show hydra dumped results in debug mode (#9460)

* show hydra dumped results in debug mode

* update hydra composition trace msg

.flake8

@@ -11,7 +11,7 @@ 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,TYP
 show_source = true

.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/ISSUE_TEMPLATE/epic_story.md

@@ -0,0 +1,60 @@
+---
+name: Epic/Story Issue Template
+about: Template for "top" level issues - Epics (>2 weeks) / Stories (<2 weeks)
+title: 'Epic: New Feature'
+labels: epic
+assignees:
+
+---
+
+## Summary / Background
+What do you want to achieve, why? business context
+...
+
+## Scope
+
+What will be impacted and what won't be?
+What needs implementation and what is invariant?
+e.g.
+- user should be able to run workflow X from UI
+- enable workflow Y, Z from CLI
+
+## Assumptions
+Product / UX assumptions as well as technical assumptions / limitations
+e.g.
+* Support only Python Runtime
+* Focus on DVC experiments only
+* Deployment environments don't change often and can be picked up from shared configuration
+
+## Open Questions
+e.g.
+- How should access control work for shared artifacts (workflow X)
+- Python runtime assumption - is it really valid? in light of <...>
+
+## Blockers / Dependencies
+List issues or other conditions / blockers
+
+## General Approach
+Invocation example:
+```shell
+$ mapper-run task.tar.gz --ray-cluster <ip>:<port>
+```
+
+## Steps
+
+### Must have (p1)
+- [ ] subissue2
+- [ ] step 2
+ - info
+ - info
+
+### Optional / followup (p2)
+- [ ] ⌛ step 3 wip
+- [ ] step 4
+
+## Timelines
+
+Put your estimations here. Update once certainty changes
+- end of week (Feb 3) for prototype with workflows X, Y
+- Feb 15 - MVP in production
+- Low priority followups can be done later

.github/mergify.yml

@@ -0,0 +1,9 @@
+pull_request_rules:
+  - name: backport patches to 2.x
+    conditions:
+      - base=main
+      - label=backport
+    actions:
+      backport:
+        branches:
+          - "2.x"

.github/workflows/codeql.yml

@@ -2,7 +2,7 @@ name: "CodeQL"
 
 on:
   push:
-    branches: ["main"]
+    branches: ["main", "2.x"]
   pull_request:
     branches: ["main"]
   schedule:

.github/workflows/packages.yaml

@@ -17,9 +17,9 @@ jobs:
     strategy:
       matrix:
         include:
-         - {pkg: "deb",  os: "ubuntu-18.04", asset: "dvc_${{ github.event.release.tag_name }}_amd64.deb"}
-         - {pkg: "rpm", os: "ubuntu-18.04", asset: "dvc-${{ github.event.release.tag_name }}-1.x86_64.rpm"}
-         - {pkg: "osxpkg", os: "macos-10.15", asset: "dvc-${{ github.event.release.tag_name }}.pkg"}
+         - {pkg: "deb",  os: "ubuntu-20.04", asset: "dvc_${{ github.event.release.tag_name }}_amd64.deb"}
+         - {pkg: "rpm", os: "ubuntu-20.04", asset: "dvc-${{ github.event.release.tag_name }}-1.x86_64.rpm"}
+         - {pkg: "osxpkg", os: "macos-11", asset: "dvc-${{ github.event.release.tag_name }}.pkg"}
          - {pkg: "exe",  os: "windows-2019", asset: "dvc-${{ github.event.release.tag_name }}.exe"}
 
     name: ${{ matrix.pkg }}
@@ -73,6 +73,8 @@ jobs:
 
   pip:
     runs-on: ubuntu-20.04
+    permissions:
+      id-token: write
     steps:
     - uses: actions/checkout@v3
       with:
@@ -100,13 +102,10 @@ jobs:
     - name: Publish packages to PyPI
       if: github.event_name == 'release'
       uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        password: ${{ secrets.PYPI_TOKEN }}
 
     - name: Publish to Test PyPI
       if: ${{ github.event_name == 'release' || (github.event_name == 'push' && github.ref == 'refs/heads/main') }}
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
-        password: ${{ secrets.TEST_PYPI_TOKEN }}
         repository_url: https://test.pypi.org/legacy/
         skip_existing: true

.github/workflows/tests.yaml

@@ -2,7 +2,7 @@ name: Tests
 
 on:
   push:
-    branches: [main]
+    branches: [main, 2.x]
   pull_request:
   schedule:
     - cron: '5 1 * * *'  # every day at 01:05
@@ -17,7 +17,7 @@ permissions:
 
 jobs:
   tests:
-    timeout-minutes: 45
+    timeout-minutes: 50
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
@@ -41,9 +41,11 @@ jobs:
         pip install -e ".[dev]"
     - uses: pre-commit/[email protected]
     - name: run tests
-      timeout-minutes: 30
+      timeout-minutes: 40
+      env:
+        PYTHONUTF8: 1
       run: >
-        pytest -nauto --timeout=300 --durations=100
+        pytest -n=logical --timeout=300 --durations=100
         --cov --cov-report=xml --cov-report=term
     - name: upload coverage report
       uses: codecov/codecov-action@v3

.pre-commit-config.yaml

@@ -35,7 +35,7 @@ repos:
         args:
           - --py38-plus
   - repo: https://github.com/psf/black
-    rev: 22.12.0
+    rev: 23.3.0
     hooks:
       - id: black
   - repo: https://github.com/PyCQA/isort
@@ -43,11 +43,11 @@ repos:
     hooks:
       - id: isort
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.238'
+    rev: 'v0.0.261'
     hooks:
       - id: ruff
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.2
+    rev: v2.2.4
     hooks:
       - id: codespell
         additional_dependencies: ["tomli"]
@@ -61,6 +61,13 @@ repos:
           - flake8-debugger
           - flake8-string-format
           - flake8-typing-imports
+  - repo: https://github.com/PyCQA/bandit
+    rev: '1.7.5'
+    hooks:
+    - id: bandit
+      args: ["-c", "pyproject.toml", "--quiet", "--format=custom"]
+      files: ^dvc/
+      additional_dependencies: [".[toml]"]
   - repo: local
     hooks:
     - id: mypy

dvc/_debug.py

@@ -16,9 +16,7 @@ def viztracer_profile(
     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
 
@@ -80,9 +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
 
@@ -194,9 +190,7 @@ def debugtools(args: Optional["Namespace"] = None, **kwargs):
             path_func = _get_path_func("viztracer", "json")
             depth = kw.get("viztracer_depth") or -1
             log_async = kw.get("viztracer_async") or False
-            prof = viztracer_profile(
-                path=path_func, depth=depth, log_async=log_async
-            )
+            prof = viztracer_profile(path=path_func, depth=depth, log_async=log_async)
             stack.enter_context(prof)
         yield
 
@@ -204,12 +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",
@@ -224,9 +214,7 @@ def add_debugging_flags(parser):
         "--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("--pdb", action="store_true", default=False, help=SUPPRESS)
     parser.add_argument(
         "--instrument", action="store_true", default=False, help=SUPPRESS
     )

dvc/analytics.py

@@ -47,7 +47,7 @@ def is_enabled():
     enabled = not os.getenv(DVC_NO_ANALYTICS)
     if enabled:
         enabled = to_bool(
-            Config(validate=False).get("core", {}).get("analytics", "true")
+            Config.from_cwd(validate=False).get("core", {}).get("analytics", "true")
         )
 
     logger.debug("Analytics is %sabled.", "en" if enabled else "dis")

dvc/annotations.py

@@ -2,6 +2,7 @@ from dataclasses import asdict, dataclass, field, fields
 from typing import Any, ClassVar, Dict, List, Optional
 
 from funcy import compact
+from voluptuous import Required
 
 
 @dataclass
@@ -26,6 +27,24 @@ class Annotation:
         return compact(asdict(self))
 
 
+@dataclass
+class Artifact:
+    PARAM_PATH: ClassVar[str] = "path"
+    PARAM_DESC: ClassVar[str] = "desc"
+    PARAM_TYPE: ClassVar[str] = "type"
+    PARAM_LABELS: ClassVar[str] = "labels"
+    PARAM_META: ClassVar[str] = "meta"
+
+    path: str
+    desc: Optional[str] = None
+    type: Optional[str] = None  # noqa: A003
+    labels: List[str] = field(default_factory=list)
+    meta: Dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> Dict[str, str]:
+        return compact(asdict(self))
+
+
 ANNOTATION_FIELDS = [field.name for field in fields(Annotation)]
 ANNOTATION_SCHEMA = {
     Annotation.PARAM_DESC: str,
@@ -33,3 +52,7 @@ ANNOTATION_SCHEMA = {
     Annotation.PARAM_LABELS: [str],
     Annotation.PARAM_META: object,
 }
+ARTIFACT_SCHEMA = {
+    Required(Artifact.PARAM_PATH): str,
+    **ANNOTATION_SCHEMA,  # type: ignore[arg-type]
+}

dvc/api/__init__.py

@@ -2,14 +2,21 @@ from dvc.fs.dvc import _DVCFileSystem as DVCFileSystem
 
 from .data import open  # pylint: disable=redefined-builtin
 from .data import get_url, read
-from .experiments import make_checkpoint
-from .params import params_show
+from .experiments import exp_save, exp_show, make_checkpoint
+from .scm import all_branches, all_commits, all_tags
+from .show import metrics_show, params_show
 
 __all__ = [
+    "all_branches",
+    "all_commits",
+    "all_tags",
+    "exp_save",
+    "exp_show",
     "get_url",
     "make_checkpoint",
     "open",
     "params_show",
+    "metrics_show",
     "read",
     "DVCFileSystem",
 ]

dvc/api/data.py

@@ -1,12 +1,30 @@
 from contextlib import _GeneratorContextManager as GCM
-from typing import Optional
+from contextlib import contextmanager
+from typing import Any, Dict, Optional
 
 from funcy import reraise
 
-from dvc.exceptions import OutputNotFoundError, PathMissingError
+from dvc.exceptions import FileMissingError, OutputNotFoundError, PathMissingError
 from dvc.repo import Repo
 
 
+@contextmanager
+def _wrap_exceptions(repo, url):
+    from dvc.config import NoRemoteError
+    from dvc.exceptions import NoOutputInExternalRepoError, NoRemoteInExternalRepoError
+
+    try:
+        yield
+    except NoRemoteError as exc:
+        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
+    except FileMissingError as exc:
+        raise PathMissingError(exc.path, url) from exc
+
+
 def get_url(path, repo=None, rev=None, remote=None):
     """
     Returns the URL to the storage location of a data file or directory tracked
@@ -19,24 +37,24 @@ def get_url(path, repo=None, rev=None, remote=None):
     directory in the remote storage.
     """
     with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
-        fs_path = _repo.dvcfs.from_os_path(path)
-        with reraise(FileNotFoundError, PathMissingError(path, repo)):
-            info = _repo.dvcfs.info(fs_path)
+        with _wrap_exceptions(_repo, path):
+            fs_path = _repo.dvcfs.from_os_path(path)
 
-        dvc_info = info.get("dvc_info")
-        if not dvc_info:
-            raise OutputNotFoundError(path, repo)
+            with reraise(FileNotFoundError, PathMissingError(path, repo)):
+                info = _repo.dvcfs.info(fs_path)
 
-        dvc_repo = info["repo"]  # pylint: disable=unsubscriptable-object
-        md5 = dvc_info["md5"]
+            dvc_info = info.get("dvc_info")
+            if not dvc_info:
+                raise OutputNotFoundError(path, repo)
 
-        return dvc_repo.cloud.get_url_for(remote, checksum=md5)
+            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 +63,7 @@ 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
@@ -198,11 +214,41 @@ def open(  # noqa, pylint: disable=redefined-builtin
 
 
 def _open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
-        with _repo.open_by_relpath(
-            path, remote=remote, mode=mode, encoding=encoding
-        ) as fd:
-            yield fd
+    repo_kwargs: Dict[str, Any] = {"subrepos": True, "uninitialized": True}
+    if remote:
+        repo_kwargs["config"] = {"core": {"remote": remote}}
+
+    with Repo.open(repo, rev=rev, **repo_kwargs) as _repo:
+        with _wrap_exceptions(_repo, path):
+            import os
+            from typing import TYPE_CHECKING, Union
+
+            from dvc.exceptions import IsADirectoryError as DvcIsADirectoryError
+            from dvc.fs.data import DataFileSystem
+            from dvc.fs.dvc import DVCFileSystem
+
+            if TYPE_CHECKING:
+                from dvc.fs import FileSystem
+
+            fs: Union["FileSystem", DataFileSystem, DVCFileSystem]
+            if os.path.isabs(path):
+                fs = DataFileSystem(index=_repo.index.data["local"])
+                fs_path = path
+            else:
+                fs = DVCFileSystem(repo=_repo, subrepos=True)
+                fs_path = fs.from_os_path(path)
+
+            try:
+                with fs.open(
+                    fs_path,
+                    mode=mode,
+                    encoding=encoding,
+                ) as fobj:
+                    yield fobj
+            except FileNotFoundError as exc:
+                raise FileMissingError(path) from exc
+            except IsADirectoryError as exc:
+                raise DvcIsADirectoryError(f"'{path}' is a directory") from exc
 
 
 def read(path, repo=None, rev=None, remote=None, mode="r", encoding=None):

dvc/api/experiments.py

@@ -1,9 +1,13 @@
 import builtins
 import os
 from time import sleep
+from typing import Dict, List, Optional, Union
+
+from rich.text import Text
 
 from dvc.env import DVC_CHECKPOINT, DVC_ROOT
 from dvc.repo import Repo
+from dvc.repo.experiments.show import tabulate
 from dvc.stage.monitor import CheckpointTask
 
 
@@ -31,3 +35,114 @@ def make_checkpoint():
         os.fsync(fobj.fileno())
     while os.path.exists(signal_file):
         sleep(0.1)
+
+
+def exp_save(
+    name: Optional[str] = None,
+    force: bool = False,
+    include_untracked: Optional[List[str]] = None,
+):
+    """
+    Create a new DVC experiment using `exp save`.
+
+    See https://dvc.org/doc/command-reference/exp/save.
+
+    Args:
+        name (str, optional): specify a name for this experiment.
+            If `None`, a default one will be generated, such as `urban-sign`.
+            Defaults to `None`.
+        force (bool):  overwrite the experiment if an experiment with the same
+            name already exists.
+            Defaults to `False`.
+        include_untracked (List[str], optional): specify untracked file(s) to
+            be included in the saved experiment.
+            Defaults to `None`.
+
+    Returns:
+        str: The `Git revision`_ of the created experiment.
+
+    Raises:
+        ExperimentExistsError: If an experiment with `name` already exists and
+            `force=False`.
+
+    .. _Git revision:
+        https://git-scm.com/docs/revisions
+    """
+    with Repo() as repo:
+        return repo.experiments.save(
+            name=name, force=force, include_untracked=include_untracked
+        )
+
+
+def _postprocess(exp_rows):
+    for exp_row in exp_rows:
+        for k, v in exp_row.items():
+            if isinstance(v, Text):
+                v_str = str(v)
+                try:
+                    exp_row[k] = float(v_str)
+                except ValueError:
+                    exp_row[k] = v_str
+
+            if not exp_row[k]:
+                exp_row[k] = None
+
+    return exp_rows
+
+
+def exp_show(
+    repo: Optional[str] = None,
+    revs: Optional[Union[str, List[str]]] = None,
+    num: int = 1,
+    param_deps: bool = False,
+    force: bool = False,
+) -> List[Dict]:
+    """Get DVC experiments tracked in `repo`.
+
+    Without arguments, this function will retrieve all experiments derived from
+    the Git `HEAD`.
+
+    See the options below to customize the experiments retrieved.
+
+    Args:
+        repo (str, optional): location of the DVC repository.
+            Defaults to the current project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+        revs (Union[str, List[str]], optional): Git revision(s) (e.g. branch,
+            tag, SHA commit) to use as a reference point to start listing
+            experiments.
+            Defaults to `None`, which will use `HEAD` as starting point.
+        num (int, optional): show experiments from the last `num` commits
+            (first parents) starting from the `revs` baseline.
+            Give a negative value to include all first-parent commits (similar
+            to `git log -n`).
+            Defaults to 1.
+        param_deps (bool, optional): include only parameters that are stage
+            dependencies.
+            Defaults to `False`.
+        force (bool, optional): force re-collection of experiments instead of
+            loading from internal experiments cache.
+            DVC caches `exp_show` data for completed experiments to improve
+            performance of subsequent calls.
+            When `force` is specified, DVC will reload all experiment data and
+            ignore any previously cached results.
+            Defaults to `False`.
+
+    Returns:
+        List[Dict]: Each item in the list will contain a dictionary with
+            the info for an individual experiment.
+            See Examples below.
+    """
+    with Repo.open(repo) as _repo:
+        experiments = _repo.experiments.show(
+            revs=revs,
+            num=num,
+            param_deps=param_deps,
+            force=force,
+        )
+        td, _ = tabulate(experiments, fill_value=None)
+
+        return _postprocess(td.as_dict())

dvc/api/scm.py

@@ -0,0 +1,54 @@
+from typing import List, Optional
+
+from dvc.repo import Repo
+
+
+def all_branches(repo: Optional[str] = None) -> List[str]:
+    """Get all Git branches in a DVC repository.
+
+    Args:
+        repo (str, optional): location of the DVC repository.
+            Defaults to the current project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+    Returns:
+        List[str]: Names of the Git branches.
+    """
+    with Repo.open(repo) as _repo:
+        return _repo.scm.list_branches()
+
+
+def all_commits(repo: Optional[str] = None) -> List[str]:
+    """Get all Git commits in a DVC repository.
+
+    Args:
+        repo (str, optional): location of the DVC repository.
+            Defaults to the current project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+    Returns:
+        List[str]: SHAs of the Git commits.
+    """
+    with Repo.open(repo) as _repo:
+        return _repo.scm.list_all_commits()
+
+
+def all_tags(repo: Optional[str] = None) -> List[str]:
+    """Get all Git tags in a DVC repository.
+
+    Args:
+        repo (str, optional): location of the DVC repository.
+            Defaults to the current project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+    Returns:
+        List[str]: Names of the Git tags.
+    """
+    with Repo.open(repo) as _repo:
+        return _repo.scm.list_tags()

dvc/api/show.py

@@ -4,10 +4,153 @@ from typing import Dict, Iterable, Optional, Union
 
 from funcy import first
 
-from dvc.exceptions import DvcException
 from dvc.repo import Repo
 
 
+def _onerror_raise(exception: Exception, *args, **kwargs):
+    raise exception
+
+
+def _postprocess(results):
+    processed: Dict[str, Dict] = {}
+    for rev, rev_data in results.items():
+        if not rev_data:
+            continue
+
+        processed[rev] = {}
+
+        counts: typing.Counter[str] = Counter()
+        for file_data in rev_data["data"].values():
+            for k in file_data["data"]:
+                counts[k] += 1
+
+        for file_name, file_data in rev_data["data"].items():
+            to_merge = {
+                (k if counts[k] == 1 else f"{file_name}:{k}"): v
+                for k, v in file_data["data"].items()
+            }
+            processed[rev] = {**processed[rev], **to_merge}
+
+    if "workspace" in processed:
+        del processed["workspace"]
+
+    return processed
+
+
+def metrics_show(
+    *targets: str,
+    repo: Optional[str] = None,
+    rev: Optional[str] = None,
+) -> Dict:
+    """Get metrics tracked in `repo`.
+
+    Without arguments, this function will retrieve all metrics from all tracked
+    metric files, for the current working tree.
+
+    See the options below to restrict the metrics retrieved.
+
+    Args:
+        *targets (str, optional): Names of the metric files to retrieve
+        metrics from. For example, "classifier_eval.json,
+        clustering_eval.json".
+        If no `targets` are provided, all metric files tracked in `dvc.yaml`
+        will be used.
+        Note that targets don't necessarily have to be defined in `dvc.yaml`.
+        repo (str, optional): Location of the DVC repository.
+            Defaults to the current project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+        rev (str, optional): Name of the `Git revision`_ to retrieve metrics
+            from.
+            Defaults to `None`.
+            An example of git revision can be a branch or tag name, a commit
+            hash or a dvc experiment name.
+            If `repo` is not a Git repo, this option is ignored.
+            If `None`, the current working tree will be used.
+
+    Returns:
+        Dict: See Examples below.
+
+    Examples:
+
+        - No arguments.
+
+        Working on https://github.com/iterative/example-get-started
+
+        >>> import dvc.api
+        >>> metrics = dvc.api.metrics_show()
+        >>> print(json.dumps(metrics, indent=4))
+        {
+            "avg_prec": 0.9249974999612706,
+            "roc_auc": 0.9460213440787918
+        }
+
+        ---
+
+        - Using `rev`.
+
+        Working on https://github.com/iterative/example-get-started
+
+        >>> import json
+        >>> import dvc.api
+        >>> metrics = dvc.api.metrics_show(rev="tune-hyperparams")
+        >>> print(json.dumps(metrics, indent=4))
+        {
+            "avg_prec": 0.9268792615819422,
+            "roc_auc": 0.945093365854111
+        }
+
+        ---
+
+        - Using `targets`.
+
+        Working on https://github.com/iterative/example-get-started
+
+        >>> import json
+        >>> import dvc.api
+        >>> metrics = dvc.api.metrics_show("evaluation.json")
+        >>> print(json.dumps(metrics, indent=4))
+        {
+            "avg_prec": 0.9249974999612706,
+            "roc_auc": 0.9460213440787918
+        }
+
+        ---
+
+        - Git URL as `repo`.
+
+        >>> import json
+        >>> import dvc.api
+        >>> metrics = dvc.api.metrics_show(
+        ...     repo="https://github.com/iterative/demo-fashion-mnist")
+        >>> print(json.dumps(metrics, indent=4))
+        {
+            "loss": 0.25284987688064575,
+            "accuracy": 0.9071000218391418
+        }
+
+
+    .. _Git revision:
+        https://git-scm.com/docs/revisions
+    """
+
+    with Repo.open(repo) as _repo:
+        metrics = _repo.metrics.show(
+            targets=targets,
+            revs=rev if rev is None else [rev],
+            onerror=_onerror_raise,
+        )
+
+    metrics = _postprocess(metrics)
+
+    if not metrics:
+        return {}
+
+    return metrics[first(metrics)]
+
+
 def params_show(
     *targets: str,
     repo: Optional[str] = None,
@@ -56,9 +199,6 @@ def params_show(
     Returns:
         Dict: See Examples below.
 
-    Raises:
-        DvcException: If no params are found in `repo`.
-
     Examples:
 
         - No arguments.
@@ -239,34 +379,6 @@ def params_show(
     if isinstance(stages, str):
         stages = [stages]
 
-    def _onerror_raise(_result: Dict, exception: Exception, *args, **kwargs):
-        raise exception
-
-    def _postprocess(params):
-        processed: Dict[str, Dict] = {}
-        for rev, rev_data in params.items():
-            processed[rev] = {}
-
-            counts: typing.Counter[str] = Counter()
-            for file_data in rev_data["data"].values():
-                for k in file_data["data"]:
-                    counts[k] += 1
-
-            for file_name, file_data in rev_data["data"].items():
-                to_merge = {
-                    (k if counts[k] == 1 else f"{file_name}:{k}"): v
-                    for k, v in file_data["data"].items()
-                }
-                processed[rev] = {**processed[rev], **to_merge}
-
-        if "workspace" in processed:
-            del processed["workspace"]
-
-        if not processed:
-            raise DvcException("No params found")
-
-        return processed[first(processed)]
-
     with Repo.open(repo) as _repo:
         params = _repo.params.show(
             revs=rev if rev is None else [rev],
@@ -276,4 +388,9 @@ def params_show(
             stages=stages,
         )
 
-    return _postprocess(params)
+    params = _postprocess(params)
+
+    if not params:
+        return {}
+
+    return params[first(params)]

dvc/cachemgr.py

@@ -1,3 +1,5 @@
+import os
+
 from dvc.fs import GitFileSystem, Schemes
 from dvc_data.hashfile.db import get_odb
 
@@ -9,12 +11,11 @@ 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,
@@ -29,16 +30,21 @@ class ODBManager:
         self.config = config = repo.config["cache"]
         self._odb = {}
 
+        default = None
+        if repo and repo.local_dvc_dir:
+            default = os.path.join(repo.local_dvc_dir, self.CACHE_DIR)
+
         local = config.get("local")
 
         if local:
             settings = {"name": local}
-        elif "dir" not in config:
+        elif "dir" not in config and not default:
             settings = None
         else:
             from dvc.config_schema import LOCAL_COMMON
 
-            settings = {"url": config["dir"]}
+            url = config.get("dir") or default
+            settings = {"url": url}
             for opt in LOCAL_COMMON:
                 if opt in config:
                     settings[str(opt)] = config.get(opt)

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]:
@@ -56,8 +61,10 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
 
         if exc.errno == errno.EMFILE:
             logger.exception(
-                "too many open files, please visit "
-                "%s to see how to handle this problem",
+                (
+                    "too many open files, please visit "
+                    "%s to see how to handle this problem"
+                ),
                 error_link("many-files"),
                 extra={"tb_only": True},
             )
@@ -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 +98,7 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
             hint = f"\nPlease report this bug to {link}. Thank you!"
 
         logger.exception(
-            "URL '%s' is supported but requires these missing "
-            "dependencies: %s. %s",
+            "URL '%s' is supported but requires these missing dependencies: %s. %s",
             exc.url,
             exc.missing_deps,
             hint,
@@ -118,9 +124,11 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
 
         directory = relpath(exc.directory)
         logger.exception(
-            "Could not open pickled '%s' cache.\n"
-            "Remove the '%s' directory and then retry this command."
-            "\nSee %s 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"),
@@ -138,7 +146,7 @@ def _log_exceptions(exc: Exception) -> Optional[int]:
     return None
 
 
-def main(argv=None):  # noqa: C901
+def main(argv=None):  # noqa: C901, PLR0912, PLR0915
     """Main entry point for dvc CLI.
 
     Args:
@@ -150,7 +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
@@ -163,9 +171,8 @@ def main(argv=None):  # noqa: C901
         logging.disable(logging.INFO)
 
     args = None
-    disable_other_loggers()
 
-    outerLogLevel = logger.level
+    outer_log_level = logger.level
     try:
         args = parse_args(argv)
 
@@ -181,11 +188,7 @@ def main(argv=None):  # noqa: C901
             set_loggers_level(level)
 
         if level and level <= logging.DEBUG:
-            from platform import (
-                platform,
-                python_implementation,
-                python_version,
-            )
+            from platform import platform, python_implementation, python_version
 
             from dvc import __version__
             from dvc.utils.pkg import PKG
@@ -240,9 +243,9 @@ def main(argv=None):  # noqa: C901
 
         return ret
     finally:
-        logger.setLevel(outerLogLevel)
+        logger.setLevel(outer_log_level)
 
-        from dvc.external_repo import clean_repos
+        from dvc.repo.open_repo import clean_repos
 
         # Remove cached repos in the end of the call, these are anonymous
         # so won't be reused by any other subsequent run anyway.

dvc/cli/actions.py

@@ -2,9 +2,7 @@ from argparse import _AppendAction
 
 
 class CommaSeparatedArgs(_AppendAction):  # pylint: disable=protected-access
-    def __call__(
-        self, parser, namespace, values, option_string=None  # noqa: ARG002
-    ):
+    def __call__(self, parser, namespace, values, option_string=None):  # noqa: ARG002
         from funcy import ldistinct
 
         items = getattr(namespace, self.dest) or []
@@ -13,9 +11,7 @@ class CommaSeparatedArgs(_AppendAction):  # pylint: disable=protected-access
 
 
 class KeyValueArgs(_AppendAction):
-    def __call__(
-        self, parser, namespace, values, option_string=None  # noqa: ARG002
-    ):
+    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/parser.py

@@ -2,6 +2,7 @@
 import argparse
 import logging
 import os
+from functools import lru_cache
 
 from dvc import __version__
 from dvc.commands import (
@@ -150,6 +151,7 @@ def get_parent_parser():
     return parent_parser
 
 
+@lru_cache(maxsize=1)
 def get_main_parser():
     parent_parser = get_parent_parser()
 

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:
@@ -65,8 +62,11 @@ class CmdAdd(CmdBase):
                 remote=self.args.remote,
                 to_remote=self.args.to_remote,
                 jobs=self.args.jobs,
+                force=self.args.force,
             )
-
+        except FileNotFoundError:
+            logger.exception("")
+            return 1
         except DvcException:
             logger.exception("")
             return 1
@@ -143,6 +143,13 @@ def add_parser(subparsers, parent_parser):
         ),
         metavar="<number>",
     )
+    parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Override local file or folder if exists.",
+    )
 
     _add_annotating_args(parser)
     parser.add_argument(

dvc/commands/cache.py

@@ -1,4 +1,5 @@
 import argparse
+import os
 
 from dvc.cli import completion
 from dvc.cli.utils import append_doc_link, fix_subparsers
@@ -9,13 +10,21 @@ from dvc.ui import ui
 class CmdCacheDir(CmdConfig):
     def run(self):
         if self.args.value is None and not self.args.unset:
+            from dvc.config import ConfigError
+
             if self.args.level:
                 conf = self.config.read(level=self.args.level)
             else:
                 # Use merged config with default values
                 conf = self.config
-            self._check(conf, False, "cache", "dir")
-            ui.write(conf["cache"]["dir"])
+            try:
+                self._check(conf, False, "cache", "dir")
+                path = conf["cache"]["dir"]
+            except ConfigError:
+                if not self.config.dvc_dir or self.args.level:
+                    raise
+                path = os.path.join(self.config.dvc_dir, "cache")
+            ui.write(path)
             return 0
         with self.config.edit(level=self.args.level) as conf:
             if self.args.unset:
@@ -68,10 +77,12 @@ 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

@@ -39,7 +39,7 @@ class CmdCheckIgnore(CmdBase):
                 target = input()
             except (KeyboardInterrupt, EOFError):
                 break
-            if target == "":
+            if not target:
                 break
             if not self._check_one_file(target):
                 ret = 0
@@ -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

@@ -24,9 +24,7 @@ class CmdCommit(CmdBase):
                     force=self.args.force,
                 )
             except DvcException:
-                logger.exception(
-                    "failed to commit%s", (" " + target) if target else ""
-                )
+                logger.exception("failed to commit%s", (" " + target) if target else "")
                 return 1
         return 0
 

dvc/commands/completion.py

@@ -15,7 +15,7 @@ class CmdCompletion(CmdBaseNoRepo):
 
         shell = self.args.shell
         parser = self.args.parser
-        script = shtab.complete(parser, shell=shell, preamble=PREAMBLE)
+        script = shtab.complete(parser, shell=shell, preamble=PREAMBLE)  # nosec B604
         ui.write(script, force=True)
         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")),
@@ -34,7 +32,7 @@ class CmdConfig(CmdBaseNoRepo):
 
         super().__init__(args)
 
-        self.config = Config(validate=False)
+        self.config = Config.from_cwd(validate=False)
 
     def run(self):
         if self.args.show_origin and (self.args.value or self.args.unset):
@@ -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

@@ -9,11 +9,11 @@ if TYPE_CHECKING:
     from networkx import DiGraph
 
 
-def _show_ascii(G: "DiGraph"):
+def _show_ascii(graph: "DiGraph"):
     from dvc.dagascii import draw
     from dvc.repo.graph import get_pipelines
 
-    pipelines = get_pipelines(G)
+    pipelines = get_pipelines(graph)
 
     ret = []
     for pipeline in pipelines:
@@ -31,7 +31,7 @@ def _quote_label(node):
     return label
 
 
-def _show_dot(G: "DiGraph"):
+def _show_dot(graph: "DiGraph"):
     import io
 
     import networkx as nx
@@ -39,15 +39,15 @@ def _show_dot(G: "DiGraph"):
 
     dot_file = io.StringIO()
 
-    nx.relabel_nodes(G, _quote_label, copy=False)
-    write_dot(G.reverse(), dot_file)
+    nx.relabel_nodes(graph, _quote_label, copy=False)
+    write_dot(graph.reverse(), dot_file)
     return dot_file.getvalue()
 
 
-def _show_mermaid(G, markdown: bool = False):
+def _show_mermaid(graph, markdown: bool = False):
     from dvc.repo.graph import get_pipelines
 
-    pipelines = get_pipelines(G)
+    pipelines = get_pipelines(graph)
 
     graph = "flowchart TD"
 
@@ -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
@@ -102,43 +100,42 @@ def _transform(index, outs):
     def _relabel(node) -> str:
         return node.addressing if isinstance(node, Stage) else str(node)
 
-    G = index.outs_graph if outs else index.graph
-    return nx.relabel_nodes(G, _relabel, copy=True)
+    graph = index.outs_graph if outs else index.graph
+    return nx.relabel_nodes(graph, _relabel, copy=True)
 
 
-def _filter(G, targets, full):
+def _filter(graph, targets, full):
     import networkx as nx
 
     if not targets:
-        return G
+        return graph
 
-    H = G.copy()
+    new_graph = graph.copy()
     if not full:
         descendants = set()
         for target in targets:
-            descendants.update(nx.descendants(G, target))
+            descendants.update(nx.descendants(graph, target))
             descendants.add(target)
-        H.remove_nodes_from(set(G.nodes()) - descendants)
+        new_graph.remove_nodes_from(set(graph.nodes()) - descendants)
 
-    undirected = H.to_undirected()
+    undirected = new_graph.to_undirected()
     connected = set()
     for target in targets:
         connected.update(nx.node_connected_component(undirected, target))
 
-    H.remove_nodes_from(set(H.nodes()) - connected)
-
-    return H
+    new_graph.remove_nodes_from(set(new_graph.nodes()) - connected)
+    return new_graph
 
 
 def _build(repo, target=None, full=False, outs=False):
     targets = _collect_targets(repo, target, outs)
-    G = _transform(repo.index, outs)
-    return _filter(G, targets, full)
+    graph = _transform(repo.index, outs)
+    return _filter(graph, targets, full)
 
 
 class CmdDAG(CmdBase):
     def run(self):
-        G = _build(
+        graph = _build(
             self.repo,
             target=self.args.target,
             full=self.args.full,
@@ -146,12 +143,12 @@ class CmdDAG(CmdBase):
         )
 
         if self.args.dot:
-            ui.write(_show_dot(G))
+            ui.write(_show_dot(graph))
         elif self.args.mermaid or self.args.markdown:
-            ui.write(_show_mermaid(G, self.args.markdown))
+            ui.write(_show_mermaid(graph, self.args.markdown))
         else:
             with ui.pager():
-                ui.write(_show_ascii(G))
+                ui.write(_show_ascii(graph))
 
         return 0
 
@@ -204,7 +201,9 @@ 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
 
@@ -25,12 +21,14 @@ logger = logging.getLogger(__name__)
 
 class CmdDataStatus(CmdBase):
     COLORS = {
+        "not_in_remote": "red",
         "not_in_cache": "red",
         "committed": "green",
         "uncommitted": "yellow",
         "untracked": "cyan",
     }
     LABELS = {
+        "not_in_remote": "Not in remote",
         "not_in_cache": "Not in cache",
         "committed": "DVC committed changes",
         "uncommitted": "DVC uncommitted changes",
@@ -38,21 +36,21 @@ class CmdDataStatus(CmdBase):
         "unchanged": "DVC unchanged files",
     }
     HINTS = {
+        "not_in_remote": ('use "dvc push <file>..." to upload files',),
         "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 +94,7 @@ 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
@@ -120,6 +117,8 @@ class CmdDataStatus(CmdBase):
             status = self.repo.data_status(
                 granular=self.args.granular,
                 untracked_files=self.args.untracked_files,
+                not_in_remote=self.args.not_in_remote,
+                remote_refresh=self.args.remote_refresh,
             )
 
         if not self.args.unchanged:
@@ -180,9 +179,7 @@ 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 +202,7 @@ 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",
@@ -248,6 +244,18 @@ def add_parser(subparsers, parent_parser):
         nargs="?",
         help="Show untracked files.",
     )
+    data_status_parser.add_argument(
+        "--not-in-remote",
+        action="store_true",
+        default=False,
+        help="Show files not in remote.",
+    )
+    data_status_parser.add_argument(
+        "--no-remote-refresh",
+        dest="remote_refresh",
+        action="store_false",
+        help="Use cached remote index (don't check remote).",
+    )
     data_status_parser.set_defaults(func=CmdDataStatus)
 
     DATA_LS_HELP = "List data tracked by DVC with its metadata."

dvc/commands/data_sync.py

@@ -40,6 +40,7 @@ class CmdDataPull(CmdDataBase):
                 recursive=self.args.recursive,
                 run_cache=self.args.run_cache,
                 glob=self.args.glob,
+                allow_missing=self.args.allow_missing,
             )
             self.log_summary(stats)
         except (CheckoutError, DvcException) as exc:
@@ -197,6 +198,12 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help=argparse.SUPPRESS,
     )
+    pull_parser.add_argument(
+        "--allow-missing",
+        action="store_true",
+        default=False,
+        help="Ignore errors if some of the files or directories are missing.",
+    )
     pull_parser.set_defaults(func=CmdDataPull)
 
     # Push
@@ -262,9 +269,7 @@ 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 +325,7 @@ 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 +363,29 @@ 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

@@ -1,13 +1,10 @@
 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,
+    clean,
     diff,
     exec_run,
     gc,
@@ -25,6 +22,7 @@ from dvc.commands.experiments import (
 SUB_COMMANDS = [
     apply,
     branch,
+    clean,
     diff,
     exec_run,
     gc,
@@ -54,8 +52,7 @@ 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)
@@ -85,6 +82,7 @@ def add_rev_selection_flags(
     experiments_subcmd_parser.add_argument(
         "--rev",
         type=str,
+        action="append",
         default=None,
         help=msg,
         metavar="<commit>",

dvc/commands/experiments/apply.py

@@ -4,25 +4,27 @@ import logging
 from dvc.cli import completion
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
+from dvc.ui import ui
 
 logger = logging.getLogger(__name__)
 
 
 class CmdExperimentsApply(CmdBase):
     def run(self):
-
-        self.repo.experiments.apply(
-            self.args.experiment, force=self.args.force
-        )
+        if not self.args.force:
+            ui.write(
+                "The --no-force option is deprecated and will be removed in a future"
+                " DVC release. To revert the result of 'exp apply', run:\n"
+                "\n\tgit reset --hard\n"
+                "\tgit stash apply refs/exps/apply/stash\n"
+            )
+        self.repo.experiments.apply(self.args.experiment)
 
         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",
@@ -29,6 +27,12 @@ def add_parser(experiments_subparsers, parent_parser):
         "experiment", help="Experiment to be promoted."
     )
     experiments_branch_parser.add_argument(
-        "branch", help="Name for the new Git branch"
+        "branch",
+        nargs="?",
+        default=None,
+        help=(
+            "Optional name for the new Git branch. "
+            "Defaults to '{experiment-name}-branch'."
+        ),
     )
     experiments_branch_parser.set_defaults(func=CmdExperimentsBranch)

dvc/commands/experiments/clean.py

@@ -0,0 +1,25 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsClean(CmdBase):
+    def run(self):
+        self.repo.experiments.clean()
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    EXPERIMENTS_CLEAN_HELP = "Cleanup experiments temporary internal files."
+    experiments_clean_parser = experiments_subparsers.add_parser(
+        "clean",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_CLEAN_HELP, "exp/clean"),
+        help=EXPERIMENTS_CLEAN_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    experiments_clean_parser.set_defaults(func=CmdExperimentsClean)

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."
 
     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))
@@ -22,6 +19,8 @@ class CmdExecutorRun(CmdBaseNoRepo):
             queue=None,
             log_level=logger.getEffectiveLevel(),
             infofile=self.args.infofile,
+            copy_paths=self.args.copy_paths,
+            message=self.args.message,
         )
         return 0
 
@@ -39,4 +38,21 @@ def add_parser(experiments_subparsers, parent_parser):
         help="Path to executor info file",
         default=None,
     )
+    exec_run_parser.add_argument(
+        "-C",
+        "--copy-paths",
+        action="append",
+        default=[],
+        help=(
+            "List of ignored or untracked paths to copy into the temp directory."
+            " Only used if `--temp` or `--queue` is specified."
+        ),
+    )
+    exec_run_parser.add_argument(
+        "-M",
+        "--message",
+        type=str,
+        default=None,
+        help="Custom commit message to use when committing the experiment.",
+    )
     exec_run_parser.set_defaults(func=CmdExecutorRun)

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 +76,10 @@ 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 specified Git 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

@@ -1,5 +1,6 @@
 import argparse
 import logging
+from typing import Any, Dict
 
 from dvc.cli import completion
 from dvc.cli.command import CmdBase
@@ -12,43 +13,79 @@ 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."
             )
 
+    @staticmethod
+    def log_result(result: Dict[str, Any], remote: str):
+        from dvc.utils import humanize
+
+        def join_exps(exps):
+            return humanize.join([f"[bold]{e}[/]" for e in exps])
+
+        if diverged_exps := result.get("diverged"):
+            exps = join_exps(diverged_exps)
+            ui.error_write(
+                f"[yellow]Local experiment {exps} has diverged "
+                "from remote experiment with the same name.\n"
+                "To override the remote experiment re-run with '--force'.",
+                styled=True,
+            )
+        if uptodate_exps := result.get("up_to_date"):
+            exps = join_exps(uptodate_exps)
+            verb = "are" if len(uptodate_exps) > 1 else "is"
+            ui.write(
+                f"Experiment {exps} {verb} up to date on Git remote {remote!r}.",
+                styled=True,
+            )
+        if pushed_exps := result.get("success"):
+            exps = join_exps(pushed_exps)
+            ui.write(f"Pushed experiment {exps} to Git remote {remote!r}.", styled=True)
+        if not uptodate_exps and not pushed_exps:
+            ui.write("No experiments to push.")
+
+        if uploaded := result.get("uploaded"):
+            stats = {"uploaded": uploaded}
+            ui.write(humanize.get_summary(stats.items()))
+
+        if project_url := result.get("url"):
+            ui.rich_print(
+                "View your experiments at", project_url, style="yellow", soft_wrap=True
+            )
+
     def run(self):
+        from dvc.repo.experiments.push import UploadError
 
         self.raise_error_if_all_disabled()
 
-        pushed_exps = self.repo.experiments.push(
-            self.args.git_remote,
-            self.args.experiment,
-            all_commits=self.args.all_commits,
-            rev=self.args.rev,
-            num=self.args.num,
-            force=self.args.force,
-            push_cache=self.args.push_cache,
-            dvc_remote=self.args.dvc_remote,
-            jobs=self.args.jobs,
-            run_cache=self.args.run_cache,
-        )
-
-        if pushed_exps:
-            ui.write(
-                f"Pushed experiment '{pushed_exps}'"
-                f"to Git remote '{self.args.git_remote}'."
+        try:
+            result = self.repo.experiments.push(
+                self.args.git_remote,
+                self.args.experiment,
+                all_commits=self.args.all_commits,
+                rev=self.args.rev,
+                num=self.args.num,
+                force=self.args.force,
+                push_cache=self.args.push_cache,
+                dvc_remote=self.args.dvc_remote,
+                jobs=self.args.jobs,
+                run_cache=self.args.run_cache,
             )
-        else:
-            ui.write("No experiments to push.")
+        except UploadError as e:
+            self.log_result(e.result, self.args.git_remote)
+            raise
+
+        self.log_result(result, self.args.git_remote)
         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 +113,7 @@ 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 +127,7 @@ 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/queue_worker.py

@@ -9,7 +9,9 @@ class CmdQueueWorker(CmdBase):
     """Run the exp queue worker."""
 
     def run(self):
-        self.repo.experiments.celery_queue.worker.start(self.args.name)
+        self.repo.experiments.celery_queue.worker.start(
+            self.args.name, fsapp_clean=self.args.clean
+        )
         return 0
 
 
@@ -22,4 +24,9 @@ def add_parser(experiments_subparsers, parent_parser):
         add_help=False,
     )
     parser.add_argument("name", help="Celery worker name.")
+    parser.add_argument(
+        "--clean",
+        action="store_true",
+        help="Automatically cleanup celery broker on shutdown.",
+    )
     parser.set_defaults(func=CmdQueueWorker)

dvc/commands/experiments/remove.py

@@ -24,10 +24,11 @@ class CmdExperimentsRemove(CmdBase):
             )
 
     def run(self):
+        from dvc.utils import humanize
 
         self.check_arguments()
 
-        removed_list = self.repo.experiments.remove(
+        removed = self.repo.experiments.remove(
             exp_names=self.args.experiment,
             all_commits=self.args.all_commits,
             rev=self.args.rev,
@@ -35,8 +36,10 @@ class CmdExperimentsRemove(CmdBase):
             queue=self.args.queue,
             git_remote=self.args.git_remote,
         )
-        removed = ",".join(removed_list)
-        ui.write(f"Removed experiments: {removed}")
+        if removed:
+            ui.write(f"Removed experiments: {humanize.join(map(repr, removed))}")
+        else:
+            ui.write("No experiments to remove.")
 
         return 0
 

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:
@@ -39,6 +36,8 @@ class CmdExperimentsRun(CmdRepro):
             reset=self.args.reset,
             tmp_dir=self.args.tmp_dir,
             machine=self.args.machine,
+            copy_paths=self.args.copy_paths,
+            message=self.args.message,
             **self._common_kwargs,
         )
 
@@ -51,7 +50,6 @@ 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",
@@ -140,3 +138,20 @@ def _add_run_common(parser):
         # )
         # metavar="<name>",
     )
+    parser.add_argument(
+        "-C",
+        "--copy-paths",
+        action="append",
+        default=[],
+        help=(
+            "List of ignored or untracked paths to copy into the temp directory."
+            " Only used if `--temp` or `--queue` is specified."
+        ),
+    )
+    parser.add_argument(
+        "-M",
+        "--message",
+        type=str,
+        default=None,
+        help="Custom commit message to use when committing the experiment.",
+    )

dvc/commands/experiments/save.py

@@ -11,12 +11,12 @@ logger = logging.getLogger(__name__)
 
 class CmdExperimentsSave(CmdBase):
     def run(self):
-
         try:
             ref = self.repo.experiments.save(
                 name=self.args.name,
                 force=self.args.force,
                 include_untracked=self.args.include_untracked,
+                message=self.args.message,
             )
         except DvcException:
             logger.exception("failed to save experiment")
@@ -36,7 +36,7 @@ class CmdExperimentsSave(CmdBase):
 
 
 def add_parser(experiments_subparsers, parent_parser):
-    EXPERIMENTS_SAVE_HELP = "Save current workspace as a dvc experiment."
+    EXPERIMENTS_SAVE_HELP = "Save current workspace as an experiment."
     save_parser = experiments_subparsers.add_parser(
         "save",
         parents=[parent_parser],
@@ -76,4 +76,11 @@ def add_parser(experiments_subparsers, parent_parser):
         help="List of untracked paths to include in the experiment.",
         metavar="<path>",
     )
+    save_parser.add_argument(
+        "-M",
+        "--message",
+        type=str,
+        default=None,
+        help="Custom commit message to use when committing the experiment.",
+    )
     save_parser.set_defaults(func=CmdExperimentsSave)

dvc/commands/experiments/show.py

@@ -2,9 +2,8 @@ import argparse
 import logging
 import os
 import re
-from collections import Counter, OrderedDict, defaultdict
 from datetime import date, datetime
-from typing import TYPE_CHECKING, Any, Dict, Set
+from typing import TYPE_CHECKING, Dict, Iterable
 
 from funcy import lmap
 
@@ -12,9 +11,8 @@ from dvc.cli import completion
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
 from dvc.commands.metrics import DEFAULT_PRECISION
-from dvc.exceptions import DvcException, InvalidArgumentError
+from dvc.exceptions import DvcException
 from dvc.ui import ui
-from dvc.utils.flatten import flatten
 from dvc.utils.serialize import encode_exception
 
 if TYPE_CHECKING:
@@ -28,30 +26,6 @@ FILL_VALUE_ERRORED = "!"
 logger = logging.getLogger(__name__)
 
 
-def _update_names(names, items):
-    for name, item in items:
-        item = item.get("data", {})
-        if isinstance(item, dict):
-            item = flatten(item)
-            names[name].update({key: None for key in item})
-
-
-def _collect_names(all_experiments, **kwargs):
-    metric_names: Dict[str, Dict[str, Any]] = defaultdict(dict)
-    param_names: Dict[str, Dict[str, Any]] = defaultdict(dict)
-    deps_names: Set[str] = set()
-
-    for _, experiments in all_experiments.items():
-        for exp_data in experiments.values():
-            exp = exp_data.get("data", {})
-            _update_names(metric_names, exp.get("metrics", {}).items())
-            _update_names(param_names, exp.get("params", {}).items())
-            for dep_name in exp.get("deps", {}):
-                deps_names.add(dep_name)
-
-    return metric_names, param_names, sorted(deps_names)
-
-
 experiment_types = {
     "checkpoint_tip": "│ ╓",
     "checkpoint_commit": "│ ╟",
@@ -62,235 +36,6 @@ experiment_types = {
 }
 
 
-def _collect_rows(  # noqa: C901
-    base_rev,
-    experiments,
-    all_headers,
-    metric_headers,
-    param_headers,
-    metric_names,
-    param_names,
-    deps_names,
-    precision=DEFAULT_PRECISION,
-    sort_by=None,
-    sort_order=None,
-    fill_value=FILL_VALUE,
-    iso=False,
-):
-    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
-        )
-
-    new_checkpoint = True
-    for i, (rev, results) in enumerate(experiments.items()):
-        fill_value = FILL_VALUE_ERRORED if results.get("error") else fill_value
-        row_dict = {k: fill_value for k in all_headers}
-
-        exp = results.get("data", {})
-
-        state = exp.get("status")
-        if state == "Success":
-            state = fill_value
-
-        is_baseline = rev == "baseline"
-
-        if is_baseline:
-            name_rev = base_rev[:7] if Git.is_sha(base_rev) else base_rev
-        else:
-            name_rev = rev[:7]
-
-        tip = exp.get("checkpoint_tip")
-        parent_rev = exp.get("checkpoint_parent", "")
-        parent_exp = experiments.get(parent_rev, {}).get("data", {})
-        parent_tip = parent_exp.get("checkpoint_tip")
-
-        parent = ""
-        if is_baseline:
-            typ = "baseline"
-        elif tip:
-            if tip == parent_tip:
-                typ = (
-                    "checkpoint_tip" if new_checkpoint else "checkpoint_commit"
-                )
-            elif parent_rev == base_rev:
-                typ = "checkpoint_base"
-            else:
-                typ = "checkpoint_commit"
-                parent = parent_rev[:7]
-        elif i < len(experiments) - 1:
-            typ = "branch_commit"
-        else:
-            typ = "branch_base"
-
-        if not is_baseline:
-            new_checkpoint = not (tip and tip == parent_tip)
-
-        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["parent"] = parent
-        row_dict["State"] = state
-        row_dict["Executor"] = exp.get("executor", fill_value)
-
-        _extend_row(
-            row_dict,
-            metric_names,
-            metric_headers,
-            exp.get("metrics", {}).items(),
-            precision,
-            fill_value=fill_value,
-        )
-        _extend_row(
-            row_dict,
-            param_names,
-            param_headers,
-            exp.get("params", {}).items(),
-            precision,
-            fill_value=fill_value,
-        )
-        for dep in deps_names:
-            hash_info = exp.get("deps", {}).get(dep, {}).get("hash")
-            if hash_info is not None:
-                hash_info = hash_info[:7]
-            row_dict[dep] = hash_info
-        yield list(row_dict.values())
-
-
-def _sort_column(sort_by, metric_names, param_names):
-    path, _, sort_name = sort_by.rpartition(":")
-    matches = set()
-
-    if path:
-        if path in metric_names and sort_name in metric_names[path]:
-            matches.add((path, sort_name, "metrics"))
-        if path in param_names and sort_name in param_names[path]:
-            matches.add((path, sort_name, "params"))
-    else:
-        for path in metric_names:
-            if sort_name in metric_names[path]:
-                matches.add((path, sort_name, "metrics"))
-        for path in param_names:
-            if sort_name in param_names[path]:
-                matches.add((path, sort_name, "params"))
-
-    if len(matches) == 1:
-        return matches.pop()
-    if len(matches) > 1:
-        raise InvalidArgumentError(
-            "Ambiguous sort column '{}' matched '{}'".format(
-                sort_by,
-                ", ".join([f"{path}:{name}" for path, name, _ in matches]),
-            )
-        )
-    raise InvalidArgumentError(f"Unknown sort column '{sort_by}'")
-
-
-def _sort_exp(experiments, sort_path, sort_name, typ, reverse):
-    def _sort(item):
-        rev, exp = item
-        exp_data = exp.get("data", {})
-        tip = exp_data.get("checkpoint_tip")
-        if tip and tip != rev:
-            # Sort checkpoint experiments by tip commit
-            return _sort((tip, experiments[tip]))
-        data = exp_data.get(typ, {}).get(sort_path, {}).get("data", {})
-        val = flatten(data).get(sort_name)
-        return val is None, val
-
-    ret = OrderedDict()
-    if "baseline" in experiments:
-        ret["baseline"] = experiments.pop("baseline")
-
-    ret.update(sorted(experiments.items(), key=_sort, reverse=reverse))
-    return ret
-
-
-def format_time(datetime_obj, fill_value=FILL_VALUE, iso=False):
-    if datetime_obj is None:
-        return fill_value
-
-    if iso:
-        return datetime_obj.isoformat()
-
-    if datetime_obj.date() == date.today():
-        fmt = "%I:%M %p"
-    else:
-        fmt = "%b %d, %Y"
-    return datetime_obj.strftime(fmt)
-
-
-def _extend_row(row, names, headers, items, precision, fill_value=FILL_VALUE):
-    from dvc.compare import _format_field, with_value
-
-    for fname, data in items:
-        item = data.get("data", {})
-        item = flatten(item) if isinstance(item, dict) else {fname: item}
-        for name in names[fname]:
-            value = with_value(
-                item.get(name),
-                FILL_VALUE_ERRORED if data.get("error", None) else fill_value,
-            )
-            # wrap field data in ui.rich_text, otherwise rich may
-            # interpret unescaped braces from list/dict types as rich
-            # markup tags
-            value = ui.rich_text(str(_format_field(value, precision)))
-            if name in headers:
-                row[name] = value
-            else:
-                row[f"{fname}:{name}"] = value
-
-
-def experiments_table(
-    all_experiments,
-    headers,
-    metric_headers,
-    metric_names,
-    param_headers,
-    param_names,
-    deps_names,
-    sort_by=None,
-    sort_order=None,
-    precision=DEFAULT_PRECISION,
-    fill_value=FILL_VALUE,
-    iso=False,
-) -> "TabularData":
-    from funcy import lconcat
-
-    from dvc.compare import TabularData
-
-    all_headers = lconcat(headers, metric_headers, param_headers, deps_names)
-    td = TabularData(all_headers, fill_value=fill_value)
-    for base_rev, experiments in all_experiments.items():
-        rows = _collect_rows(
-            base_rev,
-            experiments,
-            all_headers,
-            metric_headers,
-            param_headers,
-            metric_names,
-            param_names,
-            deps_names,
-            sort_by=sort_by,
-            sort_order=sort_order,
-            precision=precision,
-            fill_value=fill_value,
-            iso=iso,
-        )
-        td.extend(rows)
-
-    return td
-
-
 def prepare_exp_id(kwargs) -> "RichText":
     exp_name = kwargs["Experiment"]
     rev = kwargs["rev"]
@@ -314,8 +59,9 @@ def baseline_styler(typ):
     return {"style": "bold"} if typ == "baseline" else {}
 
 
-def show_experiments(  # noqa: C901
-    all_experiments,
+def show_experiments(  # noqa: C901, PLR0912
+    td: "TabularData",
+    headers: Dict[str, Iterable[str]],
     keep=None,
     drop=None,
     pager=True,
@@ -324,40 +70,6 @@ def show_experiments(  # noqa: C901
     pcp=False,
     **kwargs,
 ):
-    from funcy.seqs import flatten as flatten_list
-
-    metric_names, param_names, deps_names = _collect_names(all_experiments)
-
-    headers_list = [
-        "Experiment",
-        "rev",
-        "typ",
-        "Created",
-        "parent",
-        "State",
-        "Executor",
-    ]
-
-    names = {**metric_names, **param_names}
-    counter = Counter(flatten_list([list(a.keys()) for a in names.values()]))
-    counter.update(headers_list)
-    metric_headers = _normalize_headers(metric_names, counter)
-    param_headers = _normalize_headers(param_names, counter)
-
-    td = experiments_table(
-        all_experiments,
-        headers_list,
-        metric_headers,
-        metric_names,
-        param_headers,
-        param_names,
-        deps_names,
-        kwargs.get("sort_by"),
-        kwargs.get("sort_order"),
-        kwargs.get("precision"),
-        kwargs.get("fill_value"),
-        kwargs.get("iso"),
-    )
     if keep:
         for col in td.keys():  # noqa: SIM118
             if re.match(keep, col):
@@ -371,16 +83,9 @@ 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 = {
-        "metrics": metric_headers,
-        "params": param_headers,
-        "deps": deps_names,
-    }
     styles = {
         "Experiment": {"no_wrap": True, "header_style": "black on grey93"},
         "Created": {"header_style": "black on grey93"},
@@ -410,9 +115,7 @@ 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)
@@ -470,8 +173,10 @@ def _format_json(item):
 
 class CmdExperimentsShow(CmdBase):
     def run(self):
+        from dvc.repo.experiments.show import tabulate
+
         try:
-            all_experiments = self.repo.experiments.show(
+            exps = self.repo.experiments.show(
                 all_branches=self.args.all_branches,
                 all_tags=self.args.all_tags,
                 all_commits=self.args.all_commits,
@@ -482,31 +187,36 @@ class CmdExperimentsShow(CmdBase):
                 sha_only=self.args.sha,
                 param_deps=self.args.param_deps,
                 fetch_running=self.args.fetch_running,
+                force=self.args.force,
             )
         except DvcException:
             logger.exception("failed to show experiments")
             return 1
 
         if self.args.json:
-            ui.write_json(all_experiments, default=_format_json)
+            ui.write_json([exp.dumpd() for exp in exps], 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
+            td, headers = tabulate(
+                exps,
+                precision=precision,
+                fill_value=fill_value,
+                iso=iso,
+                sort_by=self.args.sort_by,
+                sort_order=self.args.sort_order,
+            )
 
             show_experiments(
-                all_experiments,
+                td,
+                headers,
                 keep=self.args.keep,
                 drop=self.args.drop,
                 sort_by=self.args.sort_by,
                 sort_order=self.args.sort_order,
-                precision=precision,
-                fill_value=fill_value,
-                iso=iso,
                 pager=not self.args.no_pager,
                 csv=self.args.csv,
                 markdown=self.args.markdown,
@@ -582,10 +292,7 @@ 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",
     )
@@ -665,4 +372,10 @@ def add_parser(experiments_subparsers, parent_parser):
         action="store_false",
         help=argparse.SUPPRESS,
     )
+    experiments_show_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        help="Force re-collection of experiments instead of loading from exp cache.",
+    )
     experiments_show_parser.set_defaults(func=CmdExperimentsShow)

dvc/commands/gc.py

@@ -10,7 +10,7 @@ logger = logging.getLogger(__name__)
 
 
 class CmdGC(CmdBase):
-    def run(self):  # noqa: C901
+    def run(self):  # noqa: C901, PLR0912
         from dvc.repo.gc import _validate_args
 
         _validate_args(
@@ -22,6 +22,8 @@ class CmdGC(CmdBase):
             workspace=self.args.workspace,
             rev=self.args.rev,
             num=self.args.num,
+            cloud=self.args.cloud,
+            not_in_remote=self.args.not_in_remote,
         )
 
         if self.args.rev:
@@ -40,17 +42,16 @@ 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"
+
+        if self.args.not_in_remote:
+            msg += " that are present in the DVC remote"
+
         if self.args.repos:
             msg += " of the current and the following repos:"
 
@@ -79,6 +80,7 @@ class CmdGC(CmdBase):
             workspace=self.args.workspace,
             rev=self.args.rev,
             num=self.args.num,
+            not_in_remote=self.args.not_in_remote,
         )
         return 0
 
@@ -162,12 +164,18 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Keep data files for all experiments.",
     )
+    gc_parser.add_argument(
+        "--not-in-remote",
+        action="store_true",
+        default=False,
+        help="Keep data files that are not present in the remote.",
+    )
     gc_parser.add_argument(
         "-c",
         "--cloud",
         action="store_true",
         default=False,
-        help="Collect garbage in remote repository.",
+        help="Collect garbage in remote storage in addition to local cache.",
     )
     gc_parser.add_argument(
         "-r",
@@ -198,9 +206,11 @@ 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__)
 
@@ -15,14 +14,8 @@ class CmdGet(CmdBaseNoRepo):
         from dvc.api import get_url
         from dvc.ui import ui
 
-        try:
-            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")
-            return 1
+        url = get_url(self.args.path, repo=self.args.url, rev=self.args.rev)
+        ui.write(url, force=True)
 
         return 0
 
@@ -34,6 +27,7 @@ class CmdGet(CmdBaseNoRepo):
 
     def _get_file_from_repo(self):
         from dvc.repo import Repo
+        from dvc.scm import CloneError
 
         try:
             Repo.get(
@@ -42,6 +36,7 @@ class CmdGet(CmdBaseNoRepo):
                 out=self.args.out,
                 rev=self.args.rev,
                 jobs=self.args.jobs,
+                force=self.args.force,
             )
             return 0
         except CloneError:
@@ -85,8 +80,10 @@ 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",
@@ -98,4 +95,11 @@ def add_parser(subparsers, parent_parser):
         ),
         metavar="<number>",
     )
+    get_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Override local file or folder if exists.",
+    )
     get_parser.set_defaults(func=CmdGet)

dvc/commands/get_url.py

@@ -14,7 +14,12 @@ class CmdGetUrl(CmdBaseNoRepo):
         from dvc.repo import Repo
 
         try:
-            Repo.get_url(self.args.url, out=self.args.out, jobs=self.args.jobs)
+            Repo.get_url(
+                self.args.url,
+                out=self.args.out,
+                jobs=self.args.jobs,
+                force=self.args.force,
+            )
             return 0
         except DvcException:
             logger.exception("failed to get '%s'", self.args.url)
@@ -46,4 +51,11 @@ def add_parser(subparsers, parent_parser):
         ),
         metavar="<number>",
     )
+    get_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Override local file or folder if exists.",
+    )
     get_parser.set_defaults(func=CmdGetUrl)

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,
@@ -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

@@ -25,12 +25,15 @@ class CmdImportUrl(CmdBase):
                 labels=self.args.labels,
                 meta=self.args.meta,
                 jobs=self.args.jobs,
+                force=self.args.force,
                 version_aware=self.args.version_aware,
             )
         except DvcException:
             logger.exception(
-                "failed to import %s. You could also try downloading "
-                "it manually, and adding it with `dvc add`.",
+                (
+                    "failed to import %s. You could also try downloading "
+                    "it manually, and adding it with `dvc add`."
+                ),
                 self.args.url,
             )
             return 1
@@ -40,9 +43,7 @@ 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",
@@ -53,16 +54,18 @@ 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."
@@ -95,8 +98,10 @@ 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",
@@ -108,14 +113,18 @@ def add_parser(subparsers, parent_parser):
         ),
         metavar="<number>",
     )
+    import_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Override local file or folder if exists.",
+    )
     import_parser.add_argument(
         "--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/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,
@@ -310,7 +302,7 @@ class CmdMachineSsh(CmdBase):
         return 0
 
 
-def add_parser(subparsers, parent_parser):
+def add_parser(subparsers, parent_parser):  # noqa: PLR0915
     from dvc.commands.config import parent_config_parser
 
     machine_HELP = "Set up and manage cloud machines."
@@ -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

@@ -1,9 +1,9 @@
 import argparse
-import json
 import logging
 import os
+from typing import TYPE_CHECKING, Dict, List, Optional
 
-from funcy import first
+from funcy import compact, first, get_in
 
 from dvc.cli import completion
 from dvc.cli.command import CmdBase
@@ -12,16 +12,51 @@ from dvc.exceptions import DvcException
 from dvc.ui import ui
 from dvc.utils import format_link
 
+if TYPE_CHECKING:
+    from dvc.render.match import RendererWithErrors
+
+
 logger = logging.getLogger(__name__)
 
 
-def _show_json(renderers, split=False):
+def _show_json(
+    renderers_with_errors: List["RendererWithErrors"],
+    split=False,
+    errors: Optional[Dict[str, Exception]] = None,
+):
     from dvc.render.convert import to_json
+    from dvc.utils.serialize import encode_exception
 
-    result = {
-        renderer.name: to_json(renderer, split) for renderer in renderers
-    }
-    ui.write_json(result)
+    all_errors: List[Dict] = []
+    data = {}
+
+    for renderer, src_errors, def_errors in renderers_with_errors:
+        name = renderer.name
+        data[name] = to_json(renderer, split)
+        all_errors.extend(
+            {
+                "name": name,
+                "rev": rev,
+                "source": source,
+                **encode_exception(e),
+            }
+            for rev, per_rev_src_errors in src_errors.items()
+            for source, e in per_rev_src_errors.items()
+        )
+        all_errors.extend(
+            {
+                "name": name,
+                "rev": rev,
+                **encode_exception(e),
+            }
+            for rev, e in def_errors.items()
+        )
+
+    # these errors are not tied to any renderers
+    errors = errors or {}
+    all_errors.extend({"rev": rev, **encode_exception(e)} for rev, e in errors.items())
+
+    ui.write_json(compact({"errors": all_errors, "data": data}), highlight=False)
 
 
 def _adjust_vega_renderers(renderers):
@@ -78,10 +113,6 @@ class CmdPlots(CmdBase):
         props = {p: getattr(self.args, p) for p in PLOT_PROPS}
         return {k: v for k, v in props.items() if v is not None}
 
-    def _config_files(self):
-        if self.args.from_config:
-            return {self.args.from_config}
-
     def _html_template_path(self):
         html_template_path = self.args.html_template
         if not html_template_path:
@@ -90,12 +121,10 @@ 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
-                )
+                html_template_path = os.path.join(self.repo.dvc_dir, html_template_path)
         return html_template_path
 
-    def run(self) -> int:  # noqa: C901
+    def run(self) -> int:  # noqa: C901, PLR0911, PLR0912
         from pathlib import Path
 
         from dvc.render.match import match_defs_renderers
@@ -106,14 +135,11 @@ 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
 
@@ -121,37 +147,39 @@ class CmdPlots(CmdBase):
             plots_data = self._func(
                 targets=self.args.targets,
                 props=self._props(),
-                config_files=self._config_files(),
             )
 
-            if not plots_data:
+            if not plots_data and not self.args.json:
                 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 = match_defs_renderers(
+            renderers_out = out if self.args.json else os.path.join(out, "static")
+            renderers_with_errors = match_defs_renderers(
                 data=plots_data,
                 out=renderers_out,
                 templates_dir=self.repo.plots.templates_dir,
             )
             if self.args.json:
-                _show_json(renderers, self.args.split)
+                errors = compact(
+                    {
+                        rev: get_in(data, ["definitions", "error"])
+                        for rev, data in plots_data.items()
+                    }
+                )
+                _show_json(renderers_with_errors, self.args.split, errors=errors)
                 return 0
 
+            renderers = [r.renderer for r in renderers_with_errors]
             _adjust_vega_renderers(renderers)
             if self.args.show_vega:
                 renderer = first(filter(lambda r: r.TYPE == "vega", renderers))
                 if renderer:
-                    ui.write_json(json.loads(renderer.get_filled_template()))
+                    ui.write_json(renderer.get_filled_template(as_string=False))
                 return 0
 
             output_file: Path = (Path.cwd() / out).resolve() / "index.html"
@@ -160,7 +188,7 @@ 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 +277,7 @@ 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 +300,7 @@ 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 +358,7 @@ 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 +384,8 @@ 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 +402,7 @@ 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>"
     )
@@ -431,9 +450,3 @@ def _add_ui_arguments(parser):
         help="Custom HTML template for VEGA visualization.",
         metavar="<path>",
     )
-    parser.add_argument(
-        "--from-config",
-        default=None,
-        metavar="<path>",
-        help=argparse.SUPPRESS,
-    )

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

@@ -1,10 +1,8 @@
 import argparse
 import logging
-from typing import Dict, List, Optional
 
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
-from dvc.commands.experiments.show import format_time
 from dvc.compare import TabularData
 from dvc.ui import ui
 
@@ -15,9 +13,9 @@ class CmdQueueStatus(CmdBase):
     """Show queue task and worker status."""
 
     def run(self) -> int:
-        result: List[
-            Dict[str, Optional[str]]
-        ] = self.repo.experiments.celery_queue.status()
+        from dvc.repo.experiments.show import format_time
+
+        result = self.repo.experiments.celery_queue.status()
         if result:
             all_headers = ["Task", "Name", "Created", "Status"]
             td = TabularData(all_headers)
@@ -39,9 +37,7 @@ 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 +46,7 @@ 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:
@@ -40,6 +38,7 @@ class CmdRepro(CmdBase):
             "recursive": self.args.recursive,
             "force_downstream": self.args.force_downstream,
             "pull": self.args.pull,
+            "allow_missing": self.args.allow_missing,
         }
 
     @property
@@ -55,16 +54,14 @@ 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 +82,14 @@ 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 +122,10 @@ 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",
@@ -139,19 +136,24 @@ and then the stage name name.
             "from the run-cache."
         ),
     )
+    repro_parser.add_argument(
+        "--allow-missing",
+        action="store_true",
+        default=False,
+        help=("Skip stages with missing data but no other changes."),
+    )
     repro_parser.add_argument(
         "--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

@@ -35,7 +35,7 @@ def with_value(value, default):
 
 
 class TabularData(MutableSequence[Sequence["CellT"]]):
-    def __init__(self, columns: Sequence[str], fill_value: str = ""):
+    def __init__(self, columns: Sequence[str], fill_value: Optional[str] = ""):
         self._columns: Dict[str, Column] = {name: Column() for name in columns}
         self._keys: List[str] = list(columns)
         self._fill_value = fill_value
@@ -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
@@ -212,11 +207,9 @@ 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
+    def dropna(  # noqa: C901, PLR0912
         self,
         axis: str = "rows",
         how="any",
@@ -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":
@@ -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,
@@ -388,7 +371,7 @@ def diff_table(
     return td
 
 
-def show_diff(
+def show_diff(  # noqa: PLR0913
     diff,
     title: str,
     old: bool = True,

dvc/config.py

@@ -79,9 +79,6 @@ class Config(dict):
         ConfigError: thrown if config has an invalid format.
     """
 
-    APPNAME = "dvc"
-    APPAUTHOR = "iterative"
-
     SYSTEM_LEVELS = ("system", "global")
     REPO_LEVELS = ("repo", "local")
     # In the order they shadow each other
@@ -103,28 +100,32 @@ class Config(dict):
         self.wfs = LocalFileSystem()
         self.fs = fs or self.wfs
 
-        if not dvc_dir:
-            try:
-                from dvc.repo import Repo
-
-                self.dvc_dir = Repo.find_dvc_dir()
-            except NotDvcRepoError:
-                self.dvc_dir = None
-        else:
+        if dvc_dir:
             self.dvc_dir = self.fs.path.abspath(self.fs.path.realpath(dvc_dir))
 
         self.load(validate=validate, config=config)
 
+    @classmethod
+    def from_cwd(cls, fs: Optional["FileSystem"] = None, **kwargs):
+        from dvc.repo import Repo
+
+        try:
+            dvc_dir = Repo.find_dvc_dir(fs=fs)
+        except NotDvcRepoError:
+            dvc_dir = None
+
+        return cls(dvc_dir=dvc_dir, fs=fs, **kwargs)
+
     @classmethod
     def get_dir(cls, level):
-        from appdirs import site_config_dir, user_config_dir
+        from dvc.dirs import global_config_dir, system_config_dir
 
         assert level in ("global", "system")
 
         if level == "global":
-            return user_config_dir(cls.APPNAME, cls.APPAUTHOR)
+            return global_config_dir()
         if level == "system":
-            return site_config_dir(cls.APPNAME, cls.APPAUTHOR)
+            return system_config_dir()
 
     @cached_property
     def files(self) -> Dict[str, str]:
@@ -153,9 +154,7 @@ 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:
@@ -172,10 +171,6 @@ class Config(dict):
         self.clear()
         self.update(conf)
 
-        # Add resolved default cache.dir
-        if not self["cache"].get("dir") and self.dvc_dir:
-            self["cache"]["dir"] = os.path.join(self.dvc_dir, "cache")
-
     def _get_fs(self, level):
         # NOTE: this might be a Gitfs, which doesn't see things outside of
         # the repo.
@@ -376,6 +371,5 @@ 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

@@ -1,8 +1,10 @@
+import logging
 import os
 from urllib.parse import urlparse
 
-from funcy import walk_values
+from funcy import once, walk_values
 from voluptuous import (
+    REMOVE_EXTRA,
     All,
     Any,
     Coerce,
@@ -13,6 +15,8 @@ from voluptuous import (
     Schema,
 )
 
+logger = logging.getLogger(__name__)
+
 Bool = All(
     Lower,
     Any("true", "false"),
@@ -34,14 +38,12 @@ 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
 
 
-def Choices(*choices):
+def Choices(*choices):  # noqa: N802
     """Checks that value belongs to the specified set of values
 
     Args:
@@ -51,7 +53,7 @@ def Choices(*choices):
     return Any(*choices, msg="expected one of {}".format(", ".join(choices)))
 
 
-def ByUrl(mapping):
+def ByUrl(mapping):  # noqa: N802
     schemas = walk_values(Schema, mapping)
 
     def validate(data):
@@ -60,7 +62,9 @@ def ByUrl(mapping):
 
         parsed = urlparse(data["url"])
         # Windows absolute paths should really have scheme == "" (local)
-        if os.name == "nt" and len(parsed.scheme) == 1 and parsed.netloc == "":
+        if os.name == "nt" and len(parsed.scheme) == 1 and not parsed.netloc:
+            return schemas[""](data)
+        if not parsed.netloc:
             return schemas[""](data)
         if parsed.scheme not in schemas:
             raise Invalid(f"Unsupported URL type {parsed.scheme}://")
@@ -74,6 +78,27 @@ class RelPath(str):
     pass
 
 
+class FeatureSchema(Schema):
+    def __init__(self, schema, required=False):
+        super().__init__(schema, required=required, extra=REMOVE_EXTRA)
+
+    @staticmethod
+    @once
+    def _log_deprecated(keys):
+        # only run this once per session
+        message = "%s config option%s unsupported"
+        paths = ", ".join(f"'feature.{key}'" for key in keys)
+        pluralize = " is" if len(keys) == 1 else "s are"
+        logger.warning(message, paths, pluralize)
+
+    def __call__(self, data):
+        ret = super().__call__(data)
+        extra_keys = data.keys() - ret.keys()
+        if extra_keys:
+            self._log_deprecated(sorted(extra_keys))
+        return ret
+
+
 REMOTE_COMMON = {
     "url": str,
     "checksum_jobs": All(Coerce(int), Range(1)),
@@ -125,6 +150,7 @@ SCHEMA = {
         Optional("autostage", default=False): Bool,
         Optional("experiments"): Bool,  # obsoleted
         Optional("check_update", default=True): Bool,
+        "site_cache_dir": str,
         "machine": Lower,
     },
     "cache": {
@@ -189,6 +215,7 @@ SCHEMA = {
                     "timeout": Coerce(int),
                     "gss_auth": Bool,
                     "allow_agent": Bool,
+                    "max_sessions": Coerce(int),
                     Optional("verify", default=False): Bool,
                     **REMOTE_COMMON,
                 },
@@ -248,19 +275,17 @@ SCHEMA = {
         )
     },
     "state": {
-        "dir": str,
+        "dir": str,  # obsoleted
         "row_limit": All(Coerce(int), Range(1)),  # obsoleted
         "row_cleanup_quota": All(Coerce(int), Range(0, 100)),  # obsoleted
     },
     "index": {
-        "dir": str,
+        "dir": str,  # obsoleted
     },
     "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),
@@ -273,11 +298,12 @@ SCHEMA = {
         },
     },
     # section for experimental features
-    "feature": {
-        Optional("machine", default=False): Bool,
-        # enabled by default. It's of no use, kept for backward compatibility.
-        Optional("parametrization", default=True): Bool,
-    },
+    # only specified keys are validated, others get logged and then ignored/removed
+    "feature": FeatureSchema(
+        {
+            Optional("machine", default=False): Bool,
+        },
+    ),
     "plots": {
         "html_template": str,
         Optional("auto_open", default=False): Bool,
@@ -301,4 +327,10 @@ SCHEMA = {
         "config_dir": str,
         "config_name": str,
     },
+    "studio": {
+        "token": str,
+        "url": str,
+        "repo_url": str,
+        Optional("offline", default=False): Bool,
+    },
 }

dvc/daemon.py

@@ -5,7 +5,7 @@ import logging
 import os
 import platform
 import sys
-from subprocess import Popen
+from subprocess import Popen  # nosec B404
 from typing import List
 
 from dvc.env import DVC_DAEMON
@@ -14,19 +14,26 @@ from dvc.utils import fix_env, is_binary
 logger = logging.getLogger(__name__)
 
 
-def _popen(cmd, **kwargs):
+def _suppress_resource_warning(popen: Popen):
+    """Sets the returncode to avoid ResourceWarning when popen is garbage collected."""
+    # only use for daemon processes.
+    # See https://bugs.python.org/issue38890.
+    popen.returncode = 0
+
+
+def _popen(cmd, **kwargs) -> Popen:
     prefix = [sys.executable]
     if not is_binary():
         main_entrypoint = os.path.join(
             os.path.abspath(os.path.dirname(__file__)), "__main__.py"
         )
         prefix += [main_entrypoint]
-    return Popen(prefix + cmd, close_fds=True, shell=False, **kwargs)
+    return Popen(prefix + cmd, close_fds=True, shell=False, **kwargs)  # nosec B603
 
 
 def _spawn_windows(cmd, env):
     if sys.platform == "win32":
-        from subprocess import (
+        from subprocess import (  # nosec B404
             CREATE_NEW_PROCESS_GROUP,
             CREATE_NO_WINDOW,
             STARTF_USESHOWWINDOW,
@@ -40,14 +47,22 @@ def _spawn_windows(cmd, env):
         startupinfo = STARTUPINFO()
         startupinfo.dwFlags |= STARTF_USESHOWWINDOW
 
-        _popen(
+        popen = _popen(
             cmd, env=env, creationflags=creationflags, startupinfo=startupinfo
         )
+        _suppress_resource_warning(popen)
 
 
 def _spawn_posix(cmd, env):
     from dvc.cli import main
 
+    # `fork` will copy buffers, so we need to flush them before forking.
+    # Otherwise, we will get duplicated outputs.
+    if sys.stdout and not sys.stdout.closed:
+        sys.stdout.flush()
+    if sys.stderr and not sys.stderr.closed:
+        sys.stderr.flush()
+
     # NOTE: using os._exit instead of sys.exit, because dvc built
     # with PyInstaller has trouble with SystemExit exception and throws
     # errors such as "[26338] Failed to execute script __main__"
@@ -74,6 +89,7 @@ def _spawn_posix(cmd, env):
     sys.stdin.close()
     sys.stdout.close()
     sys.stderr.close()
+    os.closerange(0, 3)
 
     if platform.system() == "Darwin":
         # workaround for MacOS bug

dvc/dagascii.py

@@ -80,7 +80,7 @@ class AsciiCanvas:
 
         self.canvas[y][x] = char
 
-    def line(self, x0, y0, x1, y1, char):  # noqa: C901
+    def line(self, x0, y0, x1, y1, char):  # noqa: C901, PLR0912
         """Create a line on ASCII canvas.
 
         Args:
@@ -213,8 +213,8 @@ def draw(vertices, edges):
     # pylint: disable=too-many-locals
     # NOTE: coordinates might me negative, so we need to shift
     # everything to the positive plane before we actually draw it.
-    Xs = []  # pylint: disable=invalid-name
-    Ys = []  # pylint: disable=invalid-name
+    Xs = []  # noqa: N806, pylint: disable=invalid-name
+    Ys = []  # noqa: N806, pylint: disable=invalid-name
 
     sug = _build_sugiyama_layout(vertices, edges)
 
@@ -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

@@ -18,10 +18,11 @@ logger = logging.getLogger(__name__)
 
 
 class Remote:
-    def __init__(self, name: str, path: str, fs: "FileSystem", **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: bool = config.pop("worktree", False)
         self.config = config
@@ -34,7 +35,7 @@ class Remote:
         if self.worktree:
             path = self.fs.path.join(path, ".dvc", "cache")
 
-        return get_odb(self.fs, path, **self.config)
+        return get_odb(self.fs, path, hash_name="md5", **self.config)
 
 
 class DataCloud:
@@ -74,19 +75,23 @@ class DataCloud:
                     config["version_aware"] = True
 
             fs = cls(**config)
-            config["tmp_dir"] = self.repo.index_db_dir
-            return Remote(name, fs_path, fs, **config)
+            config["tmp_dir"] = self.repo.site_cache_dir
+            if self.repo.data_index is not None:
+                index = self.repo.data_index.view(("remote", name))
+            else:
+                index = None
+            return Remote(name, fs_path, fs, index=index, **config)
 
         if bool(self.repo.config["remote"]):
             error_msg = (
-                "no remote specified. Setup default remote with\n"
+                f"no remote specified in {self.repo}. Setup default remote with\n"
                 "    dvc remote default <remote name>\n"
                 "or use:\n"
-                "    dvc {} -r <remote name>".format(command)
+                f"    dvc {command} -r <remote name>"
             )
         else:
             error_msg = (
-                "no remote specified. Create a default remote with\n"
+                f"no remote specified in {self.repo}. Create a default remote with\n"
                 "    dvc remote add -d <remote name> <remote url>"
             )
 
@@ -111,8 +116,10 @@ class DataCloud:
                 for hash_info in status.missing
             )
             logger.warning(
-                "Some of the cache files do not exist neither locally "
-                "nor on remote. Missing cache files:\n%s",
+                (
+                    "Some of the cache files do not exist neither locally "
+                    "nor on remote. Missing cache files:\n%s"
+                ),
                 missing_desc,
             )
 
@@ -145,12 +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,
         )
 
@@ -173,11 +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,
         )
@@ -204,12 +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

@@ -90,6 +90,4 @@ def _merge_params(s_list):
 
 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

@@ -2,9 +2,9 @@ import logging
 import os
 import typing
 from collections import defaultdict
-from typing import Dict, cast
+from typing import Dict
 
-import dpath.util
+import dpath
 from voluptuous import Any
 
 from dvc.exceptions import DvcException
@@ -87,17 +87,17 @@ class ParamsDependency(Dependency):
         if flatten:
             for param in self.params:
                 try:
-                    ret[param] = dpath.util.get(config, param, separator=".")
+                    ret[param] = dpath.get(config, param, separator=".")
                 except KeyError:
                     continue
             return ret
 
-        from dpath.util import merge
+        from dpath import merge
 
         for param in self.params:
             merge(
                 ret,
-                dpath.util.search(config, param, separator="."),
+                dpath.search(config, param, separator="."),
                 separator=".",
             )
         return ret
@@ -111,7 +111,8 @@ class ParamsDependency(Dependency):
         from funcy import ldistinct
 
         status: Dict[str, Any] = defaultdict(dict)
-        info = cast(dict, self.hash_info.value) if self.hash_info else {}
+        assert isinstance(self.hash_info.value, dict)
+        info = self.hash_info.value if self.hash_info else {}
         actual = self.read_params()
 
         # NOTE: we want to preserve the order of params as specified in the
@@ -154,9 +155,7 @@ 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

@@ -1,24 +1,14 @@
-import os
-from collections import defaultdict
-from copy import copy
-from typing import TYPE_CHECKING, Dict, Optional, Set, Tuple, Union
+from typing import TYPE_CHECKING, Dict, Optional, Union
 
 from voluptuous import Required
 
-from dvc.prompt import confirm
+from dvc.utils import as_posix
 
 from .base import Dependency
 
 if TYPE_CHECKING:
-    from typing import ContextManager
-
-    from dvc.output import Output
-    from dvc.repo import Repo
+    from dvc.fs import DVCFileSystem
     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
 
 
 class RepoDependency(Dependency):
@@ -35,14 +25,13 @@ 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"] = {}
         super().__init__(stage, *args, **kwargs)
 
+        self.fs = self._make_fs()
+        self.fs_path = as_posix(self.def_path)
+
     def _parse_path(self, fs, fs_path):  # noqa: ARG002
         return None
 
@@ -54,8 +43,8 @@ class RepoDependency(Dependency):
         return f"{self.def_path} ({self.def_repo[self.PARAM_URL]})"
 
     def workspace_status(self):
-        current = self.get_obj(locked=True).hash_info
-        updated = self.get_obj(locked=False).hash_info
+        current = self._make_fs(locked=True).repo.get_rev()
+        updated = self._make_fs(locked=False).repo.get_rev()
 
         if current != updated:
             return {str(self): "update available"}
@@ -66,33 +55,18 @@ class RepoDependency(Dependency):
         return self.workspace_status()
 
     def save(self):
-        pass
+        rev = self.fs.repo.get_rev()
+        if self.def_repo.get(self.PARAM_REV_LOCK) is None:
+            self.def_repo[self.PARAM_REV_LOCK] = rev
 
     def dumpd(self, **kwargs) -> Dict[str, Union[str, Dict[str, str]]]:
         return {self.PARAM_PATH: self.def_path, self.PARAM_REPO: self.def_repo}
 
-    def download(self, to: "Output", jobs: Optional[int] = None):
-        from dvc_data.hashfile.checkout import checkout
-
-        for odb, objs in self.get_used_objs().items():
-            self.repo.cloud.pull(objs, jobs=jobs, odb=odb)
-
-        obj = self.get_obj()
-        checkout(
-            to.fs_path,
-            to.fs,
-            obj,
-            self.repo.odb.local,
-            ignore=None,
-            state=self.repo.state,
-            prompt=confirm,
-        )
-
     def update(self, rev: Optional[str] = None):
         if rev:
             self.def_repo[self.PARAM_REV] = rev
-        with self._make_repo(locked=False) as repo:
-            self.def_repo[self.PARAM_REV_LOCK] = repo.get_rev()
+        self.fs = self._make_fs(rev=rev, locked=False)
+        self.def_repo[self.PARAM_REV_LOCK] = self.fs.repo.get_rev()
 
     def changed_checksum(self) -> bool:
         # From current repo point of view what describes RepoDependency is its
@@ -100,138 +74,21 @@ class RepoDependency(Dependency):
         # immutable, hence its impossible for checksum to change.
         return False
 
-    def get_used_objs(
-        self, **kwargs
-    ) -> Dict[Optional["ObjectDB"], Set["HashInfo"]]:
-        used, _, _ = self._get_used_and_obj(**kwargs)
-        return used
+    def _make_fs(
+        self, rev: Optional[str] = None, locked: bool = True
+    ) -> "DVCFileSystem":
+        from dvc.fs import DVCFileSystem
 
-    def _get_used_and_obj(
-        self, obj_only: bool = False, **kwargs
-    ) -> 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
+        config = {"cache": self.repo.config["cache"]}
+        config["cache"]["dir"] = self.repo.cache.local.path
 
-        local_odb = self.repo.odb.local
-        locked = kwargs.pop("locked", True)
-        with self._make_repo(locked=locked, cache_dir=local_odb.path) as repo:
-            used_obj_ids = defaultdict(set)
-            rev = repo.get_rev()
-            if locked and self.def_repo.get(self.PARAM_REV_LOCK) is None:
-                self.def_repo[self.PARAM_REV_LOCK] = rev
-
-            if not obj_only:
-                try:
-                    for odb, obj_ids in repo.used_objs(
-                        [os.path.join(repo.root_dir, self.def_path)],
-                        force=True,
-                        jobs=kwargs.get("jobs"),
-                        recursive=True,
-                    ).items():
-                        if odb is None:
-                            odb = repo.cloud.get_remote_odb()
-                            odb.read_only = True
-                        self._check_circular_import(odb, obj_ids)
-                        used_obj_ids[odb].update(obj_ids)
-                except (NoRemoteError, NoOutputOrStageError):
-                    pass  # noqa: S110
-
-            try:
-                object_store, meta, obj = build(
-                    local_odb,
-                    as_posix(self.def_path),
-                    repo.dvcfs,
-                    local_odb.fs.PARAM_CHECKSUM,
-                )
-            except (FileNotFoundError, TreeError) as exc:
-                raise PathMissingError(
-                    self.def_path, self.def_repo[self.PARAM_URL]
-                ) from exc
-            object_store = copy(object_store)
-            object_store.read_only = True
-
-            self._objs[rev] = obj
-            self._meta[rev] = meta
-
-            used_obj_ids[object_store].add(obj.hash_info)
-            if isinstance(obj, Tree):
-                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:
-        from dvc.exceptions import CircularImportError
-        from dvc.fs.dvc import DVCFileSystem
-        from dvc_data.hashfile.db.reference import ReferenceHashFileDB
-        from dvc_data.hashfile.tree import Tree
-
-        if not isinstance(odb, ReferenceHashFileDB):
-            return
-
-        def iter_objs():
-            for hash_info in obj_ids:
-                if hash_info.isdir:
-                    tree = Tree.load(odb, hash_info)
-                    yield from (odb.get(hi.value) for _, _, hi in tree)
-                else:
-                    assert hash_info.value
-                    yield odb.get(hash_info.value)
-
-        checked_urls = set()
-        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
-            ):
-                continue
-            self_url = self.repo.url or self.repo.root_dir
-            if (
-                obj.fs.repo_url is not None
-                and obj.fs.repo_url == self_url
-                or obj.fs.repo.root_dir == self.repo.root_dir
-            ):
-                raise CircularImportError(self, obj.fs.repo_url, self_url)
-            checked_urls.update([obj.fs.repo_url, obj.fs.repo.root_dir])
-
-    def get_obj(self, filter_info=None, **kwargs):
-        locked = kwargs.get("locked", True)
-        rev = self._get_rev(locked=locked)
-        if rev in self._objs:
-            return self._objs[rev]
-        _, _, obj = self._get_used_and_obj(
-            obj_only=True, filter_info=filter_info, **kwargs
+        return DVCFileSystem(
+            url=self.def_repo[self.PARAM_URL],
+            rev=rev or self._get_rev(locked=locked),
+            subrepos=True,
+            config=config,
         )
-        return obj
-
-    def get_meta(self, filter_info=None, **kwargs):
-        locked = kwargs.get("locked", True)
-        rev = self._get_rev(locked=locked)
-        if rev in self._meta:
-            return self._meta[rev]
-        _, meta, _ = self._get_used_and_obj(
-            obj_only=True, filter_info=filter_info, **kwargs
-        )
-        return meta
-
-    def _make_repo(
-        self, locked: bool = True, **kwargs
-    ) -> "ContextManager[Repo]":
-        from dvc.external_repo import external_repo
-
-        d = self.def_repo
-        rev = self._get_rev(locked=locked)
-        return external_repo(d[self.PARAM_URL], rev=rev, **kwargs)
 
     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/dirs.py

@@ -0,0 +1,26 @@
+import os
+
+import platformdirs
+
+from . import env
+
+APPNAME = "dvc"
+APPAUTHOR = "iterative"
+
+
+def system_config_dir():
+    return os.getenv(env.DVC_SYSTEM_CONFIG_DIR) or platformdirs.site_config_dir(
+        APPNAME, APPAUTHOR
+    )
+
+
+def global_config_dir():
+    return os.getenv(env.DVC_SYSTEM_CONFIG_DIR) or platformdirs.user_config_dir(
+        APPNAME, APPAUTHOR
+    )
+
+
+def site_cache_dir():
+    return os.getenv(env.DVC_SITE_CACHE_DIR) or platformdirs.site_cache_dir(
+        APPNAME, APPAUTHOR, opinion=True
+    )

dvc/dvcfile.py

@@ -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):
@@ -193,11 +187,12 @@ class FileMixin:
 
 class SingleStageFile(FileMixin):
     from dvc.schema import COMPILED_SINGLE_STAGE_SCHEMA as SCHEMA
-    from dvc.stage.loader import SingleStageLoader as LOADER
+    from dvc.stage.loader import SingleStageLoader as LOADER  # noqa: N814
 
     metrics: List[str] = []
     plots: Any = {}
     params: List[str] = []
+    artifacts: Dict[str, Optional[Dict[str, Any]]] = {}
 
     @property
     def stage(self) -> "Stage":
@@ -237,7 +232,7 @@ class ProjectFile(FileMixin):
     """Abstraction for pipelines file, .yaml + .lock combined."""
 
     from dvc.schema import COMPILED_MULTI_STAGE_SCHEMA as SCHEMA
-    from dvc.stage.loader import StageLoader as LOADER
+    from dvc.stage.loader import StageLoader as LOADER  # noqa: N814
 
     @property
     def _lockfile(self):
@@ -271,9 +266,7 @@ 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)
@@ -286,9 +279,7 @@ 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]
@@ -300,9 +291,7 @@ 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]:
@@ -335,6 +324,10 @@ class ProjectFile(FileMixin):
     def params(self) -> List[str]:
         return self.contents.get("params", [])
 
+    @property
+    def artifacts(self) -> Dict[str, Optional[Dict[str, Any]]]:
+        return self.contents.get("artifacts", {})
+
     def remove(self, force=False):
         if not force:
             logger.warning("Cannot remove pipeline file.")
@@ -366,10 +359,7 @@ 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,
@@ -381,7 +371,7 @@ def get_lockfile_schema(d):
 
 
 def migrate_lock_v1_to_v2(d, version_info):
-    stages = {k: v for k, v in d.items()}
+    stages = dict(d)
 
     for key in stages:
         d.pop(key)
@@ -422,15 +412,12 @@ 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:
-                    data.update(self.latest_version_info)
-                    # order is important, meta should always be at the top
-                    logger.info("Generating lock file '%s'", self.relpath)
+            elif not data:
+                data.update(self.latest_version_info)
+                # order is important, meta should always be at the top
+                logger.info("Generating lock file '%s'", self.relpath)
 
             data["stages"] = data.get("stages", {})
             modified = data["stages"].get(stage.name, {}) != stage_data.get(

dvc/env.py

@@ -1,11 +1,19 @@
+DVCLIVE_RESUME = "DVCLIVE_RESUME"
 DVC_CHECKPOINT = "DVC_CHECKPOINT"
 DVC_DAEMON = "DVC_DAEMON"
+DVC_EXP_AUTO_PUSH = "DVC_EXP_AUTO_PUSH"
+DVC_EXP_BASELINE_REV = "DVC_EXP_BASELINE_REV"
+DVC_EXP_GIT_REMOTE = "DVC_EXP_GIT_REMOTE"
+DVC_EXP_NAME = "DVC_EXP_NAME"
+DVC_GLOBAL_CONFIG_DIR = "DVC_GLOBAL_CONFIG_DIR"
+DVC_IGNORE_ISATTY = "DVC_IGNORE_ISATTY"
+DVC_NO_ANALYTICS = "DVC_NO_ANALYTICS"
 DVC_PAGER = "DVC_PAGER"
 DVC_ROOT = "DVC_ROOT"
-DVCLIVE_RESUME = "DVCLIVE_RESUME"
-DVC_IGNORE_ISATTY = "DVC_IGNORE_ISATTY"
-DVC_EXP_BASELINE_REV = "DVC_EXP_BASELINE_REV"
-DVC_EXP_NAME = "DVC_EXP_NAME"
-DVC_EXP_GIT_REMOTE = "DVC_EXP_GIT_REMOTE"
-DVC_EXP_AUTO_PUSH = "DVC_EXP_AUTO_PUSH"
-DVC_NO_ANALYTICS = "DVC_NO_ANALYTICS"
+DVC_SHOW_TRACEBACK = "DVC_SHOW_TRACEBACK"
+DVC_SITE_CACHE_DIR = "DVC_SITE_CACHE_DIR"
+DVC_STUDIO_OFFLINE = "DVC_STUDIO_OFFLINE"
+DVC_STUDIO_REPO_URL = "DVC_STUDIO_REPO_URL"
+DVC_STUDIO_TOKEN = "DVC_STUDIO_TOKEN"  # noqa: S105 # nosec B105
+DVC_STUDIO_URL = "DVC_STUDIO_URL"
+DVC_SYSTEM_CONFIG_DIR = "DVC_SYSTEM_CONFIG_DIR"

dvc/exceptions.py

@@ -1,4 +1,5 @@
 """Exceptions raised by the dvc."""
+import errno
 from typing import Dict, List
 
 from dvc.utils import format_link
@@ -31,14 +32,19 @@ class OutputDuplicationError(DvcException):
 
         assert isinstance(output, str)
         assert all(hasattr(stage, "relpath") for stage in stages)
+        msg = ""
+        stage_names = [s.addressing for s in stages]
+        stages_str = " ".join(stage_names)
         if len(stages) == 1:
-            msg = "output '{}' is already specified in {}.".format(
-                output, first(stages)
-            )
+            stage_name = first(stages)
+            msg = f"output '{output}' is already specified in {stage_name}."
         else:
             msg = "output '{}' is already specified in stages:\n{}".format(
-                output, "\n".join(f"\t- {s.addressing}" for s in stages)
+                output, "\n".join(f"\t- {s}" for s in stage_names)
             )
+        msg += (
+            f"\nUse `dvc remove {stages_str}` to stop tracking the overlapping output."
+        )
         super().__init__(msg)
         self.stages = stages
         self.output = output
@@ -150,8 +156,9 @@ 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 +184,7 @@ 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):
@@ -202,13 +207,23 @@ class ETagMismatchError(DvcException):
         )
 
 
+class FileExistsLocallyError(FileExistsError, DvcException):
+    def __init__(self, path, hint=None):
+        import os.path
+
+        self.path = path
+        hint = "" if hint is None else f". {hint}"
+        path_typ = "directory" if os.path.isdir(path) else "file"
+        msg = f"The {path_typ} '{path}' already exists locally{hint}"
+        super().__init__(msg)
+        self.errno = errno.EEXIST
+
+
 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 +265,7 @@ 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 +290,7 @@ 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 +306,6 @@ class URLMissingError(DvcException):
 
 class RemoteCacheRequiredError(DvcException):
     def __init__(self, scheme, fs_path):
-
         super().__init__(
             (
                 "Current operation was unsuccessful because '{}' requires "
@@ -319,8 +330,7 @@ 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 +339,8 @@ 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):
@@ -344,14 +351,6 @@ class CacheLinkError(DvcException):
         self.fs_paths = fs_paths
 
 
-class CircularImportError(DvcException):
-    def __init__(self, dep, a, b):
-        super().__init__(
-            f"'{dep}' contains invalid circular import. "
-            f"DVC repo '{a}' already imports from '{b}'."
-        )
-
-
 class PrettyDvcException(DvcException):
     def __pretty_exc__(self, **kwargs):
         """Print prettier exception message."""

dvc/fs/__init__.py

@@ -6,7 +6,6 @@ from dvc.config import ConfigError as RepoConfigError
 from dvc.config_schema import SCHEMA, Invalid
 
 # pylint: disable=unused-import
-from dvc_objects.fs import utils  # noqa: F401
 from dvc_objects.fs import (  # noqa: F401
     LocalFileSystem,
     MemoryFileSystem,
@@ -17,6 +16,7 @@ from dvc_objects.fs import (  # noqa: F401
     localfs,
     registry,
     system,
+    utils,
 )
 from dvc_objects.fs.base import AnyFSPath, FileSystem  # noqa: F401
 from dvc_objects.fs.errors import (  # noqa: F401
@@ -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)
@@ -123,7 +121,7 @@ def _get_cloud_fs(repo_config, **kwargs):
 
     remote_conf = get_fs_config(repo_config, **kwargs)
     try:
-        remote_conf = SCHEMA["remote"][str](remote_conf)
+        remote_conf = SCHEMA["remote"][str](remote_conf)  # type: ignore[index]
     except Invalid as exc:
         raise RepoConfigError(str(exc)) from None
 

dvc/fs/callbacks.py

@@ -1,6 +1,6 @@
 # pylint: disable=unused-import
 from contextlib import ExitStack
-from typing import TYPE_CHECKING, Any, BinaryIO, Dict, Optional, Union, cast
+from typing import TYPE_CHECKING, Any, BinaryIO, Dict, Optional, Union
 
 from dvc.utils.objects import cached_property
 from dvc_objects.fs.callbacks import (  # noqa: F401
@@ -54,13 +54,12 @@ class RichCallback(Callback):
             disable=self.disable,
             console=ui.error_console,
         )
-        return cast(RichTransferProgress, self._stack.enter_context(progress))
+        self._stack.enter_context(progress)
+        return progress
 
     @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

dvc/fs/dvc.py

@@ -6,16 +6,7 @@ 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
@@ -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)
@@ -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):
@@ -266,12 +251,15 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         try:
             return self.repo.fs.open(fs_path, mode=mode)
         except FileNotFoundError:
-            _, dvc_fs, subkey = self._get_subrepo_info(key)
+            repo, dvc_fs, subkey = self._get_subrepo_info(key)
             if not dvc_fs:
                 raise
 
         dvc_path = _get_dvc_path(dvc_fs, subkey)
-        return dvc_fs.open(dvc_path, mode=mode)
+        kw = {}
+        if kwargs.get("cache_remote_stream", False):
+            kw["cache_odb"] = repo.cache.local
+        return dvc_fs.open(dvc_path, mode=mode, **kw)
 
     def isdvc(self, path, **kwargs) -> bool:
         """Is this entry dvc-tracked?"""
@@ -280,19 +268,22 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         dvc_path = _get_dvc_path(dvc_fs, subkey)
         return dvc_fs is not None and dvc_fs.isdvc(dvc_path, **kwargs)
 
-    def ls(  # pylint: disable=arguments-differ
+    def ls(  # pylint: disable=arguments-differ # noqa: C901
         self, path, detail=True, dvc_only=False, **kwargs
     ):
         key = self._get_key_from_relative(path)
         repo, dvc_fs, subkey = self._get_subrepo_info(key)
 
+        dvc_exists = False
         dvc_infos = {}
         if dvc_fs:
+            dvc_path = _get_dvc_path(dvc_fs, subkey)
             with suppress(FileNotFoundError):
-                dvc_path = _get_dvc_path(dvc_fs, subkey)
                 for info in dvc_fs.ls(dvc_path, detail=True):
                     dvc_infos[dvc_fs.path.name(info["name"])] = info
+            dvc_exists = bool(dvc_infos) or dvc_fs.exists(dvc_path)
 
+        fs_exists = False
         fs_infos = {}
         ignore_subrepos = kwargs.get("ignore_subrepos", True)
         if not dvc_only:
@@ -304,13 +295,20 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
                 ):
                     fs_infos[fs.path.name(info["name"])] = info
             except (FileNotFoundError, NotADirectoryError):
-                pass  # noqa: S110
+                pass
+
+            fs_exists = bool(fs_infos) or fs.exists(fs_path)
 
         dvcfiles = kwargs.get("dvcfiles", False)
 
         infos = []
         paths = []
         names = set(dvc_infos.keys()) | set(fs_infos.keys())
+
+        if not names and (dvc_exists or fs_exists):
+            # broken symlink or TreeError
+            raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), path)
+
         for name in names:
             if not dvcfiles and _is_dvc_file(name):
                 continue
@@ -331,7 +329,7 @@ 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
+    def _info(  # noqa: C901, PLR0912
         self, key, path, ignore_subrepos=True, check_ignored=True
     ):
         repo, dvc_fs, subkey = self._get_subrepo_info(key)
@@ -376,6 +374,19 @@ class _DVCFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         info["name"] = path
         return info
 
+    def get_file(self, rpath, lpath, **kwargs):  # pylint: disable=arguments-differ
+        key = self._get_key_from_relative(rpath)
+        fs_path = self._from_key(key)
+        try:
+            return self.repo.fs.get_file(fs_path, lpath, **kwargs)
+        except FileNotFoundError:
+            _, dvc_fs, subkey = self._get_subrepo_info(key)
+            if not dvc_fs:
+                raise
+
+        dvc_path = _get_dvc_path(dvc_fs, subkey)
+        return dvc_fs.get_file(dvc_path, lpath, **kwargs)
+
 
 class DVCFileSystem(FileSystem):
     protocol = "local"

dvc/ignore.py

@@ -30,9 +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
@@ -40,20 +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
         ]
 
@@ -64,9 +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("#"))
             ]
 
@@ -158,9 +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):
@@ -249,9 +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
@@ -409,9 +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(
@@ -433,9 +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

@@ -19,7 +19,6 @@ SUBPROJECTS = (
     "dvc_objects",
     "dvc_render",
     "dvc_task",
-    "dvclive",
     "scmrepo",
 )
 package = "" if PKG is None else f" ({PKG})"
@@ -30,10 +29,10 @@ def get_dvc_info():
     info = [
         dvc_version,
         "-" * len(dvc_version),
-        f"Platform: Python {platform.python_version()} on "
-        f"{platform.platform()}",
+        f"Platform: Python {platform.python_version()} on {platform.platform()}",
         f"Subprojects:{_get_subprojects()}",
         f"Supports:{_get_supported_remotes()}",
+        f"Config:{_get_config_dirs()}",
     ]
 
     try:
@@ -42,20 +41,21 @@ 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
-            fs_root = get_fs_type(os.path.abspath(root_directory))
+            fs_root = _get_fs_type(os.path.abspath(root_directory))
             info.append(f"Workspace directory: {fs_root}")
             info.append(f"Repo: {_get_dvc_repo_info(repo)}")
+            info.append(f"Repo.site_cache_dir: {repo.site_cache_dir}")
     except NotDvcRepoError:
         pass
     except SCMError:
@@ -85,7 +85,7 @@ 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"],
@@ -125,8 +125,7 @@ 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
@@ -138,10 +137,21 @@ def _get_supported_remotes():
     return "\n\t" + ",\n\t".join(supported_remotes)
 
 
-def get_fs_type(path):
+def _get_config_dirs():
+    from dvc.config import Config
+
+    dirs = [
+        f"Global: {Config.get_dir('global')}",
+        f"System: {Config.get_dir('system')}",
+    ]
+
+    return "\n\t" + "\n\t".join(dirs)
+
+
+def _get_fs_type(path):
     partition = {}
     for part in psutil.disk_partitions(all=True):
-        if part.fstype != "":
+        if part.fstype:
             try:
                 mountpoint = pathlib.Path(part.mountpoint).resolve()
                 partition[mountpoint] = part.fstype + " on " + part.device
@@ -157,11 +167,11 @@ def get_fs_type(path):
     return ("unknown", "none")
 
 
-def _get_dvc_repo_info(self):
-    if self.config.get("core", {}).get("no_scm", False):
+def _get_dvc_repo_info(repo):
+    if repo.config.get("core", {}).get("no_scm", False):
         return "dvc (no_scm)"
 
-    if self.root_dir != self.scm.root_dir:
+    if repo.root_dir != repo.scm.root_dir:
         return "dvc (subdir), git"
 
     return "dvc, git"

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)
@@ -193,7 +187,9 @@ class HardlinkLock(flufl.lock.Lock, LockBase):
 
         if self._tmp_dir is not None:
             # Under Windows file path length is limited so we hash it
-            hasher = hashlib.md5(self._claimfile.encode())  # noqa: S324
+            hasher = hashlib.md5(  # nosec B324, B303  # noqa: S324
+                self._claimfile.encode()
+            )
             filename = hasher.hexdigest()
             self._claimfile = os.path.join(self._tmp_dir, filename + ".lock")
 

dvc/logger.py

@@ -1,63 +1,57 @@
 """Manages logging configuration for DVC repo."""
 
+import logging
 import logging.config
 import logging.handlers
+import os
+import sys
 
 import colorama
 
+from dvc.env import DVC_SHOW_TRACEBACK
 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):
+def add_logging_level(level_name, level_num, method_name=None):
     """
     Adds a new logging level to the `logging` module and the
     currently configured logging class.
 
-    Uses the existing numeric levelNum if already defined.
+    Uses the existing numeric level_num if already defined.
 
     Based on https://stackoverflow.com/questions/2183233
     """
-    if methodName is None:
-        methodName = levelName.lower()
+    if method_name is None:
+        method_name = level_name.lower()
 
     # If the level name is already defined as a top-level `logging`
     # constant, then adopt the existing numeric level.
-    if hasattr(logging, levelName):
-        existingLevelNum = getattr(logging, levelName)
-        assert isinstance(existingLevelNum, int)
-        levelNum = existingLevelNum
+    if hasattr(logging, level_name):
+        existing_level_num = getattr(logging, level_name)
+        assert isinstance(existing_level_num, int)
+        level_num = existing_level_num
 
-    def logForLevel(self, message, *args, **kwargs):
-        if self.isEnabledFor(levelNum):
+    def log_for_level(self, message, *args, **kwargs):
+        if self.isEnabledFor(level_num):
             # pylint: disable=protected-access
-            self._log(levelNum, message, args, **kwargs)
+            self._log(level_num, message, args, **kwargs)
 
-    def logToRoot(message, *args, **kwargs):
-        logging.log(levelNum, message, *args, **kwargs)
+    def log_to_root(message, *args, **kwargs):
+        logging.log(level_num, message, *args, **kwargs)
 
     # getLevelName resolves the numeric log level if already defined,
     # otherwise returns a string
-    if not isinstance(logging.getLevelName(levelName), int):
-        logging.addLevelName(levelNum, levelName)
+    if not isinstance(logging.getLevelName(level_name), int):
+        logging.addLevelName(level_num, level_name)
 
-    if not hasattr(logging, levelName):
-        setattr(logging, levelName, levelNum)
+    if not hasattr(logging, level_name):
+        setattr(logging, level_name, level_num)
 
-    if not hasattr(logging.getLoggerClass(), methodName):
-        setattr(logging.getLoggerClass(), methodName, logForLevel)
+    if not hasattr(logging.getLoggerClass(), method_name):
+        setattr(logging.getLoggerClass(), method_name, log_for_level)
 
-    if not hasattr(logging, methodName):
-        setattr(logging, methodName, logToRoot)
+    if not hasattr(logging, method_name):
+        setattr(logging, method_name, log_to_root)
 
 
 class LoggingException(Exception):
@@ -66,12 +60,11 @@ class LoggingException(Exception):
         super().__init__(msg)
 
 
-def excludeFilter(level):
-    class ExcludeLevelFilter(logging.Filter):
-        def filter(self, record):  # noqa: A003
-            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 +79,8 @@ 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,
@@ -94,51 +88,53 @@ class ColorFormatter(logging.Formatter):
         "CRITICAL": colorama.Fore.RED,
     }
 
-    def format(self, record):  # noqa: A003
+    def __init__(self, log_colors: bool = True, show_traceback: bool = False) -> None:
+        super().__init__()
+        self.log_colors = log_colors
+        self.show_traceback = show_traceback
+
+    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 = ""
+        verbose = _is_verbose()
+        if verbose:
+            asctime = self.formatTime(record, self.datefmt)
+        if verbose or self.show_traceback:
+            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):
-    def handleError(self, record):
+    def handleError(self, record):  # noqa: N802
         super().handleError(record)
         raise LoggingException(record)
 
@@ -155,13 +151,12 @@ class LoggerHandler(logging.StreamHandler):
                         self.emit_pretty_exception(exc, verbose=_is_verbose())
                         if not _is_verbose():
                             return
-                    except Exception:  # noqa, pylint: disable=broad-except
-                        pass  # noqa: S110
+                    # pylint: disable-next=broad-except
+                    except Exception:  # noqa: BLE001, S110  # nosec B110
+                        pass
 
             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 +166,7 @@ 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 +176,47 @@ 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))
+
+    add_logging_level("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))
+
+    show_traceback = bool(os.environ.get(DVC_SHOW_TRACEBACK))
+    err_formatter = ColorFormatter(
+        log_colors=log_colors and sys.stderr.isatty(), show_traceback=show_traceback
+    )
+    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 +227,3 @@ 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

@@ -67,9 +67,7 @@ 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
 

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

@@ -1,7 +1,11 @@
+import errno
 import logging
 import os
+import posixpath
 from collections import defaultdict
-from typing import TYPE_CHECKING, Dict, List, Optional, Set, Tuple, Type, cast
+from contextlib import suppress
+from operator import itemgetter
+from typing import TYPE_CHECKING, Dict, List, Optional, Set, Tuple, Type, Union
 from urllib.parse import urlparse
 
 from funcy import collecting, first, project
@@ -18,21 +22,21 @@ from dvc.exceptions import (
     RemoteCacheRequiredError,
 )
 from dvc.utils.objects import cached_property
-from dvc_data.hashfile import Tree
 from dvc_data.hashfile import check as ocheck
 from dvc_data.hashfile import load as oload
 from dvc_data.hashfile.build import build
 from dvc_data.hashfile.checkout import checkout
+from dvc_data.hashfile.db import HashFileDB, add_update_tree
 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_data.hashfile.tree import Tree, du
 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
+from .fs.callbacks import DEFAULT_CALLBACK, Callback, TqdmCallback
 from .utils import relpath
 from .utils.fs import path_isin
 
@@ -41,7 +45,6 @@ if TYPE_CHECKING:
     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__)
@@ -151,9 +154,7 @@ def _merge_data(s_list):
             d[key].update({})
             continue
         if not isinstance(key, dict):
-            raise ValueError(  # noqa: TRY004
-                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):
@@ -231,6 +232,17 @@ def merge_file_meta_from_cloud(entry: Dict) -> Dict:
     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"
@@ -264,6 +276,11 @@ class OutputIsIgnoredError(DvcException):
         super().__init__(f"Path '{match.file}' is ignored by\n{lines}")
 
 
+class CheckoutCallback(TqdmCallback):
+    # disable branching for checkouts
+    branch = Callback.branch  # type: ignore[assignment]
+
+
 class Output:
     IS_DEPENDENCY = False
 
@@ -301,7 +318,7 @@ class Output:
     IsStageFileError: Type[DvcException] = OutputIsStageFileError
     IsIgnoredError: Type[DvcException] = OutputIsIgnoredError
 
-    def __init__(
+    def __init__(  # noqa: PLR0913
         self,
         stage,
         path,
@@ -336,9 +353,7 @@ class Output:
         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 (
@@ -385,6 +400,7 @@ 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:
@@ -407,11 +423,14 @@ class Output:
     def _compute_meta_hash_info_from_files(self) -> None:
         if self.files:
             tree = Tree.from_list(self.files, hash_name=self.hash_name)
-            tree.digest()
+            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.size = sum(filter(None, (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
@@ -491,17 +510,17 @@ 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):
@@ -510,9 +529,9 @@ 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,
@@ -554,26 +573,6 @@ class Output:
             key = self.fs.path.parts(no_drive)[1:]
         return workspace, key
 
-    def get_entry(self) -> "DataIndexEntry":
-        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,
-        )
-        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()
 
@@ -586,7 +585,7 @@ class Output:
             return True
 
         try:
-            ocheck(self.odb, obj)
+            ocheck(self.cache, obj)
             return False
         except (FileNotFoundError, ObjectFormatError):
             return True
@@ -675,7 +674,7 @@ class Output:
 
         if self.use_cache:
             _, self.meta, self.obj = build(
-                self.odb,
+                self.cache,
                 self.fs_path,
                 self.fs,
                 self.hash_name,
@@ -683,7 +682,7 @@ class Output:
             )
         else:
             _, self.meta, self.obj = build(
-                self.repo.odb.local,
+                self.repo.cache.local,
                 self.fs_path,
                 self.fs,
                 self.hash_name,
@@ -691,16 +690,14 @@ 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
@@ -716,7 +713,7 @@ class Output:
         except _CheckoutError as exc:
             raise CheckoutError(exc.paths, {})  # noqa: B904
 
-    def commit(self, filter_info=None) -> None:
+    def commit(self, filter_info=None, relink=True) -> None:
         if not self.exists:
             raise self.DoesNotExistError(self)
 
@@ -724,15 +721,16 @@ 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
             )
+            # NOTE: trying to use hardlink during transfer only if we will be
+            # relinking later
+            hardlink = relink
             if granular:
-                obj = self._commit_granular_dir(filter_info)
+                obj = self._commit_granular_dir(filter_info, hardlink)
             else:
                 staging, _, obj = build(
-                    self.odb,
+                    self.cache,
                     filter_info or self.fs_path,
                     self.fs,
                     self.hash_name,
@@ -740,46 +738,49 @@ class Output:
                 )
                 otransfer(
                     staging,
-                    self.odb,
+                    self.cache,
                     {obj.hash_info},
                     shallow=False,
-                    hardlink=True,
+                    hardlink=hardlink,
                 )
-            self._checkout(
-                filter_info or self.fs_path,
-                self.fs,
-                obj,
-                self.odb,
-                relink=True,
-                state=self.repo.state,
-                prompt=prompt.confirm,
-            )
-            self.set_exec()
+            if relink:
+                rel = self.fs.path.relpath(filter_info or self.fs_path)
+                with CheckoutCallback(desc=f"Checking out {rel}", unit="files") as cb:
+                    self._checkout(
+                        filter_info or self.fs_path,
+                        self.fs,
+                        obj,
+                        self.cache,
+                        relink=True,
+                        state=self.repo.state,
+                        prompt=prompt.confirm,
+                        progress_callback=cb,
+                    )
+                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)
-        )
-        staging, _, save_obj = build(
-            self.odb,
+    def _commit_granular_dir(self, filter_info, hardlink) -> Optional["HashFile"]:
+        prefix = self.fs.path.parts(self.fs.path.relpath(filter_info, self.fs_path))
+        staging, _, obj = build(
+            self.cache,
             self.fs_path,
             self.fs,
             self.hash_name,
             ignore=self.dvcignore,
         )
-        save_obj = cast(Tree, save_obj)
-        save_obj = cast(Tree, save_obj.filter(prefix))
-        checkout_obj = save_obj.get_obj(self.odb, prefix)
+        assert isinstance(obj, Tree)
+        save_obj = obj.filter(prefix)
+        assert isinstance(save_obj, Tree)
+        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,
+            hardlink=hardlink,
         )
         return checkout_obj
 
-    def dumpd(self, **kwargs):  # noqa: C901
+    def dumpd(self, **kwargs):  # noqa: C901, PLR0912
         ret: Dict[str, Any] = {}
         with_files = (
             (not self.IS_DEPENDENCY or self.stage.is_import)
@@ -794,9 +795,7 @@ class Output:
             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
 
@@ -835,18 +834,16 @@ class Output:
         if with_files:
             obj = self.obj or self.get_obj()
             if obj:
-                obj = cast("Tree", obj)
+                assert isinstance(obj, Tree)
                 ret[self.PARAM_FILES] = [
                     split_file_meta_from_cloud(f)
-                    for f in obj.as_list(with_meta=True)
+                    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
 
@@ -869,16 +866,15 @@ 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
 
@@ -886,8 +882,8 @@ class Output:
         fs_path = self.fs.path
         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)
+            assert isinstance(obj, Tree)
+            obj = obj.get_obj(self.cache, prefix)
 
         return obj
 
@@ -901,11 +897,16 @@ class Output:
         checkpoint_reset: bool = False,
         **kwargs,
     ) -> Optional[Tuple[bool, Optional[bool]]]:
+        # callback passed act as a aggregate callback.
+        # do not let checkout to call set_size and change progressbar.
+        class CallbackProxy(Callback):
+            def relative_update(self, inc: int = 1) -> None:
+                progress_callback.relative_update(inc)
+                return super().relative_update(inc)
+
+        callback = CallbackProxy()
         if not self.use_cache:
-            if progress_callback != DEFAULT_CALLBACK:
-                progress_callback.relative_update(
-                    self.get_files_number(filter_info)
-                )
+            callback.relative_update(self.get_files_number(filter_info))
             return None
 
         obj = self.get_obj(filter_info=filter_info)
@@ -925,9 +926,9 @@ class Output:
                 filter_info or self.fs_path,
                 self.fs,
                 obj,
-                self.odb,
+                self.cache,
                 force=force,
-                progress_callback=progress_callback,
+                progress_callback=callback,
                 relink=relink,
                 state=self.repo.state,
                 prompt=prompt.confirm,
@@ -966,7 +967,7 @@ 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)
@@ -1018,29 +1019,33 @@ 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):
+    def get_dir_cache(self, **kwargs) -> Optional["Tree"]:
         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
-            self.repo.cloud.pull([obj.hash_info], **kwargs)
+            with suppress(Exception):
+                self.repo.cloud.pull([obj.hash_info], **kwargs)
 
         if self.obj:
+            assert isinstance(self.obj, Tree)
             return self.obj
 
         try:
-            self.obj = oload(self.odb, self.hash_info)
+            obj = oload(self.cache, self.hash_info)
+            assert isinstance(obj, Tree)
         except (FileNotFoundError, ObjectFormatError):
-            self.obj = None
+            obj = None
 
-        return self.obj
+        self.obj = obj
+        return obj
 
     def _collect_used_dir_cache(
         self, remote=None, force=False, jobs=None, filter_info=None
@@ -1055,7 +1060,7 @@ 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 '{}'. "
@@ -1070,14 +1075,12 @@ class Output:
             return None
 
         obj = self.get_obj()
+        assert obj is None or isinstance(obj, Tree)
         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)
-            )
-            obj = cast(Tree, obj)
+            prefix = self.fs.path.parts(self.fs.path.relpath(filter_info, self.fs_path))
             return obj.filter(prefix)
-        return cast(Tree, obj)
+        return obj
 
     def get_used_objs(  # noqa: C901
         self, **kwargs
@@ -1089,9 +1092,7 @@ class Output:
 
         push: bool = kwargs.pop("push", False)
         if self.stage.is_repo_import:
-            if push:
-                return {}
-            return self.get_used_external(**kwargs)
+            return {}
 
         if push and not self.can_push:
             return {}
@@ -1121,7 +1122,7 @@ 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 {}
@@ -1143,15 +1144,6 @@ class Output:
                 oids.add(oid)
         return oids
 
-    def get_used_external(
-        self, **kwargs
-    ) -> Dict[Optional["ObjectDB"], Set["HashInfo"]]:
-        if not self.use_cache or not self.stage.is_repo_import:
-            return {}
-
-        (dep,) = self.stage.deps
-        return dep.get_used_objs(**kwargs)
-
     def _validate_output_path(self, path, stage=None):
         from dvc.dvcfile import is_valid_filename
 
@@ -1182,18 +1174,14 @@ 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
-        from dvc_data.hashfile.tree import du, merge
+        from dvc_data.hashfile.tree import merge
 
         assert other
 
@@ -1208,7 +1196,7 @@ class Output:
 
         try:
             merged = merge(
-                self.odb,
+                self.cache,
                 ancestor_info,
                 self.hash_info,
                 other.hash_info,
@@ -1217,15 +1205,176 @@ 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),
         )
 
+    def unstage(self, path: str) -> Tuple["Meta", "Tree"]:
+        from pygtrie import Trie
+
+        from dvc_objects.fs.path import Path
+
+        assert isinstance(self.fs.path, Path)
+        rel_key = tuple(self.fs.path.parts(self.fs.path.relpath(path, self.fs_path)))
+
+        if self.hash_info:
+            tree = self.get_dir_cache()
+            if tree is None:
+                raise DvcException(f"could not read {self.hash_info.value!r}")
+        else:
+            tree = Tree()
+
+        trie = tree.as_trie()
+        assert isinstance(trie, Trie)
+
+        try:
+            del trie[rel_key:]  # type: ignore[misc]
+        except KeyError:
+            raise FileNotFoundError(  # noqa: B904
+                errno.ENOENT,
+                os.strerror(errno.ENOENT),
+                self.fs.path.relpath(path),
+            )
+
+        new = tree.from_trie(trie)
+        new.digest()
+        return Meta(nfiles=len(new), isdir=True), new
+
+    def apply(
+        self,
+        path: str,
+        obj: Union["Tree", "HashFile"],
+        meta: "Meta",
+    ) -> Tuple["Meta", "Tree"]:
+        from pygtrie import Trie
+
+        from dvc_objects.fs.path import Path
+
+        assert isinstance(self.fs.path, Path)
+        append_only = True
+        rel_key = tuple(self.fs.path.parts(self.fs.path.relpath(path, self.fs_path)))
+
+        if self.hash_info:
+            tree = self.get_dir_cache()
+            if tree is None:
+                raise DvcException(f"could not read {self.hash_info.value!r}")
+        else:
+            tree = Tree()
+
+        trie = tree.as_trie()
+        assert isinstance(trie, Trie)
+
+        try:
+            del trie[rel_key:]  # type: ignore[misc]
+        except KeyError:
+            pass
+        else:
+            append_only = False
+
+        items = {}
+        if isinstance(obj, Tree):
+            items = {(*rel_key, *key): (m, o) for key, m, o in obj}
+        else:
+            items = {rel_key: (meta, obj.hash_info)}
+        trie.update(items)
+
+        new = Tree.from_trie(trie)
+        new.digest()
+
+        size = self.meta.size if self.meta and self.meta.size else None
+        if append_only and size and meta.size is not None:
+            # if files were only appended, we can sum to the existing size
+            size += meta.size
+        elif self.hash_info and self.hash_info == new.hash_info:
+            # if hashes are same, sizes must have been the same
+            size = self.meta.size
+        else:
+            size = None
+
+        meta = Meta(nfiles=len(new), size=size, isdir=True)
+        return meta, new
+
+    def add(  # noqa: C901
+        self, path: Optional[str] = None, no_commit: bool = False, relink: bool = True
+    ) -> Optional["HashFile"]:
+        path = path or self.fs_path
+        if self.hash_info and not self.is_dir_checksum and self.fs_path != path:
+            raise DvcException(
+                f"Cannot modify '{self}' which is being tracked as a file"
+            )
+
+        assert self.repo
+        cache = self.cache if self.use_cache else self.repo.cache.local
+        assert isinstance(cache, HashFileDB)
+
+        new: "HashFile"
+        try:
+            assert self.hash_name
+            staging, meta, obj = build(
+                cache,
+                path,
+                self.fs,
+                self.hash_name,
+                ignore=self.dvcignore,
+                dry_run=not self.use_cache,
+            )
+        except FileNotFoundError as exc:
+            if self.fs_path == path:
+                raise self.DoesNotExistError(self) from exc
+            if not self.is_dir_checksum:
+                raise
+
+            meta, new = self.unstage(path)
+            staging, obj = None, None
+        else:
+            assert obj
+            assert staging
+            if self.fs_path != path:
+                meta, new = self.apply(path, obj, meta)
+                add_update_tree(staging, new)
+            else:
+                new = obj
+
+        self.obj = new
+        self.hash_info = self.obj.hash_info
+        self.meta = meta
+        self.files = None
+        self.ignore()
+
+        if no_commit or not self.use_cache:
+            return obj
+
+        if isinstance(new, Tree):
+            add_update_tree(cache, new)
+
+        if not obj:
+            return obj
+
+        assert staging
+        assert obj.hash_info
+        otransfer(staging, self.cache, {obj.hash_info}, hardlink=relink, shallow=False)
+
+        if relink:
+            rel = self.fs.path.relpath(path)
+            with CheckoutCallback(desc=f"Checking out {rel}", unit="files") as callback:
+                self._checkout(
+                    path,
+                    self.fs,
+                    obj,
+                    self.cache,
+                    relink=True,
+                    state=self.repo.state,
+                    prompt=prompt.confirm,
+                    progress_callback=callback,
+                )
+            self.set_exec()
+        return obj
+
     @property
     def fspath(self):
         return self.fs_path

dvc/parsing/__init__.py

@@ -72,9 +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)
 
@@ -116,8 +114,7 @@ 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)
@@ -188,9 +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):
@@ -203,9 +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
@@ -309,9 +304,7 @@ class EntryDefinition:
                 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):
@@ -354,9 +347,7 @@ class ForeachDefinition:
         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)
@@ -381,8 +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,
@@ -399,7 +392,7 @@ class ForeachDefinition:
         """Convert sequence to Mapping with keys normalized."""
         iterable = self.resolved_iterable
         if isinstance(iterable, Mapping):
-            return iterable
+            return {to_str(k): v for k, v in iterable.items()}
 
         assert isinstance(iterable, Sequence)
         if any(map(is_map_or_seq, iterable)):

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)
@@ -159,7 +155,7 @@ class Value(Node):
 PRIMITIVES = (int, float, str, bytes, bool)
 
 
-class Container(Node, ABC):  # noqa: B024
+class Container(Node, ABC):
     meta: Meta
     data: Union[list, dict]
     _key_transform = staticmethod(identity)
@@ -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):
@@ -219,9 +212,7 @@ 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
@@ -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

@@ -73,7 +73,7 @@ def embrace(s: str):
 
 def escape_str(value):
     if os.name == "nt":
-        from subprocess import list2cmdline
+        from subprocess import list2cmdline  # nosec B404
 
         return list2cmdline([value])
     from shlex import quote
@@ -95,17 +95,15 @@ def _(obj: bool):
 def _(obj: dict):  # noqa: C901
     from dvc.config import Config
 
-    config = Config().get("parsing", {})
+    config = Config.from_cwd().get("parsing", {})
 
     result = ""
     for k, v in flatten(obj).items():
-
         if isinstance(v, bool):
             if v:
                 result += f"--{k} "
-            else:
-                if config.get("bool", "store_true") == "boolean_optional":
-                    result += f"--no-{k} "
+            elif config.get("bool", "store_true") == "boolean_optional":
+                result += f"--no-{k} "
 
         elif isinstance(v, str):
             result += f"--{k} {escape_str(v)} "
@@ -115,9 +113,7 @@ 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 +202,7 @@ 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(