Revert "scm: use dulwich backend when fetching exps during clone/pull" (#9041)

Revert "scm: use dulwich backend when fetching exps during clone/pull (#9023)"

This reverts commit ed1ab7fa75.

.flake8

@@ -11,8 +11,9 @@ ignore=
     P1
     # use `!r` instead of surrounding by quotes
     B028
-max_line_length = 79
+max_line_length = 88
 max-complexity = 10
-select = B,C,E,F,W,T4,B902,T,P
+select = B,C,E,F,W,T4,B902,T,P,TYP
 show_source = true
 count = true
+min_python_version = 3.8.0

.git-blame-ignore-revs

@@ -0,0 +1,10 @@
+# The following commits will be ignored by the GitHub blame view.
+# You can configure `git blame` to use this file as the default ignore file:
+#     git config blame.ignoreRevsFile .git-blame-ignore-revs
+# or, you can also manually ignore commits from this file by doing:
+#     git blame --ignore-revs-file .git-blame-ignore-revs <filepath>
+# see the `blame.markIgnoredLines` and `blame.markUnblamableLines` options as well.
+# Refer to: https://git-scm.com/docs/git-blame#Documentation/git-blame.txt---ignore-revs-fileltfilegt
+
+# update black to 2023 stable style and change line-length to 88
+a86470ccbc693d6f0a4f8066cbd1357e5191c4ff

.github/workflows/plugin_tests.yaml

@@ -0,0 +1,54 @@
+name: Remote Plugin Tests
+
+on:
+  pull_request:
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  tests:
+    timeout-minutes: 45
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-20.04]
+        pyv: ["3.10"]
+        plugin: ["dvc-s3"]
+
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        path: dvc
+
+    - uses: actions/checkout@v3
+      with:
+        repository: iterative/${{ matrix.plugin }}
+        ref: main
+        path: ${{ matrix.plugin }}
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.pyv }}
+        cache: pip
+        cache-dependency-path: |
+          dvc/pyproject.toml
+          ${{ matrix.plugin }}/setup.cfg
+
+    - name: Install plugin + DVC@PR
+      run: |
+        pip install --upgrade pip wheel
+        pip install "./dvc[testing]"
+        pip install -e "./${{ matrix.plugin }}[tests]"
+
+    - name: Run plugin tests
+      timeout-minutes: 15
+      working-directory: ${{ matrix.plugin }}
+      run: pytest -v -n=auto

.pre-commit-config.yaml

@@ -35,18 +35,17 @@ repos:
         args:
           - --py38-plus
   - repo: https://github.com/psf/black
-    rev: 22.12.0
+    rev: 23.1.0
     hooks:
       - id: black
   - repo: https://github.com/PyCQA/isort
-    rev: 5.11.4
+    rev: 5.12.0
     hooks:
       - id: isort
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.223'
+    rev: 'v0.0.238'
     hooks:
       - id: ruff
-        args: ["--force-exclude"]
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.2
     hooks:
@@ -61,6 +60,7 @@ repos:
           - flake8-comprehensions
           - flake8-debugger
           - flake8-string-format
+          - flake8-typing-imports
   - repo: local
     hooks:
     - id: mypy

dvc/_debug.py

@@ -8,17 +8,19 @@ if TYPE_CHECKING:
 
 
 @contextmanager
-def viztracer_profile(path: Union[Callable[[], str], str], depth: int = -1):
+def viztracer_profile(
+    path: Union[Callable[[], str], str],
+    depth: int = -1,
+    log_async: bool = False,
+):
     try:
         import viztracer  # pylint: disable=import-error
     except ImportError:
-        print(  # noqa: T201
-            "Failed to run profiler, viztracer is not installed"
-        )
+        print("Failed to run profiler, viztracer is not installed")  # noqa: T201
         yield
         return
 
-    tracer = viztracer.VizTracer(max_stack_depth=depth)
+    tracer = viztracer.VizTracer(max_stack_depth=depth, log_async=log_async)
 
     tracer.start()
     yield
@@ -76,9 +78,7 @@ def instrument(html_output=False):
     try:
         from pyinstrument import Profiler  # pylint: disable=import-error
     except ImportError:
-        print(  # noqa: T201
-            "Failed to run profiler, pyinstrument is not installed"
-        )
+        print("Failed to run profiler, pyinstrument is not installed")  # noqa: T201
         yield
         return
 
@@ -182,10 +182,15 @@ def debugtools(args: Optional["Namespace"] = None, **kwargs):
                     separate_threads=kw.get("yappi_separate_threads"),
                 )
             )
-        if kw.get("viztracer") or kw.get("viztracer_depth"):
+        if (
+            kw.get("viztracer")
+            or kw.get("viztracer_depth")
+            or kw.get("viztracer_async")
+        ):
             path_func = _get_path_func("viztracer", "json")
             depth = kw.get("viztracer_depth") or -1
-            prof = viztracer_profile(path=path_func, depth=depth)
+            log_async = kw.get("viztracer_async") or False
+            prof = viztracer_profile(path=path_func, depth=depth, log_async=log_async)
             stack.enter_context(prof)
         yield
 
@@ -193,12 +198,8 @@ def debugtools(args: Optional["Namespace"] = None, **kwargs):
 def add_debugging_flags(parser):
     from argparse import SUPPRESS
 
-    parser.add_argument(
-        "--cprofile", action="store_true", default=False, help=SUPPRESS
-    )
-    parser.add_argument(
-        "--yappi", action="store_true", default=False, help=SUPPRESS
-    )
+    parser.add_argument("--cprofile", action="store_true", default=False, help=SUPPRESS)
+    parser.add_argument("--yappi", action="store_true", default=False, help=SUPPRESS)
     parser.add_argument(
         "--yappi-separate-threads",
         action="store_true",
@@ -209,10 +210,11 @@ def add_debugging_flags(parser):
         "--viztracer", action="store_true", default=False, help=SUPPRESS
     )
     parser.add_argument("--viztracer-depth", type=int, help=SUPPRESS)
-    parser.add_argument("--cprofile-dump", help=SUPPRESS)
     parser.add_argument(
-        "--pdb", action="store_true", default=False, help=SUPPRESS
+        "--viztracer-async", action="store_true", default=False, help=SUPPRESS
     )
+    parser.add_argument("--cprofile-dump", help=SUPPRESS)
+    parser.add_argument("--pdb", action="store_true", default=False, help=SUPPRESS)
     parser.add_argument(
         "--instrument", action="store_true", default=False, help=SUPPRESS
     )

dvc/analytics.py

@@ -82,10 +82,9 @@ def send(path):
 
 
 def _scm_in_use():
-    from scmrepo.noscm import NoSCM
-
     from dvc.exceptions import NotDvcRepoError
     from dvc.repo import Repo
+    from dvc.scm import NoSCM
 
     from .scm import SCM, SCMError
 
@@ -102,17 +101,24 @@ def _runtime_info():
     """
     Gather information from the environment where DVC runs to fill a report.
     """
-    from iterative_telemetry import find_or_create_user_id
+    from iterative_telemetry import _generate_ci_id, find_or_create_user_id
 
     from dvc import __version__
     from dvc.utils import is_binary
 
+    ci_id = _generate_ci_id()
+    if ci_id:
+        group_id, user_id = ci_id
+    else:
+        group_id, user_id = None, find_or_create_user_id()
+
     return {
         "dvc_version": __version__,
         "is_binary": is_binary(),
         "scm_class": _scm_in_use(),
         "system_info": _system_info(),
-        "user_id": find_or_create_user_id(),
+        "user_id": user_id,
+        "group_id": group_id,
     }
 
 

dvc/annotations.py

@@ -12,7 +12,7 @@ class Annotation:
     PARAM_META: ClassVar[str] = "meta"
 
     desc: Optional[str] = None
-    type: Optional[str] = None
+    type: Optional[str] = None  # noqa: A003
     labels: List[str] = field(default_factory=list)
     meta: Dict[str, Any] = field(default_factory=dict)
 

dvc/api/data.py

@@ -27,16 +27,14 @@ def get_url(path, repo=None, rev=None, remote=None):
         if not dvc_info:
             raise OutputNotFoundError(path, repo)
 
-        dvc_repo = info["repo"]
+        dvc_repo = info["repo"]  # pylint: disable=unsubscriptable-object
         md5 = dvc_info["md5"]
 
         return dvc_repo.cloud.get_url_for(remote, checksum=md5)
 
 
 class _OpenContextManager(GCM):
-    def __init__(
-        self, func, args, kwds
-    ):  # pylint: disable=super-init-not-called
+    def __init__(self, func, args, kwds):  # pylint: disable=super-init-not-called
         self.gen = func(*args, **kwds)
         self.func, self.args, self.kwds = (  # type: ignore[assignment]
             func,
@@ -45,9 +43,7 @@ class _OpenContextManager(GCM):
         )
 
     def __getattr__(self, name):
-        raise AttributeError(
-            "dvc.api.open() should be used in a with statement."
-        )
+        raise AttributeError("dvc.api.open() should be used in a with statement.")
 
 
 def open(  # noqa, pylint: disable=redefined-builtin

dvc/cachemgr.py

@@ -9,12 +9,11 @@ def _get_odb(repo, settings, fs=None):
         return None
 
     cls, config, fs_path = get_cloud_fs(repo, **settings)
-    config["tmp_dir"] = repo.tmp_dir
     fs = fs or cls(**config)
     return get_odb(fs, fs_path, state=repo.state, **config)
 
 
-class ODBManager:
+class CacheManager:
     CACHE_DIR = "cache"
     CLOUD_SCHEMES = [
         Schemes.S3,

dvc/cli/__init__.py

@@ -39,12 +39,17 @@ def parse_args(argv=None):
 
 def _log_unknown_exceptions() -> None:
     from dvc.info import get_dvc_info
-    from dvc.logger import FOOTER
+    from dvc.ui import ui
+    from dvc.utils import colorize
 
     logger.exception("unexpected error")
     if logger.isEnabledFor(logging.DEBUG):
         logger.debug("Version info for developers:\n%s", get_dvc_info())
-    logger.info(FOOTER)
+
+    q = colorize("Having any troubles?", "yellow")
+    link = colorize("https://dvc.org/support", "blue")
+    footer = f"\n{q} Hit us up at {link}, we are always happy to help!"
+    ui.error_write(footer)
 
 
 def _log_exceptions(exc: Exception) -> Optional[int]:
@@ -56,9 +61,11 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
 
         if exc.errno == errno.EMFILE:
             logger.exception(
-                "too many open files, please visit "
-                "{} to see how to handle this "
-                "problem".format(error_link("many-files")),
+                (
+                    "too many open files, please visit "
+                    "%s to see how to handle this problem"
+                ),
+                error_link("many-files"),
                 extra={"tb_only": True},
             )
         else:
@@ -80,7 +87,7 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
         if cmd:
             link = format_link("https://dvc.org/doc/install")
             hint = (
-                f"To install dvc with those dependencies, run:\n"
+                "To install dvc with those dependencies, run:\n"
                 "\n"
                 f"\t{cmd}\n"
                 "\n"
@@ -91,8 +98,10 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
             hint = f"\nPlease report this bug to {link}. Thank you!"
 
         logger.exception(
-            f"URL '{exc.url}' is supported but requires these missing "
-            f"dependencies: {exc.missing_deps}. {hint}",
+            "URL '%s' is supported but requires these missing dependencies: %s. %s",
+            exc.url,
+            exc.missing_deps,
+            hint,
             extra={"tb_only": True},
         )
         return None
@@ -101,7 +110,9 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
         link = format_link("https://man.dvc.org/remote/modify")
         logger.exception("configuration error")
         logger.exception(
-            f"{exc!s}\nLearn more about configuration settings at {link}.",
+            "%s\nLearn more about configuration settings at %s.",
+            exc,
+            link,
             extra={"tb_only": True},
         )
         return 251
@@ -113,9 +124,14 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
 
         directory = relpath(exc.directory)
         logger.exception(
-            f"Could not open pickled '{exc.type}' cache.\n"
-            f"Remove the '{directory}' directory and then retry this command."
-            f"\nSee {error_link('pickle')} for more information.",
+            (
+                "Could not open pickled '%s' cache.\n"
+                "Remove the '%s' directory and then retry this command."
+                "\nSee %s for more information."
+            ),
+            exc.type,
+            directory,
+            error_link("pickle"),
             extra={"tb_only": True},
         )
         return None
@@ -142,7 +158,7 @@ def main(argv=None):  # noqa: C901
     from dvc._debug import debugtools
     from dvc.config import ConfigError
     from dvc.exceptions import DvcException, NotDvcRepoError
-    from dvc.logger import disable_other_loggers, set_loggers_level
+    from dvc.logger import set_loggers_level
 
     # NOTE: stderr/stdout may be closed if we are running from dvc.daemon.
     # On Linux we directly call cli.main after double forking and closing
@@ -155,7 +171,6 @@ def main(argv=None):  # noqa: C901
         logging.disable(logging.INFO)
 
     args = None
-    disable_other_loggers()
 
     outerLogLevel = logger.level
     try:
@@ -172,6 +187,17 @@ def main(argv=None):  # noqa: C901
         if level is not None:
             set_loggers_level(level)
 
+        if level and level <= logging.DEBUG:
+            from platform import platform, python_implementation, python_version
+
+            from dvc import __version__
+            from dvc.utils.pkg import PKG
+
+            pyv = " ".join([python_implementation(), python_version()])
+            pkg = f" ({PKG})" if PKG else ""
+            logger.debug("v%s%s, %s on %s", __version__, pkg, pyv, platform())
+            logger.debug("command: %s", " ".join(argv or sys.argv))
+
         logger.trace(args)  # type: ignore[attr-defined]
 
         if not sys.stdout.closed and not args.quiet:

dvc/cli/actions.py

@@ -2,7 +2,7 @@ from argparse import _AppendAction
 
 
 class CommaSeparatedArgs(_AppendAction):  # pylint: disable=protected-access
-    def __call__(self, parser, namespace, values, option_string=None):
+    def __call__(self, parser, namespace, values, option_string=None):  # noqa: ARG002
         from funcy import ldistinct
 
         items = getattr(namespace, self.dest) or []
@@ -11,7 +11,7 @@ class CommaSeparatedArgs(_AppendAction):  # pylint: disable=protected-access
 
 
 class KeyValueArgs(_AppendAction):
-    def __call__(self, parser, namespace, values, option_string=None):
+    def __call__(self, parser, namespace, values, option_string=None):  # noqa: ARG002
         items = getattr(namespace, self.dest) or {}
         for value in filter(bool, values):
             key, _, value = value.partition("=")

dvc/cli/utils.py

@@ -28,7 +28,5 @@ def hide_subparsers_from_help(subparsers):
     # Need to set `add_help=False`, but avoid setting `help`
     # (not even to `argparse.SUPPPRESS`).
     # NOTE: The argument is the parent subparser, not the subcommand parser.
-    cmds = [
-        cmd for cmd, parser in subparsers.choices.items() if parser.add_help
-    ]
+    cmds = [cmd for cmd, parser in subparsers.choices.items() if parser.add_help]
     subparsers.metavar = "{{{}}}".format(",".join(cmds))

dvc/commands/add.py

@@ -41,10 +41,7 @@ def _add_annotating_args(parser: argparse.ArgumentParser) -> None:
 
 class CmdAdd(CmdBase):
     def run(self):
-        from dvc.exceptions import (
-            DvcException,
-            RecursiveAddingWhileUsingFilename,
-        )
+        from dvc.exceptions import DvcException, RecursiveAddingWhileUsingFilename
 
         try:
             if len(self.args.targets) > 1 and self.args.file:

dvc/commands/cache.py

@@ -68,10 +68,12 @@ def add_parser(subparsers, parent_parser):
     )
     cache_dir_parser.add_argument(
         "value",
-        help="Path to cache directory. Relative paths are resolved relative "
-        "to the current directory and saved to config relative to the "
-        "config file location. If no path is provided, it returns the "
-        "current cache directory.",
+        help=(
+            "Path to cache directory. Relative paths are resolved relative "
+            "to the current directory and saved to config relative to the "
+            "config file location. If no path is provided, it returns the "
+            "current cache directory."
+        ),
         nargs="?",
     ).complete = completion.DIR
     cache_dir_parser.set_defaults(func=CmdCacheDir)

dvc/commands/check_ignore.py

@@ -62,9 +62,7 @@ class CmdCheckIgnore(CmdBase):
             raise DvcException("cannot have both `targets` and `--stdin`")
 
         if self.args.non_matching and not self.args.details:
-            raise DvcException(
-                "`--non-matching` is only valid with `--details`"
-            )
+            raise DvcException("`--non-matching` is only valid with `--details`")
 
         if self.args.all and not self.args.details:
             raise DvcException("`--all` is only valid with `--details`")
@@ -80,9 +78,7 @@ class CmdCheckIgnore(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
-    ADD_HELP = (
-        "Check whether files or directories are excluded due to `.dvcignore`."
-    )
+    ADD_HELP = "Check whether files or directories are excluded due to `.dvcignore`."
 
     parser = subparsers.add_parser(
         "check-ignore",
@@ -103,16 +99,20 @@ def add_parser(subparsers, parent_parser):
         "--all",
         action="store_true",
         default=False,
-        help="Include the target paths which don't match any pattern "
-        "in the `--details` list.",
+        help=(
+            "Include the target paths which don't match any pattern "
+            "in the `--details` list."
+        ),
     )
     parser.add_argument(
         "-n",
         "--non-matching",
         action="store_true",
         default=False,
-        help="Include the target paths which don't match any pattern "
-        "in the `--details` list.",
+        help=(
+            "Include the target paths which don't match any pattern "
+            "in the `--details` list."
+        ),
     )
     parser.add_argument(
         "--stdin",

dvc/commands/checkout.py

@@ -22,9 +22,7 @@ def log_changes(stats):
             continue
 
         for entry in entries:
-            ui.write(
-                f"[{color}]{state[0].upper()}", entry, styled=True, sep="\t"
-            )
+            ui.write(f"[{color}]{state[0].upper()}", entry, styled=True, sep="\t")
 
 
 class CmdCheckout(CmdBase):
@@ -46,9 +44,7 @@ class CmdCheckout(CmdBase):
 
         if self.args.summary:
             default_message = "No changes."
-            msg = get_summary(
-                sorted(stats.items(), key=operator.itemgetter(0))
-            )
+            msg = get_summary(sorted(stats.items(), key=operator.itemgetter(0)))
             ui.write(msg or default_message)
         else:
             log_changes(stats)

dvc/commands/commit.py

@@ -24,11 +24,7 @@ class CmdCommit(CmdBase):
                     force=self.args.force,
                 )
             except DvcException:
-                logger.exception(
-                    "failed to commit{}".format(
-                        (" " + target) if target else ""
-                    )
-                )
+                logger.exception("failed to commit%s", (" " + target) if target else "")
                 return 1
         return 0
 

dvc/commands/config.py

@@ -17,9 +17,7 @@ def _name_type(value):
     match = re.match(NAME_REGEX, value)
     if not match:
         raise argparse.ArgumentTypeError(
-            "name argument should look like "
-            "remote.name.option or "
-            "section.option"
+            "name argument should look like remote.name.option or section.option"
         )
     return (
         bool(match.group("remote")),
@@ -70,9 +68,7 @@ class CmdConfig(CmdBaseNoRepo):
 
         for level in levels:
             conf = self.config.read(level)
-            prefix = self._config_file_prefix(
-                self.args.show_origin, self.config, level
-            )
+            prefix = self._config_file_prefix(self.args.show_origin, self.config, level)
             configs = list(self._format_config(conf, prefix))
             if configs:
                 ui.write("\n".join(configs))
@@ -131,9 +127,7 @@ class CmdConfig(CmdBaseNoRepo):
             raise ConfigError(f"{name} '{section}' doesn't exist")
 
         if opt and opt not in conf[section]:
-            raise ConfigError(
-                f"option '{opt}' doesn't exist in {name} '{section}'"
-            )
+            raise ConfigError(f"option '{opt}' doesn't exist in {name} '{section}'")
 
     def _get_appropriate_levels(self, levels):
         if levels:

dvc/commands/dag.py

@@ -86,9 +86,7 @@ def _collect_targets(repo, target, outs):
             targets.extend([str(out) for out in stage.outs])
             continue
 
-        for out in outs_trie.itervalues(  # noqa: B301
-            prefix=repo.fs.path.parts(path)
-        ):
+        for out in outs_trie.itervalues(prefix=repo.fs.path.parts(path)):  # noqa: B301
             targets.extend(str(out))
 
     return targets
@@ -204,7 +202,9 @@ def add_parser(subparsers, parent_parser):
     dag_parser.add_argument(
         "target",
         nargs="?",
-        help="Stage name or output to show pipeline for. "
-        "Finds all stages in the workspace by default.",
+        help=(
+            "Stage name or output to show pipeline for. "
+            "Finds all stages in the workspace by default."
+        ),
     )
     dag_parser.set_defaults(func=CmdDAG)

dvc/commands/data.py

@@ -8,11 +8,7 @@ from funcy import chunks, compact, log_durations
 from dvc.cli import completion
 from dvc.cli.actions import CommaSeparatedArgs
 from dvc.cli.command import CmdBase
-from dvc.cli.utils import (
-    append_doc_link,
-    fix_subparsers,
-    hide_subparsers_from_help,
-)
+from dvc.cli.utils import append_doc_link, fix_subparsers, hide_subparsers_from_help
 from dvc.ui import ui
 from dvc.utils import colorize
 
@@ -39,20 +35,19 @@ class CmdDataStatus(CmdBase):
     }
     HINTS = {
         "not_in_cache": ('use "dvc fetch <file>..." to download files',),
-        "committed": (
-            "git commit the corresponding dvc files to update the repo",
-        ),
+        "committed": ("git commit the corresponding dvc files to update the repo",),
         "uncommitted": (
             'use "dvc commit <file>..." to track changes',
             'use "dvc checkout <file>..." to discard changes',
         ),
         "untracked": (
-            'use "git add <file> ..." or '
-            '"dvc add <file>..." to commit to git or to dvc',
+            (
+                'use "git add <file> ..." or '
+                '"dvc add <file>..." to commit to git or to dvc'
+            ),
         ),
         "git_dirty": (
-            "there are {}changes not tracked by dvc, "
-            'use "git status" to see',
+            'there are {}changes not tracked by dvc, use "git status" to see',
         ),
     }
 
@@ -96,8 +91,7 @@ class CmdDataStatus(CmdBase):
 
             if isinstance(stage_status, dict):
                 items = [
-                    ": ".join([state, file])
-                    for file, state in stage_status.items()
+                    ": ".join([state, file]) for file, state in stage_status.items()
                 ]
             else:
                 items = stage_status
@@ -180,9 +174,7 @@ class CmdDataLs(CmdBase):
 
         filter_labels = set(self.args.labels)
         filter_types = set(self.args.type)
-        d = ls(
-            self.repo, targets=self.args.targets, recursive=self.args.recursive
-        )
+        d = ls(self.repo, targets=self.args.targets, recursive=self.args.recursive)
         self._show_table(
             d,
             filter_labels=filter_labels,
@@ -205,8 +197,7 @@ def add_parser(subparsers, parent_parser):
     fix_subparsers(data_subparsers)
 
     DATA_STATUS_HELP = (
-        "Show changes between the last git commit, "
-        "the dvcfiles and the workspace."
+        "Show changes between the last git commit, the dvcfiles and the workspace."
     )
     data_status_parser = data_subparsers.add_parser(
         "status",

dvc/commands/data_sync.py

@@ -262,9 +262,7 @@ def add_parser(subparsers, _parent_parser):
     push_parser.set_defaults(func=CmdDataPush)
 
     # Fetch
-    FETCH_HELP = (
-        "Download files or directories from remote storage to the cache."
-    )
+    FETCH_HELP = "Download files or directories from remote storage to the cache."
 
     fetch_parser = subparsers.add_parser(
         "fetch",
@@ -320,9 +318,7 @@ def add_parser(subparsers, _parent_parser):
     fetch_parser.set_defaults(func=CmdDataFetch)
 
     # Status
-    STATUS_HELP = (
-        "Show changed stages, compare local cache and a remote storage."
-    )
+    STATUS_HELP = "Show changed stages, compare local cache and a remote storage."
 
     status_parser = subparsers.add_parser(
         "status",
@@ -360,24 +356,29 @@ def add_parser(subparsers, _parent_parser):
         "--all-branches",
         action="store_true",
         default=False,
-        help="Show status of a local cache compared to a remote repository "
-        "for all branches.",
+        help=(
+            "Show status of a local cache compared to a remote repository "
+            "for all branches."
+        ),
     )
     status_parser.add_argument(
         "-T",
         "--all-tags",
         action="store_true",
         default=False,
-        help="Show status of a local cache compared to a remote repository "
-        "for all tags.",
+        help=(
+            "Show status of a local cache compared to a remote repository for all tags."
+        ),
     )
     status_parser.add_argument(
         "-A",
         "--all-commits",
         action="store_true",
         default=False,
-        help="Show status of a local cache compared to a remote repository "
-        "for all commits.",
+        help=(
+            "Show status of a local cache compared to a remote repository "
+            "for all commits."
+        ),
     )
     status_parser.add_argument(
         "-d",

dvc/commands/diff.py

@@ -112,9 +112,7 @@ class CmdDiff(CmdBase):
             return
 
         states_summary = ", ".join(
-            f"{summary[state]} {state}"
-            for state in states
-            if summary[state] > 0
+            f"{summary[state]} {state}" for state in states if summary[state] > 0
         )
         ui.write("files summary:", states_summary)
 
@@ -122,9 +120,7 @@ class CmdDiff(CmdBase):
         from dvc.exceptions import DvcException
 
         try:
-            diff = self.repo.diff(
-                self.args.a_rev, self.args.b_rev, self.args.targets
-            )
+            diff = self.repo.diff(self.args.a_rev, self.args.b_rev, self.args.targets)
             show_hash = self.args.show_hash
             hide_missing = self.args.b_rev or self.args.hide_missing
             if hide_missing:
@@ -133,9 +129,11 @@ class CmdDiff(CmdBase):
             for key, entries in diff.items():
                 entries = sorted(
                     entries,
-                    key=lambda entry: entry["path"]["old"]
-                    if isinstance(entry["path"], dict)
-                    else entry["path"],
+                    key=lambda entry: (
+                        entry["path"]["old"]
+                        if isinstance(entry["path"], dict)
+                        else entry["path"]
+                    ),
                 )
                 if not show_hash:
                     for entry in entries:
@@ -170,10 +168,7 @@ def add_parser(subparsers, parent_parser):
     diff_parser.add_argument(
         "--targets",
         nargs="*",
-        help=(
-            "Specific DVC-tracked files to compare. "
-            "Accepts one or more file paths."
-        ),
+        help="Specific DVC-tracked files to compare. Accepts one or more file paths.",
         metavar="<paths>",
     ).complete = completion.FILE
     diff_parser.add_argument(
@@ -184,7 +179,7 @@ def add_parser(subparsers, parent_parser):
     )
     diff_parser.add_argument(
         "b_rev",
-        help=("New Git commit to compare (defaults to the current workspace)"),
+        help="New Git commit to compare (defaults to the current workspace)",
         nargs="?",
     )
     diff_parser.add_argument(

dvc/commands/experiments/__init__.py

@@ -1,10 +1,6 @@
 import argparse
 
-from dvc.cli.utils import (
-    append_doc_link,
-    fix_subparsers,
-    hide_subparsers_from_help,
-)
+from dvc.cli.utils import append_doc_link, fix_subparsers, hide_subparsers_from_help
 from dvc.commands.experiments import (
     apply,
     branch,
@@ -54,8 +50,7 @@ def add_parser(subparsers, parent_parser):
 
     experiments_subparsers = experiments_parser.add_subparsers(
         dest="cmd",
-        help="Use `dvc experiments CMD --help` to display "
-        "command-specific help.",
+        help="Use `dvc experiments CMD --help` to display command-specific help.",
     )
 
     fix_subparsers(experiments_subparsers)

dvc/commands/experiments/apply.py

@@ -10,19 +10,13 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsApply(CmdBase):
     def run(self):
-
-        self.repo.experiments.apply(
-            self.args.experiment, force=self.args.force
-        )
+        self.repo.experiments.apply(self.args.experiment, force=self.args.force)
 
         return 0
 
 
 def add_parser(experiments_subparsers, parent_parser):
-
-    EXPERIMENTS_APPLY_HELP = (
-        "Apply the changes from an experiment to your workspace."
-    )
+    EXPERIMENTS_APPLY_HELP = "Apply the changes from an experiment to your workspace."
     experiments_apply_parser = experiments_subparsers.add_parser(
         "apply",
         parents=[parent_parser],

dvc/commands/experiments/branch.py

@@ -9,14 +9,12 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsBranch(CmdBase):
     def run(self):
-
         self.repo.experiments.branch(self.args.experiment, self.args.branch)
 
         return 0
 
 
 def add_parser(experiments_subparsers, parent_parser):
-
     EXPERIMENTS_BRANCH_HELP = "Promote an experiment to a Git branch."
     experiments_branch_parser = experiments_subparsers.add_parser(
         "branch",
@@ -28,7 +26,5 @@ def add_parser(experiments_subparsers, parent_parser):
     experiments_branch_parser.add_argument(
         "experiment", help="Experiment to be promoted."
     )
-    experiments_branch_parser.add_argument(
-        "branch", help="Name for the new Git branch"
-    )
+    experiments_branch_parser.add_argument("branch", help="Name for the new Git branch")
     experiments_branch_parser.set_defaults(func=CmdExperimentsBranch)

dvc/commands/experiments/diff.py

@@ -13,7 +13,6 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsDiff(CmdBase):
     def run(self):
-
         try:
             diff = self.repo.experiments.diff(
                 a_rev=self.args.a_rev,
@@ -53,10 +52,7 @@ class CmdExperimentsDiff(CmdBase):
 
 
 def add_parser(experiments_subparsers, parent_parser):
-
-    EXPERIMENTS_DIFF_HELP = (
-        "Show changes between experiments in the DVC repository."
-    )
+    EXPERIMENTS_DIFF_HELP = "Show changes between experiments in the DVC repository."
 
     experiments_diff_parser = experiments_subparsers.add_parser(
         "diff",

dvc/commands/experiments/exec_run.py

@@ -9,10 +9,7 @@ class CmdExecutorRun(CmdBaseNoRepo):
     """Run an experiment executor."""
 
     def run(self):
-        from dvc.repo.experiments.executor.base import (
-            BaseExecutor,
-            ExecutorInfo,
-        )
+        from dvc.repo.experiments.executor.base import BaseExecutor, ExecutorInfo
         from dvc.utils.serialize import load_json
 
         info = ExecutorInfo.from_dict(load_json(self.args.infofile))

dvc/commands/experiments/gc.py

@@ -41,10 +41,7 @@ class CmdExperimentsGC(CmdBase):
                 msg += " and all git tags"
 
             if self.args.commit_date:
-                msg += (
-                    " and all git commits before date "
-                    f"{self.args.commit_date}"
-                )
+                msg += f" and all git commits before date {self.args.commit_date}"
         msg += " of the current repo."
 
         if self.args.queued:
@@ -79,11 +76,9 @@ class CmdExperimentsGC(CmdBase):
 
 
 def add_parser(experiments_subparsers, parent_parser):
-
     EXPERIMENTS_GC_HELP = "Garbage collect unneeded experiments."
     EXPERIMENTS_GC_DESCRIPTION = (
-        "Removes all experiments which are not derived from the specified"
-        "Git revisions."
+        "Removes all experiments which are not derived from the specifiedGit revisions."
     )
     experiments_gc_parser = experiments_subparsers.add_parser(
         "gc",

dvc/commands/experiments/init.py

@@ -92,9 +92,7 @@ class CmdExperimentsInit(CmdBase):
 
         if new_out_dirs:
             out_dirs_paths = humanize.join(map(path_fmt, new_out_dirs))
-            ui.write(
-                f"Creating output directories: {out_dirs_paths}", styled=True
-            )
+            ui.write(f"Creating output directories: {out_dirs_paths}", styled=True)
 
         ui.write(
             f"Creating [b]{self.args.name}[/b] stage in [green]dvc.yaml[/]",
@@ -120,7 +118,6 @@ class CmdExperimentsInit(CmdBase):
 
 
 def add_parser(experiments_subparsers, parent_parser):
-
     EXPERIMENTS_INIT_HELP = "Quickly setup any project to use experiments."
     experiments_init_parser = experiments_subparsers.add_parser(
         "init",
@@ -167,35 +164,47 @@ def add_parser(experiments_subparsers, parent_parser):
     )
     experiments_init_parser.add_argument(
         "--code",
-        help="Path to the source file or directory "
-        "which your experiments depend"
-        f" (default: {CmdExperimentsInit.CODE})",
+        help=(
+            "Path to the source file or directory "
+            "which your experiments depend"
+            f" (default: {CmdExperimentsInit.CODE})"
+        ),
     )
     experiments_init_parser.add_argument(
         "--data",
-        help="Path to the data file or directory "
-        "which your experiments depend"
-        f" (default: {CmdExperimentsInit.DATA})",
+        help=(
+            "Path to the data file or directory "
+            "which your experiments depend"
+            f" (default: {CmdExperimentsInit.DATA})"
+        ),
     )
     experiments_init_parser.add_argument(
         "--models",
-        help="Path to the model file or directory for your experiments"
-        f" (default: {CmdExperimentsInit.MODELS})",
+        help=(
+            "Path to the model file or directory for your experiments"
+            f" (default: {CmdExperimentsInit.MODELS})"
+        ),
     )
     experiments_init_parser.add_argument(
         "--params",
-        help="Path to the parameters file for your experiments"
-        f" (default: {CmdExperimentsInit.DEFAULT_PARAMS})",
+        help=(
+            "Path to the parameters file for your experiments"
+            f" (default: {CmdExperimentsInit.DEFAULT_PARAMS})"
+        ),
     )
     experiments_init_parser.add_argument(
         "--metrics",
-        help="Path to the metrics file for your experiments"
-        f" (default: {CmdExperimentsInit.DEFAULT_METRICS})",
+        help=(
+            "Path to the metrics file for your experiments"
+            f" (default: {CmdExperimentsInit.DEFAULT_METRICS})"
+        ),
     )
     experiments_init_parser.add_argument(
         "--plots",
-        help="Path to the plots file or directory for your experiments"
-        f" (default: {CmdExperimentsInit.PLOTS})",
+        help=(
+            "Path to the plots file or directory for your experiments"
+            f" (default: {CmdExperimentsInit.PLOTS})"
+        ),
     )
     experiments_init_parser.add_argument(
         "--live",

dvc/commands/experiments/pull.py

@@ -11,9 +11,7 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsPull(CmdBase):
     def raise_error_if_all_disabled(self):
-        if not any(
-            [self.args.experiment, self.args.all_commits, self.args.rev]
-        ):
+        if not any([self.args.experiment, self.args.all_commits, self.args.rev]):
             raise InvalidArgumentError(
                 "Either provide an `experiment` argument, or use the "
                 "`--rev` or `--all-commits` flag."
@@ -74,10 +72,7 @@ def add_parser(experiments_subparsers, parent_parser):
         "--no-cache",
         action="store_false",
         dest="pull_cache",
-        help=(
-            "Do not pull cached outputs for this experiment from DVC remote "
-            "storage."
-        ),
+        help="Do not pull cached outputs for this experiment from DVC remote storage.",
     )
     experiments_pull_parser.add_argument(
         "-r",
@@ -92,8 +87,7 @@ def add_parser(experiments_subparsers, parent_parser):
         type=int,
         metavar="<number>",
         help=(
-            "Number of jobs to run simultaneously when pulling from DVC "
-            "remote storage."
+            "Number of jobs to run simultaneously when pulling from DVC remote storage."
         ),
     )
     experiments_pull_parser.add_argument(

dvc/commands/experiments/push.py

@@ -12,16 +12,13 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsPush(CmdBase):
     def raise_error_if_all_disabled(self):
-        if not any(
-            [self.args.experiment, self.args.all_commits, self.args.rev]
-        ):
+        if not any([self.args.experiment, self.args.all_commits, self.args.rev]):
             raise InvalidArgumentError(
                 "Either provide an `experiment` argument, or use the "
                 "`--rev` or `--all-commits` flag."
             )
 
     def run(self):
-
         self.raise_error_if_all_disabled()
 
         pushed_exps = self.repo.experiments.push(
@@ -47,8 +44,10 @@ class CmdExperimentsPush(CmdBase):
         if not self.args.push_cache:
             ui.write(
                 "To push cached outputs",
-                "for this experiment to DVC remote storage,"
-                "re-run this command without '--no-cache'.",
+                (
+                    "for this experiment to DVC remote storage,"
+                    "re-run this command without '--no-cache'."
+                ),
             )
 
         return 0
@@ -76,10 +75,7 @@ def add_parser(experiments_subparsers, parent_parser):
         "--no-cache",
         action="store_false",
         dest="push_cache",
-        help=(
-            "Do not push cached outputs for this experiment to DVC remote "
-            "storage."
-        ),
+        help="Do not push cached outputs for this experiment to DVC remote storage.",
     )
     experiments_push_parser.add_argument(
         "-r",
@@ -93,10 +89,7 @@ def add_parser(experiments_subparsers, parent_parser):
         "--jobs",
         type=int,
         metavar="<number>",
-        help=(
-            "Number of jobs to run simultaneously when pushing to DVC remote "
-            "storage."
-        ),
+        help="Number of jobs to run simultaneously when pushing to DVC remote storage.",
     )
     experiments_push_parser.add_argument(
         "--run-cache",

dvc/commands/experiments/remove.py

@@ -24,7 +24,6 @@ class CmdExperimentsRemove(CmdBase):
             )
 
     def run(self):
-
         self.check_arguments()
 
         removed_list = self.repo.experiments.remove(

dvc/commands/experiments/run.py

@@ -17,13 +17,10 @@ class CmdExperimentsRun(CmdRepro):
 
         if self.args.checkpoint_resume:
             if self.args.reset:
-                raise InvalidArgumentError(
-                    "--reset and --rev are mutually exclusive."
-                )
+                raise InvalidArgumentError("--reset and --rev are mutually exclusive.")
             if not (self.args.queue or self.args.tmp_dir):
                 raise InvalidArgumentError(
-                    "--rev can only be used in conjunction with "
-                    "--queue or --temp."
+                    "--rev can only be used in conjunction with --queue or --temp."
                 )
 
         if self.args.reset:
@@ -51,7 +48,6 @@ class CmdExperimentsRun(CmdRepro):
 
 
 def add_parser(experiments_subparsers, parent_parser):
-
     EXPERIMENTS_RUN_HELP = "Run or resume an experiment."
     experiments_run_parser = experiments_subparsers.add_parser(
         "run",

dvc/commands/experiments/save.py

@@ -11,7 +11,6 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsSave(CmdBase):
     def run(self):
-
         try:
             ref = self.repo.experiments.save(
                 name=self.args.name,

dvc/commands/experiments/show.py

@@ -77,16 +77,14 @@ def _collect_rows(  # noqa: C901
     fill_value=FILL_VALUE,
     iso=False,
 ):
-    from scmrepo.git import Git
+    from dvc.scm import Git
 
     if sort_by:
         sort_path, sort_name, sort_type = _sort_column(
             sort_by, metric_names, param_names
         )
         reverse = sort_order == "desc"
-        experiments = _sort_exp(
-            experiments, sort_path, sort_name, sort_type, reverse
-        )
+        experiments = _sort_exp(experiments, sort_path, sort_name, sort_type, reverse)
 
     new_checkpoint = True
     for i, (rev, results) in enumerate(experiments.items()):
@@ -116,9 +114,7 @@ def _collect_rows(  # noqa: C901
             typ = "baseline"
         elif tip:
             if tip == parent_tip:
-                typ = (
-                    "checkpoint_tip" if new_checkpoint else "checkpoint_commit"
-                )
+                typ = "checkpoint_tip" if new_checkpoint else "checkpoint_commit"
             elif parent_rev == base_rev:
                 typ = "checkpoint_base"
             else:
@@ -135,9 +131,7 @@ def _collect_rows(  # noqa: C901
         row_dict["Experiment"] = exp.get("name", "")
         row_dict["rev"] = name_rev
         row_dict["typ"] = typ
-        row_dict["Created"] = format_time(
-            exp.get("timestamp"), fill_value, iso
-        )
+        row_dict["Created"] = format_time(exp.get("timestamp"), fill_value, iso)
         row_dict["parent"] = parent
         row_dict["State"] = state
         row_dict["Executor"] = exp.get("executor", fill_value)
@@ -371,9 +365,7 @@ def show_experiments(  # noqa: C901
 
     if not csv:
         merge_headers = ["Experiment", "rev", "typ", "parent"]
-        td.column("Experiment")[:] = map(
-            prepare_exp_id, td.as_dict(merge_headers)
-        )
+        td.column("Experiment")[:] = map(prepare_exp_id, td.as_dict(merge_headers))
         td.drop(*merge_headers[1:])
 
     headers = {
@@ -410,9 +402,7 @@ def show_experiments(  # noqa: C901
 
     cols_to_drop = set()
     if drop is not None:
-        cols_to_drop = {
-            col for col in td.keys() if re.match(drop, col)  # noqa: SIM118
-        }
+        cols_to_drop = {col for col in td.keys() if re.match(drop, col)}  # noqa: SIM118
     if pcp:
         cols_to_drop.add("Created")
     td.drop(*cols_to_drop)
@@ -491,9 +481,7 @@ class CmdExperimentsShow(CmdBase):
             ui.write_json(all_experiments, default=_format_json)
         else:
             precision = (
-                self.args.precision or None
-                if self.args.csv
-                else DEFAULT_PRECISION
+                self.args.precision or None if self.args.csv else DEFAULT_PRECISION
             )
             fill_value = "" if self.args.csv else FILL_VALUE
             iso = self.args.csv
@@ -582,10 +570,7 @@ def add_parser(experiments_subparsers, parent_parser):
     )
     experiments_show_parser.add_argument(
         "--sort-order",
-        help=(
-            "Sort order to use with --sort-by."
-            " Defaults to ascending ('asc')."
-        ),
+        help="Sort order to use with --sort-by. Defaults to ascending ('asc').",
         choices=("asc", "desc"),
         default="asc",
     )

dvc/commands/gc.py

@@ -40,14 +40,9 @@ class CmdGC(CmdBase):
             elif self.args.all_tags:
                 msg += " and all git tags"
             if self.args.commit_date:
-                msg += (
-                    " and all git commits before date "
-                    f"{self.args.commit_date}"
-                )
+                msg += f" and all git commits before date {self.args.commit_date}"
             if self.args.rev:
-                msg += (
-                    f" and last {self.args.num} commits from {self.args.rev}"
-                )
+                msg += f" and last {self.args.num} commits from {self.args.rev}"
 
         if self.args.all_experiments:
             msg += " and all experiments"
@@ -198,9 +193,11 @@ def add_parser(subparsers, parent_parser):
         dest="repos",
         type=str,
         nargs="*",
-        help="Keep data files required by these projects "
-        "in addition to the current one. "
-        "Useful if you share a single cache across repos.",
+        help=(
+            "Keep data files required by these projects "
+            "in addition to the current one. "
+            "Useful if you share a single cache across repos."
+        ),
         metavar="<paths>",
     )
     gc_parser.set_defaults(func=CmdGC)

dvc/commands/get.py

@@ -5,7 +5,6 @@ from dvc.cli import completion
 from dvc.cli.command import CmdBaseNoRepo
 from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
-from dvc.scm import CloneError
 
 logger = logging.getLogger(__name__)
 
@@ -16,9 +15,7 @@ class CmdGet(CmdBaseNoRepo):
         from dvc.ui import ui
 
         try:
-            url = get_url(
-                self.args.path, repo=self.args.url, rev=self.args.rev
-            )
+            url = get_url(self.args.path, repo=self.args.url, rev=self.args.rev)
             ui.write(url, force=True)
         except DvcException:
             logger.exception("failed to show URL")
@@ -34,6 +31,7 @@ class CmdGet(CmdBaseNoRepo):
 
     def _get_file_from_repo(self):
         from dvc.repo import Repo
+        from dvc.scm import CloneError
 
         try:
             Repo.get(
@@ -45,13 +43,11 @@ class CmdGet(CmdBaseNoRepo):
             )
             return 0
         except CloneError:
-            logger.exception(f"failed to get '{self.args.path}'")
+            logger.exception("failed to get '%s'", self.args.path)
             return 1
         except DvcException:
             logger.exception(
-                "failed to get '{}' from '{}'".format(
-                    self.args.path, self.args.url
-                )
+                "failed to get '%s' from '%s'", self.args.path, self.args.url
             )
             return 1
 
@@ -87,8 +83,10 @@ def add_parser(subparsers, parent_parser):
     get_parser.add_argument(
         "--show-url",
         action="store_true",
-        help="Print the storage location (URL) the target data would be "
-        "downloaded from, and exit.",
+        help=(
+            "Print the storage location (URL) the target data would be "
+            "downloaded from, and exit."
+        ),
     )
     get_parser.add_argument(
         "-j",

dvc/commands/imp.py

@@ -5,13 +5,14 @@ from dvc.cli import completion
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
-from dvc.scm import CloneError
 
 logger = logging.getLogger(__name__)
 
 
 class CmdImport(CmdBase):
     def run(self):
+        from dvc.scm import CloneError
+
         try:
             self.repo.imp(
                 self.args.url,
@@ -28,13 +29,13 @@ class CmdImport(CmdBase):
                 jobs=self.args.jobs,
             )
         except CloneError:
-            logger.exception(f"failed to import '{self.args.path}'")
+            logger.exception("failed to import '%s'", self.args.path)
             return 1
         except DvcException:
             logger.exception(
-                "failed to import '{}' from '{}'.".format(
-                    self.args.path, self.args.url
-                )
+                "failed to import '%s' from '%s'.",
+                self.args.path,
+                self.args.url,
             )
             return 1
         return 0
@@ -90,8 +91,10 @@ def add_parser(subparsers, parent_parser):
         "--no-download",
         action="store_true",
         default=False,
-        help="Create .dvc file including target data hash value(s)"
-        " but do not actually download the file(s).",
+        help=(
+            "Create .dvc file including target data hash value(s)"
+            " but do not actually download the file(s)."
+        ),
     )
     import_parser.add_argument(
         "-j",

dvc/commands/imp_url.py

@@ -29,10 +29,11 @@ class CmdImportUrl(CmdBase):
             )
         except DvcException:
             logger.exception(
-                "failed to import {}. You could also try downloading "
-                "it manually, and adding it with `dvc add`.".format(
-                    self.args.url
-                )
+                (
+                    "failed to import %s. You could also try downloading "
+                    "it manually, and adding it with `dvc add`."
+                ),
+                self.args.url,
             )
             return 1
         return 0
@@ -41,9 +42,7 @@ class CmdImportUrl(CmdBase):
 def add_parser(subparsers, parent_parser):
     from .add import _add_annotating_args
 
-    IMPORT_HELP = (
-        "Download or copy file from URL and take it under DVC control."
-    )
+    IMPORT_HELP = "Download or copy file from URL and take it under DVC control."
 
     import_parser = subparsers.add_parser(
         "import-url",
@@ -54,16 +53,18 @@ def add_parser(subparsers, parent_parser):
     )
     import_parser.add_argument(
         "url",
-        help="Location of the data to download. Supported URLs:\n"
-        "/absolute/path/to/file/or/dir\n"
-        "relative/path/to/file/or/dir\n"
-        "C:\\\\path\\to\\file\\or\\dir\n"
-        "https://example.com/path/to/file\n"
-        "s3://bucket/key/path\n"
-        "gs://bucket/path/to/file/or/dir\n"
-        "hdfs://example.com/path/to/file\n"
-        "ssh://example.com/absolute/path/to/file/or/dir\n"
-        "remote://remote_name/path/to/file/or/dir (see `dvc remote`)",
+        help=(
+            "Location of the data to download. Supported URLs:\n"
+            "/absolute/path/to/file/or/dir\n"
+            "relative/path/to/file/or/dir\n"
+            "C:\\\\path\\to\\file\\or\\dir\n"
+            "https://example.com/path/to/file\n"
+            "s3://bucket/key/path\n"
+            "gs://bucket/path/to/file/or/dir\n"
+            "hdfs://example.com/path/to/file\n"
+            "ssh://example.com/absolute/path/to/file/or/dir\n"
+            "remote://remote_name/path/to/file/or/dir (see `dvc remote`)"
+        ),
     )
     import_parser.add_argument(
         "out", nargs="?", help="Destination path to put files to."
@@ -96,8 +97,10 @@ def add_parser(subparsers, parent_parser):
         "--no-download",
         action="store_true",
         default=False,
-        help="Create .dvc file including target data hash value(s)"
-        " but do not actually download the file(s).",
+        help=(
+            "Create .dvc file including target data hash value(s)"
+            " but do not actually download the file(s)."
+        ),
     )
     import_parser.add_argument(
         "-j",
@@ -113,10 +116,7 @@ def add_parser(subparsers, parent_parser):
         "--version-aware",
         action="store_true",
         default=False,
-        help=(
-            "Import using cloud versioning. Implied if the URL contains a "
-            "version ID."
-        ),
+        help="Import using cloud versioning. Implied if the URL contains a version ID.",
     )
     _add_annotating_args(import_parser)
     import_parser.set_defaults(func=CmdImportUrl)

dvc/commands/init.py

@@ -75,8 +75,9 @@ def add_parser(subparsers, parent_parser):
         "--no-scm",
         action="store_true",
         default=False,
-        help="Initiate DVC in directory that is "
-        "not tracked by any SCM tool (e.g. Git).",
+        help=(
+            "Initiate DVC in directory that is not tracked by any SCM tool (e.g. Git)."
+        ),
     )
     init_parser.add_argument(
         "-f",
@@ -84,8 +85,7 @@ def add_parser(subparsers, parent_parser):
         action="store_true",
         default=False,
         help=(
-            "Overwrite existing '.dvc/' directory. "
-            "This operation removes local cache."
+            "Overwrite existing '.dvc/' directory. This operation removes local cache."
         ),
     )
     init_parser.add_argument(

dvc/commands/install.py

@@ -31,7 +31,9 @@ def add_parser(subparsers, parent_parser):
         "--use-pre-commit-tool",
         action="store_true",
         default=False,
-        help="Install DVC hooks using pre-commit "
-        "(https://pre-commit.com) if it is installed.",
+        help=(
+            "Install DVC hooks using pre-commit "
+            "(https://pre-commit.com) if it is installed."
+        ),
     )
     install_parser.set_defaults(func=CmdInstall)

dvc/commands/ls/ls_colors.py

@@ -20,7 +20,7 @@ class LsColors:
             else:
                 self._codes[code] = color
 
-    def format(self, entry):
+    def format(self, entry):  # noqa: A003
         text = entry["path"]
 
         if entry.get("isout", False) and "out" in self._codes:

dvc/commands/machine.py

@@ -18,7 +18,6 @@ class MachineDisabledError(ConfigError):
 
 class CmdMachineConfig(CmdConfig):
     def __init__(self, args):
-
         super().__init__(args)
         if not self.config["feature"].get("machine", False):
             raise MachineDisabledError
@@ -163,14 +162,11 @@ class CmdMachineRename(CmdBase):
         all_config = self.config.load_config_to_level(None)
         if self.args.new in all_config.get("machine", {}):
             raise ConfigError(
-                "Rename failed. Machine '{}' already exists.".format(
-                    self.args.new
-                )
+                f"Rename failed. Machine '{self.args.new}' already exists."
             )
         ui.write(f"Rename machine '{self.args.name}' to '{self.args.new}'.")
 
     def run(self):
-
         self._check_before_rename()
 
         with self.config.edit(self.args.level) as conf:
@@ -209,9 +205,7 @@ class CmdMachineDefault(CmdMachineConfig):
                 if self.args.unset:
                     conf["core"].pop("machine", None)
                 else:
-                    merged_conf = self.config.load_config_to_level(
-                        self.args.level
-                    )
+                    merged_conf = self.config.load_config_to_level(self.args.level)
                     if (
                         self.args.name in conf["machine"]
                         or self.args.name in merged_conf["machine"]
@@ -219,8 +213,7 @@ class CmdMachineDefault(CmdMachineConfig):
                         conf["core"]["machine"] = self.args.name
                     else:
                         raise ConfigError(
-                            "default machine must be present in machine "
-                            "list."
+                            "default machine must be present in machine list."
                         )
         return 0
 
@@ -251,7 +244,6 @@ class CmdMachineStatus(CmdBase):
         all_status: List[Dict],
         td: TabularData,
     ):
-
         if not all_status:
             row = [
                 name,
@@ -343,8 +335,7 @@ def add_parser(subparsers, parent_parser):
         "cloud",
         help="Machine cloud. See full list of supported clouds at {}".format(
             format_link(
-                "https://github.com/iterative/"
-                "terraform-provider-iterative#machine"
+                "https://github.com/iterative/terraform-provider-iterative#machine"
             )
         ),
     )
@@ -372,9 +363,7 @@ def add_parser(subparsers, parent_parser):
         help=machine_DEFAULT_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    machine_default_parser.add_argument(
-        "name", nargs="?", help="Name of the machine"
-    )
+    machine_default_parser.add_argument("name", nargs="?", help="Name of the machine")
     machine_default_parser.add_argument(
         "-u",
         "--unset",
@@ -414,9 +403,7 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     machine_modify_parser.add_argument("name", help="Name of the machine")
-    machine_modify_parser.add_argument(
-        "option", help="Name of the option to modify."
-    )
+    machine_modify_parser.add_argument("option", help="Name of the option to modify.")
     machine_modify_parser.add_argument(
         "value", nargs="?", help="(optional) Value of the option."
     )
@@ -449,9 +436,7 @@ def add_parser(subparsers, parent_parser):
         help=machine_REMOVE_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    machine_remove_parser.add_argument(
-        "name", help="Name of the machine to remove."
-    )
+    machine_remove_parser.add_argument("name", help="Name of the machine to remove.")
     machine_remove_parser.set_defaults(func=CmdMachineRemove)
 
     machine_CREATE_HELP = "Create and start a machine instance."
@@ -462,14 +447,10 @@ def add_parser(subparsers, parent_parser):
         help=machine_CREATE_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    machine_create_parser.add_argument(
-        "name", help="Name of the machine to create."
-    )
+    machine_create_parser.add_argument("name", help="Name of the machine to create.")
     machine_create_parser.set_defaults(func=CmdMachineCreate)
 
-    machine_STATUS_HELP = (
-        "List the status of running instances for one/all machines."
-    )
+    machine_STATUS_HELP = "List the status of running instances for one/all machines."
     machine_status_parser = machine_subparsers.add_parser(
         "status",
         parents=[parent_parser],

dvc/commands/move.py

@@ -14,9 +14,7 @@ class CmdMove(CmdBase):
         try:
             self.repo.move(self.args.src, self.args.dst)
         except DvcException:
-            msg = "failed to move '{}' -> '{}'".format(
-                self.args.src, self.args.dst
-            )
+            msg = f"failed to move '{self.args.src}' -> '{self.args.dst}'"
             logger.exception(msg)
             return 1
         return 0
@@ -40,7 +38,5 @@ def add_parser(subparsers, parent_parser):
     move_parser.add_argument(
         "src", help="Source path to a data file or directory."
     ).complete = completion.FILE
-    move_parser.add_argument(
-        "dst", help="Destination path."
-    ).complete = completion.FILE
+    move_parser.add_argument("dst", help="Destination path.").complete = completion.FILE
     move_parser.set_defaults(func=CmdMove)

dvc/commands/params.py

@@ -79,7 +79,7 @@ def add_parser(subparsers, parent_parser):
     params_diff_parser.add_argument(
         "b_rev",
         nargs="?",
-        help=("New Git commit to compare (defaults to the current workspace)"),
+        help="New Git commit to compare (defaults to the current workspace)",
     )
     params_diff_parser.add_argument(
         "--targets",

dvc/commands/plots.py

@@ -18,9 +18,7 @@ logger = logging.getLogger(__name__)
 def _show_json(renderers, split=False):
     from dvc.render.convert import to_json
 
-    result = {
-        renderer.name: to_json(renderer, split) for renderer in renderers
-    }
+    result = {renderer.name: to_json(renderer, split) for renderer in renderers}
     ui.write_json(result)
 
 
@@ -90,10 +88,8 @@ class CmdPlots(CmdBase):
             )
             if html_template_path and not os.path.isabs(html_template_path):
                 assert self.repo.dvc_dir
-                html_template_path = os.path.join(
-                    self.repo.dvc_dir, html_template_path
-                )
-        return html_template_path
+                html_template_path = os.path.join(self.repo.dvc_dir, html_template_path)
+        return html_template_path  # noqa: RET504
 
     def run(self) -> int:  # noqa: C901
         from pathlib import Path
@@ -106,14 +102,11 @@ class CmdPlots(CmdBase):
                 logger.error("please specify a target for `--show-vega`")
                 return 1
             if len(self.args.targets) > 1:
-                logger.error(
-                    "you can only specify one target for `--show-vega`"
-                )
+                logger.error("you can only specify one target for `--show-vega`")
                 return 1
             if self.args.json:
                 logger.error(
-                    "'--show-vega' and '--json' are mutually exclusive "
-                    "options."
+                    "'--show-vega' and '--json' are mutually exclusive options."
                 )
                 return 1
 
@@ -126,17 +119,14 @@ class CmdPlots(CmdBase):
 
             if not plots_data:
                 ui.error_write(
-                    "No plots were loaded, "
-                    "visualization file will not be created."
+                    "No plots were loaded, visualization file will not be created."
                 )
 
             out: str = self.args.out or self.repo.config.get("plots", {}).get(
                 "out_dir", "dvc_plots"
             )
 
-            renderers_out = (
-                out if self.args.json else os.path.join(out, "static")
-            )
+            renderers_out = out if self.args.json else os.path.join(out, "static")
 
             renderers = match_defs_renderers(
                 data=plots_data,
@@ -160,7 +150,7 @@ class CmdPlots(CmdBase):
                 render_html(
                     renderers=renderers,
                     output_file=output_file,
-                    template_path=self._html_template_path(),
+                    html_template=self._html_template_path(),
                 )
 
                 ui.write(output_file.as_uri())
@@ -249,8 +239,7 @@ def add_parser(subparsers, parent_parser):
     fix_subparsers(plots_subparsers)
 
     SHOW_HELP = (
-        "Generate plots from target files or from `plots`"
-        " definitions in `dvc.yaml`."
+        "Generate plots from target files or from `plots` definitions in `dvc.yaml`."
     )
     plots_show_parser = plots_subparsers.add_parser(
         "show",
@@ -273,8 +262,7 @@ def add_parser(subparsers, parent_parser):
     plots_show_parser.set_defaults(func=CmdPlotsShow)
 
     PLOTS_DIFF_HELP = (
-        "Show multiple versions of a plot by overlaying them "
-        "in a single image."
+        "Show multiple versions of a plot by overlaying them in a single image."
     )
     plots_diff_parser = plots_subparsers.add_parser(
         "diff",
@@ -332,9 +320,7 @@ def add_parser(subparsers, parent_parser):
     )
     plots_modify_parser.set_defaults(func=CmdPlotsModify)
 
-    TEMPLATES_HELP = (
-        "List built-in plots templates or show JSON specification for one."
-    )
+    TEMPLATES_HELP = "List built-in plots templates or show JSON specification for one."
     plots_templates_parser = plots_subparsers.add_parser(
         "templates",
         parents=[parent_parser],
@@ -360,11 +346,8 @@ def _add_props_arguments(parser):
         "--template",
         nargs="?",
         default=None,
-        help=(
-            "Special JSON or HTML schema file to inject with the data. "
-            "See {}".format(
-                format_link("https://man.dvc.org/plots#plot-templates")
-            )
+        help="Special JSON or HTML schema file to inject with the data. See {}".format(
+            format_link("https://man.dvc.org/plots#plot-templates")
         ),
         metavar="<path>",
     ).complete = completion.FILE
@@ -381,9 +364,7 @@ def _add_props_arguments(parser):
         default=None,  # Use default None to distinguish when it's not used
         help="Provided CSV or TSV datafile does not have a header.",
     )
-    parser.add_argument(
-        "--title", default=None, metavar="<text>", help="Plot title."
-    )
+    parser.add_argument("--title", default=None, metavar="<text>", help="Plot title.")
     parser.add_argument(
         "--x-label", default=None, help="X axis label", metavar="<text>"
     )

dvc/commands/queue/kill.py

@@ -20,8 +20,7 @@ class CmdQueueKill(CmdBase):
 
 def add_parser(queue_subparsers, parent_parser):
     QUEUE_KILL_HELP = (
-        "Gracefully interrupt running experiment queue tasks "
-        "(equivalent to Ctrl-C)"
+        "Gracefully interrupt running experiment queue tasks (equivalent to Ctrl-C)"
     )
     queue_kill_parser = queue_subparsers.add_parser(
         "kill",

dvc/commands/queue/logs.py

@@ -34,9 +34,7 @@ def add_parser(queue_subparsers, parent_parser):
     queue_logs_parser.add_argument(
         "-e",
         "--encoding",
-        help=(
-            "Text encoding for log output. Defaults to system locale encoding."
-        ),
+        help="Text encoding for log output. Defaults to system locale encoding.",
         metavar="<encoding>",
     )
     queue_logs_parser.add_argument(

dvc/commands/queue/remove.py

@@ -28,7 +28,6 @@ class CmdQueueRemove(CmdBase):
             )
 
     def run(self):
-
         self.check_arguments()
 
         if self.args.all:
@@ -57,7 +56,6 @@ class CmdQueueRemove(CmdBase):
 
 
 def add_parser(queue_subparsers, parent_parser):
-
     QUEUE_REMOVE_HELP = "Remove queued and completed tasks from the queue."
     queue_remove_parser = queue_subparsers.add_parser(
         "remove",

dvc/commands/queue/start.py

@@ -12,20 +12,15 @@ class CmdQueueStart(CmdBase):
     """Start exp queue workers."""
 
     def run(self):
-        started = self.repo.experiments.celery_queue.start_workers(
-            self.args.jobs
-        )
+        started = self.repo.experiments.celery_queue.start_workers(self.args.jobs)
 
         suffix = "s" if started > 1 else ""
-        ui.write(
-            f"Started '{started}' new experiments task queue worker{suffix}."
-        )
+        ui.write(f"Started '{started}' new experiments task queue worker{suffix}.")
 
         return 0
 
 
 def add_parser(queue_subparsers, parent_parser):
-
     QUEUE_START_HELP = "Start the experiments task queue worker."
     queue_start_parser = queue_subparsers.add_parser(
         "start",
@@ -39,10 +34,7 @@ def add_parser(queue_subparsers, parent_parser):
         "--jobs",
         type=int,
         default=1,
-        help=(
-            "Maximum number of concurrent queue workers to start. "
-            "Defaults to 1."
-        ),
+        help="Maximum number of concurrent queue workers to start. Defaults to 1.",
         metavar="<number>",
     )
     queue_start_parser.set_defaults(func=CmdQueueStart)

dvc/commands/queue/status.py

@@ -39,9 +39,7 @@ class CmdQueueStatus(CmdBase):
         ui.write()
 
         worker_status = self.repo.experiments.celery_queue.worker_status()
-        active_count = len(
-            [name for name, task in worker_status.items() if task]
-        )
+        active_count = len([name for name, task in worker_status.items() if task])
         idle_count = len(worker_status) - active_count
 
         ui.write(f"Worker status: {active_count} active, {idle_count} idle")
@@ -50,9 +48,7 @@ class CmdQueueStatus(CmdBase):
 
 
 def add_parser(queue_subparsers, parent_parser):
-    QUEUE_STATUS_HELP = (
-        "Show the status of experiments queue tasks and workers."
-    )
+    QUEUE_STATUS_HELP = "Show the status of experiments queue tasks and workers."
     queue_status_parser = queue_subparsers.add_parser(
         "status",
         parents=[parent_parser],

dvc/commands/queue/stop.py

@@ -26,7 +26,6 @@ class CmdQueueStop(CmdBase):
 
 
 def add_parser(queue_subparsers, parent_parser):
-
     QUEUE_STOP_HELP = "Stop all experiments task queue workers."
     queue_stop_parser = queue_subparsers.add_parser(
         "stop",

dvc/commands/remote.py

@@ -95,9 +95,7 @@ class CmdRemoteDefault(CmdRemote):
                 if self.args.unset:
                     conf["core"].pop("remote", None)
                 else:
-                    merged_conf = self.config.load_config_to_level(
-                        self.args.level
-                    )
+                    merged_conf = self.config.load_config_to_level(self.args.level)
                     if (
                         self.args.name in conf["remote"]
                         or self.args.name in merged_conf["remote"]
@@ -208,9 +206,7 @@ def add_parser(subparsers, parent_parser):
         help=REMOTE_DEFAULT_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    remote_default_parser.add_argument(
-        "name", nargs="?", help="Name of the remote"
-    )
+    remote_default_parser.add_argument("name", nargs="?", help="Name of the remote")
     remote_default_parser.add_argument(
         "-u",
         "--unset",
@@ -229,9 +225,7 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     remote_modify_parser.add_argument("name", help="Name of the remote")
-    remote_modify_parser.add_argument(
-        "option", help="Name of the option to modify."
-    )
+    remote_modify_parser.add_argument("option", help="Name of the option to modify.")
     remote_modify_parser.add_argument(
         "value", nargs="?", help="(optional) Value of the option."
     )
@@ -262,9 +256,7 @@ def add_parser(subparsers, parent_parser):
         help=REMOTE_REMOVE_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    remote_remove_parser.add_argument(
-        "name", help="Name of the remote to remove."
-    )
+    remote_remove_parser.add_argument("name", help="Name of the remote to remove.")
     remote_remove_parser.set_defaults(func=CmdRemoteRemove)
     REMOTE_RENAME_HELP = "Rename a DVC remote"
     remote_rename_parser = remote_subparsers.add_parser(

dvc/commands/remove.py

@@ -22,8 +22,7 @@ class CmdRemove(CmdBase):
 
 def add_parser(subparsers, parent_parser):
     REMOVE_HELP = (
-        "Remove stages from dvc.yaml and/or"
-        " stop tracking files or directories."
+        "Remove stages from dvc.yaml and/or stop tracking files or directories."
     )
     remove_parser = subparsers.add_parser(
         "remove",

dvc/commands/repro.py

@@ -10,9 +10,7 @@ class CmdRepro(CmdBase):
     def run(self):
         from dvc.ui import ui
 
-        stages = self.repo.reproduce(
-            **self._common_kwargs, **self._repro_kwargs
-        )
+        stages = self.repo.reproduce(**self._common_kwargs, **self._repro_kwargs)
         if len(stages) == 0:
             ui.write(CmdDataStatus.UP_TO_DATE_MSG)
         else:
@@ -55,16 +53,14 @@ def add_arguments(repro_parser):
     repro_parser.add_argument(
         "targets",
         nargs="*",
-        help=(
-            """\
+        help="""\
 Stages to reproduce. 'dvc.yaml' by default.
 The targets can be path to a dvc.yaml file or `.dvc` file,
 or a stage name from dvc.yaml file from
 current working directory. To run a stage from dvc.yaml
 from other directories, the target must be a path followed by colon `:`
 and then the stage name name.
-"""
-        ),
+""",
     ).complete = completion.DVCFILES_AND_STAGE
     repro_parser.add_argument(
         "-f",
@@ -85,16 +81,14 @@ and then the stage name name.
         "--single-item",
         action="store_true",
         default=False,
-        help="Reproduce only single data item without recursive dependencies "
-        "check.",
+        help="Reproduce only single data item without recursive dependencies check.",
     )
     repro_parser.add_argument(
         "-p",
         "--pipeline",
         action="store_true",
         default=False,
-        help="Reproduce the whole pipeline that the specified targets "
-        "belong to.",
+        help="Reproduce the whole pipeline that the specified targets belong to.",
     )
     repro_parser.add_argument(
         "-P",
@@ -127,8 +121,10 @@ and then the stage name name.
         "--force-downstream",
         action="store_true",
         default=False,
-        help="Reproduce all descendants of a changed stage even if their "
-        "direct dependencies didn't change.",
+        help=(
+            "Reproduce all descendants of a changed stage even if their "
+            "direct dependencies didn't change."
+        ),
     )
     repro_parser.add_argument(
         "--pull",
@@ -143,15 +139,14 @@ and then the stage name name.
         "--dry",
         action="store_true",
         default=False,
-        help="Only print the commands that would be executed without "
-        "actually executing.",
+        help=(
+            "Only print the commands that would be executed without actually executing."
+        ),
     )
 
 
 def add_parser(subparsers, parent_parser):
-    REPRO_HELP = (
-        "Reproduce complete or partial pipelines by executing their stages."
-    )
+    REPRO_HELP = "Reproduce complete or partial pipelines by executing their stages."
     repro_parser = subparsers.add_parser(
         "repro",
         parents=[parent_parser],

dvc/commands/run.py

@@ -39,7 +39,7 @@ class CmdRun(CmdBase):
             {
                 "cmd": parse_cmd(self.args.command),
                 "fname": kwargs.pop("file"),
-                "no_exec": (self.args.no_exec or bool(self.args.checkpoints)),
+                "no_exec": self.args.no_exec or bool(self.args.checkpoints),
                 "run_cache": not kwargs.pop("no_run_cache"),
             }
         )
@@ -55,9 +55,7 @@ class CmdRun(CmdBase):
 def add_parser(subparsers, parent_parser):
     from dvc.commands.stage import _add_common_args
 
-    RUN_HELP = (
-        "Generate a dvc.yaml file from a command and execute the command."
-    )
+    RUN_HELP = "Generate a dvc.yaml file from a command and execute the command."
     run_parser = subparsers.add_parser(
         "run",
         parents=[parent_parser],
@@ -66,9 +64,7 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     run_parser.add_argument("-n", "--name", help="Stage name.")
-    run_parser.add_argument(
-        "--file", metavar="<filename>", help=argparse.SUPPRESS
-    )
+    run_parser.add_argument("--file", metavar="<filename>", help=argparse.SUPPRESS)
     run_parser.add_argument(
         "--single-stage",
         action="store_true",

dvc/commands/stage.py

@@ -44,9 +44,7 @@ def generate_description(stage: "Stage") -> str:
     return "; ".join(desc)
 
 
-def prepare_description(
-    stage: "Stage", max_length: int = MAX_TEXT_LENGTH
-) -> str:
+def prepare_description(stage: "Stage", max_length: int = MAX_TEXT_LENGTH) -> str:
     desc = stage.short_description() or generate_description(stage)
     return truncate_text(desc, max_length)
 
@@ -57,9 +55,9 @@ def prepare_stages_data(
     max_length: int = MAX_TEXT_LENGTH,
 ) -> Dict[str, str]:
     return {
-        stage.addressing: prepare_description(stage, max_length=max_length)
-        if description
-        else ""
+        stage.addressing: (
+            prepare_description(stage, max_length=max_length) if description else ""
+        )
         for stage in stages
     }
 
@@ -75,9 +73,7 @@ class CmdStageList(CmdBase):
 
         # removing duplicates while maintaining order
         collected = chain.from_iterable(
-            self.repo.stage.collect(
-                target=target, recursive=self.args.recursive
-            )
+            self.repo.stage.collect(target=target, recursive=self.args.recursive)
             for target in self.args.targets
         )
         return dict.fromkeys(collected).keys()
@@ -173,8 +169,7 @@ def _add_common_args(parser):
         "--outs-no-cache",
         action="append",
         default=[],
-        help="Declare output file or directory "
-        "(do not put into DVC cache).",
+        help="Declare output file or directory (do not put into DVC cache).",
         metavar="<filename>",
     ).complete = completion.FILE
     parser.add_argument(
@@ -182,8 +177,10 @@ def _add_common_args(parser):
         "--checkpoints",
         action="append",
         default=[],
-        help="Declare checkpoint output file or directory for 'dvc exp run'. "
-        "Not compatible with 'dvc repro'.",
+        help=(
+            "Declare checkpoint output file or directory for 'dvc exp run'. "
+            "Not compatible with 'dvc repro'."
+        ),
         metavar="<filename>",
     ).complete = completion.FILE
     parser.add_argument(
@@ -196,16 +193,17 @@ def _add_common_args(parser):
         "--outs-persist",
         action="append",
         default=[],
-        help="Declare output file or directory that will not be "
-        "removed upon repro.",
+        help="Declare output file or directory that will not be removed upon repro.",
         metavar="<filename>",
     )
     parser.add_argument(
         "--outs-persist-no-cache",
         action="append",
         default=[],
-        help="Declare output file or directory that will not be "
-        "removed upon repro (do not put into DVC cache).",
+        help=(
+            "Declare output file or directory that will not be "
+            "removed upon repro (do not put into DVC cache)."
+        ),
         metavar="<filename>",
     )
     parser.add_argument(

dvc/commands/status.py

@@ -81,9 +81,7 @@ class CmdDataStatus(CmdDataBase):
             if not self.repo.index.stages:
                 ui.write(self.EMPTY_PROJECT_MSG)
             elif self.args.cloud or self.args.remote:
-                remote = self.args.remote or self.repo.config["core"].get(
-                    "remote"
-                )
+                remote = self.args.remote or self.repo.config["core"].get("remote")
                 ui.write(self.IN_SYNC_MSG.format(remote=remote))
             else:
                 ui.write(self.UP_TO_DATE_MSG)

dvc/commands/update.py

@@ -31,8 +31,7 @@ class CmdUpdate(CmdBase):
 def add_parser(subparsers, parent_parser):
     UPDATE_HELP = (
         "Update data artifact imported (via dvc import or dvc import-url) "
-        "from an external DVC repository or URL, or update data from a "
-        "DVC worktree remote."
+        "from an external DVC repository or URL."
     )
     update_parser = subparsers.add_parser(
         "update",
@@ -61,8 +60,10 @@ def add_parser(subparsers, parent_parser):
         "--no-download",
         action="store_true",
         default=False,
-        help="Update .dvc file git revision/hash value(s)"
-        " but do not download the file(s).",
+        help=(
+            "Update .dvc file git revision/hash value(s)"
+            " but do not download the file(s)."
+        ),
     )
     update_parser.add_argument(
         "--to-remote",

dvc/commands/version.py

@@ -21,9 +21,7 @@ class CmdVersion(CmdBaseNoRepo):
 
 
 def add_parser(subparsers, parent_parser):
-    VERSION_HELP = (
-        "Display the DVC version and system/environment information."
-    )
+    VERSION_HELP = "Display the DVC version and system/environment information."
     version_parser = subparsers.add_parser(
         "version",
         parents=[parent_parser],

dvc/compare.py

@@ -64,9 +64,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
     def keys(self) -> List[str]:
         return self._keys
 
-    def _iter_col_row(
-        self, row: Sequence["CellT"]
-    ) -> Iterator[Tuple["CellT", Column]]:
+    def _iter_col_row(self, row: Sequence["CellT"]) -> Iterator[Tuple["CellT", Column]]:
         for val, col in zip_longest(row, self.columns):
             if col is None:
                 break
@@ -103,9 +101,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         ...
 
     @overload
-    def __setitem__(
-        self, item: slice, value: Iterable[Sequence["CellT"]]
-    ) -> None:
+    def __setitem__(self, item: slice, value: Iterable[Sequence["CellT"]]) -> None:
         ...
 
     def __setitem__(self, item, value) -> None:
@@ -113,8 +109,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         if isinstance(item, slice):
             n = len(self.columns)
             normalized_rows = (
-                chain(val, repeat(self._fill_value, n - len(val)))
-                for val in value
+                chain(val, repeat(self._fill_value, n - len(val))) for val in value
             )
             # we need to transpose those rows into columnar format
             # as we work in terms of column-based arrays
@@ -212,9 +207,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         self, cols: Optional[Iterable[str]] = None
     ) -> Iterable[Dict[str, "CellT"]]:
         keys = self.keys() if cols is None else set(cols)
-        return [
-            {k: self._columns[k][i] for k in keys} for i in range(len(self))
-        ]
+        return [{k: self._columns[k][i] for k in keys} for i in range(len(self))]
 
     def dropna(  # noqa: C901
         self,
@@ -224,13 +217,10 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
     ):
         if axis not in ["rows", "cols"]:
             raise ValueError(
-                f"Invalid 'axis' value {axis}."
-                "Choose one of ['rows', 'cols']"
+                f"Invalid 'axis' value {axis}.Choose one of ['rows', 'cols']"
             )
         if how not in ["any", "all"]:
-            raise ValueError(
-                f"Invalid 'how' value {how}. Choose one of ['any', 'all']"
-            )
+            raise ValueError(f"Invalid 'how' value {how}. Choose one of ['any', 'all']")
 
         match_line: Set = set()
         match_any = True
@@ -258,11 +248,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         if axis == "rows":
             for name in self.keys():  # noqa: SIM118
                 self._columns[name] = Column(
-                    [
-                        x
-                        for n, x in enumerate(self._columns[name])
-                        if n not in to_drop
-                    ]
+                    [x for n, x in enumerate(self._columns[name]) if n not in to_drop]
                 )
         else:
             self.drop(*to_drop)
@@ -275,8 +261,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
     ):
         if axis not in ["rows", "cols"]:
             raise ValueError(
-                f"Invalid 'axis' value {axis}."
-                "Choose one of ['rows', 'cols']"
+                f"Invalid 'axis' value {axis}.Choose one of ['rows', 'cols']"
             )
 
         if axis == "cols":
@@ -329,8 +314,8 @@ def _format_field(
     def _format(_val):
         if isinstance(_val, float) and precision:
             if round_digits:
-                return round(val, precision)
-            return _normalize_float(val, precision)
+                return round(_val, precision)
+            return _normalize_float(_val, precision)
         if isinstance(_val, abc.Mapping):
             return {k: _format(v) for k, v in _val.items()}
         if isinstance(_val, list):
@@ -362,9 +347,7 @@ def diff_table(
         for item, change in sorted(diff_in_file.items()):
             old_value = with_value(change.get("old"), fill_value)
             new_value = with_value(change.get("new"), fill_value)
-            diff_value = with_value(
-                change.get("diff", on_empty_diff), fill_value
-            )
+            diff_value = with_value(change.get("diff", on_empty_diff), fill_value)
             td.append(
                 [
                     fname,

dvc/config.py

@@ -9,12 +9,12 @@ from typing import TYPE_CHECKING, Dict, Optional
 from funcy import compact, memoize, re_find
 
 from dvc.exceptions import DvcException, NotDvcRepoError
-from dvc.types import DictStrAny, StrPath
 
 from .utils.objects import cached_property
 
 if TYPE_CHECKING:
     from dvc.fs import FileSystem
+    from dvc.types import DictStrAny, StrPath
 
 logger = logging.getLogger(__name__)
 
@@ -92,10 +92,10 @@ class Config(dict):
 
     def __init__(
         self,
-        dvc_dir: Optional[StrPath] = None,
+        dvc_dir: Optional["StrPath"] = None,
         validate: bool = True,
         fs: Optional["FileSystem"] = None,
-        config: Optional[DictStrAny] = None,
+        config: Optional["DictStrAny"] = None,
     ):  # pylint: disable=super-init-not-called
         from dvc.fs import LocalFileSystem
 
@@ -153,7 +153,7 @@ class Config(dict):
         with open(config_file, "w+", encoding="utf-8"):
             return Config(dvc_dir)
 
-    def load(self, validate: bool = True, config: Optional[DictStrAny] = None):
+    def load(self, validate: bool = True, config: Optional["DictStrAny"] = None):
         """Loads config from all the config files.
 
         Raises:
@@ -374,6 +374,5 @@ def merge(into, update):
 
 def _lower_keys(data):
     return {
-        k.lower(): _lower_keys(v) if isinstance(v, dict) else v
-        for k, v in data.items()
+        k.lower(): _lower_keys(v) if isinstance(v, dict) else v for k, v in data.items()
     }

dvc/config_schema.py

@@ -2,16 +2,7 @@ import os
 from urllib.parse import urlparse
 
 from funcy import walk_values
-from voluptuous import (
-    All,
-    Any,
-    Coerce,
-    Invalid,
-    Lower,
-    Optional,
-    Range,
-    Schema,
-)
+from voluptuous import All, Any, Coerce, Invalid, Lower, Optional, Range, Schema
 
 Bool = All(
     Lower,
@@ -34,9 +25,7 @@ def supported_cache_type(types):
 
     unsupported = set(types) - {"reflink", "hardlink", "symlink", "copy"}
     if unsupported:
-        raise Invalid(
-            "Unsupported cache type(s): {}".format(", ".join(unsupported))
-        )
+        raise Invalid("Unsupported cache type(s): {}".format(", ".join(unsupported)))
 
     return types
 
@@ -62,6 +51,8 @@ def ByUrl(mapping):
         # Windows absolute paths should really have scheme == "" (local)
         if os.name == "nt" and len(parsed.scheme) == 1 and parsed.netloc == "":
             return schemas[""](data)
+        if parsed.netloc == "":
+            return schemas[""](data)
         if parsed.scheme not in schemas:
             raise Invalid(f"Unsupported URL type {parsed.scheme}://")
 
@@ -106,6 +97,7 @@ WEBDAV_COMMON = {
     "password": str,
     "ask_password": Bool,
     "token": str,
+    "custom_auth_header": str,
     "cert_path": str,
     "key_path": str,
     "timeout": Coerce(int),
@@ -257,9 +249,7 @@ SCHEMA = {
     "machine": {
         str: {
             "cloud": All(Lower, Choices("aws", "azure")),
-            "region": All(
-                Lower, Choices("us-west", "us-east", "eu-west", "eu-north")
-            ),
+            "region": All(Lower, Choices("us-west", "us-east", "eu-west", "eu-north")),
             "image": str,
             "spot": Bool,
             "spot_price": Coerce(float),
@@ -274,6 +264,7 @@ SCHEMA = {
     # section for experimental features
     "feature": {
         Optional("machine", default=False): Bool,
+        Optional("data_index_cache", default=False): Bool,
         # enabled by default. It's of no use, kept for backward compatibility.
         Optional("parametrization", default=True): Bool,
     },

dvc/daemon.py

@@ -40,9 +40,7 @@ def _spawn_windows(cmd, env):
         startupinfo = STARTUPINFO()
         startupinfo.dwFlags |= STARTF_USESHOWWINDOW
 
-        _popen(
-            cmd, env=env, creationflags=creationflags, startupinfo=startupinfo
-        )
+        _popen(cmd, env=env, creationflags=creationflags, startupinfo=startupinfo)
 
 
 def _spawn_posix(cmd, env):
@@ -105,7 +103,7 @@ def daemon(args):
     Args:
         args (list): list of arguments to append to `dvc daemon` command.
     """
-    daemonize(["daemon", "-q"] + args)
+    daemonize(["daemon", "-q", *args])
 
 
 def daemonize(cmd: List[str]):

dvc/dagascii.py

@@ -272,8 +272,6 @@ def draw(vertices, edges):
             vertex.view.h,
         )
 
-        canvas.text(
-            int(round(x - minx)) + 1, int(round(y - miny)) + 1, vertex.data
-        )
+        canvas.text(int(round(x - minx)) + 1, int(round(y - miny)) + 1, vertex.data)
 
     return canvas.draw()

dvc/data_cloud.py

@@ -8,6 +8,7 @@ from dvc.utils.objects import cached_property
 from dvc_data.hashfile.db import get_index
 
 if TYPE_CHECKING:
+    from dvc.fs import FileSystem
     from dvc_data.hashfile.db import HashFileDB
     from dvc_data.hashfile.hash_info import HashInfo
     from dvc_data.hashfile.status import CompareStatusResult
@@ -17,20 +18,14 @@ logger = logging.getLogger(__name__)
 
 
 class Remote:
-    def __init__(self, path, fs, **config):
+    def __init__(self, name: str, path: str, fs: "FileSystem", *, index=None, **config):
         self.path = path
         self.fs = fs
+        self.name = name
+        self.index = index
 
-        self.worktree = config.pop("worktree", False)
+        self.worktree: bool = config.pop("worktree", False)
         self.config = config
-        if self.worktree:
-            version_aware = self.config.get("version_aware")
-            if version_aware is False:
-                raise RemoteConfigError(
-                    "worktree remotes require version_aware cloud"
-                )
-            if version_aware is None:
-                self.fs.version_aware = True
 
     @cached_property
     def odb(self) -> "HashFileDB":
@@ -69,9 +64,23 @@ class DataCloud:
             from dvc.fs import get_cloud_fs
 
             cls, config, fs_path = get_cloud_fs(self.repo, name=name)
+
+            if config.get("worktree"):
+                version_aware = config.get("version_aware")
+                if version_aware is False:
+                    raise RemoteConfigError(
+                        "worktree remotes require version_aware cloud"
+                    )
+                if version_aware is None:
+                    config["version_aware"] = True
+
             fs = cls(**config)
             config["tmp_dir"] = self.repo.index_db_dir
-            return Remote(fs_path, fs, **config)
+            if self.repo.data_index is not None:
+                index = self.repo.data_index.view(("remotes", name))
+            else:
+                index = None
+            return Remote(name, fs_path, fs, index=index, **config)
 
         if bool(self.repo.config["remote"]):
             error_msg = (
@@ -107,8 +116,11 @@ class DataCloud:
                 for hash_info in status.missing
             )
             logger.warning(
-                "Some of the cache files do not exist neither locally "
-                f"nor on remote. Missing cache files:\n{missing_desc}"
+                (
+                    "Some of the cache files do not exist neither locally "
+                    "nor on remote. Missing cache files:\n%s"
+                ),
+                missing_desc,
             )
 
     def transfer(
@@ -140,12 +152,12 @@ class DataCloud:
         """
         odb = odb or self.get_remote_odb(remote, "push")
         return self.transfer(
-            self.repo.odb.local,
+            self.repo.cache.local,
             odb,
             objs,
             jobs=jobs,
             dest_index=get_index(odb),
-            cache_odb=self.repo.odb.local,
+            cache_odb=self.repo.cache.local,
             validate_status=self._log_missing,
         )
 
@@ -168,11 +180,11 @@ class DataCloud:
         odb = odb or self.get_remote_odb(remote, "pull")
         return self.transfer(
             odb,
-            self.repo.odb.local,
+            self.repo.cache.local,
             objs,
             jobs=jobs,
             src_index=get_index(odb),
-            cache_odb=self.repo.odb.local,
+            cache_odb=self.repo.cache.local,
             verify=odb.verify,
             validate_status=self._log_missing,
         )
@@ -199,12 +211,12 @@ class DataCloud:
         if not odb:
             odb = self.get_remote_odb(remote, "status")
         return compare_status(
-            self.repo.odb.local,
+            self.repo.cache.local,
             odb,
             objs,
             jobs=jobs,
             dest_index=get_index(odb),
-            cache_odb=self.repo.odb.local,
+            cache_odb=self.repo.cache.local,
         )
 
     def get_url_for(self, remote, checksum):

dvc/dependency/__init__.py

@@ -74,7 +74,7 @@ def _merge_params(s_list):
         if not isinstance(key, dict):
             msg = "Only list of str/dict is supported. Got: "
             msg += f"'{type(key).__name__}'."
-            raise ValueError(msg)
+            raise ValueError(msg)  # noqa: TRY004
 
         for k, params in key.items():
             if k in wholly_tracked:
@@ -83,13 +83,11 @@ def _merge_params(s_list):
             if not isinstance(params, list):
                 msg = "Expected list of params for custom params file "
                 msg += f"'{k}', got '{type(params).__name__}'."
-                raise ValueError(msg)
+                raise ValueError(msg)  # noqa: TRY004
             d[k].extend(params)
     return d
 
 
 def loads_params(stage, s_list):
     d = _merge_params(s_list)
-    return [
-        ParamsDependency(stage, path, params) for path, params in d.items()
-    ]
+    return [ParamsDependency(stage, path, params) for path, params in d.items()]

dvc/dependency/base.py

@@ -47,9 +47,7 @@ class Dependency(Output):
             self.def_path = self.fs.path.version_path(
                 self.def_path, self.meta.version_id
             )
-            self.fs_path = self.fs.path.version_path(
-                self.fs_path, self.meta.version_id
-            )
+            self.fs_path = self.fs.path.version_path(self.fs_path, self.meta.version_id)
 
     def download(self, to, jobs=None):
         fs_download(self.fs, self.fs_path, to, jobs=jobs)
@@ -57,9 +55,7 @@ class Dependency(Output):
     def save(self):
         super().save()
         if self.fs.version_aware:
-            self.fs_path = self.fs.path.version_path(
-                self.fs_path, self.meta.version_id
-            )
+            self.fs_path = self.fs.path.version_path(self.fs_path, self.meta.version_id)
 
     def dumpd(self, **kwargs):
         if self.fs.version_aware:

dvc/dependency/param.py

@@ -130,8 +130,7 @@ class ParamsDependency(Dependency):
                     and list(actual[param]) == info[param]
                 ):
                     continue
-                else:
-                    st = "modified"
+                st = "modified"
             else:
                 continue
 
@@ -155,9 +154,7 @@ class ParamsDependency(Dependency):
         try:
             return load_path(self.fs_path, self.repo.fs)
         except ParseError as exc:
-            raise BadParamFileError(
-                f"Unable to read parameters from '{self}'"
-            ) from exc
+            raise BadParamFileError(f"Unable to read parameters from '{self}'") from exc
 
     def get_hash(self):
         info = self.read_params()

dvc/dependency/repo.py

@@ -1,28 +1,22 @@
 import os
 from collections import defaultdict
 from copy import copy
-from typing import (
-    TYPE_CHECKING,
-    ContextManager,
-    Dict,
-    Optional,
-    Set,
-    Tuple,
-    Union,
-)
+from typing import TYPE_CHECKING, Dict, Optional, Set, Tuple, Union
 
 from voluptuous import Required
 
 from dvc.prompt import confirm
-from dvc_data.hashfile.meta import Meta
 
 from .base import Dependency
 
 if TYPE_CHECKING:
+    from typing import ContextManager
+
     from dvc.output import Output
     from dvc.repo import Repo
     from dvc.stage import Stage
     from dvc_data.hashfile.hash_info import HashInfo
+    from dvc_data.hashfile.meta import Meta
     from dvc_data.hashfile.obj import HashFile
     from dvc_objects.db import ObjectDB
 
@@ -41,15 +35,13 @@ class RepoDependency(Dependency):
         }
     }
 
-    def __init__(
-        self, def_repo: Dict[str, str], stage: "Stage", *args, **kwargs
-    ):
+    def __init__(self, def_repo: Dict[str, str], stage: "Stage", *args, **kwargs):
         self.def_repo = def_repo
         self._objs: Dict[str, "HashFile"] = {}
-        self._meta: Dict[str, Meta] = {}
+        self._meta: Dict[str, "Meta"] = {}
         super().__init__(stage, *args, **kwargs)
 
-    def _parse_path(self, fs, fs_path):
+    def _parse_path(self, fs, fs_path):  # noqa: ARG002
         return None
 
     @property
@@ -88,7 +80,7 @@ class RepoDependency(Dependency):
             to.fs_path,
             to.fs,
             obj,
-            self.repo.odb.local,
+            self.repo.cache.local,
             ignore=None,
             state=self.repo.state,
             prompt=confirm,
@@ -106,22 +98,20 @@ class RepoDependency(Dependency):
         # immutable, hence its impossible for checksum to change.
         return False
 
-    def get_used_objs(
-        self, **kwargs
-    ) -> Dict[Optional["ObjectDB"], Set["HashInfo"]]:
+    def get_used_objs(self, **kwargs) -> Dict[Optional["ObjectDB"], Set["HashInfo"]]:
         used, _, _ = self._get_used_and_obj(**kwargs)
         return used
 
     def _get_used_and_obj(
         self, obj_only: bool = False, **kwargs
-    ) -> Tuple[Dict[Optional["ObjectDB"], Set["HashInfo"]], Meta, "HashFile"]:
+    ) -> Tuple[Dict[Optional["ObjectDB"], Set["HashInfo"]], "Meta", "HashFile"]:
         from dvc.config import NoRemoteError
         from dvc.exceptions import NoOutputOrStageError, PathMissingError
         from dvc.utils import as_posix
         from dvc_data.hashfile.build import build
         from dvc_data.hashfile.tree import Tree, TreeError
 
-        local_odb = self.repo.odb.local
+        local_odb = self.repo.cache.local
         locked = kwargs.pop("locked", True)
         with self._make_repo(locked=locked, cache_dir=local_odb.path) as repo:
             used_obj_ids = defaultdict(set)
@@ -143,7 +133,7 @@ class RepoDependency(Dependency):
                         self._check_circular_import(odb, obj_ids)
                         used_obj_ids[odb].update(obj_ids)
                 except (NoRemoteError, NoOutputOrStageError):
-                    pass
+                    pass  # noqa: S110
 
             try:
                 object_store, meta, obj = build(
@@ -167,9 +157,7 @@ class RepoDependency(Dependency):
                 used_obj_ids[object_store].update(oid for _, _, oid in obj)
             return used_obj_ids, meta, obj
 
-    def _check_circular_import(
-        self, odb: "ObjectDB", obj_ids: Set["HashInfo"]
-    ) -> None:
+    def _check_circular_import(self, odb: "ObjectDB", obj_ids: Set["HashInfo"]) -> None:
         from dvc.exceptions import CircularImportError
         from dvc.fs.dvc import DVCFileSystem
         from dvc_data.hashfile.db.reference import ReferenceHashFileDB
@@ -191,10 +179,7 @@ class RepoDependency(Dependency):
         for obj in iter_objs():
             if not isinstance(obj.fs, DVCFileSystem):
                 continue
-            if (
-                obj.fs.repo_url in checked_urls
-                or obj.fs.repo.root_dir in checked_urls
-            ):
+            if obj.fs.repo_url in checked_urls or obj.fs.repo.root_dir in checked_urls:
                 continue
             self_url = self.repo.url or self.repo.root_dir
             if (
@@ -225,9 +210,7 @@ class RepoDependency(Dependency):
         )
         return meta
 
-    def _make_repo(
-        self, locked: bool = True, **kwargs
-    ) -> "ContextManager[Repo]":
+    def _make_repo(self, locked: bool = True, **kwargs) -> "ContextManager[Repo]":
         from dvc.external_repo import external_repo
 
         d = self.def_repo
@@ -236,6 +219,4 @@ class RepoDependency(Dependency):
 
     def _get_rev(self, locked: bool = True):
         d = self.def_repo
-        return (d.get(self.PARAM_REV_LOCK) if locked else None) or d.get(
-            self.PARAM_REV
-        )
+        return (d.get(self.PARAM_REV_LOCK) if locked else None) or d.get(self.PARAM_REV)

dvc/dvcfile.py

@@ -21,7 +21,6 @@ from dvc.stage.exceptions import (
     StageFileDoesNotExistError,
     StageFileIsNotDvcFileError,
 )
-from dvc.types import StrOrBytesPath
 from dvc.utils import relpath
 from dvc.utils.collections import apply_diff
 from dvc.utils.objects import cached_property
@@ -29,6 +28,7 @@ from dvc.utils.serialize import dump_yaml, modify_yaml
 
 if TYPE_CHECKING:
     from dvc.repo import Repo
+    from dvc.types import StrOrBytesPath
 
     from .parsing import DataResolver
     from .stage import Stage
@@ -63,9 +63,7 @@ def is_valid_filename(path):
 
 
 def is_dvc_file(path):
-    return os.path.isfile(path) and (
-        is_valid_filename(path) or is_lock_file(path)
-    )
+    return os.path.isfile(path) and (is_valid_filename(path) or is_lock_file(path))
 
 
 def is_lock_file(path):
@@ -77,9 +75,7 @@ def is_git_ignored(repo, path):
     from dvc.scm import NoSCMError
 
     try:
-        return isinstance(repo.fs, LocalFileSystem) and repo.scm.is_ignored(
-            path
-        )
+        return isinstance(repo.fs, LocalFileSystem) and repo.scm.is_ignored(path)
     except NoSCMError:
         return False
 
@@ -152,9 +148,7 @@ class FileMixin:
         # 4. when the file is git ignored
         if not self.exists():
             dvc_ignored = self.repo.dvcignore.is_ignored_file(self.path)
-            raise StageFileDoesNotExistError(
-                self.path, dvc_ignored=dvc_ignored
-            )
+            raise StageFileDoesNotExistError(self.path, dvc_ignored=dvc_ignored)
 
         self._verify_filename()
         if not self.repo.fs.isfile(self.path):
@@ -179,7 +173,8 @@ class FileMixin:
             **kwargs,
         )
 
-    def remove(self, force=False):  # pylint: disable=unused-argument
+    # pylint: disable-next=unused-argument
+    def remove(self, force=False):  # noqa: ARG002
         with contextlib.suppress(FileNotFoundError):
             os.unlink(self.path)
 
@@ -219,7 +214,8 @@ class SingleStageFile(FileMixin):
         dump_yaml(self.path, serialize.to_single_stage_file(stage, **kwargs))
         self.repo.scm_context.track_file(self.relpath)
 
-    def remove_stage(self, stage):  # pylint: disable=unused-argument
+    # pylint: disable-next=unused-argument
+    def remove_stage(self, stage):  # noqa: ARG002
         self.remove()
 
     def merge(self, ancestor, other, allowed=None):
@@ -269,9 +265,7 @@ class ProjectFile(FileMixin):
     @staticmethod
     def _check_if_parametrized(stage, action: str = "dump") -> None:
         if stage.raw_data.parametrized:
-            raise ParametrizedDumpError(
-                f"cannot {action} a parametrized {stage}"
-            )
+            raise ParametrizedDumpError(f"cannot {action} a parametrized {stage}")
 
     def _dump_pipeline_file(self, stage):
         self._check_if_parametrized(stage)
@@ -284,9 +278,7 @@ class ProjectFile(FileMixin):
             data["stages"] = data.get("stages", {})
             existing_entry = stage.name in data["stages"]
             action = "Modifying" if existing_entry else "Adding"
-            logger.info(
-                "%s stage '%s' in '%s'", action, stage.name, self.relpath
-            )
+            logger.info("%s stage '%s' in '%s'", action, stage.name, self.relpath)
 
             if existing_entry:
                 orig_stage_data = data["stages"][stage.name]
@@ -298,9 +290,7 @@ class ProjectFile(FileMixin):
 
     @property
     def stage(self):
-        raise DvcException(
-            "ProjectFile has multiple stages. Please specify it's name."
-        )
+        raise DvcException("ProjectFile has multiple stages. Please specify it's name.")
 
     @cached_property
     def contents(self) -> Dict[str, Any]:
@@ -364,10 +354,7 @@ class ProjectFile(FileMixin):
 
 
 def get_lockfile_schema(d):
-    from dvc.schema import (
-        COMPILED_LOCKFILE_V1_SCHEMA,
-        COMPILED_LOCKFILE_V2_SCHEMA,
-    )
+    from dvc.schema import COMPILED_LOCKFILE_V1_SCHEMA, COMPILED_LOCKFILE_V2_SCHEMA
 
     schema = {
         LOCKFILE_VERSION.V1: COMPILED_LOCKFILE_V1_SCHEMA,
@@ -420,9 +407,7 @@ class Lockfile(FileMixin):
         with modify_yaml(self.path, fs=self.repo.fs) as data:
             version = LOCKFILE_VERSION.from_dict(data)
             if version == LOCKFILE_VERSION.V1:
-                logger.info(
-                    "Migrating lock file '%s' from v1 to v2", self.relpath
-                )
+                logger.info("Migrating lock file '%s' from v1 to v2", self.relpath)
                 migrate_lock_v1_to_v2(data, self.latest_version_info)
             else:
                 if not data:
@@ -465,7 +450,7 @@ class Lockfile(FileMixin):
 
 
 def load_file(
-    repo: "Repo", path: StrOrBytesPath, **kwargs: Any
+    repo: "Repo", path: "StrOrBytesPath", **kwargs: Any
 ) -> Union[ProjectFile, SingleStageFile]:
     _, ext = os.path.splitext(path)
     if ext in (".yaml", ".yml"):

dvc/exceptions.py

@@ -150,8 +150,9 @@ class CyclicGraphError(DvcException):
 class ConfirmRemoveError(DvcException):
     def __init__(self, path):
         super().__init__(
-            "unable to remove '{}' without a confirmation. Use "
-            "`-f` to force.".format(path)
+            "unable to remove '{}' without a confirmation. Use `-f` to force.".format(
+                path
+            )
         )
 
 
@@ -177,9 +178,7 @@ class BadMetricError(DvcException):
 
 class RecursiveAddingWhileUsingFilename(DvcException):
     def __init__(self):
-        super().__init__(
-            "cannot use `fname` with multiple targets or `-R|--recursive`"
-        )
+        super().__init__("cannot use `fname` with multiple targets or `-R|--recursive`")
 
 
 class OverlappingOutputPathsError(DvcException):
@@ -206,9 +205,7 @@ class FileMissingError(DvcException):
     def __init__(self, path, hint=None):
         self.path = path
         hint = "" if hint is None else f". {hint}"
-        super().__init__(
-            f"Can't find '{path}' neither locally nor on remote{hint}"
-        )
+        super().__init__(f"Can't find '{path}' neither locally nor on remote{hint}")
 
 
 class FileTransferError(DvcException):
@@ -250,9 +247,7 @@ class CollectCacheError(DvcException):
 
 class NoRemoteInExternalRepoError(DvcException):
     def __init__(self, url):
-        super().__init__(
-            f"No DVC remote is specified in target repository '{url}'."
-        )
+        super().__init__(f"No DVC remote is specified in target repository '{url}'.")
 
 
 class NoOutputInExternalRepoError(DvcException):
@@ -277,8 +272,7 @@ class PathMissingError(DvcException):
         " neither as a DVC output nor as a Git-tracked file."
     )
     default_msg_dvc_only = (
-        "The path '{}' does not exist in the target repository '{}'"
-        " as an DVC output."
+        "The path '{}' does not exist in the target repository '{}' as an DVC output."
     )
 
     def __init__(self, path, repo, dvc_only=False):
@@ -294,7 +288,6 @@ class URLMissingError(DvcException):
 
 class RemoteCacheRequiredError(DvcException):
     def __init__(self, scheme, fs_path):
-
         super().__init__(
             (
                 "Current operation was unsuccessful because '{}' requires "
@@ -319,8 +312,7 @@ class NoOutputOrStageError(DvcException):
 
     def __init__(self, target, file):
         super().__init__(
-            f"'{target}' "
-            f"does not exist as an output or a stage name in '{file}'"
+            f"'{target}' does not exist as an output or a stage name in '{file}'"
         )
 
 
@@ -329,11 +321,8 @@ class MergeError(DvcException):
 
 
 class CacheLinkError(DvcException):
-
     SUPPORT_LINK = "See {} for more information.".format(
-        format_link(
-            "https://dvc.org/doc/user-guide/troubleshooting#cache-types"
-        )
+        format_link("https://dvc.org/doc/user-guide/troubleshooting#cache-types")
     )
 
     def __init__(self, fs_paths):

dvc/external_repo.py

@@ -17,11 +17,12 @@ from dvc.exceptions import (
 )
 from dvc.repo import Repo
 from dvc.scm import CloneError, map_scm_exception
-from dvc.types import StrPath
 from dvc.utils import relpath
 
 if TYPE_CHECKING:
-    from scmrepo import Git
+    from dvc.types import StrPath
+
+    from .scm import Git
 
 logger = logging.getLogger(__name__)
 
@@ -32,14 +33,13 @@ def external_repo(
     url,
     rev: Optional[str] = None,
     for_write: bool = False,
-    cache_dir: Optional[StrPath] = None,
+    cache_dir: Optional["StrPath"] = None,
     cache_types: Optional[Collection[str]] = None,
     **kwargs,
 ) -> Iterator["Repo"]:
-    from scmrepo.git import Git
-
     from dvc.config import NoRemoteError
     from dvc.fs import GitFileSystem
+    from dvc.scm import Git
 
     logger.debug("Creating external repo %s@%s", url, rev)
     path = _cached_clone(url, rev, for_write=for_write)
@@ -88,9 +88,7 @@ def external_repo(
         raise NoRemoteInExternalRepoError(url) from exc
     except OutputNotFoundError as exc:
         if exc.repo is repo:
-            raise NoOutputInExternalRepoError(
-                exc.output, repo.root_dir, url
-            ) from exc
+            raise NoOutputInExternalRepoError(exc.output, repo.root_dir, url) from exc
         raise
     except FileMissingError as exc:
         raise PathMissingError(exc.path, url) from exc
@@ -151,7 +149,7 @@ def _get_remote_config(url):
             name = "auto-generated-upstream"
             return {
                 "core": {"remote": name},
-                "remote": {name: {"url": repo.odb.local.path}},
+                "remote": {name: {"url": repo.cache.local.path}},
             }
 
         # Use original remote to make sure that we are using correct url,
@@ -196,7 +194,7 @@ def _clone_default_branch(url, rev, for_write=False):  # noqa: C901
 
     The cloned is reactualized with git pull unless rev is a known sha.
     """
-    from scmrepo.git import Git
+    from dvc.scm import Git
 
     clone_path, shallow = CLONES.get(url) or (None, False)
 
@@ -234,9 +232,7 @@ def _clone_default_branch(url, rev, for_write=False):  # noqa: C901
                         os.path.join(clone_path, Git.GIT_DIR, "shallow")
                     )
                     if shallow:
-                        logger.debug(
-                            "erepo: using shallow clone for branch '%s'", rev
-                        )
+                        logger.debug("erepo: using shallow clone for branch '%s'", rev)
                 except CloneError:
                     git_dir = os.path.join(clone_path, ".git")
                     if os.path.exists(git_dir):
@@ -273,7 +269,7 @@ def _merge_upstream(git: "Git"):
 
 
 def _git_checkout(repo_path, rev):
-    from scmrepo.git import Git
+    from dvc.scm import Git
 
     logger.debug("erepo: git checkout %s@%s", repo_path, rev)
     git = Git(repo_path)
@@ -292,8 +288,6 @@ def _remove(path):
         try:
             os_retry(remove)(path)
         except PermissionError:
-            logger.warning(
-                "Failed to remove '%s'", relpath(path), exc_info=True
-            )
+            logger.warning("Failed to remove '%s'", relpath(path), exc_info=True)
     else:
         remove(path)

dvc/fs/__init__.py

@@ -72,9 +72,7 @@ def get_fs_config(config, **kwargs):
         except KeyError:
             from dvc.config import RemoteNotFoundError
 
-            raise RemoteNotFoundError(  # noqa: B904
-                f"remote '{name}' doesn't exist"
-            )
+            raise RemoteNotFoundError(f"remote '{name}' doesn't exist")  # noqa: B904
     else:
         remote_conf = kwargs
     return _resolve_remote_refs(config, remote_conf)

dvc/fs/callbacks.py

@@ -58,9 +58,7 @@ class RichCallback(Callback):
 
     @cached_property
     def task(self) -> "TaskID":
-        return self.progress.add_task(
-            **self._task_kwargs  # type: ignore[arg-type]
-        )
+        return self.progress.add_task(**self._task_kwargs)  # type: ignore[arg-type]
 
     def __enter__(self):
         return self
@@ -70,7 +68,7 @@ class RichCallback(Callback):
             self.progress.clear_task(self.task)
         self._stack.close()
 
-    def call(self, hook_name=None, **kwargs):
+    def call(self, hook_name=None, **kwargs):  # noqa: ARG002
         self.progress.update(
             self.task,
             completed=self.value,

dvc/fs/dvc.py

@@ -6,21 +6,11 @@ import os
 import posixpath
 import threading
 from contextlib import suppress
-from typing import (
-    TYPE_CHECKING,
-    Any,
-    Callable,
-    Dict,
-    Optional,
-    Tuple,
-    Type,
-    Union,
-)
+from typing import TYPE_CHECKING, Any, Callable, Dict, Optional, Tuple, Type, Union
 
 from fsspec.spec import AbstractFileSystem
 from funcy import wrap_with
 
-from dvc.types import StrPath
 from dvc_objects.fs.base import FileSystem
 from dvc_objects.fs.path import Path
 
@@ -28,6 +18,7 @@ from .data import DataFileSystem
 
 if TYPE_CHECKING:
     from dvc.repo import Repo
+    from dvc.types import StrPath
 
 logger = logging.getLogger(__name__)
 
@@ -126,9 +117,7 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
 
         super().__init__()
         if repo is None:
-            repo = self._make_repo(
-                url=url, rev=rev, subrepos=subrepos, **repo_kwargs
-            )
+            repo = self._make_repo(url=url, rev=rev, subrepos=subrepos, **repo_kwargs)
             assert repo is not None
             # pylint: disable=protected-access
             repo_factory = repo._fs_conf["repo_factory"]
@@ -144,9 +133,7 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
             relparts = ()
             assert repo is not None
             if repo.fs.path.isin(repo.fs.path.getcwd(), repo.root_dir):
-                relparts = repo.fs.path.relparts(
-                    repo.fs.path.getcwd(), repo.root_dir
-                )
+                relparts = repo.fs.path.relparts(repo.fs.path.getcwd(), repo.root_dir)
             return self.root_marker + self.sep.join(relparts)
 
         self.path = Path(self.sep, getcwd=_getcwd)
@@ -166,7 +153,7 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         if hasattr(repo, "dvc_dir"):
             self._datafss[key] = DataFileSystem(index=repo.index.data["repo"])
 
-    def _get_key(self, path: StrPath) -> Key:
+    def _get_key(self, path: "StrPath") -> Key:
         parts = self.repo.fs.path.relparts(path, self.repo.root_dir)
         if parts == (os.curdir,):
             return ()
@@ -222,9 +209,7 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
                     scm=self.repo.scm,
                     repo_factory=self.repo_factory,
                 )
-                self._datafss[key] = DataFileSystem(
-                    index=repo.index.data["repo"]
-                )
+                self._datafss[key] = DataFileSystem(index=repo.index.data["repo"])
             self._subrepos_trie[key] = repo
 
     def _is_dvc_repo(self, dir_path):
@@ -304,7 +289,7 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
                 ):
                     fs_infos[fs.path.name(info["name"])] = info
             except (FileNotFoundError, NotADirectoryError):
-                pass
+                pass  # noqa: S110
 
         dvcfiles = kwargs.get("dvcfiles", False)
 
@@ -331,9 +316,7 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         ignore_subrepos = kwargs.get("ignore_subrepos", True)
         return self._info(key, path, ignore_subrepos=ignore_subrepos)
 
-    def _info(  # noqa: C901
-        self, key, path, ignore_subrepos=True, check_ignored=True
-    ):
+    def _info(self, key, path, ignore_subrepos=True, check_ignored=True):  # noqa: C901
         repo, dvc_fs, subkey = self._get_subrepo_info(key)
 
         dvc_info = None

dvc/fs/git.py

@@ -5,9 +5,10 @@ from . import FileSystem
 
 if TYPE_CHECKING:
     from scmrepo.fs import GitFileSystem as FsspecGitFileSystem
-    from scmrepo.git import Git
     from scmrepo.git.objects import GitTrie
 
+    from dvc.scm import Git
+
 
 class GitFileSystem(FileSystem):  # pylint:disable=abstract-method
     """Proxies the repo file access methods to Git objects"""

dvc/ignore.py

@@ -3,15 +3,18 @@ import os
 import re
 from collections import namedtuple
 from itertools import chain, groupby, takewhile
-from typing import List, Optional
+from typing import TYPE_CHECKING, List, Optional
 
 from pathspec.patterns import GitWildMatchPattern
 from pathspec.util import normalize_file
 from pygtrie import Trie
 
-from dvc.fs import AnyFSPath, FileSystem, Schemes, localfs
+from dvc.fs import Schemes, localfs
 from dvc.pathspec_math import PatternInfo, merge_patterns
 
+if TYPE_CHECKING:
+    from dvc.fs import AnyFSPath, FileSystem
+
 logger = logging.getLogger(__name__)
 
 
@@ -27,9 +30,7 @@ class DvcIgnorePatterns(DvcIgnore):
         from pathspec.patterns.gitwildmatch import _DIR_MARK
 
         if pattern_list and isinstance(pattern_list[0], str):
-            pattern_list = [
-                PatternInfo(pattern, "") for pattern in pattern_list
-            ]
+            pattern_list = [PatternInfo(pattern, "") for pattern in pattern_list]
 
         self.sep = sep
         self.pattern_list = pattern_list
@@ -37,20 +38,14 @@ class DvcIgnorePatterns(DvcIgnore):
 
         self.regex_pattern_list = []
         for count, pattern in enumerate(pattern_list):
-            pattern, group = GitWildMatchPattern.pattern_to_regex(
-                pattern.patterns
-            )
+            pattern, group = GitWildMatchPattern.pattern_to_regex(pattern.patterns)
             if pattern:
-                pattern = pattern.replace(
-                    f"<{_DIR_MARK}>", f"<{_DIR_MARK}{count}>"
-                )
+                pattern = pattern.replace(f"<{_DIR_MARK}>", f"<{_DIR_MARK}{count}>")
                 self.regex_pattern_list.append((pattern, group))
 
         self.ignore_spec = [
             (ignore, re.compile("|".join(item[0] for item in group)))
-            for ignore, group in groupby(
-                self.regex_pattern_list, lambda x: x[1]
-            )
+            for ignore, group in groupby(self.regex_pattern_list, lambda x: x[1])
             if ignore is not None
         ]
 
@@ -61,9 +56,7 @@ class DvcIgnorePatterns(DvcIgnore):
         with fs.open(path, encoding="utf-8") as fobj:
             path_spec_lines = [
                 PatternInfo(line, f"{name}:{line_no + 1}:{line}")
-                for line_no, line in enumerate(
-                    map(str.strip, fobj.readlines())
-                )
+                for line_no, line in enumerate(map(str.strip, fobj.readlines()))
                 if line and not (line.strip().startswith("#"))
             ]
 
@@ -155,9 +148,7 @@ class DvcIgnorePatterns(DvcIgnore):
         return bool(self.pattern_list)
 
 
-CheckIgnoreResult = namedtuple(
-    "CheckIgnoreResult", ["file", "match", "patterns"]
-)
+CheckIgnoreResult = namedtuple("CheckIgnoreResult", ["file", "match", "patterns"])
 
 
 def _no_match(path):
@@ -246,9 +237,7 @@ class DvcIgnoreFilter:
                     dnames = []
 
             for dname in dnames:
-                self._update_sub_repo(
-                    self.fs.path.join(dirname, dname), ignore_trie
-                )
+                self._update_sub_repo(self.fs.path.join(dirname, dname), ignore_trie)
 
     def _update_sub_repo(self, path, ignore_trie: Trie):
         from dvc.repo import Repo
@@ -306,7 +295,7 @@ class DvcIgnoreFilter:
 
         return [fs_dict[name] for name in chain(dirs, nondirs)]
 
-    def walk(self, fs: FileSystem, path: AnyFSPath, **kwargs):
+    def walk(self, fs: "FileSystem", path: "AnyFSPath", **kwargs):
         detail = kwargs.get("detail", False)
         ignore_subrepos = kwargs.pop("ignore_subrepos", True)
         if fs.protocol == Schemes.LOCAL:
@@ -330,7 +319,7 @@ class DvcIgnoreFilter:
         else:
             yield from fs.walk(path, **kwargs)
 
-    def find(self, fs: FileSystem, path: AnyFSPath, **kwargs):
+    def find(self, fs: "FileSystem", path: "AnyFSPath", **kwargs):
         if fs.protocol == Schemes.LOCAL:
             for root, _, files in self.walk(fs, path, **kwargs):
                 for file in files:
@@ -406,9 +395,7 @@ class DvcIgnoreFilter:
         # https://github.com/iterative/dvc/issues/5046
         full_target = self.fs.path.abspath(target)
         if not self._outside_repo(full_target):
-            dirname, basename = self.fs.path.split(
-                self.fs.path.normpath(full_target)
-            )
+            dirname, basename = self.fs.path.split(self.fs.path.normpath(full_target))
             pattern = self._get_trie_pattern(dirname)
             if pattern:
                 matches = pattern.matches(
@@ -420,7 +407,7 @@ class DvcIgnoreFilter:
         return _no_match(target)
 
     def is_ignored(
-        self, fs: FileSystem, path: str, ignore_subrepos: bool = True
+        self, fs: "FileSystem", path: str, ignore_subrepos: bool = True
     ) -> bool:
         # NOTE: can't use self.check_ignore(path).match for now, see
         # https://github.com/iterative/dvc/issues/4555
@@ -430,9 +417,9 @@ class DvcIgnoreFilter:
             return self.is_ignored_file(path, ignore_subrepos)
         if fs.isdir(path):
             return self.is_ignored_dir(path, ignore_subrepos)
-        return self.is_ignored_file(
+        return self.is_ignored_file(path, ignore_subrepos) or self.is_ignored_dir(
             path, ignore_subrepos
-        ) or self.is_ignored_dir(path, ignore_subrepos)
+        )
 
 
 def init(path):

dvc/info.py

@@ -22,15 +22,15 @@ SUBPROJECTS = (
     "dvclive",
     "scmrepo",
 )
-package = "" if PKG is None else f"({PKG})"
+package = "" if PKG is None else f" ({PKG})"
 
 
 def get_dvc_info():
+    dvc_version = f"DVC version: {__version__}{package}"
     info = [
-        f"DVC version: {__version__} {package}",
-        "---------------------------------",
-        f"Platform: Python {platform.python_version()} on "
-        f"{platform.platform()}",
+        dvc_version,
+        "-" * len(dvc_version),
+        f"Platform: Python {platform.python_version()} on {platform.platform()}",
         f"Subprojects:{_get_subprojects()}",
         f"Supports:{_get_supported_remotes()}",
     ]
@@ -41,14 +41,14 @@ def get_dvc_info():
             # can't auto-create it, as it might cause issues if the user
             # later decides to enable shared cache mode with
             # `dvc config cache.shared group`.
-            if os.path.exists(repo.odb.local.path):
+            if os.path.exists(repo.cache.local.path):
                 info.append(f"Cache types: {_get_linktype_support_info(repo)}")
-                fs_type = get_fs_type(repo.odb.local.path)
+                fs_type = get_fs_type(repo.cache.local.path)
                 info.append(f"Cache directory: {fs_type}")
             else:
                 info.append("Cache types: " + error_link("no-dvc-cache"))
 
-            info.append(f"Caches: {_get_caches(repo.odb)}")
+            info.append(f"Caches: {_get_caches(repo.cache)}")
             info.append(f"Remotes: {_get_remotes(repo.config)}")
 
             root_directory = repo.root_dir
@@ -84,7 +84,7 @@ def _get_remotes(config):
 
 
 def _get_linktype_support_info(repo):
-    odb = repo.odb.local
+    odb = repo.cache.local
 
     links = generic.test_links(
         ["reflink", "hardlink", "symlink"],
@@ -124,8 +124,7 @@ def _get_supported_remotes():
             dependencies = []
             for requirement in fs_cls.REQUIRES:
                 dependencies.append(
-                    f"{requirement} = "
-                    f"{importlib_metadata.version(requirement)}"
+                    f"{requirement} = {importlib_metadata.version(requirement)}"
                 )
 
             remote_info = scheme

dvc/lock.py

@@ -20,9 +20,7 @@ FAILED_TO_LOCK_MESSAGE = (
     "Unable to acquire lock. Most likely another DVC process is running or "
     "was terminated abruptly. Check the page {} for other possible reasons "
     "and to learn how to resolve this."
-).format(
-    format_link("https://dvc.org/doc/user-guide/troubleshooting#lock-issue")
-)
+).format(format_link("https://dvc.org/doc/user-guide/troubleshooting#lock-issue"))
 
 
 class LockError(DvcException):
@@ -61,9 +59,7 @@ class LockBase(ABC):
 
 
 class LockNoop(LockBase):
-    def __init__(
-        self, *args, **kwargs
-    ):  # pylint: disable=super-init-not-called
+    def __init__(self, *args, **kwargs):  # pylint: disable=super-init-not-called
         self._lock = False
 
     def lock(self):
@@ -107,10 +103,8 @@ class Lock(LockBase):
             with Tqdm(
                 bar_format="{desc}",
                 disable=not self._friendly,
-                desc=(
-                    "If DVC froze, see `hardlink_lock` in {}".format(
-                        format_link("https://man.dvc.org/config#core")
-                    )
+                desc="If DVC froze, see `hardlink_lock` in {}".format(
+                    format_link("https://man.dvc.org/config#core")
                 ),
             ):
                 self._lock = zc.lockfile.LockFile(self._lockfile)

dvc/logger.py

@@ -1,22 +1,14 @@
 """Manages logging configuration for DVC repo."""
 
+import logging
 import logging.config
 import logging.handlers
+import sys
 
 import colorama
 
 from dvc.progress import Tqdm
 
-FOOTER = (
-    "\n{yellow}Having any troubles?{nc}"
-    " Hit us up at {blue}https://dvc.org/support{nc},"
-    " we are always happy to help!"
-).format(
-    blue=colorama.Fore.BLUE,
-    nc=colorama.Fore.RESET,
-    yellow=colorama.Fore.YELLOW,
-)
-
 
 def addLoggingLevel(levelName, levelNum, methodName=None):
     """
@@ -66,12 +58,11 @@ class LoggingException(Exception):
         super().__init__(msg)
 
 
-def excludeFilter(level):
-    class ExcludeLevelFilter(logging.Filter):
-        def filter(self, record):
-            return record.levelno < level
+def exclude_filter(level: int):
+    def filter_fn(record: "logging.LogRecord") -> bool:
+        return record.levelno < level
 
-    return ExcludeLevelFilter
+    return filter_fn
 
 
 class ColorFormatter(logging.Formatter):
@@ -86,7 +77,8 @@ class ColorFormatter(logging.Formatter):
     exception cause, just the message and the traceback.
     """
 
-    color_code = {
+    reset = colorama.Fore.RESET
+    color_codes = {
         "TRACE": colorama.Fore.GREEN,
         "DEBUG": colorama.Fore.BLUE,
         "WARNING": colorama.Fore.YELLOW,
@@ -94,47 +86,46 @@ class ColorFormatter(logging.Formatter):
         "CRITICAL": colorama.Fore.RED,
     }
 
-    def format(self, record):
+    def __init__(self, log_colors: bool = True) -> None:
+        super().__init__()
+        self.log_colors = log_colors
+
+    def format(self, record) -> str:  # noqa: A003, C901
         record.message = record.getMessage()
         msg = self.formatMessage(record)
 
-        if record.levelname == "INFO":
+        if record.levelno == logging.INFO:
             return msg
 
-        if record.exc_info:
-            if getattr(record, "tb_only", False):
-                cause = ""
-            else:
-                cause = ": ".join(_iter_causes(record.exc_info[1]))
+        ei = record.exc_info
+        if ei:
+            cause = ""
+            if not getattr(record, "tb_only", False):
+                cause = ": ".join(_iter_causes(ei[1]))
+            sep = " - " if msg and cause else ""
+            msg = msg + sep + cause
 
-            msg = "{message}{separator}{cause}".format(
-                message=msg or "",
-                separator=" - " if msg and cause else "",
-                cause=cause,
-            )
+        asctime = ""
+        if _is_verbose():
+            asctime = self.formatTime(record, self.datefmt)
+            if ei and not record.exc_text:
+                record.exc_text = self.formatException(ei)
+            if record.exc_text:
+                if msg[-1:] != "\n":
+                    msg = msg + "\n"
+                msg = msg + record.exc_text + "\n"
+            if record.stack_info:
+                if msg[-1:] != "\n":
+                    msg = msg + "\n"
+                msg = msg + self.formatStack(record.stack_info) + "\n"
 
-            if _is_verbose():
-                msg += _stack_trace(record.exc_info)
-
-        return "{asctime}{color}{levelname}{nc}: {msg}".format(
-            asctime=self.formatTime(record, self.datefmt),
-            color=self.color_code[record.levelname],
-            nc=colorama.Fore.RESET,
-            levelname=record.levelname,
-            msg=msg,
-        )
-
-    def formatTime(self, record, datefmt=None):
-        # only show if current level is set to DEBUG
-        # also, skip INFO as it is used for UI
-        if not _is_verbose() or record.levelno == logging.INFO:
-            return ""
-
-        return "{green}{date}{nc} ".format(
-            green=colorama.Fore.GREEN,
-            date=super().formatTime(record, datefmt),
-            nc=colorama.Fore.RESET,
-        )
+        level = record.levelname
+        if self.log_colors:
+            color = self.color_codes[level]
+            if asctime:
+                asctime = color + asctime + self.reset
+            level = color + level + self.reset
+        return asctime + (" " if asctime else "") + level + ": " + msg
 
 
 class LoggerHandler(logging.StreamHandler):
@@ -156,12 +147,10 @@ class LoggerHandler(logging.StreamHandler):
                         if not _is_verbose():
                             return
                     except Exception:  # noqa, pylint: disable=broad-except
-                        pass
+                        pass  # noqa: S110
 
             msg = self.format(record)
-            Tqdm.write(
-                msg, file=self.stream, end=getattr(self, "terminator", "\n")
-            )
+            Tqdm.write(msg, file=self.stream, end=getattr(self, "terminator", "\n"))
             self.flush()
         except (BrokenPipeError, RecursionError):
             raise
@@ -171,9 +160,7 @@ class LoggerHandler(logging.StreamHandler):
 
 def _is_verbose():
     return (
-        logging.NOTSET
-        < logging.getLogger("dvc").getEffectiveLevel()
-        <= logging.DEBUG
+        logging.NOTSET < logging.getLogger("dvc").getEffectiveLevel() <= logging.DEBUG
     )
 
 
@@ -183,36 +170,44 @@ def _iter_causes(exc):
         exc = exc.__cause__
 
 
-def _stack_trace(exc_info):
-    import traceback
-
-    return (
-        "\n"
-        "{red}{line}{nc}\n"
-        "{trace}"
-        "{red}{line}{nc}".format(
-            red=colorama.Fore.RED,
-            line="-" * 60,
-            trace="".join(traceback.format_exception(*exc_info)),
-            nc=colorama.Fore.RESET,
-        )
-    )
-
-
-def disable_other_loggers():
-    logging.captureWarnings(True)
-    loggerDict = logging.root.manager.loggerDict  # pylint: disable=no-member
-    for logger_name, logger in loggerDict.items():
-        if logger_name != "dvc" and not logger_name.startswith("dvc."):
-            logger.disabled = True  # type: ignore[union-attr]
-
-
 def set_loggers_level(level: int = logging.INFO) -> None:
     for name in ["dvc", "dvc_objects", "dvc_data"]:
         logging.getLogger(name).setLevel(level)
 
 
-def setup(level: int = logging.INFO) -> None:
+def setup(level: int = logging.INFO, log_colors: bool = True) -> None:
+    colorama.init()
+
+    formatter = ColorFormatter(log_colors=log_colors and sys.stdout.isatty())
+
+    console_info = LoggerHandler(sys.stdout)
+    console_info.setLevel(logging.INFO)
+    console_info.setFormatter(formatter)
+    console_info.addFilter(exclude_filter(logging.WARNING))
+
+    console_debug = LoggerHandler(sys.stdout)
+    console_debug.setLevel(logging.DEBUG)
+    console_debug.setFormatter(formatter)
+    console_debug.addFilter(exclude_filter(logging.INFO))
+
+    addLoggingLevel("TRACE", logging.DEBUG - 5)
+
+    console_trace = LoggerHandler(sys.stdout)
+    console_trace.setLevel(logging.TRACE)  # type: ignore[attr-defined]
+    console_trace.setFormatter(formatter)
+    console_trace.addFilter(exclude_filter(logging.DEBUG))
+
+    err_formatter = ColorFormatter(log_colors=log_colors and sys.stderr.isatty())
+    console_errors = LoggerHandler(sys.stderr)
+    console_errors.setLevel(logging.WARNING)
+    console_errors.setFormatter(err_formatter)
+
+    for name in ["dvc", "dvc_objects", "dvc_data"]:
+        logger = logging.getLogger(name)
+        logger.setLevel(level)
+        for handler in [console_info, console_debug, console_trace, console_errors]:
+            logger.addHandler(handler)
+
     if level >= logging.DEBUG:
         # Unclosed session errors for asyncio/aiohttp are only available
         # on the tracing mode for extensive debug purposes. They are really
@@ -223,80 +218,3 @@ def setup(level: int = logging.INFO) -> None:
         # action.
         logging.getLogger("asyncio").setLevel(logging.CRITICAL)
         logging.getLogger("aiohttp").setLevel(logging.CRITICAL)
-
-    addLoggingLevel("TRACE", logging.DEBUG - 5)
-    logging.config.dictConfig(
-        {
-            "version": 1,
-            "filters": {
-                "exclude_errors": {"()": excludeFilter(logging.WARNING)},
-                "exclude_info": {"()": excludeFilter(logging.INFO)},
-                "exclude_debug": {"()": excludeFilter(logging.DEBUG)},
-            },
-            "formatters": {"color": {"()": ColorFormatter}},
-            "handlers": {
-                "console_info": {
-                    "class": "dvc.logger.LoggerHandler",
-                    "level": "INFO",
-                    "formatter": "color",
-                    "stream": "ext://sys.stdout",
-                    "filters": ["exclude_errors"],
-                },
-                "console_debug": {
-                    "class": "dvc.logger.LoggerHandler",
-                    "level": "DEBUG",
-                    "formatter": "color",
-                    "stream": "ext://sys.stdout",
-                    "filters": ["exclude_info"],
-                },
-                "console_trace": {
-                    "class": "dvc.logger.LoggerHandler",
-                    "level": "TRACE",
-                    "formatter": "color",
-                    "stream": "ext://sys.stdout",
-                    "filters": ["exclude_debug"],
-                },
-                "console_errors": {
-                    "class": "dvc.logger.LoggerHandler",
-                    "level": "WARNING",
-                    "formatter": "color",
-                    "stream": "ext://sys.stderr",
-                },
-            },
-            "loggers": {
-                "dvc": {
-                    "level": level,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
-                        "console_trace",
-                        "console_errors",
-                    ],
-                },
-                "dvc_objects": {
-                    "level": level,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
-                        "console_trace",
-                        "console_errors",
-                    ],
-                },
-                "dvc_data": {
-                    "level": level,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
-                        "console_trace",
-                        "console_errors",
-                    ],
-                },
-            },
-            "disable_existing_loggers": False,
-        }
-    )
-
-    # NOTE: colorama init needs to go after logging config to avoid potential
-    # conflicts with libs that modify logging (like tensorflow/abseil)
-    # https://github.com/iterative/dvc/issues/8387
-    colorama.init()

dvc/machine/__init__.py

@@ -13,10 +13,10 @@ from typing import (
 )
 
 from dvc.exceptions import DvcException
-from dvc.types import StrPath
 
 if TYPE_CHECKING:
     from dvc.repo import Repo
+    from dvc.types import StrPath
 
     from .backend.base import BaseMachineBackend
 
@@ -67,16 +67,14 @@ class MachineBackends(Mapping):
         initialized = self.initialized.get(key)
         if not initialized:
             backend = self.backends[key]
-            initialized = backend(
-                os.path.join(self.tmp_dir, key), **self.kwargs
-            )
+            initialized = backend(os.path.join(self.tmp_dir, key), **self.kwargs)
             self.initialized[key] = initialized
         return initialized
 
     def __init__(
         self,
         selected: Optional[Iterable[str]],
-        tmp_dir: StrPath,
+        tmp_dir: "StrPath",
         **kwargs,
     ) -> None:
         selected = selected or list(self.DEFAULT)

dvc/machine/backend/base.py

@@ -21,9 +21,7 @@ class BaseMachineBackend(ABC):
         """Stop and destroy all instances of the specified machine."""
 
     @abstractmethod
-    def instances(
-        self, name: Optional[str] = None, **config
-    ) -> Iterator[dict]:
+    def instances(self, name: Optional[str] = None, **config) -> Iterator[dict]:
         """Iterate over status of all instances of the specified machine."""
 
     def close(self):  # noqa: B027

dvc/machine/backend/terraform.py

@@ -56,12 +56,8 @@ class TerraformBackend(BaseMachineBackend):
 
     create = partialmethod(_tpi_func, "create")  # type: ignore[assignment]
     destroy = partialmethod(_tpi_func, "destroy")  # type: ignore[assignment]
-    instances = partialmethod(
-        _tpi_func, "instances"
-    )  # type: ignore[assignment]
-    run_shell = partialmethod(
-        _tpi_func, "run_shell"
-    )  # type: ignore[assignment]
+    instances = partialmethod(_tpi_func, "instances")  # type: ignore[assignment]
+    run_shell = partialmethod(_tpi_func, "run_shell")  # type: ignore[assignment]
 
     def get_executor_kwargs(self, name: str, **config) -> dict:
         with self.make_tpi(name) as tpi:

dvc/output.py

@@ -1,11 +1,13 @@
 import logging
 import os
+import posixpath
 from collections import defaultdict
+from operator import itemgetter
 from typing import TYPE_CHECKING, Dict, List, Optional, Set, Tuple, Type, cast
 from urllib.parse import urlparse
 
-from funcy import collecting, project
-from voluptuous import And, Any, Coerce, Length, Lower, Required, SetTo
+from funcy import collecting, first, project
+from voluptuous import All, And, Any, Coerce, Length, Lower, Required, SetTo
 
 from dvc import prompt
 from dvc.exceptions import (
@@ -27,20 +29,21 @@ from dvc_data.hashfile.hash_info import HashInfo
 from dvc_data.hashfile.istextfile import istextfile
 from dvc_data.hashfile.meta import Meta
 from dvc_data.hashfile.transfer import transfer as otransfer
-from dvc_data.index import DataIndexEntry
 from dvc_objects.errors import ObjectFormatError
 
 from .annotations import ANNOTATION_FIELDS, ANNOTATION_SCHEMA, Annotation
 from .fs import LocalFileSystem, RemoteMissingDepsError, Schemes, get_cloud_fs
-from .fs.callbacks import DEFAULT_CALLBACK, Callback
+from .fs.callbacks import DEFAULT_CALLBACK
 from .utils import relpath
 from .utils.fs import path_isin
 
 if TYPE_CHECKING:
+    from dvc_data.hashfile.db import HashFileDB
     from dvc_data.hashfile.obj import HashFile
     from dvc_data.index import DataIndexKey
     from dvc_objects.db import ObjectDB
 
+    from .fs.callbacks import Callback
     from .ignore import DvcIgnoreFilter
 
 logger = logging.getLogger(__name__)
@@ -150,11 +153,11 @@ def _merge_data(s_list):
             d[key].update({})
             continue
         if not isinstance(key, dict):
-            raise ValueError(f"'{type(key).__name__}' not supported.")
+            raise ValueError(f"'{type(key).__name__}' not supported.")  # noqa: TRY004
 
         for k, flags in key.items():
             if not isinstance(flags, dict):
-                raise ValueError(
+                raise ValueError(  # noqa: TRY004
                     f"Expected dict for '{k}', got: '{type(flags).__name__}'"
                 )
             d[k].update(flags)
@@ -204,6 +207,41 @@ def load_from_pipeline(stage, data, typ="outs"):
         )
 
 
+def split_file_meta_from_cloud(entry: Dict) -> Dict:
+    if remote_name := entry.pop(Meta.PARAM_REMOTE, None):
+        remote_meta = {}
+        for key in (
+            S3_PARAM_CHECKSUM,
+            HDFS_PARAM_CHECKSUM,
+            Meta.PARAM_VERSION_ID,
+        ):
+            if value := entry.pop(key, None):
+                remote_meta[key] = value
+
+        if remote_meta:
+            entry[Output.PARAM_CLOUD] = {remote_name: remote_meta}
+    return entry
+
+
+def merge_file_meta_from_cloud(entry: Dict) -> Dict:
+    cloud_meta = entry.pop(Output.PARAM_CLOUD, {})
+    if remote_name := first(cloud_meta):
+        entry.update(cloud_meta[remote_name])
+        entry[Meta.PARAM_REMOTE] = remote_name
+    return entry
+
+
+def _serialize_tree_obj_to_files(obj: "Tree") -> List[Dict[str, Any]]:
+    key = obj.PARAM_RELPATH
+    return sorted(
+        (
+            {key: posixpath.sep.join(parts), **hi.to_dict(), **meta.to_dict()}
+            for parts, meta, hi in obj
+        ),
+        key=itemgetter(key),
+    )
+
+
 class OutputDoesNotExistError(DvcException):
     def __init__(self, path):
         msg = f"output '{path}' does not exist"
@@ -258,6 +296,7 @@ class Output:
     PARAM_PERSIST = "persist"
     PARAM_REMOTE = "remote"
     PARAM_PUSH = "push"
+    PARAM_CLOUD = "cloud"
 
     METRIC_SCHEMA = Any(
         None,
@@ -297,17 +336,18 @@ class Output:
             desc=desc, type=type, labels=labels or [], meta=meta or {}
         )
         self.repo = stage.repo if not repo and stage else repo
-        meta = Meta.from_dict(info or {})
+        meta_d = merge_file_meta_from_cloud(info or {})
+        meta = Meta.from_dict(meta_d)
         # NOTE: when version_aware is not passed into get_cloud_fs, it will be
         # set based on whether or not path is versioned
-        fs_kwargs = {"version_aware": True} if meta.version_id else {}
+        fs_kwargs = {}
+        if meta.version_id or files:
+            fs_kwargs["version_aware"] = True
 
         if fs_config is not None:
             fs_kwargs.update(**fs_config)
 
-        fs_cls, fs_config, fs_path = get_cloud_fs(
-            self.repo, url=path, **fs_kwargs
-        )
+        fs_cls, fs_config, fs_path = get_cloud_fs(self.repo, url=path, **fs_kwargs)
         self.fs = fs_cls(**fs_config)
 
         if (
@@ -340,6 +380,9 @@ class Output:
         # should be absolute and don't contain remote:// refs.
         self.stage = stage
         self.meta = meta
+
+        if files is not None:
+            files = [merge_file_meta_from_cloud(f) for f in files]
         self.files = files
         self.use_cache = False if self.IS_DEPENDENCY else cache
         self.metric = False if self.IS_DEPENDENCY else metric
@@ -351,6 +394,7 @@ class Output:
         self.fs_path = self._parse_path(self.fs, fs_path)
         self.obj: Optional["HashFile"] = None
 
+        self.odb: Optional["HashFileDB"] = None
         self.remote = remote
 
         if self.fs.version_aware:
@@ -368,7 +412,23 @@ class Output:
             name=self.hash_name,
             value=getattr(self.meta, self.hash_name, None),
         )
-        if self.meta.nfiles or self.hash_info and self.hash_info.isdir:
+        self._compute_meta_hash_info_from_files()
+
+    def _compute_meta_hash_info_from_files(self) -> None:
+        if self.files:
+            from dvc_data.hashfile.db import HashFileDB
+
+            tree = Tree.from_list(self.files, hash_name=self.hash_name)
+            tree.digest(with_meta=True)
+            self.odb = HashFileDB(tree.fs, tree.path + ".odb")
+            self.odb.add(tree.path, tree.fs, tree.hash_info.value)
+
+            self.hash_info = tree.hash_info
+            self.meta.isdir = True
+            self.meta.nfiles = len(self.files)
+            self.meta.size = sum(f.get("size") for f in self.files)
+            self.meta.remote = first(f.get("remote") for f in self.files)
+        elif self.meta.nfiles or self.hash_info and self.hash_info.isdir:
             self.meta.isdir = True
             if not self.hash_info and self.hash_name != "md5":
                 md5 = getattr(self.meta, "md5", None)
@@ -446,17 +506,17 @@ class Output:
         return self.use_cache or self.stage.is_repo_import
 
     @property
-    def odb(self):
+    def cache(self):
         odb_name = "repo" if self.is_in_repo else self.protocol
-        odb = getattr(self.repo.odb, odb_name)
+        odb = getattr(self.repo.cache, odb_name)
         if self.use_cache and odb is None:
             raise RemoteCacheRequiredError(self.fs.protocol, self.fs_path)
         return odb
 
     @property
     def cache_path(self):
-        return self.odb.fs.unstrip_protocol(
-            self.odb.oid_to_path(self.hash_info.value)
+        return self.cache.fs.unstrip_protocol(
+            self.cache.oid_to_path(self.hash_info.value)
         )
 
     def get_hash(self):
@@ -465,9 +525,9 @@ class Output:
 
     def _get_hash_meta(self):
         if self.use_cache:
-            odb = self.odb
+            odb = self.cache
         else:
-            odb = self.repo.odb.local
+            odb = self.repo.cache.local
         _, meta, obj = build(
             odb,
             self.fs_path,
@@ -509,36 +569,6 @@ class Output:
             key = self.fs.path.parts(no_drive)[1:]
         return workspace, key
 
-    def get_entry(self) -> "DataIndexEntry":
-        from dvc.config import NoRemoteError
-
-        try:
-            remote = self.repo.cloud.get_remote_odb(self.remote)
-        except NoRemoteError:
-            remote = None
-
-        if self.files and not self.obj:
-            self.obj = self.get_obj()
-
-        entry = DataIndexEntry(
-            meta=self.meta,
-            obj=self.obj,
-            hash_info=self.hash_info,
-            odb=self.odb,
-            cache=self.odb,
-            remote=remote,
-        )
-        if self.stage.is_import and not self.stage.is_repo_import:
-            dep = self.stage.deps[0]
-            entry.fs = dep.fs
-            entry.path = dep.fs_path
-            entry.meta = dep.meta
-            if not entry.obj:
-                if not dep.obj and dep.files:
-                    dep.obj = dep.get_obj()
-                entry.obj = dep.obj
-        return entry
-
     def changed_checksum(self):
         return self.hash_info != self.get_hash()
 
@@ -551,7 +581,7 @@ class Output:
             return True
 
         try:
-            ocheck(self.odb, obj)
+            ocheck(self.cache, obj)
             return False
         except (FileNotFoundError, ObjectFormatError):
             return True
@@ -640,7 +670,7 @@ class Output:
 
         if self.use_cache:
             _, self.meta, self.obj = build(
-                self.odb,
+                self.cache,
                 self.fs_path,
                 self.fs,
                 self.hash_name,
@@ -648,7 +678,7 @@ class Output:
             )
         else:
             _, self.meta, self.obj = build(
-                self.repo.odb.local,
+                self.repo.cache.local,
                 self.fs_path,
                 self.fs,
                 self.hash_name,
@@ -656,16 +686,14 @@ class Output:
                 dry_run=True,
             )
             if not self.IS_DEPENDENCY:
-                logger.debug(
-                    "Output '%s' doesn't use cache. Skipping saving.", self
-                )
+                logger.debug("Output '%s' doesn't use cache. Skipping saving.", self)
 
         self.hash_info = self.obj.hash_info
         self.files = None
 
     def set_exec(self) -> None:
         if self.isfile() and self.meta.isexec:
-            self.odb.set_exec(self.fs_path)
+            self.cache.set_exec(self.fs_path)
 
     def _checkout(self, *args, **kwargs) -> Optional[bool]:
         from dvc_data.hashfile.checkout import CheckoutError as _CheckoutError
@@ -689,15 +717,13 @@ class Output:
 
         if self.use_cache:
             granular = (
-                self.is_dir_checksum
-                and filter_info
-                and filter_info != self.fs_path
+                self.is_dir_checksum and filter_info and filter_info != self.fs_path
             )
             if granular:
                 obj = self._commit_granular_dir(filter_info)
             else:
                 staging, _, obj = build(
-                    self.odb,
+                    self.cache,
                     filter_info or self.fs_path,
                     self.fs,
                     self.hash_name,
@@ -705,7 +731,7 @@ class Output:
                 )
                 otransfer(
                     staging,
-                    self.odb,
+                    self.cache,
                     {obj.hash_info},
                     shallow=False,
                     hardlink=True,
@@ -714,7 +740,7 @@ class Output:
                 filter_info or self.fs_path,
                 self.fs,
                 obj,
-                self.odb,
+                self.cache,
                 relink=True,
                 state=self.repo.state,
                 prompt=prompt.confirm,
@@ -722,11 +748,9 @@ class Output:
             self.set_exec()
 
     def _commit_granular_dir(self, filter_info) -> Optional["HashFile"]:
-        prefix = self.fs.path.parts(
-            self.fs.path.relpath(filter_info, self.fs_path)
-        )
+        prefix = self.fs.path.parts(self.fs.path.relpath(filter_info, self.fs_path))
         staging, _, save_obj = build(
-            self.odb,
+            self.cache,
             self.fs_path,
             self.fs,
             self.hash_name,
@@ -734,10 +758,10 @@ class Output:
         )
         save_obj = cast(Tree, save_obj)
         save_obj = cast(Tree, save_obj.filter(prefix))
-        checkout_obj = save_obj.get_obj(self.odb, prefix)
+        checkout_obj = save_obj.get_obj(self.cache, prefix)
         otransfer(
             staging,
-            self.odb,
+            self.cache,
             {save_obj.hash_info} | {oid for _, _, oid in save_obj},
             shallow=True,
             hardlink=True,
@@ -745,14 +769,21 @@ class Output:
         return checkout_obj
 
     def dumpd(self, **kwargs):  # noqa: C901
-        meta = self.meta.to_dict()
-        meta.pop("isdir", None)
-        ret: Dict[str, Any] = {**self.hash_info.to_dict(), **meta}
+        ret: Dict[str, Any] = {}
+        with_files = (
+            (not self.IS_DEPENDENCY or self.stage.is_import)
+            and self.hash_info.isdir
+            and (kwargs.get("with_files") or self.files is not None)
+        )
+
+        if not with_files:
+            meta_d = self.meta.to_dict()
+            meta_d.pop("isdir", None)
+            ret.update(self.hash_info.to_dict())
+            ret.update(split_file_meta_from_cloud(meta_d))
 
         if self.is_in_repo:
-            path = self.fs.path.as_posix(
-                relpath(self.fs_path, self.stage.wdir)
-            )
+            path = self.fs.path.as_posix(relpath(self.fs_path, self.stage.wdir))
         else:
             path = self.def_path
 
@@ -788,27 +819,19 @@ class Output:
             if not self.can_push:
                 ret[self.PARAM_PUSH] = self.can_push
 
-        if (
-            (not self.IS_DEPENDENCY or self.stage.is_import)
-            and self.hash_info.isdir
-            and (kwargs.get("with_files") or self.files is not None)
-        ):
-            obj: Optional["HashFile"]
-            if self.obj:
-                obj = self.obj
-            else:
-                obj = self.get_obj()
+        if with_files:
+            obj = self.obj or self.get_obj()
             if obj:
-                obj = cast(Tree, obj)
-                ret[self.PARAM_FILES] = obj.as_list(with_meta=True)
-
+                obj = cast("Tree", obj)
+                ret[self.PARAM_FILES] = [
+                    split_file_meta_from_cloud(f)
+                    for f in _serialize_tree_obj_to_files(obj)
+                ]
         return ret
 
     def verify_metric(self):
         if self.fs.protocol != "local":
-            raise DvcException(
-                f"verify metric is not supported for {self.protocol}"
-            )
+            raise DvcException(f"verify metric is not supported for {self.protocol}")
         if not self.metric:
             return
 
@@ -831,16 +854,15 @@ class Output:
         obj: Optional["HashFile"] = None
         if self.obj:
             obj = self.obj
+        elif self.files:
+            tree = Tree.from_list(self.files, hash_name=self.hash_name)
+            tree.digest()
+            obj = tree
         elif self.hash_info:
-            if self.files:
-                tree = Tree.from_list(self.files, hash_name=self.hash_name)
-                tree.digest()
-                obj = tree
-            else:
-                try:
-                    obj = oload(self.odb, self.hash_info)
-                except (FileNotFoundError, ObjectFormatError):
-                    return None
+            try:
+                obj = oload(self.cache, self.hash_info)
+            except (FileNotFoundError, ObjectFormatError):
+                return None
         else:
             return None
 
@@ -849,7 +871,7 @@ class Output:
         if filter_info and filter_info != self.fs_path:
             prefix = fs_path.relparts(filter_info, self.fs_path)
             obj = cast(Tree, obj)
-            obj = obj.get_obj(self.odb, prefix)
+            obj = obj.get_obj(self.cache, prefix)
 
         return obj
 
@@ -865,9 +887,7 @@ class Output:
     ) -> Optional[Tuple[bool, Optional[bool]]]:
         if not self.use_cache:
             if progress_callback != DEFAULT_CALLBACK:
-                progress_callback.relative_update(
-                    self.get_files_number(filter_info)
-                )
+                progress_callback.relative_update(self.get_files_number(filter_info))
             return None
 
         obj = self.get_obj(filter_info=filter_info)
@@ -887,7 +907,7 @@ class Output:
                 filter_info or self.fs_path,
                 self.fs,
                 obj,
-                self.odb,
+                self.cache,
                 force=force,
                 progress_callback=progress_callback,
                 relink=relink,
@@ -928,7 +948,7 @@ class Output:
         self, source, odb=None, jobs=None, update=False, no_progress_bar=False
     ):
         if odb is None:
-            odb = self.odb
+            odb = self.cache
 
         cls, config, from_info = get_cloud_fs(self.repo, url=source)
         from_fs = cls(**config)
@@ -980,15 +1000,15 @@ class Output:
 
     def unprotect(self):
         if self.exists:
-            self.odb.unprotect(self.fs_path)
+            self.cache.unprotect(self.fs_path)
 
     def get_dir_cache(self, **kwargs):
         if not self.is_dir_checksum:
             raise DvcException("cannot get dir cache for file checksum")
 
-        obj = self.odb.get(self.hash_info.value)
+        obj = self.cache.get(self.hash_info.value)
         try:
-            ocheck(self.odb, obj)
+            ocheck(self.cache, obj)
         except FileNotFoundError:
             if self.remote:
                 kwargs["remote"] = self.remote
@@ -998,7 +1018,7 @@ class Output:
             return self.obj
 
         try:
-            self.obj = oload(self.odb, self.hash_info)
+            self.obj = oload(self.cache, self.hash_info)
         except (FileNotFoundError, ObjectFormatError):
             self.obj = None
 
@@ -1017,7 +1037,7 @@ class Output:
             logger.debug("failed to pull cache for '%s'", self)
 
         try:
-            ocheck(self.odb, self.odb.get(self.hash_info.value))
+            ocheck(self.cache, self.cache.get(self.hash_info.value))
         except FileNotFoundError:
             msg = (
                 "Missing cache for directory '{}'. "
@@ -1034,9 +1054,7 @@ class Output:
         obj = self.get_obj()
         if filter_info and filter_info != self.fs_path:
             assert obj
-            prefix = self.fs.path.parts(
-                self.fs.path.relpath(filter_info, self.fs_path)
-            )
+            prefix = self.fs.path.parts(self.fs.path.relpath(filter_info, self.fs_path))
             obj = cast(Tree, obj)
             return obj.filter(prefix)
         return cast(Tree, obj)
@@ -1083,7 +1101,7 @@ class Output:
         else:
             obj = self.get_obj(filter_info=kwargs.get("filter_info"))
             if not obj:
-                obj = self.odb.get(self.hash_info.value)
+                obj = self.cache.get(self.hash_info.value)
 
         if not obj:
             return {}
@@ -1144,14 +1162,10 @@ class Output:
             other.pop(opt, None)
 
         if my != other:
-            raise MergeError(
-                "unable to auto-merge outputs with different options"
-            )
+            raise MergeError("unable to auto-merge outputs with different options")
 
         if not out.is_dir_checksum:
-            raise MergeError(
-                "unable to auto-merge outputs that are not directories"
-            )
+            raise MergeError("unable to auto-merge outputs that are not directories")
 
     def merge(self, ancestor, other, allowed=None):
         from dvc_data.hashfile.tree import MergeError as TreeMergeError
@@ -1170,7 +1184,7 @@ class Output:
 
         try:
             merged = merge(
-                self.odb,
+                self.cache,
                 ancestor_info,
                 self.hash_info,
                 other.hash_info,
@@ -1179,12 +1193,12 @@ class Output:
         except TreeMergeError as exc:
             raise MergeError(str(exc)) from exc
 
-        self.odb.add(merged.path, merged.fs, merged.oid)
+        self.cache.add(merged.path, merged.fs, merged.oid)
 
         self.hash_info = merged.hash_info
         self.files = None
         self.meta = Meta(
-            size=du(self.odb, merged),
+            size=du(self.cache, merged),
             nfiles=len(merged),
         )
 
@@ -1226,7 +1240,8 @@ class Output:
         if not self.obj or not other.hash_info.isdir:
             return
         other_obj = other.obj if other.obj is not None else other.get_obj()
-        assert isinstance(self.obj, Tree) and isinstance(other_obj, Tree)
+        assert isinstance(self.obj, Tree)
+        assert isinstance(other_obj, Tree)
         updated = update_meta(self.obj, other_obj)
         assert updated.hash_info == self.obj.hash_info
         self.obj = updated
@@ -1240,6 +1255,8 @@ META_SCHEMA = {
     Meta.PARAM_VERSION_ID: str,
 }
 
+CLOUD_SCHEMA = All({str: {**META_SCHEMA, **CHECKSUMS_SCHEMA}}, Length(max=1))
+
 ARTIFACT_SCHEMA = {
     **CHECKSUMS_SCHEMA,
     **META_SCHEMA,
@@ -1247,12 +1264,14 @@ ARTIFACT_SCHEMA = {
     Output.PARAM_PLOT: bool,
     Output.PARAM_PERSIST: bool,
     Output.PARAM_CHECKPOINT: bool,
+    Output.PARAM_CLOUD: CLOUD_SCHEMA,
 }
 
 DIR_FILES_SCHEMA: Dict[str, Any] = {
     **CHECKSUMS_SCHEMA,
     **META_SCHEMA,
     Required(Tree.PARAM_RELPATH): str,
+    Output.PARAM_CLOUD: CLOUD_SCHEMA,
 }
 
 SCHEMA = {

dvc/parsing/__init__.py

@@ -26,7 +26,6 @@ from .context import (
     KeyNotInContext,
     MergeError,
     Node,
-    SeqOrMap,
     VarsAlreadyLoaded,
 )
 from .interpolate import (
@@ -40,8 +39,10 @@ if TYPE_CHECKING:
     from typing import NoReturn
 
     from dvc.repo import Repo
+    from dvc.types import DictStrAny
+
+    from .context import SeqOrMap
 
-from dvc.types import DictStrAny
 
 logger = logging.getLogger(__name__)
 
@@ -71,9 +72,7 @@ def _format_preamble(msg: str, path: str, spacing: str = " ") -> str:
 
 def format_and_raise(exc: Exception, msg: str, path: str) -> "NoReturn":
     spacing = (
-        "\n"
-        if isinstance(exc, (ParseError, MergeError, VarsAlreadyLoaded))
-        else " "
+        "\n" if isinstance(exc, (ParseError, MergeError, VarsAlreadyLoaded)) else " "
     )
     message = _format_preamble(msg, path, spacing) + str(exc)
 
@@ -92,7 +91,7 @@ def _reraise_err(
 
 
 def check_syntax_errors(
-    definition: DictStrAny, name: str, path: str, where: str = "stages"
+    definition: "DictStrAny", name: str, path: str, where: str = "stages"
 ):
     for key, d in definition.items():
         try:
@@ -111,12 +110,11 @@ def split_foreach_name(name: str) -> Tuple[str, Optional[str]]:
     return group, first(keys)
 
 
-def check_interpolations(data: DictStrAny, where: str, path: str):
-    def func(s: DictStrAny) -> None:
+def check_interpolations(data: "DictStrAny", where: str, path: str):
+    def func(s: "DictStrAny") -> None:
         if is_interpolated_string(s):
             raise ResolveError(
-                _format_preamble(f"'{where}'", path)
-                + "interpolating is not allowed"
+                _format_preamble(f"'{where}'", path) + "interpolating is not allowed"
             )
 
     return recurse(func)(data)
@@ -126,7 +124,7 @@ Definition = Union["ForeachDefinition", "EntryDefinition"]
 
 
 def make_definition(
-    resolver: "DataResolver", name: str, definition: DictStrAny, **kwargs
+    resolver: "DataResolver", name: str, definition: "DictStrAny", **kwargs
 ) -> Definition:
     args = resolver, resolver.context, name, definition
     if FOREACH_KWD in definition:
@@ -187,9 +185,7 @@ class DataResolver:
     def resolve(self):
         """Used for testing purposes, otherwise use resolve_one()."""
         data = join(map(self.resolve_one, self.get_keys()))
-        logger.trace(  # type: ignore[attr-defined]
-            "Resolved dvc.yaml:\n%s", data
-        )
+        logger.trace("Resolved dvc.yaml:\n%s", data)  # type: ignore[attr-defined]
         return {STAGES_KWD: data}
 
     def has_key(self, key: str):
@@ -202,9 +198,9 @@ class DataResolver:
             return False
 
         if key:
-            return isinstance(
-                definition, ForeachDefinition
-            ) and definition.has_member(key)
+            return isinstance(definition, ForeachDefinition) and definition.has_member(
+                key
+            )
         return not isinstance(definition, ForeachDefinition)
 
     @collecting
@@ -225,7 +221,7 @@ class EntryDefinition:
         resolver: DataResolver,
         context: Context,
         name: str,
-        definition: DictStrAny,
+        definition: "DictStrAny",
         where: str = STAGES_KWD,
     ):
         self.resolver = resolver
@@ -254,7 +250,7 @@ class EntryDefinition:
         except ContextError as exc:
             format_and_raise(exc, f"stage '{self.name}'", self.relpath)
 
-    def resolve_stage(self, skip_checks: bool = False) -> DictStrAny:
+    def resolve_stage(self, skip_checks: bool = False) -> "DictStrAny":
         context = self.context
         name = self.name
         if not skip_checks:
@@ -302,15 +298,13 @@ class EntryDefinition:
 
     def _resolve(
         self, context: "Context", value: Any, key: str, skip_checks: bool
-    ) -> DictStrAny:
+    ) -> "DictStrAny":
         try:
             return context.resolve(
                 value, skip_interpolation_checks=skip_checks, key=key
             )
         except (ParseError, KeyNotInContext) as exc:
-            format_and_raise(
-                exc, f"'{self.where}.{self.name}.{key}'", self.relpath
-            )
+            format_and_raise(exc, f"'{self.where}.{self.name}.{key}'", self.relpath)
 
 
 class IterationPair(NamedTuple):
@@ -324,7 +318,7 @@ class ForeachDefinition:
         resolver: DataResolver,
         context: Context,
         name: str,
-        definition: DictStrAny,
+        definition: "DictStrAny",
         where: str = STAGES_KWD,
     ):
         self.resolver = resolver
@@ -349,13 +343,11 @@ class ForeachDefinition:
     def resolved_iterable(self):
         return self._resolve_foreach_data()
 
-    def _resolve_foreach_data(self) -> SeqOrMap:
+    def _resolve_foreach_data(self) -> "SeqOrMap":
         try:
             iterable = self.context.resolve(self.foreach_data, unwrap=False)
         except (ContextError, ParseError) as exc:
-            format_and_raise(
-                exc, f"'{self.where}.{self.name}.foreach'", self.relpath
-            )
+            format_and_raise(exc, f"'{self.where}.{self.name}.foreach'", self.relpath)
 
         # foreach data can be a resolved dictionary/list.
         self._check_is_map_or_seq(iterable)
@@ -380,8 +372,10 @@ class ForeachDefinition:
         if warn_for:
             linking_verb = "is" if len(warn_for) == 1 else "are"
             logger.warning(
-                "%s %s already specified, "
-                "will be overwritten for stages generated from '%s'",
+                (
+                    "%s %s already specified, "
+                    "will be overwritten for stages generated from '%s'"
+                ),
                 " and ".join(warn_for),
                 linking_verb,
                 self.name,
@@ -417,13 +411,13 @@ class ForeachDefinition:
     def _generate_name(self, key: str) -> str:
         return f"{self.name}{JOIN}{key}"
 
-    def resolve_all(self) -> DictStrAny:
+    def resolve_all(self) -> "DictStrAny":
         return join(map(self.resolve_one, self.normalized_iterable))
 
-    def resolve_one(self, key: str) -> DictStrAny:
+    def resolve_one(self, key: str) -> "DictStrAny":
         return self._each_iter(key)
 
-    def _each_iter(self, key: str) -> DictStrAny:
+    def _each_iter(self, key: str) -> "DictStrAny":
         err_message = f"Could not find '{key}' in foreach group '{self.name}'"
         with reraise(KeyError, EntryNotFound(err_message)):
             value = self.normalized_iterable[key]

dvc/parsing/context.py

@@ -48,9 +48,7 @@ class MergeError(ContextError):
         self.key = key
         to_node = into[key]
         if not isinstance(to_node, Node) or not isinstance(new, Node):
-            super().__init__(
-                f"cannot merge '{key}' as it already exists in {into}"
-            )
+            super().__init__(f"cannot merge '{key}' as it already exists in {into}")
             return
 
         assert isinstance(to_node, Node)
@@ -138,9 +136,7 @@ class Node:
 @dataclass
 class Value(Node):
     _value: Any
-    meta: Meta = field(
-        compare=False, default_factory=_default_meta, repr=False
-    )
+    meta: Meta = field(compare=False, default_factory=_default_meta, repr=False)
 
     def __repr__(self):
         return repr(self._value)
@@ -182,10 +178,7 @@ class Container(Node, ABC):  # noqa: B024
             assert meta
             container = CtxDict if isinstance(value, dict) else CtxList
             return container(value, meta=meta)
-        msg = (
-            "Unsupported value of type "
-            f"'{type(value).__name__}' in '{meta}'"
-        )
+        msg = f"Unsupported value of type '{type(value).__name__}' in '{meta}'"
         raise TypeError(msg)
 
     def __repr__(self):
@@ -219,16 +212,14 @@ class Container(Node, ABC):  # noqa: B024
         try:
             d = self[index]
         except LookupError as exc:
-            raise ValueError(
-                f"Could not find '{index}' in {self.data}"
-            ) from exc
+            raise ValueError(f"Could not find '{index}' in {self.data}") from exc
 
         if not rems:
             return d
 
         rem = rems[0]
         if not isinstance(d, Container):
-            raise ValueError(
+            raise ValueError(  # noqa: TRY004
                 f"{index} is a primitive value, cannot get '{rem}'"
             )
         return d.select(rem)
@@ -380,9 +371,7 @@ class Context(CtxDict):
                 data = {key: data[key] for key in select_keys}
             except KeyError as exc:
                 key, *_ = exc.args
-                raise ParamsLoadError(
-                    f"could not find '{key}' in '{path}'"
-                ) from exc
+                raise ParamsLoadError(f"could not find '{key}' in '{path}'") from exc
 
         meta = Meta(source=path, local=False)
         ctx = cls(data, meta=meta)
@@ -480,9 +469,7 @@ class Context(CtxDict):
         But for now, just `item` and `key`, this should do.
         """
         # using dict to make the error messages ordered
-        new = dict.fromkeys(
-            [key for key in keys if key not in self._reserved_keys]
-        )
+        new = dict.fromkeys([key for key in keys if key not in self._reserved_keys])
         self._reserved_keys.update(new)
         try:
             yield
@@ -542,9 +529,7 @@ class Context(CtxDict):
         if is_exact_string(src, matches):
             # replace "${enabled}", if `enabled` is a boolean, with it's actual
             # value rather than it's string counterparts.
-            expr = get_expression(
-                matches[0], skip_checks=skip_interpolation_checks
-            )
+            expr = get_expression(matches[0], skip_checks=skip_interpolation_checks)
             value = self.select(expr, unwrap=unwrap)
             validate_value(value, key)
             return value

dvc/parsing/interpolate.py

@@ -99,7 +99,6 @@ def _(obj: dict):  # noqa: C901
 
     result = ""
     for k, v in flatten(obj).items():
-
         if isinstance(v, bool):
             if v:
                 result += f"--{k} "
@@ -115,9 +114,7 @@ def _(obj: dict):  # noqa: C901
                 if isinstance(i, str):
                     i = escape_str(i)
                 elif isinstance(i, Iterable):
-                    raise ParseError(
-                        f"Cannot interpolate nested iterable in '{k}'"
-                    )
+                    raise ParseError(f"Cannot interpolate nested iterable in '{k}'")
 
                 if config.get("list", "nargs") == "append":
                     result += f"--{k} {i} "
@@ -206,9 +203,7 @@ def validate_value(value, key):
     if not_primitive and not_foreach:
         if isinstance(value, dict) and key == "cmd":
             return True
-        raise ParseError(
-            f"Cannot interpolate data of type '{type(value).__name__}'"
-        )
+        raise ParseError(f"Cannot interpolate data of type '{type(value).__name__}'")
 
 
 def str_interpolate(

dvc/parsing/versions.py

@@ -9,9 +9,7 @@ META_KWD = "meta"
 
 def lockfile_version_schema(value):
     expected = [LOCKFILE_VERSION.V2.value]  # pylint: disable=no-member
-    msg = "invalid schema version {}, expected one of {}".format(
-        value, expected
-    )
+    msg = f"invalid schema version {value}, expected one of {expected}"
     return validators.Any(*expected, msg=msg)(value)
 
 

dvc/proc/exceptions.py

@@ -13,9 +13,7 @@ class ProcessNotFoundError(DvcException):
 
 class TimeoutExpired(DvcException):
     def __init__(self, cmd, timeout):
-        super().__init__(
-            f"'{cmd}' did not complete before timeout '{timeout}'"
-        )
+        super().__init__(f"'{cmd}' did not complete before timeout '{timeout}'")
         self.cmd = cmd
         self.timeout = timeout
 

dvc/proc/manager.py

@@ -91,9 +91,7 @@ class ProcessManager:
             raise UnsupportedSignalError(sig)
 
         def handle_closed_process():
-            logging.warning(
-                f"Process {name} had already aborted unexpectedly."
-            )
+            logging.warning("Process %s had already aborted unexpectedly.", name)
             process_info.returncode = -1
             self[name] = process_info
 

dvc/progress.py

@@ -28,9 +28,7 @@ class Tqdm(tqdm):
         "{postfix[info]}{n_fmt}/{total_fmt}"
         " [{elapsed}<{remaining}, {rate_fmt:>11}]"
     )
-    BAR_FMT_NOTOTAL = (
-        "{desc}{bar:b}|{postfix[info]}{n_fmt} [{elapsed}, {rate_fmt:>11}]"
-    )
+    BAR_FMT_NOTOTAL = "{desc}{bar:b}|{postfix[info]}{n_fmt} [{elapsed}, {rate_fmt:>11}]"
     BYTES_DEFAULTS = {
         "unit": "B",
         "unit_scale": True,
@@ -75,11 +73,7 @@ class Tqdm(tqdm):
         if not disable:
             disable = logger.getEffectiveLevel() > level
         # auto-disable based on TTY
-        if (
-            not disable
-            and not env2bool(DVC_IGNORE_ISATTY)
-            and hasattr(file, "isatty")
-        ):
+        if not disable and not env2bool(DVC_IGNORE_ISATTY) and hasattr(file, "isatty"):
             disable = not file.isatty()
         super().__init__(
             iterable=iterable,
@@ -95,9 +89,7 @@ class Tqdm(tqdm):
         if bar_format is None:
             if self.__len__():
                 self.bar_format = (
-                    self.BAR_FMT_DEFAULT_NESTED
-                    if self.pos
-                    else self.BAR_FMT_DEFAULT
+                    self.BAR_FMT_DEFAULT_NESTED if self.pos else self.BAR_FMT_DEFAULT
                 )
             else:
                 self.bar_format = self.BAR_FMT_NOTOTAL

dvc/prompt.py

@@ -24,10 +24,7 @@ def ask(prompt: str, limited_to: Optional[Collection[str]] = None):
         if answer in limited_to:
             return answer
 
-        logger.info(
-            "Your response must be one of: {options}. "
-            "Please try again.".format(options=limited_to)
-        )
+        logger.info("Your response must be one of: %s. Please try again.", limited_to)
 
 
 def confirm(statement: str) -> bool:

dvc/render/convert.py

@@ -2,13 +2,7 @@ import json
 from collections import defaultdict
 from typing import Dict, List, Union
 
-from dvc.render import (
-    REVISION_FIELD,
-    REVISIONS_KEY,
-    SRC_FIELD,
-    TYPE_KEY,
-    VERSION_FIELD,
-)
+from dvc.render import REVISION_FIELD, REVISIONS_KEY, SRC_FIELD, TYPE_KEY, VERSION_FIELD
 from dvc.render.converter.image import ImageConverter
 from dvc.render.converter.vega import VegaConverter
 
@@ -35,10 +29,8 @@ def _group_by_rev(datapoints):
 
 
 def to_json(renderer, split: bool = False) -> List[Dict]:
-    from copy import deepcopy
-
     if renderer.TYPE == "vega":
-        grouped = _group_by_rev(deepcopy(renderer.datapoints))
+        grouped = _group_by_rev(renderer.datapoints)
         if split:
             content = renderer.get_filled_template(skip_anchors=["data"])
         else:

dvc/render/converter/vega.py

@@ -1,4 +1,3 @@
-from copy import deepcopy
 from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
 
 from funcy import first, last
@@ -81,9 +80,9 @@ def _is_datapoints(lst: List[Dict]):
     to unexpected behavior
     """
 
-    return all(isinstance(item, dict) for item in lst) and set(
-        first(lst).keys()
-    ) == {key for keys in lst for key in keys}
+    return all(isinstance(item, dict) for item in lst) and set(first(lst).keys()) == {
+        key for keys in lst for key in keys
+    }
 
 
 def get_datapoints(file_content: Dict):
@@ -195,7 +194,6 @@ class VegaConverter(Converter):
         return "x"
 
     def flat_datapoints(self, revision):  # noqa: C901
-
         file2datapoints, properties = self.convert()
 
         props_update = {}
@@ -218,7 +216,7 @@ class VegaConverter(Converter):
         num_ys = len(ys)
         if num_xs > 1 and num_xs != num_ys:
             raise DvcException(
-                f"Cannot have different number of x and y data sources. Found "
+                "Cannot have different number of x and y data sources. Found "
                 f"{num_xs} x and {num_ys} y data sources."
             )
 
@@ -234,7 +232,7 @@ class VegaConverter(Converter):
         for i, (y_file, y_field) in enumerate(ys):
             if num_xs > 1:
                 x_file, x_field = xs[i]
-            datapoints = deepcopy(file2datapoints.get(y_file, []))
+            datapoints = [d.copy() for d in file2datapoints.get(y_file, [])]
 
             if props_update.get("y", None) == "dvc_inferred_y_value":
                 _update_from_field(
@@ -316,9 +314,7 @@ def _update_from_field(
         source_field = field
 
     if len(source_datapoints) != len(target_datapoints):
-        raise IndexError(
-            "Source and target datapoints must have the same length"
-        )
+        raise IndexError("Source and target datapoints must have the same length")
 
     for index, datapoint in enumerate(target_datapoints):
         source_datapoint = source_datapoints[index]
@@ -332,6 +328,5 @@ def _update_from_index(datapoints: List[Dict], new_field: str):
 
 
 def _update_all(datapoints: List[Dict], update_dict: Dict):
-
     for datapoint in datapoints:
         datapoint.update(update_dict)

dvc/render/match.py

@@ -62,7 +62,6 @@ def match_defs_renderers(
     out=None,
     templates_dir: Optional["StrPath"] = None,
 ):
-
     from dvc_render import ImageRenderer, VegaRenderer
 
     plots_data = PlotsData(data)
@@ -80,9 +79,7 @@ def match_defs_renderers(
 
         for rev, inner_id, plot_definition in group:
             plot_sources = infer_data_sources(inner_id, plot_definition)
-            definitions_data = plots_data.get_definition_data(
-                plot_sources, rev
-            )
+            definitions_data = plots_data.get_definition_data(plot_sources, rev)
 
             if ImageRenderer.matches(inner_id, None):
                 renderer_cls = ImageRenderer
@@ -91,9 +88,7 @@ def match_defs_renderers(
                 renderer_cls = VegaRenderer
                 renderer_id = plot_id
 
-            converter = _get_converter(
-                renderer_cls, inner_id, props, definitions_data
-            )
+            converter = _get_converter(renderer_cls, inner_id, props, definitions_data)
 
             dps, rev_props = converter.flat_datapoints(rev)
             if not final_props and rev_props:
@@ -103,7 +98,5 @@ def match_defs_renderers(
         if "title" not in final_props:
             final_props["title"] = renderer_id
         if renderer_cls is not None:
-            renderers.append(
-                renderer_cls(plot_datapoints, renderer_id, **final_props)
-            )
+            renderers.append(renderer_cls(plot_datapoints, renderer_id, **final_props))
     return renderers

dvc/repo/__init__.py

@@ -3,16 +3,7 @@ import os
 from collections import defaultdict
 from contextlib import contextmanager
 from functools import wraps
-from typing import (
-    TYPE_CHECKING,
-    Callable,
-    Iterable,
-    List,
-    Optional,
-    Tuple,
-    Union,
-    cast,
-)
+from typing import TYPE_CHECKING, Callable, Iterable, List, Optional, Tuple, Union, cast
 
 from dvc.exceptions import FileMissingError
 from dvc.exceptions import IsADirectoryError as DvcIsADirectoryError
@@ -28,10 +19,11 @@ if TYPE_CHECKING:
     from dvc.fs.dvc import DVCFileSystem
     from dvc.lock import LockBase
     from dvc.machine import MachineManager
-    from dvc.scm import Base, Git, NoSCM
+    from dvc.scm import Git, NoSCM
     from dvc.stage import Stage
     from dvc.types import DictStrAny
     from dvc_data.hashfile.state import StateBase
+    from dvc_data.index import DataIndex
 
     from .experiments import Experiments
     from .index import Index
@@ -148,9 +140,7 @@ class Repo:
 
         import hashlib
 
-        root_dir_hash = hashlib.sha224(
-            self.root_dir.encode("utf-8")
-        ).hexdigest()
+        root_dir_hash = hashlib.sha224(self.root_dir.encode("utf-8")).hexdigest()
 
         db_dir = self.fs.path.join(
             base_db_dir,
@@ -171,13 +161,13 @@ class Repo:
         config: Optional["DictStrAny"] = None,
         url: Optional[str] = None,
         repo_factory: Optional[Callable] = None,
-        scm: Optional["Base"] = None,
+        scm: Optional[Union["Git", "NoSCM"]] = None,
     ):
+        from dvc.cachemgr import CacheManager
         from dvc.config import Config
         from dvc.data_cloud import DataCloud
         from dvc.fs import GitFileSystem, LocalFileSystem, localfs
         from dvc.lock import LockNoop, make_lock
-        from dvc.odbmgr import ODBManager
         from dvc.repo.metrics import Metrics
         from dvc.repo.params import Params
         from dvc.repo.plots import Plots
@@ -190,6 +180,7 @@ class Repo:
         self._fs_conf = {"repo_factory": repo_factory}
         self._fs = fs or localfs
         self._scm = scm
+        self._data_index = None
 
         if rev and not fs:
             self._scm = scm = SCM(root_dir or os.curdir)
@@ -212,16 +203,16 @@ class Repo:
         # used by DVCFileSystem to determine if it should traverse subrepos
         self.subrepos = subrepos
 
-        self.cloud = DataCloud(self)
+        self.cloud: "DataCloud" = DataCloud(self)
         self.stage: "StageLoad" = StageLoad(self)
 
         self.lock: "LockBase"
-        self.odb: ODBManager
+        self.cache: CacheManager
         self.state: "StateBase"
         if isinstance(self.fs, GitFileSystem) or not self.dvc_dir:
             self.lock = LockNoop()
             self.state = StateNoop()
-            self.odb = ODBManager(self)
+            self.cache = CacheManager(self)
             self.tmp_dir = None
         else:
             self.fs.makedirs(cast(str, self.tmp_dir), exist_ok=True)
@@ -230,9 +221,7 @@ class Repo:
                 self.lock = make_lock(
                     self.fs.path.join(self.tmp_dir, "lock"),
                     tmp_dir=self.tmp_dir,
-                    hardlink_lock=self.config["core"].get(
-                        "hardlink_lock", False
-                    ),
+                    hardlink_lock=self.config["core"].get("hardlink_lock", False),
                     friendly=True,
                 )
                 state_db_dir = self._get_database_dir("state")
@@ -241,7 +230,7 @@ class Repo:
                 self.lock = LockNoop()
                 self.state = StateNoop()
 
-            self.odb = ODBManager(self)
+            self.cache = CacheManager(self)
 
             self.stage_cache = StageCache(self)
 
@@ -275,7 +264,7 @@ class Repo:
             new.check_graph()
 
     @staticmethod
-    def open(url, *args, **kwargs):
+    def open(url, *args, **kwargs):  # noqa: A003
         if url is None:
             url = os.getcwd()
 
@@ -338,8 +327,7 @@ class Repo:
         from dvc.machine import MachineManager
 
         if self.tmp_dir and (
-            self.config["feature"].get("machine", False)
-            or env2bool("DVC_TEST")
+            self.config["feature"].get("machine", False) or env2bool("DVC_TEST")
         ):
             return MachineManager(self)
         return None
@@ -355,6 +343,31 @@ class Repo:
         # fs.
         self._reset()
 
+    @property
+    def data_index(self) -> Optional["DataIndex"]:
+        from appdirs import user_cache_dir
+        from fsspec.utils import tokenize
+
+        from dvc_data.index import DataIndex
+
+        if not self.config["feature"].get("data_index_cache"):
+            return None
+
+        if self._data_index is None:
+            cache_dir = user_cache_dir(self.config.APPNAME, self.config.APPAUTHOR)
+            index_dir = os.path.join(
+                cache_dir,
+                "index",
+                "data",
+                # scm.root_dir and repo.root_dir don't match for subrepos
+                tokenize((self.scm.root_dir, self.root_dir)),
+            )
+            os.makedirs(index_dir, exist_ok=True)
+
+            self._data_index = DataIndex.open(os.path.join(index_dir, "db.db"))
+
+        return self._data_index
+
     def __repr__(self):
         return f"{self.__class__.__name__}: '{self.root_dir}'"
 
@@ -393,24 +406,20 @@ class Repo:
         return os.path.join(root_dir, cls.DVC_DIR)
 
     @staticmethod
-    def init(
-        root_dir=os.curdir, no_scm=False, force=False, subdir=False
-    ) -> "Repo":
+    def init(root_dir=os.curdir, no_scm=False, force=False, subdir=False) -> "Repo":
         from dvc.repo.init import init
 
-        return init(
-            root_dir=root_dir, no_scm=no_scm, force=force, subdir=subdir
-        )
+        return init(root_dir=root_dir, no_scm=no_scm, force=force, subdir=subdir)
 
     def unprotect(self, target):
-        return self.odb.repo.unprotect(target)
+        return self.cache.repo.unprotect(target)
 
     def _ignore(self):
         flist = [self.config.files["local"]]
         if tmp_dir := self.tmp_dir:
             flist.append(tmp_dir)
-        if path_isin(self.odb.repo.path, self.root_dir):
-            flist.append(self.odb.repo.path)
+        if path_isin(self.cache.repo.path, self.root_dir):
+            flist.append(self.cache.repo.path)
 
         for file in flist:
             self.scm_context.ignore(file)
@@ -530,9 +539,7 @@ class Repo:
     def dvcfs(self) -> "DVCFileSystem":
         from dvc.fs.dvc import DVCFileSystem
 
-        return DVCFileSystem(
-            repo=self, subrepos=self.subrepos, **self._fs_conf
-        )
+        return DVCFileSystem(repo=self, subrepos=self.subrepos, **self._fs_conf)
 
     @cached_property
     def index_db_dir(self):
@@ -573,18 +580,17 @@ class Repo:
     def close(self):
         self.scm.close()
         self.state.close()
+        if self._data_index is not None:
+            self._data_index.close()
 
-    def _reset_cached_indecies(self):
+    def _reset(self):
+        self.scm._reset()  # pylint: disable=protected-access
+        self.state.close()
         self.__dict__.pop("index", None)
         self.__dict__.pop("dvcignore", None)
         self.__dict__.pop("dvcfs", None)
         self.__dict__.pop("datafs", None)
 
-    def _reset(self):
-        self.state.close()
-        self.scm._reset()  # pylint: disable=protected-access
-        self._reset_cached_indecies()
-
     def __enter__(self):
         return self
 

dvc/repo/add.py

@@ -15,12 +15,7 @@ from dvc.exceptions import (
 )
 from dvc.repo.scm_context import scm_context
 from dvc.ui import ui
-from dvc.utils import (
-    LARGE_DIR_SIZE,
-    glob_targets,
-    resolve_output,
-    resolve_paths,
-)
+from dvc.utils import LARGE_DIR_SIZE, glob_targets, resolve_output, resolve_paths
 from dvc.utils.collections import ensure_list, validate
 
 from . import locked
@@ -108,9 +103,7 @@ def translate_graph_error(stages: Stages) -> Iterator[None]:
 def progress_iter(stages: Stages) -> Iterator["Stage"]:
     total = len(stages)
     desc = "Adding..."
-    with ui.progress(
-        stages, total=total, desc=desc, unit="file", leave=True
-    ) as pbar:
+    with ui.progress(stages, total=total, desc=desc, unit="file", leave=True) as pbar:
         if total == 1:
             pbar.bar_format = desc
             pbar.refresh()
@@ -194,7 +187,7 @@ def add(  # noqa: C901
                 stage.transfer(source, to_remote=to_remote, odb=odb, **kwargs)
             else:
                 try:
-                    stage.save(merge_versioned=True)
+                    stage.save()
                     if not no_commit:
                         stage.commit()
                 except CacheLinkError:

dvc/repo/brancher.py

@@ -1,7 +1,10 @@
+import logging
 from typing import Optional
 
 from dvc.scm import iter_revs
 
+logger = logging.getLogger(__name__)
+
 
 def brancher(  # noqa: E302
     self,
@@ -32,7 +35,16 @@ def brancher(  # noqa: E302
             - empty string it there is no branches to iterate over
             - "workspace" if there are uncommitted changes in the SCM repo
     """
-    if not any([revs, all_branches, all_tags, all_commits, all_experiments]):
+    if not any(
+        [
+            revs,
+            all_branches,
+            all_tags,
+            all_commits,
+            all_experiments,
+            commit_date,
+        ]
+    ):
         yield ""
         return
 
@@ -40,21 +52,18 @@ def brancher(  # noqa: E302
 
     repo_root_parts = ()
     if self.fs.path.isin(self.root_dir, self.scm.root_dir):
-        repo_root_parts = self.fs.path.relparts(
-            self.root_dir, self.scm.root_dir
-        )
+        repo_root_parts = self.fs.path.relparts(self.root_dir, self.scm.root_dir)
 
     cwd_parts = ()
     if self.fs.path.isin(self.fs.path.getcwd(), self.scm.root_dir):
-        cwd_parts = self.fs.path.relparts(
-            self.fs.path.getcwd(), self.scm.root_dir
-        )
+        cwd_parts = self.fs.path.relparts(self.fs.path.getcwd(), self.scm.root_dir)
 
     saved_fs = self.fs
     saved_root = self.root_dir
 
     scm = self.scm
 
+    logger.trace("switching fs to workspace")  # type: ignore[attr-defined]
     self.fs = LocalFileSystem(url=self.root_dir)
     yield "workspace"
 
@@ -77,14 +86,14 @@ def brancher(  # noqa: E302
         from dvc.fs import GitFileSystem
 
         for sha, names in found_revs.items():
-            self._reset_cached_indecies()  # pylint: disable=W0212
+            logger.trace(  # type: ignore[attr-defined]
+                "switching fs to revision %s [%s]", sha[:7], ", ".join(names)
+            )
             self.fs = GitFileSystem(scm=scm, rev=sha)
             self.root_dir = self.fs.path.join("/", *repo_root_parts)
 
             if cwd_parts:
-                cwd = self.fs.path.join(  # type: ignore[unreachable]
-                    "/", *cwd_parts
-                )
+                cwd = self.fs.path.join("/", *cwd_parts)  # type: ignore[unreachable]
                 self.fs.path.chdir(cwd)
 
             # ignore revs that don't contain repo root

dvc/repo/checkout.py

@@ -2,11 +2,7 @@ import logging
 import os
 from typing import TYPE_CHECKING, Dict, List, Set
 
-from dvc.exceptions import (
-    CheckoutError,
-    CheckoutErrorSuggestGit,
-    NoOutputOrStageError,
-)
+from dvc.exceptions import CheckoutError, CheckoutErrorSuggestGit, NoOutputOrStageError
 from dvc.utils import relpath
 
 from . import locked
@@ -35,18 +31,13 @@ def _remove_unused_links(repo):
 
 
 def get_all_files_numbers(pairs):
-    return sum(
-        stage.get_all_files_number(filter_info) for stage, filter_info in pairs
-    )
+    return sum(stage.get_all_files_number(filter_info) for stage, filter_info in pairs)
 
 
 def _collect_pairs(
     self: "Repo", targets, with_deps: bool, recursive: bool
 ) -> Set["StageInfo"]:
-    from dvc.stage.exceptions import (
-        StageFileBadNameError,
-        StageFileDoesNotExistError,
-    )
+    from dvc.stage.exceptions import StageFileBadNameError, StageFileDoesNotExistError
 
     pairs: Set["StageInfo"] = set()
     for target in targets: