]
+    )
     flexmock(module.borgmatic.borg.create).should_receive('make_base_create_command').with_args(
         dry_run=True,
         repository_path='repo',
         config=object,
-        source_directories=['foo', 'bar'],
+        patterns=[Pattern('foo'), Pattern('bar')],
         local_borg_version=object,
         global_arguments=object,
         borgmatic_runtime_directory='/run/borgmatic',
@@ -572,7 +579,7 @@ def test_collect_spot_check_source_paths_parses_borg_output():
         remote_path=object,
         list_files=True,
         stream_processes=True,
-    ).and_return((('borg', 'create'), ('repo::archive',), flexmock(), flexmock()))
+    ).and_return((('borg', 'create'), ('repo::archive',), flexmock()))
     flexmock(module.borgmatic.borg.environment).should_receive('make_environment').and_return(
         flexmock()
     )
@@ -599,14 +606,20 @@ def test_collect_spot_check_source_paths_passes_through_stream_processes_false()
     flexmock(module.borgmatic.hooks.dispatch).should_receive('call_hooks').and_return(
         {'hook1': False, 'hook2': False}
     )
-    flexmock(module.borgmatic.actions.create).should_receive(
-        'process_source_directories'
-    ).and_return(['foo', 'bar'])
+    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('collect_patterns').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('process_patterns').and_return(
+        [Pattern('foo'), Pattern('bar')]
+    )
     flexmock(module.borgmatic.borg.create).should_receive('make_base_create_command').with_args(
         dry_run=True,
         repository_path='repo',
         config=object,
-        source_directories=['foo', 'bar'],
+        patterns=[Pattern('foo'), Pattern('bar')],
         local_borg_version=object,
         global_arguments=object,
         borgmatic_runtime_directory='/run/borgmatic',
@@ -614,7 +627,7 @@ def test_collect_spot_check_source_paths_passes_through_stream_processes_false()
         remote_path=object,
         list_files=True,
         stream_processes=False,
-    ).and_return((('borg', 'create'), ('repo::archive',), flexmock(), flexmock()))
+    ).and_return((('borg', 'create'), ('repo::archive',), flexmock()))
     flexmock(module.borgmatic.borg.environment).should_receive('make_environment').and_return(
         flexmock()
     )
@@ -641,14 +654,20 @@ def test_collect_spot_check_source_paths_without_working_directory_parses_borg_o
     flexmock(module.borgmatic.hooks.dispatch).should_receive('call_hooks').and_return(
         {'hook1': False, 'hook2': True}
     )
-    flexmock(module.borgmatic.actions.create).should_receive(
-        'process_source_directories'
-    ).and_return(['foo', 'bar'])
+    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('collect_patterns').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('process_patterns').and_return(
+        [Pattern('foo'), Pattern('bar')]
+    )
     flexmock(module.borgmatic.borg.create).should_receive('make_base_create_command').with_args(
         dry_run=True,
         repository_path='repo',
         config=object,
-        source_directories=['foo', 'bar'],
+        patterns=[Pattern('foo'), Pattern('bar')],
         local_borg_version=object,
         global_arguments=object,
         borgmatic_runtime_directory='/run/borgmatic',
@@ -656,7 +675,7 @@ def test_collect_spot_check_source_paths_without_working_directory_parses_borg_o
         remote_path=object,
         list_files=True,
         stream_processes=True,
-    ).and_return((('borg', 'create'), ('repo::archive',), flexmock(), flexmock()))
+    ).and_return((('borg', 'create'), ('repo::archive',), flexmock()))
     flexmock(module.borgmatic.borg.environment).should_receive('make_environment').and_return(
         flexmock()
     )
@@ -683,14 +702,20 @@ def test_collect_spot_check_source_paths_skips_directories():
     flexmock(module.borgmatic.hooks.dispatch).should_receive('call_hooks').and_return(
         {'hook1': False, 'hook2': True}
     )
-    flexmock(module.borgmatic.actions.create).should_receive(
-        'process_source_directories'
-    ).and_return(['foo', 'bar'])
+    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('collect_patterns').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('process_patterns').and_return(
+        [Pattern('foo'), Pattern('bar')]
+    )
     flexmock(module.borgmatic.borg.create).should_receive('make_base_create_command').with_args(
         dry_run=True,
         repository_path='repo',
         config=object,
-        source_directories=['foo', 'bar'],
+        patterns=[Pattern('foo'), Pattern('bar')],
         local_borg_version=object,
         global_arguments=object,
         borgmatic_runtime_directory='/run/borgmatic',
@@ -698,7 +723,7 @@ def test_collect_spot_check_source_paths_skips_directories():
         remote_path=object,
         list_files=True,
         stream_processes=True,
-    ).and_return((('borg', 'create'), ('repo::archive',), flexmock(), flexmock()))
+    ).and_return((('borg', 'create'), ('repo::archive',), flexmock()))
     flexmock(module.borgmatic.borg.environment).should_receive('make_environment').and_return(
         flexmock()
     )
@@ -823,14 +848,20 @@ def test_collect_spot_check_source_paths_uses_working_directory():
     flexmock(module.borgmatic.hooks.dispatch).should_receive('call_hooks').and_return(
         {'hook1': False, 'hook2': True}
     )
-    flexmock(module.borgmatic.actions.create).should_receive(
-        'process_source_directories'
-    ).and_return(['foo', 'bar'])
+    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('collect_patterns').and_return(
+        flexmock()
+    )
+    flexmock(module.borgmatic.actions.create).should_receive('process_patterns').and_return(
+        [Pattern('foo'), Pattern('bar')]
+    )
     flexmock(module.borgmatic.borg.create).should_receive('make_base_create_command').with_args(
         dry_run=True,
         repository_path='repo',
         config=object,
-        source_directories=['foo', 'bar'],
+        patterns=[Pattern('foo'), Pattern('bar')],
         local_borg_version=object,
         global_arguments=object,
         borgmatic_runtime_directory='/run/borgmatic',
@@ -838,7 +869,7 @@ def test_collect_spot_check_source_paths_uses_working_directory():
         remote_path=object,
         list_files=True,
         stream_processes=True,
-    ).and_return((('borg', 'create'), ('repo::archive',), flexmock(), flexmock()))
+    ).and_return((('borg', 'create'), ('repo::archive',), flexmock()))
     flexmock(module.borgmatic.borg.environment).should_receive('make_environment').and_return(
         flexmock()
     )
@@ -1220,7 +1251,7 @@ def test_spot_check_without_any_configuration_errors():
         )
 
 
-def test_spot_check_data_tolerance_percenatge_greater_than_data_sample_percentage_errors():
+def test_spot_check_data_tolerance_percentage_greater_than_data_sample_percentage_errors():
     with pytest.raises(ValueError):
         module.spot_check(
             repository={'path': 'repo'},
@@ -1338,6 +1369,35 @@ def test_spot_check_with_high_enough_tolerances_does_not_raise():
     )
 
 
+def test_spot_check_without_any_source_paths_errors():
+    flexmock(module).should_receive('collect_spot_check_source_paths').and_return(())
+    flexmock(module.borgmatic.borg.repo_list).should_receive('resolve_archive_name').and_return(
+        'archive'
+    )
+    flexmock(module).should_receive('collect_spot_check_archive_paths').and_return(('/foo', '/bar'))
+    flexmock(module).should_receive('compare_spot_check_hashes').never()
+
+    with pytest.raises(ValueError):
+        module.spot_check(
+            repository={'path': 'repo'},
+            config={
+                'checks': [
+                    {
+                        'name': 'spot',
+                        'count_tolerance_percentage': 10,
+                        'data_tolerance_percentage': 40,
+                        'data_sample_percentage': 50,
+                    },
+                ]
+            },
+            local_borg_version=flexmock(),
+            global_arguments=flexmock(),
+            local_path=flexmock(),
+            remote_path=flexmock(),
+            borgmatic_runtime_directory='/run/borgmatic',
+        )
+
+
 def test_run_check_checks_archives_for_configured_repository():
     flexmock(module.logger).answer = lambda message: None
     flexmock(module.borgmatic.config.validate).should_receive('repositories_match').never()

tests/unit/actions/test_create.py

@@ -1,7 +1,104 @@
+import io
+import sys
+
 import pytest
 from flexmock import flexmock
 
 from borgmatic.actions import create as module
+from borgmatic.borg.pattern import Pattern, Pattern_style, Pattern_type
+
+
+@pytest.mark.parametrize(
+    'pattern_line,expected_pattern',
+    (
+        ('R /foo', Pattern('/foo')),
+        ('P sh', Pattern('sh', Pattern_type.PATTERN_STYLE)),
+        ('+ /foo*', Pattern('/foo*', Pattern_type.INCLUDE)),
+        ('+ sh:/foo*', Pattern('/foo*', Pattern_type.INCLUDE, Pattern_style.SHELL)),
+    ),
+)
+def test_parse_pattern_transforms_pattern_line_to_instance(pattern_line, expected_pattern):
+    module.parse_pattern(pattern_line) == expected_pattern
+
+
+def test_parse_pattern_with_invalid_pattern_line_errors():
+    with pytest.raises(ValueError):
+        module.parse_pattern('/foo')
+
+
+def test_collect_patterns_converts_source_directories():
+    assert module.collect_patterns({'source_directories': ['/foo', '/bar']}) == (
+        Pattern('/foo'),
+        Pattern('/bar'),
+    )
+
+
+def test_collect_patterns_parses_config_patterns():
+    flexmock(module).should_receive('parse_pattern').with_args('R /foo').and_return(Pattern('/foo'))
+    flexmock(module).should_receive('parse_pattern').with_args('# comment').never()
+    flexmock(module).should_receive('parse_pattern').with_args('R /bar').and_return(Pattern('/bar'))
+
+    assert module.collect_patterns({'patterns': ['R /foo', '# comment', 'R /bar']}) == (
+        Pattern('/foo'),
+        Pattern('/bar'),
+    )
+
+
+def test_collect_patterns_converts_exclude_patterns():
+    assert module.collect_patterns({'exclude_patterns': ['/foo', '/bar']}) == (
+        Pattern('/foo', Pattern_type.EXCLUDE, Pattern_style.FNMATCH),
+        Pattern('/bar', Pattern_type.EXCLUDE, Pattern_style.FNMATCH),
+    )
+
+
+def test_collect_patterns_reads_config_patterns_from_file():
+    builtins = flexmock(sys.modules['builtins'])
+    builtins.should_receive('open').with_args('file1.txt').and_return(io.StringIO('R /foo'))
+    builtins.should_receive('open').with_args('file2.txt').and_return(
+        io.StringIO('R /bar\n# comment\nR /baz')
+    )
+    flexmock(module).should_receive('parse_pattern').with_args('R /foo').and_return(Pattern('/foo'))
+    flexmock(module).should_receive('parse_pattern').with_args('# comment').never()
+    flexmock(module).should_receive('parse_pattern').with_args('R /bar').and_return(Pattern('/bar'))
+    flexmock(module).should_receive('parse_pattern').with_args('R /baz').and_return(Pattern('/baz'))
+
+    assert module.collect_patterns({'patterns_from': ['file1.txt', 'file2.txt']}) == (
+        Pattern('/foo'),
+        Pattern('/bar'),
+        Pattern('/baz'),
+    )
+
+
+def test_collect_patterns_errors_on_missing_config_patterns_from_file():
+    builtins = flexmock(sys.modules['builtins'])
+    builtins.should_receive('open').with_args('file1.txt').and_raise(FileNotFoundError)
+    flexmock(module).should_receive('parse_pattern').never()
+
+    with pytest.raises(ValueError):
+        module.collect_patterns({'patterns_from': ['file1.txt', 'file2.txt']})
+
+
+def test_collect_patterns_reads_config_excludes_from_file():
+    builtins = flexmock(sys.modules['builtins'])
+    builtins.should_receive('open').with_args('file1.txt').and_return(io.StringIO('/foo'))
+    builtins.should_receive('open').with_args('file2.txt').and_return(
+        io.StringIO('/bar\n# comment\n/baz')
+    )
+
+    assert module.collect_patterns({'excludes_from': ['file1.txt', 'file2.txt']}) == (
+        Pattern('/foo', Pattern_type.EXCLUDE, Pattern_style.FNMATCH),
+        Pattern('/bar', Pattern_type.EXCLUDE, Pattern_style.FNMATCH),
+        Pattern('/baz', Pattern_type.EXCLUDE, Pattern_style.FNMATCH),
+    )
+
+
+def test_collect_patterns_errors_on_missing_config_excludes_from_file():
+    builtins = flexmock(sys.modules['builtins'])
+    builtins.should_receive('open').with_args('file1.txt').and_raise(OSError)
+    flexmock(module).should_receive('parse_pattern').never()
+
+    with pytest.raises(ValueError):
+        module.collect_patterns({'excludes_from': ['file1.txt', 'file2.txt']})
 
 
 def test_expand_directory_with_basic_path_passes_it_through():
@@ -53,7 +150,18 @@ def test_expand_directory_with_slashdot_hack_globs_working_directory_and_strips_
     assert paths == ['./foo', './food']
 
 
-def test_expand_directories_flattens_expanded_directories():
+def test_expand_directory_with_working_directory_matching_start_of_directory_does_not_strip_it_off():
+    flexmock(module.os.path).should_receive('expanduser').and_return('/working/dir/foo')
+    flexmock(module.glob).should_receive('glob').with_args('/working/dir/foo').and_return(
+        ['/working/dir/foo']
+    ).once()
+
+    paths = module.expand_directory('/working/dir/foo', working_directory='/working/dir')
+
+    assert paths == ['/working/dir/foo']
+
+
+def test_expand_patterns_flattens_expanded_directories():
     flexmock(module).should_receive('expand_directory').with_args('~/foo', None).and_return(
         ['/root/foo']
     )
@@ -61,167 +169,224 @@ def test_expand_directories_flattens_expanded_directories():
         ['bar', 'barf']
     )
 
-    paths = module.expand_directories(('~/foo', 'bar*'))
+    paths = module.expand_patterns((Pattern('~/foo'), Pattern('bar*')))
 
-    assert paths == ('/root/foo', 'bar', 'barf')
+    assert paths == (Pattern('/root/foo'), Pattern('bar'), Pattern('barf'))
 
 
-def test_expand_directories_with_working_directory_passes_it_through():
+def test_expand_patterns_with_working_directory_passes_it_through():
     flexmock(module).should_receive('expand_directory').with_args('foo', '/working/dir').and_return(
         ['/working/dir/foo']
     )
 
-    paths = module.expand_directories(('foo',), working_directory='/working/dir')
+    patterns = module.expand_patterns((Pattern('foo'),), working_directory='/working/dir')
+
+    assert patterns == (Pattern('/working/dir/foo'),)
+
+
+def test_expand_patterns_does_not_expand_skip_paths():
+    flexmock(module).should_receive('expand_directory').with_args('/foo', None).and_return(['/foo'])
+    flexmock(module).should_receive('expand_directory').with_args('/bar*', None).never()
 
-    assert paths == ('/working/dir/foo',)
+    patterns = module.expand_patterns((Pattern('/foo'), Pattern('/bar*')), skip_paths=('/bar*',))
 
+    assert patterns == (Pattern('/foo'), Pattern('/bar*'))
 
-def test_expand_directories_considers_none_as_no_directories():
-    paths = module.expand_directories(None, None)
 
-    assert paths == ()
+def test_expand_patterns_considers_none_as_no_patterns():
+    assert module.expand_patterns(None) == ()
+
+
+def test_expand_patterns_only_considers_root_patterns():
+    flexmock(module).should_receive('expand_directory').with_args('~/foo', None).and_return(
+        ['/root/foo']
+    )
+    flexmock(module).should_receive('expand_directory').with_args('bar*', None).never()
 
+    paths = module.expand_patterns((Pattern('~/foo'), Pattern('bar*', Pattern_type.INCLUDE)))
 
-def test_map_directories_to_devices_gives_device_id_per_path():
+    assert paths == (Pattern('/root/foo'), Pattern('bar*', Pattern_type.INCLUDE))
+
+
+def test_device_map_patterns_gives_device_id_per_path():
     flexmock(module.os.path).should_receive('exists').and_return(True)
     flexmock(module.os).should_receive('stat').with_args('/foo').and_return(flexmock(st_dev=55))
     flexmock(module.os).should_receive('stat').with_args('/bar').and_return(flexmock(st_dev=66))
 
-    device_map = module.map_directories_to_devices(('/foo', '/bar'))
+    device_map = module.device_map_patterns((Pattern('/foo'), Pattern('/bar')))
+
+    assert device_map == (
+        Pattern('/foo', device=55),
+        Pattern('/bar', device=66),
+    )
+
+
+def test_device_map_patterns_only_considers_root_patterns():
+    flexmock(module.os.path).should_receive('exists').and_return(True)
+    flexmock(module.os).should_receive('stat').with_args('/foo').and_return(flexmock(st_dev=55))
+    flexmock(module.os).should_receive('stat').with_args('/bar*').never()
+
+    device_map = module.device_map_patterns(
+        (Pattern('/foo'), Pattern('/bar*', Pattern_type.INCLUDE))
+    )
 
-    assert device_map == {
-        '/foo': 55,
-        '/bar': 66,
-    }
+    assert device_map == (
+        Pattern('/foo', device=55),
+        Pattern('/bar*', Pattern_type.INCLUDE),
+    )
 
 
-def test_map_directories_to_devices_with_missing_path_does_not_error():
+def test_device_map_patterns_with_missing_path_does_not_error():
     flexmock(module.os.path).should_receive('exists').and_return(True).and_return(False)
     flexmock(module.os).should_receive('stat').with_args('/foo').and_return(flexmock(st_dev=55))
     flexmock(module.os).should_receive('stat').with_args('/bar').never()
 
-    device_map = module.map_directories_to_devices(('/foo', '/bar'))
+    device_map = module.device_map_patterns((Pattern('/foo'), Pattern('/bar')))
 
-    assert device_map == {
-        '/foo': 55,
-        '/bar': None,
-    }
+    assert device_map == (
+        Pattern('/foo', device=55),
+        Pattern('/bar'),
+    )
 
 
-def test_map_directories_to_devices_uses_working_directory_to_construct_path():
+def test_device_map_patterns_uses_working_directory_to_construct_path():
     flexmock(module.os.path).should_receive('exists').and_return(True)
     flexmock(module.os).should_receive('stat').with_args('/foo').and_return(flexmock(st_dev=55))
     flexmock(module.os).should_receive('stat').with_args('/working/dir/bar').and_return(
         flexmock(st_dev=66)
     )
 
-    device_map = module.map_directories_to_devices(
-        ('/foo', 'bar'), working_directory='/working/dir'
+    device_map = module.device_map_patterns(
+        (Pattern('/foo'), Pattern('bar')), working_directory='/working/dir'
     )
 
-    assert device_map == {
-        '/foo': 55,
-        'bar': 66,
-    }
-
-
-@pytest.mark.parametrize(
-    'directories,additional_directories,expected_directories',
-    (
-        ({'/': 1, '/root': 1}, {}, ['/']),
-        ({'/': 1, '/root/': 1}, {}, ['/']),
-        ({'/': 1, '/root': 2}, {}, ['/', '/root']),
-        ({'/root': 1, '/': 1}, {}, ['/']),
-        ({'/root': 1, '/root/foo': 1}, {}, ['/root']),
-        ({'/root/': 1, '/root/foo': 1}, {}, ['/root/']),
-        ({'/root': 1, '/root/foo/': 1}, {}, ['/root']),
-        ({'/root': 1, '/root/foo': 2}, {}, ['/root', '/root/foo']),
-        ({'/root/foo': 1, '/root': 1}, {}, ['/root']),
-        ({'/root': None, '/root/foo': None}, {}, ['/root', '/root/foo']),
-        ({'/root': 1, '/etc': 1, '/root/foo/bar': 1}, {}, ['/etc', '/root']),
-        ({'/root': 1, '/root/foo': 1, '/root/foo/bar': 1}, {}, ['/root']),
-        ({'/dup': 1, '/dup': 1}, {}, ['/dup']),
-        ({'/foo': 1, '/bar': 1}, {}, ['/bar', '/foo']),
-        ({'/foo': 1, '/bar': 2}, {}, ['/bar', '/foo']),
-        ({'/root/foo': 1}, {'/root': 1}, []),
-        ({'/root/foo': 1}, {'/root': 2}, ['/root/foo']),
-        ({'/root/foo': 1}, {}, ['/root/foo']),
-    ),
-)
-def test_deduplicate_directories_removes_child_paths_on_the_same_filesystem(
-    directories, additional_directories, expected_directories
-):
-    assert (
-        module.deduplicate_directories(directories, additional_directories) == expected_directories
+    assert device_map == (
+        Pattern('/foo', device=55),
+        Pattern('bar', device=66),
     )
 
 
-def test_pattern_root_directories_deals_with_none_patterns():
-    assert module.pattern_root_directories(patterns=None) == []
-
-
-def test_pattern_root_directories_parses_roots_and_ignores_others():
-    assert module.pattern_root_directories(
-        ['R /root', '+ /root/foo', '- /root/foo/bar', 'R /baz']
-    ) == ['/root', '/baz']
+def test_device_map_patterns_with_existing_device_id_does_not_overwrite_it():
+    flexmock(module.os.path).should_receive('exists').and_return(True)
+    flexmock(module.os).should_receive('stat').with_args('/foo').and_return(flexmock(st_dev=55))
+    flexmock(module.os).should_receive('stat').with_args('/bar').and_return(flexmock(st_dev=100))
 
+    device_map = module.device_map_patterns((Pattern('/foo'), Pattern('/bar', device=66)))
 
-def test_process_source_directories_includes_source_directories():
-    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
-        '/working'
+    assert device_map == (
+        Pattern('/foo', device=55),
+        Pattern('/bar', device=66),
     )
-    flexmock(module).should_receive('deduplicate_directories').and_return(('foo', 'bar'))
-    flexmock(module).should_receive('map_directories_to_devices').and_return({})
-    flexmock(module).should_receive('expand_directories').with_args(
-        ('foo', 'bar'), working_directory='/working'
-    ).and_return(()).once()
-    flexmock(module).should_receive('pattern_root_directories').and_return(())
-    flexmock(module).should_receive('expand_directories').with_args(
-        (), working_directory='/working'
-    ).and_return(())
 
-    assert module.process_source_directories(
-        config={'source_directories': ['foo', 'bar']},
-    ) == ('foo', 'bar')
+
+@pytest.mark.parametrize(
+    'patterns,expected_patterns',
+    (
+        ((Pattern('/', device=1), Pattern('/root', device=1)), (Pattern('/', device=1),)),
+        ((Pattern('/', device=1), Pattern('/root/', device=1)), (Pattern('/', device=1),)),
+        (
+            (Pattern('/', device=1), Pattern('/root', device=2)),
+            (Pattern('/', device=1), Pattern('/root', device=2)),
+        ),
+        ((Pattern('/root', device=1), Pattern('/', device=1)), (Pattern('/', device=1),)),
+        (
+            (Pattern('/root', device=1), Pattern('/root/foo', device=1)),
+            (Pattern('/root', device=1),),
+        ),
+        (
+            (Pattern('/root/', device=1), Pattern('/root/foo', device=1)),
+            (Pattern('/root/', device=1),),
+        ),
+        (
+            (Pattern('/root', device=1), Pattern('/root/foo/', device=1)),
+            (Pattern('/root', device=1),),
+        ),
+        (
+            (Pattern('/root', device=1), Pattern('/root/foo', device=2)),
+            (Pattern('/root', device=1), Pattern('/root/foo', device=2)),
+        ),
+        (
+            (Pattern('/root/foo', device=1), Pattern('/root', device=1)),
+            (Pattern('/root', device=1),),
+        ),
+        (
+            (Pattern('/root', device=None), Pattern('/root/foo', device=None)),
+            (Pattern('/root'), Pattern('/root/foo')),
+        ),
+        (
+            (
+                Pattern('/root', device=1),
+                Pattern('/etc', device=1),
+                Pattern('/root/foo/bar', device=1),
+            ),
+            (Pattern('/root', device=1), Pattern('/etc', device=1)),
+        ),
+        (
+            (
+                Pattern('/root', device=1),
+                Pattern('/root/foo', device=1),
+                Pattern('/root/foo/bar', device=1),
+            ),
+            (Pattern('/root', device=1),),
+        ),
+        ((Pattern('/dup', device=1), Pattern('/dup', device=1)), (Pattern('/dup', device=1),)),
+        (
+            (Pattern('/foo', device=1), Pattern('/bar', device=1)),
+            (Pattern('/foo', device=1), Pattern('/bar', device=1)),
+        ),
+        (
+            (Pattern('/foo', device=1), Pattern('/bar', device=2)),
+            (Pattern('/foo', device=1), Pattern('/bar', device=2)),
+        ),
+        ((Pattern('/root/foo', device=1),), (Pattern('/root/foo', device=1),)),
+        (
+            (Pattern('/', device=1), Pattern('/root', Pattern_type.INCLUDE, device=1)),
+            (Pattern('/', device=1), Pattern('/root', Pattern_type.INCLUDE, device=1)),
+        ),
+        (
+            (Pattern('/root', Pattern_type.INCLUDE, device=1), Pattern('/', device=1)),
+            (Pattern('/root', Pattern_type.INCLUDE, device=1), Pattern('/', device=1)),
+        ),
+    ),
+)
+def test_deduplicate_patterns_omits_child_paths_on_the_same_filesystem(patterns, expected_patterns):
+    assert module.deduplicate_patterns(patterns) == expected_patterns
 
 
-def test_process_source_directories_prefers_source_directory_argument_to_config():
-    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
-        '/working'
+def test_process_patterns_includes_patterns():
+    flexmock(module).should_receive('deduplicate_patterns').and_return(
+        (Pattern('foo'), Pattern('bar'))
     )
-    flexmock(module).should_receive('deduplicate_directories').and_return(('foo', 'bar'))
-    flexmock(module).should_receive('map_directories_to_devices').and_return({})
-    flexmock(module).should_receive('expand_directories').with_args(
-        ('foo', 'bar'), working_directory='/working'
+    flexmock(module).should_receive('device_map_patterns').and_return({})
+    flexmock(module).should_receive('expand_patterns').with_args(
+        (Pattern('foo'), Pattern('bar')),
+        working_directory='/working',
+        skip_paths=set(),
     ).and_return(()).once()
-    flexmock(module).should_receive('pattern_root_directories').and_return(())
-    flexmock(module).should_receive('expand_directories').with_args(
-        (), working_directory='/working'
-    ).and_return(())
 
-    assert module.process_source_directories(
-        config={'source_directories': ['nope']},
-        source_directories=['foo', 'bar'],
-    ) == ('foo', 'bar')
+    assert module.process_patterns(
+        (Pattern('foo'), Pattern('bar')),
+        working_directory='/working',
+    ) == [Pattern('foo'), Pattern('bar')]
 
 
-def test_process_source_directories_skips_expand_for_requested_paths():
-    flexmock(module.borgmatic.config.paths).should_receive('get_working_directory').and_return(
-        '/working'
+def test_process_patterns_skips_expand_for_requested_paths():
+    skip_paths = {flexmock()}
+    flexmock(module).should_receive('deduplicate_patterns').and_return(
+        (Pattern('foo'), Pattern('bar'))
     )
-    flexmock(module).should_receive('deduplicate_directories').and_return(('foo', 'bar'))
-    flexmock(module).should_receive('map_directories_to_devices').and_return({})
-    flexmock(module).should_receive('expand_directories').with_args(
-        ('bar',), working_directory='/working'
+    flexmock(module).should_receive('device_map_patterns').and_return({})
+    flexmock(module).should_receive('expand_patterns').with_args(
+        (Pattern('foo'), Pattern('bar')),
+        working_directory='/working',
+        skip_paths=skip_paths,
     ).and_return(()).once()
-    flexmock(module).should_receive('pattern_root_directories').and_return(())
-    flexmock(module).should_receive('expand_directories').with_args(
-        (), working_directory='/working'
-    ).and_return(())
 
-    assert module.process_source_directories(
-        config={'source_directories': ['foo', 'bar']}, skip_expand_paths=('foo',)
-    ) == ('foo', 'bar')
+    assert module.process_patterns(
+        (Pattern('foo'), Pattern('bar')),
+        working_directory='/working',
+        skip_expand_paths=skip_paths,
+    ) == [Pattern('foo'), Pattern('bar')]
 
 
 def test_run_create_executes_and_calls_hooks_for_configured_repository():
@@ -236,7 +401,8 @@ def test_run_create_executes_and_calls_hooks_for_configured_repository():
     flexmock(module.borgmatic.hooks.dispatch).should_receive(
         'call_hooks_even_if_unconfigured'
     ).and_return({})
-    flexmock(module).should_receive('process_source_directories').and_return([])
+    flexmock(module).should_receive('collect_patterns').and_return(())
+    flexmock(module).should_receive('process_patterns').and_return([])
     flexmock(module.os.path).should_receive('join').and_return('/run/borgmatic/bootstrap')
     create_arguments = flexmock(
         repository=None,
@@ -278,7 +444,8 @@ def test_run_create_runs_with_selected_repository():
     flexmock(module.borgmatic.hooks.dispatch).should_receive(
         'call_hooks_even_if_unconfigured'
     ).and_return({})
-    flexmock(module).should_receive('process_source_directories').and_return([])
+    flexmock(module).should_receive('collect_patterns').and_return(())
+    flexmock(module).should_receive('process_patterns').and_return([])
     flexmock(module.os.path).should_receive('join').and_return('/run/borgmatic/bootstrap')
     create_arguments = flexmock(
         repository=flexmock(),
@@ -357,7 +524,8 @@ def test_run_create_produces_json():
     flexmock(module.borgmatic.hooks.dispatch).should_receive(
         'call_hooks_even_if_unconfigured'
     ).and_return({})
-    flexmock(module).should_receive('process_source_directories').and_return([])
+    flexmock(module).should_receive('collect_patterns').and_return(())
+    flexmock(module).should_receive('process_patterns').and_return([])
     flexmock(module.os.path).should_receive('join').and_return('/run/borgmatic/bootstrap')
     create_arguments = flexmock(
         repository=flexmock(),

tests/unit/hooks/data_source/test_bootstrap.py

@@ -27,7 +27,7 @@ def test_dump_data_sources_creates_manifest_file():
         log_prefix='test',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     )
 
@@ -43,7 +43,7 @@ def test_dump_data_sources_with_store_config_files_false_does_not_create_manifes
         log_prefix='test',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=True,
     )
 
@@ -58,7 +58,7 @@ def test_dump_data_sources_with_dry_run_does_not_create_manifest_file():
         log_prefix='test',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=True,
     )
 

tests/unit/hooks/data_source/test_btrfs.py

@@ -1,6 +1,7 @@
 import pytest
 from flexmock import flexmock
 
+from borgmatic.borg.pattern import Pattern, Pattern_style, Pattern_type
 from borgmatic.hooks.data_source import btrfs as module
 
 
@@ -80,7 +81,7 @@ def test_get_subvolumes_for_filesystem_skips_empty_filesystem_mount_points():
     assert module.get_subvolumes_for_filesystem('btrfs', ' ') == ()
 
 
-def test_get_subvolumes_collects_subvolumes_matching_source_directories_from_all_filesystems():
+def test_get_subvolumes_collects_subvolumes_matching_patterns_from_all_filesystems():
     flexmock(module).should_receive('get_filesystem_mount_points').and_return(('/mnt1', '/mnt2'))
     flexmock(module).should_receive('get_subvolumes_for_filesystem').with_args(
         'btrfs', '/mnt1'
@@ -91,22 +92,31 @@ def test_get_subvolumes_collects_subvolumes_matching_source_directories_from_all
 
     for path in ('/one', '/four'):
         flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-            'get_contained_directories'
-        ).with_args(path, object).and_return((path,))
+            'get_contained_patterns'
+        ).with_args(path, object).and_return((Pattern(path),))
     for path in ('/two', '/three'):
         flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-            'get_contained_directories'
+            'get_contained_patterns'
         ).with_args(path, object).and_return(())
 
     assert module.get_subvolumes(
-        'btrfs', 'findmnt', source_directories=['/one', '/four', '/five', '/six', '/mnt2', '/mnt3']
+        'btrfs',
+        'findmnt',
+        patterns=[
+            Pattern('/one'),
+            Pattern('/four'),
+            Pattern('/five'),
+            Pattern('/six'),
+            Pattern('/mnt2'),
+            Pattern('/mnt3'),
+        ],
     ) == (
-        module.Subvolume('/four', contained_source_directories=('/four',)),
-        module.Subvolume('/one', contained_source_directories=('/one',)),
+        module.Subvolume('/four', contained_patterns=(Pattern('/four'),)),
+        module.Subvolume('/one', contained_patterns=(Pattern('/one'),)),
     )
 
 
-def test_get_subvolumes_without_source_directories_collects_all_subvolumes_from_all_filesystems():
+def test_get_subvolumes_without_patterns_collects_all_subvolumes_from_all_filesystems():
     flexmock(module).should_receive('get_filesystem_mount_points').and_return(('/mnt1', '/mnt2'))
     flexmock(module).should_receive('get_subvolumes_for_filesystem').with_args(
         'btrfs', '/mnt1'
@@ -117,14 +127,14 @@ def test_get_subvolumes_without_source_directories_collects_all_subvolumes_from_
 
     for path in ('/one', '/two', '/three', '/four'):
         flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-            'get_contained_directories'
-        ).with_args(path, object).and_return((path,))
+            'get_contained_patterns'
+        ).with_args(path, object).and_return((Pattern(path),))
 
     assert module.get_subvolumes('btrfs', 'findmnt') == (
-        module.Subvolume('/four', contained_source_directories=('/four',)),
-        module.Subvolume('/one', contained_source_directories=('/one',)),
-        module.Subvolume('/three', contained_source_directories=('/three',)),
-        module.Subvolume('/two', contained_source_directories=('/two',)),
+        module.Subvolume('/four', contained_patterns=(Pattern('/four'),)),
+        module.Subvolume('/one', contained_patterns=(Pattern('/one'),)),
+        module.Subvolume('/three', contained_patterns=(Pattern('/three'),)),
+        module.Subvolume('/two', contained_patterns=(Pattern('/two'),)),
     )
 
 
@@ -144,32 +154,51 @@ def test_make_snapshot_path_includes_stripped_subvolume_path(
 
 
 @pytest.mark.parametrize(
-    'subvolume_path,source_directory_path,expected_path',
+    'subvolume_path,pattern,expected_pattern',
     (
-        ('/foo/bar', '/foo/bar/baz', '/foo/bar/.borgmatic-snapshot-1234/./foo/bar/baz'),
-        ('/foo/bar', '/foo/bar', '/foo/bar/.borgmatic-snapshot-1234/./foo/bar'),
-        ('/', '/foo', '/.borgmatic-snapshot-1234/./foo'),
-        ('/', '/', '/.borgmatic-snapshot-1234/./'),
+        (
+            '/foo/bar',
+            Pattern('/foo/bar/baz'),
+            Pattern('/foo/bar/.borgmatic-snapshot-1234/./foo/bar/baz'),
+        ),
+        ('/foo/bar', Pattern('/foo/bar'), Pattern('/foo/bar/.borgmatic-snapshot-1234/./foo/bar')),
+        (
+            '/foo/bar',
+            Pattern('^/foo/bar', Pattern_type.INCLUDE, Pattern_style.REGULAR_EXPRESSION),
+            Pattern(
+                '^/foo/bar/.borgmatic-snapshot-1234/./foo/bar',
+                Pattern_type.INCLUDE,
+                Pattern_style.REGULAR_EXPRESSION,
+            ),
+        ),
+        (
+            '/foo/bar',
+            Pattern('/foo/bar', Pattern_type.INCLUDE, Pattern_style.REGULAR_EXPRESSION),
+            Pattern(
+                '/foo/bar/.borgmatic-snapshot-1234/./foo/bar',
+                Pattern_type.INCLUDE,
+                Pattern_style.REGULAR_EXPRESSION,
+            ),
+        ),
+        ('/', Pattern('/foo'), Pattern('/.borgmatic-snapshot-1234/./foo')),
+        ('/', Pattern('/'), Pattern('/.borgmatic-snapshot-1234/./')),
     ),
 )
-def test_make_borg_source_directory_path_includes_slashdot_hack_and_stripped_source_directory_path(
-    subvolume_path, source_directory_path, expected_path
+def test_make_borg_snapshot_pattern_includes_slashdot_hack_and_stripped_pattern_path(
+    subvolume_path, pattern, expected_pattern
 ):
     flexmock(module.os).should_receive('getpid').and_return(1234)
 
-    assert (
-        module.make_borg_source_directory_path(subvolume_path, source_directory_path)
-        == expected_path
-    )
+    assert module.make_borg_snapshot_pattern(subvolume_path, pattern) == expected_pattern
 
 
-def test_dump_data_sources_snapshots_each_subvolume_and_updates_source_directories():
-    source_directories = ['/foo', '/mnt/subvol1']
+def test_dump_data_sources_snapshots_each_subvolume_and_updates_patterns():
+    patterns = [Pattern('/foo'), Pattern('/mnt/subvol1')]
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
@@ -184,18 +213,30 @@ def test_dump_data_sources_snapshots_each_subvolume_and_updates_source_directori
     flexmock(module).should_receive('snapshot_subvolume').with_args(
         'btrfs', '/mnt/subvol2', '/mnt/subvol2/.borgmatic-1234/mnt/subvol2'
     ).once()
-    flexmock(module).should_receive('make_snapshot_exclude_path').with_args(
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').with_args(
         '/mnt/subvol1'
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234')
-    flexmock(module).should_receive('make_snapshot_exclude_path').with_args(
+    ).and_return(
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        )
+    )
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').with_args(
         '/mnt/subvol2'
-    ).and_return('/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234')
-    flexmock(module).should_receive('make_borg_source_directory_path').with_args(
+    ).and_return(
+        Pattern(
+            '/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        )
+    )
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
         '/mnt/subvol1', object
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1')
-    flexmock(module).should_receive('make_borg_source_directory_path').with_args(
+    ).and_return(Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'))
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
         '/mnt/subvol2', object
-    ).and_return('/mnt/subvol2/.borgmatic-1234/mnt/subvol2')
+    ).and_return(Pattern('/mnt/subvol2/.borgmatic-1234/mnt/subvol2'))
 
     assert (
         module.dump_data_sources(
@@ -204,31 +245,37 @@ def test_dump_data_sources_snapshots_each_subvolume_and_updates_source_directori
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/foo',
-        '/mnt/subvol1/.borgmatic-1234/mnt/subvol1',
-        '/mnt/subvol2/.borgmatic-1234/mnt/subvol2',
+    assert patterns == [
+        Pattern('/foo'),
+        Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'),
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        ),
+        Pattern('/mnt/subvol2/.borgmatic-1234/mnt/subvol2'),
+        Pattern(
+            '/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        ),
     ]
     assert config == {
         'btrfs': {},
-        'exclude_patterns': [
-            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
-            '/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234',
-        ],
     }
 
 
 def test_dump_data_sources_uses_custom_btrfs_command_in_commands():
-    source_directories = ['/foo', '/mnt/subvol1']
+    patterns = [Pattern('/foo'), Pattern('/mnt/subvol1')]
     config = {'btrfs': {'btrfs_command': '/usr/local/bin/btrfs'}}
     flexmock(module).should_receive('get_subvolumes').and_return(
-        (module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),)
+        (module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),)
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
         '/mnt/subvol1/.borgmatic-1234/mnt/subvol1'
@@ -236,12 +283,18 @@ def test_dump_data_sources_uses_custom_btrfs_command_in_commands():
     flexmock(module).should_receive('snapshot_subvolume').with_args(
         '/usr/local/bin/btrfs', '/mnt/subvol1', '/mnt/subvol1/.borgmatic-1234/mnt/subvol1'
     ).once()
-    flexmock(module).should_receive('make_snapshot_exclude_path').with_args(
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').with_args(
         '/mnt/subvol1'
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234')
-    flexmock(module).should_receive('make_borg_source_directory_path').with_args(
+    ).and_return(
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        )
+    )
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
         '/mnt/subvol1', object
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1')
+    ).and_return(Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'))
 
     assert (
         module.dump_data_sources(
@@ -250,33 +303,35 @@ def test_dump_data_sources_uses_custom_btrfs_command_in_commands():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/foo',
-        '/mnt/subvol1/.borgmatic-1234/mnt/subvol1',
+    assert patterns == [
+        Pattern('/foo'),
+        Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'),
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        ),
     ]
     assert config == {
         'btrfs': {
             'btrfs_command': '/usr/local/bin/btrfs',
         },
-        'exclude_patterns': [
-            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
-        ],
     }
 
 
 def test_dump_data_sources_uses_custom_findmnt_command_in_commands():
-    source_directories = ['/foo', '/mnt/subvol1']
+    patterns = [Pattern('/foo'), Pattern('/mnt/subvol1')]
     config = {'btrfs': {'findmnt_command': '/usr/local/bin/findmnt'}}
     flexmock(module).should_receive('get_subvolumes').with_args(
-        'btrfs', '/usr/local/bin/findmnt', source_directories
+        'btrfs', '/usr/local/bin/findmnt', patterns
     ).and_return(
-        (module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),)
+        (module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),)
     ).once()
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
         '/mnt/subvol1/.borgmatic-1234/mnt/subvol1'
@@ -284,12 +339,18 @@ def test_dump_data_sources_uses_custom_findmnt_command_in_commands():
     flexmock(module).should_receive('snapshot_subvolume').with_args(
         'btrfs', '/mnt/subvol1', '/mnt/subvol1/.borgmatic-1234/mnt/subvol1'
     ).once()
-    flexmock(module).should_receive('make_snapshot_exclude_path').with_args(
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').with_args(
         '/mnt/subvol1'
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234')
-    flexmock(module).should_receive('make_borg_source_directory_path').with_args(
+    ).and_return(
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        )
+    )
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
         '/mnt/subvol1', object
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1')
+    ).and_return(Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'))
 
     assert (
         module.dump_data_sources(
@@ -298,37 +359,39 @@ def test_dump_data_sources_uses_custom_findmnt_command_in_commands():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/foo',
-        '/mnt/subvol1/.borgmatic-1234/mnt/subvol1',
+    assert patterns == [
+        Pattern('/foo'),
+        Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'),
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        ),
     ]
     assert config == {
         'btrfs': {
             'findmnt_command': '/usr/local/bin/findmnt',
         },
-        'exclude_patterns': [
-            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
-        ],
     }
 
 
-def test_dump_data_sources_with_dry_run_skips_snapshot_and_source_directories_update():
-    source_directories = ['/foo', '/mnt/subvol1']
+def test_dump_data_sources_with_dry_run_skips_snapshot_and_patterns_update():
+    patterns = [Pattern('/foo'), Pattern('/mnt/subvol1')]
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
-        (module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),)
+        (module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),)
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
         '/mnt/subvol1/.borgmatic-1234/mnt/subvol1'
     )
     flexmock(module).should_receive('snapshot_subvolume').never()
-    flexmock(module).should_receive('make_snapshot_exclude_path').never()
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').never()
 
     assert (
         module.dump_data_sources(
@@ -337,23 +400,23 @@ def test_dump_data_sources_with_dry_run_skips_snapshot_and_source_directories_up
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=True,
         )
         == []
     )
 
-    assert source_directories == ['/foo', '/mnt/subvol1']
+    assert patterns == [Pattern('/foo'), Pattern('/mnt/subvol1')]
     assert config == {'btrfs': {}}
 
 
-def test_dump_data_sources_without_matching_subvolumes_skips_snapshot_and_source_directories_update():
-    source_directories = ['/foo', '/mnt/subvol1']
+def test_dump_data_sources_without_matching_subvolumes_skips_snapshot_and_patterns_update():
+    patterns = [Pattern('/foo'), Pattern('/mnt/subvol1')]
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(())
     flexmock(module).should_receive('make_snapshot_path').never()
     flexmock(module).should_receive('snapshot_subvolume').never()
-    flexmock(module).should_receive('make_snapshot_exclude_path').never()
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').never()
 
     assert (
         module.dump_data_sources(
@@ -362,23 +425,23 @@ def test_dump_data_sources_without_matching_subvolumes_skips_snapshot_and_source
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == ['/foo', '/mnt/subvol1']
+    assert patterns == [Pattern('/foo'), Pattern('/mnt/subvol1')]
     assert config == {'btrfs': {}}
 
 
 def test_dump_data_sources_snapshots_adds_to_existing_exclude_patterns():
-    source_directories = ['/foo', '/mnt/subvol1']
+    patterns = [Pattern('/foo'), Pattern('/mnt/subvol1')]
     config = {'btrfs': {}, 'exclude_patterns': ['/bar']}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
@@ -393,18 +456,30 @@ def test_dump_data_sources_snapshots_adds_to_existing_exclude_patterns():
     flexmock(module).should_receive('snapshot_subvolume').with_args(
         'btrfs', '/mnt/subvol2', '/mnt/subvol2/.borgmatic-1234/mnt/subvol2'
     ).once()
-    flexmock(module).should_receive('make_snapshot_exclude_path').with_args(
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').with_args(
         '/mnt/subvol1'
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234')
-    flexmock(module).should_receive('make_snapshot_exclude_path').with_args(
+    ).and_return(
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        )
+    )
+    flexmock(module).should_receive('make_snapshot_exclude_pattern').with_args(
         '/mnt/subvol2'
-    ).and_return('/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234')
-    flexmock(module).should_receive('make_borg_source_directory_path').with_args(
+    ).and_return(
+        Pattern(
+            '/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        )
+    )
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
         '/mnt/subvol1', object
-    ).and_return('/mnt/subvol1/.borgmatic-1234/mnt/subvol1')
-    flexmock(module).should_receive('make_borg_source_directory_path').with_args(
+    ).and_return(Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'))
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
         '/mnt/subvol2', object
-    ).and_return('/mnt/subvol2/.borgmatic-1234/mnt/subvol2')
+    ).and_return(Pattern('/mnt/subvol2/.borgmatic-1234/mnt/subvol2'))
 
     assert (
         module.dump_data_sources(
@@ -413,24 +488,30 @@ def test_dump_data_sources_snapshots_adds_to_existing_exclude_patterns():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/foo',
-        '/mnt/subvol1/.borgmatic-1234/mnt/subvol1',
-        '/mnt/subvol2/.borgmatic-1234/mnt/subvol2',
+    assert patterns == [
+        Pattern('/foo'),
+        Pattern('/mnt/subvol1/.borgmatic-1234/mnt/subvol1'),
+        Pattern(
+            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        ),
+        Pattern('/mnt/subvol2/.borgmatic-1234/mnt/subvol2'),
+        Pattern(
+            '/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234',
+            Pattern_type.EXCLUDE,
+            Pattern_style.FNMATCH,
+        ),
     ]
     assert config == {
         'btrfs': {},
-        'exclude_patterns': [
-            '/bar',
-            '/mnt/subvol1/.borgmatic-1234/mnt/subvol1/.borgmatic-1234',
-            '/mnt/subvol2/.borgmatic-1234/mnt/subvol2/.borgmatic-1234',
-        ],
+        'exclude_patterns': ['/bar'],
     }
 
 
@@ -438,8 +519,8 @@ def test_remove_data_source_dumps_deletes_snapshots():
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
@@ -582,8 +663,8 @@ def test_remove_data_source_dumps_with_dry_run_skips_deletes():
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
@@ -665,8 +746,8 @@ def test_remove_data_source_without_snapshots_skips_deletes():
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
@@ -709,8 +790,8 @@ def test_remove_data_source_dumps_with_delete_snapshot_file_not_found_error_bail
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(
@@ -773,8 +854,8 @@ def test_remove_data_source_dumps_with_delete_snapshot_called_process_error_bail
     config = {'btrfs': {}}
     flexmock(module).should_receive('get_subvolumes').and_return(
         (
-            module.Subvolume('/mnt/subvol1', contained_source_directories=('/mnt/subvol1',)),
-            module.Subvolume('/mnt/subvol2', contained_source_directories=('/mnt/subvol2',)),
+            module.Subvolume('/mnt/subvol1', contained_patterns=(Pattern('/mnt/subvol1'),)),
+            module.Subvolume('/mnt/subvol2', contained_patterns=(Pattern('/mnt/subvol2'),)),
         )
     )
     flexmock(module).should_receive('make_snapshot_path').with_args('/mnt/subvol1').and_return(

tests/unit/hooks/data_source/test_lvm.py

@@ -1,10 +1,11 @@
 import pytest
 from flexmock import flexmock
 
+from borgmatic.borg.pattern import Pattern, Pattern_style, Pattern_type
 from borgmatic.hooks.data_source import lvm as module
 
 
-def test_get_logical_volumes_filters_by_source_directories():
+def test_get_logical_volumes_filters_by_patterns():
     flexmock(module.borgmatic.execute).should_receive(
         'execute_command_and_capture_output'
     ).and_return(
@@ -36,28 +37,30 @@ def test_get_logical_volumes_filters_by_source_directories():
         }
         '''
     )
-    contained = {'/mnt/lvolume', '/mnt/lvolume/subdir'}
+    contained = {Pattern('/mnt/lvolume'), Pattern('/mnt/lvolume/subdir')}
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).with_args(None, contained).never()
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
-    ).with_args('/mnt/lvolume', contained).and_return(('/mnt/lvolume', '/mnt/lvolume/subdir'))
+        'get_contained_patterns'
+    ).with_args('/mnt/lvolume', contained).and_return(
+        (Pattern('/mnt/lvolume'), Pattern('/mnt/lvolume/subdir'))
+    )
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).with_args('/mnt/other', contained).and_return(())
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).with_args('/mnt/notlvm', contained).never()
 
     assert module.get_logical_volumes(
-        'lsblk', source_directories=('/mnt/lvolume', '/mnt/lvolume/subdir')
+        'lsblk', patterns=(Pattern('/mnt/lvolume'), Pattern('/mnt/lvolume/subdir'))
     ) == (
         module.Logical_volume(
-            'vgroup-lvolume',
-            '/dev/mapper/vgroup-lvolume',
-            '/mnt/lvolume',
-            ('/mnt/lvolume', '/mnt/lvolume/subdir'),
+            name='vgroup-lvolume',
+            device_path='/dev/mapper/vgroup-lvolume',
+            mount_point='/mnt/lvolume',
+            contained_patterns=(Pattern('/mnt/lvolume'), Pattern('/mnt/lvolume/subdir')),
         ),
     )
 
@@ -68,12 +71,12 @@ def test_get_logical_volumes_with_invalid_lsblk_json_errors():
     ).and_return('{')
 
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).never()
 
     with pytest.raises(ValueError):
         module.get_logical_volumes(
-            'lsblk', source_directories=('/mnt/lvolume', '/mnt/lvolume/subdir')
+            'lsblk', patterns=(Pattern('/mnt/lvolume'), Pattern('/mnt/lvolume/subdir'))
         )
 
 
@@ -83,12 +86,12 @@ def test_get_logical_volumes_with_lsblk_json_missing_keys_errors():
     ).and_return('{"block_devices": [{}]}')
 
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).never()
 
     with pytest.raises(ValueError):
         module.get_logical_volumes(
-            'lsblk', source_directories=('/mnt/lvolume', '/mnt/lvolume/subdir')
+            'lsblk', patterns=(Pattern('/mnt/lvolume'), Pattern('/mnt/lvolume/subdir'))
         )
 
 
@@ -130,22 +133,56 @@ def test_snapshot_logical_volume_with_non_percentage_snapshot_name_uses_lvcreate
     module.snapshot_logical_volume('lvcreate', 'snap', '/dev/snap', '10TB')
 
 
-def test_dump_data_sources_snapshots_and_mounts_and_updates_source_directories():
+@pytest.mark.parametrize(
+    'pattern,expected_pattern',
+    (
+        (
+            Pattern('/foo/bar/baz'),
+            Pattern('/run/borgmatic/lvm_snapshots/./foo/bar/baz'),
+        ),
+        (Pattern('/foo/bar'), Pattern('/run/borgmatic/lvm_snapshots/./foo/bar')),
+        (
+            Pattern('^/foo/bar', Pattern_type.INCLUDE, Pattern_style.REGULAR_EXPRESSION),
+            Pattern(
+                '^/run/borgmatic/lvm_snapshots/./foo/bar',
+                Pattern_type.INCLUDE,
+                Pattern_style.REGULAR_EXPRESSION,
+            ),
+        ),
+        (
+            Pattern('/foo/bar', Pattern_type.INCLUDE, Pattern_style.REGULAR_EXPRESSION),
+            Pattern(
+                '/run/borgmatic/lvm_snapshots/./foo/bar',
+                Pattern_type.INCLUDE,
+                Pattern_style.REGULAR_EXPRESSION,
+            ),
+        ),
+        (Pattern('/foo'), Pattern('/run/borgmatic/lvm_snapshots/./foo')),
+        (Pattern('/'), Pattern('/run/borgmatic/lvm_snapshots/./')),
+    ),
+)
+def test_make_borg_snapshot_pattern_includes_slashdot_hack_and_stripped_pattern_path(
+    pattern, expected_pattern
+):
+    assert module.make_borg_snapshot_pattern(pattern, '/run/borgmatic') == expected_pattern
+
+
+def test_dump_data_sources_snapshots_and_mounts_and_updates_patterns():
     config = {'lvm': {}}
-    source_directories = ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    patterns = [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
     flexmock(module).should_receive('get_logical_volumes').and_return(
         (
             module.Logical_volume(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -172,6 +209,12 @@ def test_dump_data_sources_snapshots_and_mounts_and_updates_source_directories()
     flexmock(module).should_receive('mount_snapshot').with_args(
         'mount', '/dev/lvolume2_snap', '/run/borgmatic/lvm_snapshots/mnt/lvolume2'
     ).once()
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume1/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'))
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume2'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'))
 
     assert (
         module.dump_data_sources(
@@ -180,21 +223,21 @@ def test_dump_data_sources_snapshots_and_mounts_and_updates_source_directories()
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir',
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume2',
+    assert patterns == [
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'),
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'),
     ]
 
 
 def test_dump_data_sources_with_no_logical_volumes_skips_snapshots():
     config = {'lvm': {}}
-    source_directories = ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    patterns = [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
     flexmock(module).should_receive('get_logical_volumes').and_return(())
     flexmock(module).should_receive('snapshot_logical_volume').never()
     flexmock(module).should_receive('mount_snapshot').never()
@@ -206,31 +249,31 @@ def test_dump_data_sources_with_no_logical_volumes_skips_snapshots():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    assert patterns == [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
 
 
 def test_dump_data_sources_uses_snapshot_size_for_snapshot():
     config = {'lvm': {'snapshot_size': '1000PB'}}
-    source_directories = ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    patterns = [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
     flexmock(module).should_receive('get_logical_volumes').and_return(
         (
             module.Logical_volume(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -263,6 +306,12 @@ def test_dump_data_sources_uses_snapshot_size_for_snapshot():
     flexmock(module).should_receive('mount_snapshot').with_args(
         'mount', '/dev/lvolume2_snap', '/run/borgmatic/lvm_snapshots/mnt/lvolume2'
     ).once()
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume1/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'))
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume2'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'))
 
     assert (
         module.dump_data_sources(
@@ -271,15 +320,15 @@ def test_dump_data_sources_uses_snapshot_size_for_snapshot():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir',
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume2',
+    assert patterns == [
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'),
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'),
     ]
 
 
@@ -292,20 +341,20 @@ def test_dump_data_sources_uses_custom_commands():
             'mount_command': '/usr/local/bin/mount',
         },
     }
-    source_directories = ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    patterns = [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
     flexmock(module).should_receive('get_logical_volumes').and_return(
         (
             module.Logical_volume(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -338,6 +387,12 @@ def test_dump_data_sources_uses_custom_commands():
     flexmock(module).should_receive('mount_snapshot').with_args(
         '/usr/local/bin/mount', '/dev/lvolume2_snap', '/run/borgmatic/lvm_snapshots/mnt/lvolume2'
     ).once()
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume1/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'))
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume2'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'))
 
     assert (
         module.dump_data_sources(
@@ -346,34 +401,34 @@ def test_dump_data_sources_uses_custom_commands():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir',
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume2',
+    assert patterns == [
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'),
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'),
     ]
 
 
-def test_dump_data_sources_with_dry_run_skips_snapshots_and_does_not_touch_source_directories():
+def test_dump_data_sources_with_dry_run_skips_snapshots_and_does_not_touch_patterns():
     config = {'lvm': {}}
-    source_directories = ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    patterns = [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
     flexmock(module).should_receive('get_logical_volumes').and_return(
         (
             module.Logical_volume(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -398,34 +453,34 @@ def test_dump_data_sources_with_dry_run_skips_snapshots_and_does_not_touch_sourc
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=True,
         )
         == []
     )
 
-    assert source_directories == [
-        '/mnt/lvolume1/subdir',
-        '/mnt/lvolume2',
+    assert patterns == [
+        Pattern('/mnt/lvolume1/subdir'),
+        Pattern('/mnt/lvolume2'),
     ]
 
 
-def test_dump_data_sources_ignores_mismatch_between_source_directories_and_contained_source_directories():
+def test_dump_data_sources_ignores_mismatch_between_given_patterns_and_contained_patterns():
     config = {'lvm': {}}
-    source_directories = ['/hmm']
+    patterns = [Pattern('/hmm')]
     flexmock(module).should_receive('get_logical_volumes').and_return(
         (
             module.Logical_volume(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -452,6 +507,12 @@ def test_dump_data_sources_ignores_mismatch_between_source_directories_and_conta
     flexmock(module).should_receive('mount_snapshot').with_args(
         'mount', '/dev/lvolume2_snap', '/run/borgmatic/lvm_snapshots/mnt/lvolume2'
     ).once()
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume1/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'))
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/lvolume2'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'))
 
     assert (
         module.dump_data_sources(
@@ -460,35 +521,35 @@ def test_dump_data_sources_ignores_mismatch_between_source_directories_and_conta
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [
-        '/hmm',
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir',
-        '/run/borgmatic/lvm_snapshots/./mnt/lvolume2',
+    assert patterns == [
+        Pattern('/hmm'),
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume1/subdir'),
+        Pattern('/run/borgmatic/lvm_snapshots/./mnt/lvolume2'),
     ]
 
 
 def test_dump_data_sources_with_missing_snapshot_errors():
     config = {'lvm': {}}
-    source_directories = ['/mnt/lvolume1/subdir', '/mnt/lvolume2']
+    patterns = [Pattern('/mnt/lvolume1/subdir'), Pattern('/mnt/lvolume2')]
     flexmock(module).should_receive('get_logical_volumes').and_return(
         (
             module.Logical_volume(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -514,7 +575,7 @@ def test_dump_data_sources_with_missing_snapshot_errors():
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
 
@@ -627,13 +688,13 @@ def test_remove_data_source_dumps_unmounts_and_remove_snapshots():
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -736,13 +797,13 @@ def test_remove_data_source_dumps_with_missing_snapshot_directory_skips_unmount(
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -781,13 +842,13 @@ def test_remove_data_source_dumps_with_missing_snapshot_mount_path_skips_unmount
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -839,13 +900,13 @@ def test_remove_data_source_dumps_with_successful_mount_point_removal_skips_unmo
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -897,13 +958,13 @@ def test_remove_data_source_dumps_bails_for_missing_umount_command():
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -941,13 +1002,13 @@ def test_remove_data_source_dumps_bails_for_umount_command_error():
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -985,13 +1046,13 @@ def test_remove_data_source_dumps_bails_for_missing_lvs_command():
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -1029,13 +1090,13 @@ def test_remove_data_source_dumps_bails_for_lvs_command_error():
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )
@@ -1075,13 +1136,13 @@ def test_remove_data_source_with_dry_run_skips_snapshot_unmount_and_delete():
                 name='lvolume1',
                 device_path='/dev/lvolume1',
                 mount_point='/mnt/lvolume1',
-                contained_source_directories=('/mnt/lvolume1/subdir',),
+                contained_patterns=(Pattern('/mnt/lvolume1/subdir'),),
             ),
             module.Logical_volume(
                 name='lvolume2',
                 device_path='/dev/lvolume2',
                 mount_point='/mnt/lvolume2',
-                contained_source_directories=('/mnt/lvolume2',),
+                contained_patterns=(Pattern('/mnt/lvolume2'),),
             ),
         )
     )

tests/unit/hooks/data_source/test_mariadb.py

@@ -80,7 +80,7 @@ def test_dump_data_sources_dumps_each_database():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -111,7 +111,7 @@ def test_dump_data_sources_dumps_with_password():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -137,7 +137,7 @@ def test_dump_data_sources_dumps_all_databases_at_once():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -166,7 +166,7 @@ def test_dump_data_sources_dumps_all_databases_separately_when_format_configured
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -478,7 +478,7 @@ def test_dump_data_sources_errors_for_missing_all_databases():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
 
@@ -498,7 +498,7 @@ def test_dump_data_sources_does_not_error_for_missing_all_databases_with_dry_run
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=True,
         )
         == []

tests/unit/hooks/data_source/test_mongodb.py

@@ -48,7 +48,7 @@ def test_dump_data_sources_runs_mongodump_for_each_database():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -71,7 +71,7 @@ def test_dump_data_sources_with_dry_run_skips_mongodump():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=True,
         )
         == []
@@ -110,7 +110,7 @@ def test_dump_data_sources_runs_mongodump_with_hostname_and_port():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -156,7 +156,7 @@ def test_dump_data_sources_runs_mongodump_with_username_and_password():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -182,7 +182,7 @@ def test_dump_data_sources_runs_mongodump_with_directory_format():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == []
@@ -218,7 +218,7 @@ def test_dump_data_sources_runs_mongodump_with_options():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -244,7 +244,7 @@ def test_dump_data_sources_runs_mongodumpall_for_all_databases():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 

tests/unit/hooks/data_source/test_mysql.py

@@ -80,7 +80,7 @@ def test_dump_data_sources_dumps_each_database():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -111,7 +111,7 @@ def test_dump_data_sources_dumps_with_password():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -137,7 +137,7 @@ def test_dump_data_sources_dumps_all_databases_at_once():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -166,7 +166,7 @@ def test_dump_data_sources_dumps_all_databases_separately_when_format_configured
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -476,7 +476,7 @@ def test_dump_data_sources_errors_for_missing_all_databases():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
 
@@ -496,7 +496,7 @@ def test_dump_data_sources_does_not_error_for_missing_all_databases_with_dry_run
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=True,
         )
         == []

tests/unit/hooks/data_source/test_postgresql.py

@@ -258,7 +258,7 @@ def test_dump_data_sources_runs_pg_dump_for_each_database():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -278,7 +278,7 @@ def test_dump_data_sources_raises_when_no_database_names_to_dump():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
 
@@ -295,7 +295,7 @@ def test_dump_data_sources_does_not_raise_when_no_database_names_to_dump():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=True,
     ) == []
 
@@ -321,7 +321,7 @@ def test_dump_data_sources_with_duplicate_dump_skips_pg_dump():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == []
@@ -349,7 +349,7 @@ def test_dump_data_sources_with_dry_run_skips_pg_dump():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=True,
         )
         == []
@@ -395,7 +395,7 @@ def test_dump_data_sources_runs_pg_dump_with_hostname_and_port():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -439,7 +439,7 @@ def test_dump_data_sources_runs_pg_dump_with_username_and_password():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -483,7 +483,7 @@ def test_dump_data_sources_with_username_injection_attack_gets_escaped():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -523,7 +523,7 @@ def test_dump_data_sources_runs_pg_dump_with_directory_format():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == []
@@ -566,7 +566,7 @@ def test_dump_data_sources_runs_pg_dump_with_options():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -596,7 +596,7 @@ def test_dump_data_sources_runs_pg_dumpall_for_all_databases():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 
@@ -638,7 +638,7 @@ def test_dump_data_sources_runs_non_default_pg_dump():
         'test.yaml',
         config_paths=('test.yaml',),
         borgmatic_runtime_directory='/run/borgmatic',
-        source_directories=[],
+        patterns=[],
         dry_run=False,
     ) == [process]
 

tests/unit/hooks/data_source/test_snapshot.py

@@ -1,26 +1,34 @@
+from borgmatic.borg.pattern import Pattern
 from borgmatic.hooks.data_source import snapshot as module
 
 
-def test_get_contained_directories_without_candidates_returns_empty():
-    assert module.get_contained_directories('/mnt', {}) == ()
+def test_get_contained_patterns_without_candidates_returns_empty():
+    assert module.get_contained_patterns('/mnt', {}) == ()
 
 
-def test_get_contained_directories_with_self_candidate_returns_self():
-    candidates = {'/foo', '/mnt', '/bar'}
+def test_get_contained_patterns_with_self_candidate_returns_self():
+    candidates = {Pattern('/foo'), Pattern('/mnt'), Pattern('/bar')}
 
-    assert module.get_contained_directories('/mnt', candidates) == ('/mnt',)
-    assert candidates == {'/foo', '/bar'}
+    assert module.get_contained_patterns('/mnt', candidates) == (Pattern('/mnt'),)
+    assert candidates == {Pattern('/foo'), Pattern('/bar')}
 
 
-def test_get_contained_directories_with_child_candidate_returns_child():
-    candidates = {'/foo', '/mnt/subdir', '/bar'}
+def test_get_contained_patterns_with_self_candidate_and_caret_prefix_returns_self():
+    candidates = {Pattern('^/foo'), Pattern('^/mnt'), Pattern('^/bar')}
 
-    assert module.get_contained_directories('/mnt', candidates) == ('/mnt/subdir',)
-    assert candidates == {'/foo', '/bar'}
+    assert module.get_contained_patterns('/mnt', candidates) == (Pattern('^/mnt'),)
+    assert candidates == {Pattern('^/foo'), Pattern('^/bar')}
 
 
-def test_get_contained_directories_with_grandchild_candidate_returns_child():
-    candidates = {'/foo', '/mnt/sub/dir', '/bar'}
+def test_get_contained_patterns_with_child_candidate_returns_child():
+    candidates = {Pattern('/foo'), Pattern('/mnt/subdir'), Pattern('/bar')}
 
-    assert module.get_contained_directories('/mnt', candidates) == ('/mnt/sub/dir',)
-    assert candidates == {'/foo', '/bar'}
+    assert module.get_contained_patterns('/mnt', candidates) == (Pattern('/mnt/subdir'),)
+    assert candidates == {Pattern('/foo'), Pattern('/bar')}
+
+
+def test_get_contained_patterns_with_grandchild_candidate_returns_child():
+    candidates = {Pattern('/foo'), Pattern('/mnt/sub/dir'), Pattern('/bar')}
+
+    assert module.get_contained_patterns('/mnt', candidates) == (Pattern('/mnt/sub/dir'),)
+    assert candidates == {Pattern('/foo'), Pattern('/bar')}

tests/unit/hooks/data_source/test_sqlite.py

@@ -33,7 +33,7 @@ def test_dump_data_sources_logs_and_skips_if_dump_already_exists():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == []
@@ -64,7 +64,7 @@ def test_dump_data_sources_dumps_each_database():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -102,7 +102,7 @@ def test_dump_data_sources_with_path_injection_attack_gets_escaped():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -131,7 +131,7 @@ def test_dump_data_sources_with_non_existent_path_warns_and_dumps_database():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -162,7 +162,7 @@ def test_dump_data_sources_with_name_all_warns_and_dumps_all_databases():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=False,
         )
         == processes
@@ -187,7 +187,7 @@ def test_dump_data_sources_does_not_dump_if_dry_run():
             'test.yaml',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=[],
+            patterns=[],
             dry_run=True,
         )
         == []

tests/unit/hooks/data_source/test_zfs.py

@@ -3,27 +3,35 @@ import os
 import pytest
 from flexmock import flexmock
 
+from borgmatic.borg.pattern import Pattern, Pattern_style, Pattern_type
 from borgmatic.hooks.data_source import zfs as module
 
 
-def test_get_datasets_to_backup_filters_datasets_by_source_directories():
+def test_get_datasets_to_backup_filters_datasets_by_patterns():
     flexmock(module.borgmatic.execute).should_receive(
         'execute_command_and_capture_output'
     ).and_return(
         'dataset\t/dataset\t-\nother\t/other\t-',
     )
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
-    ).with_args('/dataset', object).and_return(('/dataset',))
+        'get_contained_patterns'
+    ).with_args('/dataset', object).and_return((Pattern('/dataset'),))
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).with_args('/other', object).and_return(())
 
     assert module.get_datasets_to_backup(
-        'zfs', source_directories=('/foo', '/dataset', '/bar')
+        'zfs',
+        patterns=(
+            Pattern('/foo'),
+            Pattern('/dataset'),
+            Pattern('/bar'),
+        ),
     ) == (
         module.Dataset(
-            name='dataset', mount_point='/dataset', contained_source_directories=('/dataset',)
+            name='dataset',
+            mount_point='/dataset',
+            contained_patterns=(Pattern('/dataset'),),
         ),
     )
 
@@ -35,18 +43,18 @@ def test_get_datasets_to_backup_filters_datasets_by_user_property():
         'dataset\t/dataset\tauto\nother\t/other\t-',
     )
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
-    ).with_args('/dataset', object).never()
+        'get_contained_patterns'
+    ).with_args('/dataset', object).and_return(())
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).with_args('/other', object).and_return(())
 
-    assert module.get_datasets_to_backup('zfs', source_directories=('/foo', '/bar')) == (
+    assert module.get_datasets_to_backup('zfs', patterns=(Pattern('/foo'), Pattern('/bar'))) == (
         module.Dataset(
             name='dataset',
             mount_point='/dataset',
             auto_backup=True,
-            contained_source_directories=('/dataset',),
+            contained_patterns=(Pattern('/dataset'),),
         ),
     )
 
@@ -58,11 +66,11 @@ def test_get_datasets_to_backup_with_invalid_list_output_raises():
         'dataset',
     )
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
+        'get_contained_patterns'
     ).never()
 
     with pytest.raises(ValueError, match='zfs'):
-        module.get_datasets_to_backup('zfs', source_directories=('/foo', '/bar'))
+        module.get_datasets_to_backup('zfs', patterns=(Pattern('/foo'), Pattern('/bar')))
 
 
 def test_get_all_dataset_mount_points_does_not_filter_datasets():
@@ -72,8 +80,8 @@ def test_get_all_dataset_mount_points_does_not_filter_datasets():
         '/dataset\n/other',
     )
     flexmock(module.borgmatic.hooks.data_source.snapshot).should_receive(
-        'get_contained_directories'
-    ).and_return(('/dataset',))
+        'get_contained_patterns'
+    ).and_return((Pattern('/dataset'),))
 
     assert module.get_all_dataset_mount_points('zfs') == (
         ('/dataset'),
@@ -81,13 +89,47 @@ def test_get_all_dataset_mount_points_does_not_filter_datasets():
     )
 
 
-def test_dump_data_sources_snapshots_and_mounts_and_updates_source_directories():
+@pytest.mark.parametrize(
+    'pattern,expected_pattern',
+    (
+        (
+            Pattern('/foo/bar/baz'),
+            Pattern('/run/borgmatic/zfs_snapshots/./foo/bar/baz'),
+        ),
+        (Pattern('/foo/bar'), Pattern('/run/borgmatic/zfs_snapshots/./foo/bar')),
+        (
+            Pattern('^/foo/bar', Pattern_type.INCLUDE, Pattern_style.REGULAR_EXPRESSION),
+            Pattern(
+                '^/run/borgmatic/zfs_snapshots/./foo/bar',
+                Pattern_type.INCLUDE,
+                Pattern_style.REGULAR_EXPRESSION,
+            ),
+        ),
+        (
+            Pattern('/foo/bar', Pattern_type.INCLUDE, Pattern_style.REGULAR_EXPRESSION),
+            Pattern(
+                '/run/borgmatic/zfs_snapshots/./foo/bar',
+                Pattern_type.INCLUDE,
+                Pattern_style.REGULAR_EXPRESSION,
+            ),
+        ),
+        (Pattern('/foo'), Pattern('/run/borgmatic/zfs_snapshots/./foo')),
+        (Pattern('/'), Pattern('/run/borgmatic/zfs_snapshots/./')),
+    ),
+)
+def test_make_borg_snapshot_pattern_includes_slashdot_hack_and_stripped_pattern_path(
+    pattern, expected_pattern
+):
+    assert module.make_borg_snapshot_pattern(pattern, '/run/borgmatic') == expected_pattern
+
+
+def test_dump_data_sources_snapshots_and_mounts_and_updates_patterns():
     flexmock(module).should_receive('get_datasets_to_backup').and_return(
         (
             flexmock(
                 name='dataset',
                 mount_point='/mnt/dataset',
-                contained_source_directories=('/mnt/dataset/subdir',),
+                contained_patterns=(Pattern('/mnt/dataset/subdir'),),
             )
         )
     )
@@ -103,7 +145,10 @@ def test_dump_data_sources_snapshots_and_mounts_and_updates_source_directories()
         full_snapshot_name,
         module.os.path.normpath(snapshot_mount_path),
     ).once()
-    source_directories = ['/mnt/dataset/subdir']
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/dataset/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/zfs_snapshots/./mnt/dataset/subdir'))
+    patterns = [Pattern('/mnt/dataset/subdir')]
 
     assert (
         module.dump_data_sources(
@@ -112,13 +157,13 @@ def test_dump_data_sources_snapshots_and_mounts_and_updates_source_directories()
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [os.path.join(snapshot_mount_path, 'subdir')]
+    assert patterns == [Pattern(os.path.join(snapshot_mount_path, 'subdir'))]
 
 
 def test_dump_data_sources_with_no_datasets_skips_snapshots():
@@ -126,22 +171,22 @@ def test_dump_data_sources_with_no_datasets_skips_snapshots():
     flexmock(module.os).should_receive('getpid').and_return(1234)
     flexmock(module).should_receive('snapshot_dataset').never()
     flexmock(module).should_receive('mount_snapshot').never()
-    source_directories = ['/mnt/dataset']
+    patterns = [Pattern('/mnt/dataset')]
 
     assert (
         module.dump_data_sources(
             hook_config={},
-            config={'source_directories': '/mnt/dataset', 'zfs': {}},
+            config={'patterns': flexmock(), 'zfs': {}},
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == ['/mnt/dataset']
+    assert patterns == [Pattern('/mnt/dataset')]
 
 
 def test_dump_data_sources_uses_custom_commands():
@@ -150,7 +195,7 @@ def test_dump_data_sources_uses_custom_commands():
             flexmock(
                 name='dataset',
                 mount_point='/mnt/dataset',
-                contained_source_directories=('/mnt/dataset/subdir',),
+                contained_patterns=(Pattern('/mnt/dataset/subdir'),),
             )
         )
     )
@@ -166,7 +211,10 @@ def test_dump_data_sources_uses_custom_commands():
         full_snapshot_name,
         module.os.path.normpath(snapshot_mount_path),
     ).once()
-    source_directories = ['/mnt/dataset/subdir']
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/dataset/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/zfs_snapshots/./mnt/dataset/subdir'))
+    patterns = [Pattern('/mnt/dataset/subdir')]
     hook_config = {
         'zfs_command': '/usr/local/bin/zfs',
         'mount_command': '/usr/local/bin/mount',
@@ -176,53 +224,53 @@ def test_dump_data_sources_uses_custom_commands():
         module.dump_data_sources(
             hook_config=hook_config,
             config={
-                'source_directories': source_directories,
+                'patterns': flexmock(),
                 'zfs': hook_config,
             },
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == [os.path.join(snapshot_mount_path, 'subdir')]
+    assert patterns == [Pattern(os.path.join(snapshot_mount_path, 'subdir'))]
 
 
-def test_dump_data_sources_with_dry_run_skips_commands_and_does_not_touch_source_directories():
+def test_dump_data_sources_with_dry_run_skips_commands_and_does_not_touch_patterns():
     flexmock(module).should_receive('get_datasets_to_backup').and_return(
         (flexmock(name='dataset', mount_point='/mnt/dataset'),)
     )
     flexmock(module.os).should_receive('getpid').and_return(1234)
     flexmock(module).should_receive('snapshot_dataset').never()
     flexmock(module).should_receive('mount_snapshot').never()
-    source_directories = ['/mnt/dataset']
+    patterns = [Pattern('/mnt/dataset')]
 
     assert (
         module.dump_data_sources(
             hook_config={},
-            config={'source_directories': '/mnt/dataset', 'zfs': {}},
+            config={'patterns': ('R /mnt/dataset',), 'zfs': {}},
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=True,
         )
         == []
     )
 
-    assert source_directories == ['/mnt/dataset']
+    assert patterns == [Pattern('/mnt/dataset')]
 
 
-def test_dump_data_sources_ignores_mismatch_between_source_directories_and_contained_source_directories():
+def test_dump_data_sources_ignores_mismatch_between_given_patterns_and_contained_patterns():
     flexmock(module).should_receive('get_datasets_to_backup').and_return(
         (
             flexmock(
                 name='dataset',
                 mount_point='/mnt/dataset',
-                contained_source_directories=('/mnt/dataset/subdir',),
+                contained_patterns=(Pattern('/mnt/dataset/subdir'),),
             )
         )
     )
@@ -238,22 +286,25 @@ def test_dump_data_sources_ignores_mismatch_between_source_directories_and_conta
         full_snapshot_name,
         module.os.path.normpath(snapshot_mount_path),
     ).once()
-    source_directories = ['/hmm']
+    flexmock(module).should_receive('make_borg_snapshot_pattern').with_args(
+        Pattern('/mnt/dataset/subdir'), '/run/borgmatic'
+    ).and_return(Pattern('/run/borgmatic/zfs_snapshots/./mnt/dataset/subdir'))
+    patterns = [Pattern('/hmm')]
 
     assert (
         module.dump_data_sources(
             hook_config={},
-            config={'source_directories': '/mnt/dataset', 'zfs': {}},
+            config={'patterns': ('R /mnt/dataset',), 'zfs': {}},
             log_prefix='test',
             config_paths=('test.yaml',),
             borgmatic_runtime_directory='/run/borgmatic',
-            source_directories=source_directories,
+            patterns=patterns,
             dry_run=False,
         )
         == []
     )
 
-    assert source_directories == ['/hmm', os.path.join(snapshot_mount_path, 'subdir')]
+    assert patterns == [Pattern('/hmm'), Pattern(os.path.join(snapshot_mount_path, 'subdir'))]
 
 
 def test_get_all_snapshots_parses_list_output():