fix db completions result

Fixes #10879.
Upstream PR: https://github.com/iterative/shtab/pull/195.

.github/ISSUE_TEMPLATE/epic_story.md

@@ -1,60 +0,0 @@
----
-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/workflows/benchmarks.yaml

@@ -5,14 +5,40 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
+env:
+  FORCE_COLOR: "1"
+  PY_COLORS: "1"
+
 jobs:
   bench:
     name: run benchmarks
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v6
         with:
-            python-version: "3.11"
-      - uses: iterative/dvc-bench@main
+            python-version: "3.13"
+
+      - uses: actions/checkout@v5
         with:
-            pytest_options: "-k 'test_init or test_help'"
+          ref: ${{ github.event.pull_request.base.sha }}
+          fetch-depth: 0
+
+      - uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+          cache-dependency-glob: pyproject.toml
+
+      - run: uv pip install '.[tests]' --system
+      - name: run benchmarks on base branch
+        run: pytest --benchmark-autosave dvc/testing/benchmarks/ -k 'test_init or test_help'
+
+      - uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+          clean: false
+      - run: uv pip install '.[tests]' --system
+      - name: run benchmarks for PR
+        run: >
+          pytest --benchmark-compare --benchmark-compare-fail=min:5%
+          --benchmark-group-by name
+          dvc/testing/benchmarks/ -k 'test_init or test_help'

.github/workflows/build.yaml

@@ -19,30 +19,33 @@ jobs:
     name: Build & Verify package
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
       with:
         fetch-depth: 0
 
-    - uses: actions/setup-python@v5
+    - uses: actions/setup-python@v6
       with:
-        python-version: 3.12
+        python-version: 3.13
 
-    - run: python -m pip install --upgrade pip setuptools_scm build twine
+    - uses: astral-sh/setup-uv@v6
 
-    - name: Force version for Test PyPI upload
-      if: ${{ !startsWith(github.ref, 'refs/tags') }}
-      run: echo version=$(python -m setuptools_scm | awk -F+ '{print $1}' | tail -1) >> $GITHUB_ENV
+    - name: Omit local version for Test PyPI upload
+      if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+      run: echo SETUPTOOLS_SCM_OVERRIDES_FOR_DVC='{local_scheme="no-local-version"}' >> $GITHUB_ENV
 
-    - run: echo 'PKG = "pip"'>dvc/_build.py
-    - run: python -m build
-      env:
-        SETUPTOOLS_SCM_PRETEND_VERSION_FOR_DVC: ${{ env.version }}
-    - run: twine check --strict dist/*
+    - name: Build Python Package
+      run: |
+        echo 'PKG = "pip"'>dvc/_build.py
+        uv build
+
+    - name: Check dist
+      run: uv tool run twine check --strict dist/*
 
     - uses: actions/upload-artifact@v4
       with:
         name: Packages
         path: dist/
+        if-no-files-found: error
 
   test-pypi-publish:
     name: Publish dev package to test.pypi.org
@@ -52,13 +55,13 @@ jobs:
 
     environment:
       name: test-pypi
-      url: https://test.pypi.org/p/dvc
+      url: https://test.pypi.org/p/dvc/${{ github.event.release.tag_name }}
 
     permissions:
       id-token: write
 
     steps:
-    - uses: actions/download-artifact@v4
+    - uses: actions/download-artifact@v5
       with:
         name: Packages
         path: dist
@@ -77,13 +80,13 @@ jobs:
 
     environment:
       name: pypi
-      url: https://pypi.org/p/dvc
+      url: https://pypi.org/p/dvc/${{ github.event.release.tag_name }}
 
     permissions:
       id-token: write
 
     steps:
-    - uses: actions/download-artifact@v4
+    - uses: actions/download-artifact@v5
       with:
         name: Packages
         path: dist

.github/workflows/codeql.yml

@@ -28,7 +28,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v5
 
     - name: Initialize CodeQL
       uses: github/codeql-action/init@v3

.github/workflows/plugin_tests.yaml

@@ -18,35 +18,36 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04]
-        pyv: ["3.10"]
+        os: [ubuntu-latest]
+        pyv: ["3.13"]
         plugin: ["dvc-s3"]
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
       with:
         path: dvc
 
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
       with:
         repository: iterative/${{ matrix.plugin }}
         ref: main
         path: ${{ matrix.plugin }}
 
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: ${{ matrix.pyv }}
-        cache: pip
-        cache-dependency-path: |
-          dvc/pyproject.toml
-          ${{ matrix.plugin }}/setup.cfg
+
+    - uses: astral-sh/setup-uv@v6
+      with:
+        enable-cache: true
+        cache-dependency-glob: "**/pyproject.toml"
+        cache-suffix: ${{ matrix.pyv }}
 
     - name: Install plugin + DVC@PR
       run: |
-        pip install --upgrade pip wheel
-        pip install "./dvc[testing]"
-        pip install -e "./${{ matrix.plugin }}[tests]"
+        uv pip install "./dvc[testing]" --system
+        uv pip install -e "./${{ matrix.plugin }}[tests]" --system
 
     - name: Run plugin tests
       timeout-minutes: 15

.github/workflows/tests.yaml

@@ -16,42 +16,134 @@ permissions:
   contents: read
 
 jobs:
+  lint:
+    timeout-minutes: 10
+    runs-on: ${{ matrix.os }}
+    env:
+       DVC_NO_ANALYTICS: true
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+    steps:
+    - uses: actions/checkout@v5
+      with:
+        fetch-depth: 0
+    - name: Set up Python
+      uses: actions/setup-python@v6
+      with:
+        python-version: '3.13'
+    - uses: astral-sh/setup-uv@v6
+      with:
+        enable-cache: true
+        cache-dependency-glob: pyproject.toml
+    - run: uv pip install -e ".[dev]" --system
+      env:
+        UV_LINK_MODE: ${{ runner.os == 'Windows' && 'symlink' || 'hardlink' }}
+
+    - name: Cache mypy
+      uses: actions/cache@v4
+      with:
+        path: .mypy_cache
+        key: mypy-${{ runner.os }}-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml') }}
+    - uses: pre-commit/[email protected]
+
   tests:
-    timeout-minutes: 50
+    timeout-minutes: 20
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, windows-latest, macos-latest]
-        pyv: ["3.9", "3.10", "3.11", "3.12"]
-
+        os: [ubuntu-latest, macos-latest]
+        pyv: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        include:
+        - os: windows-latest
+          pyv: "3.9"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 1"
+        - os: windows-latest
+          pyv: "3.9"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 2"
+        - os: windows-latest
+          pyv: "3.9"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 3"
+        - os: windows-latest
+          pyv: "3.9"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 4"
+        - os: windows-latest
+          pyv: "3.10"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 1"
+        - os: windows-latest
+          pyv: "3.10"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 2"
+        - os: windows-latest
+          pyv: "3.10"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 3"
+        - os: windows-latest
+          pyv: "3.10"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 4"
+        - os: windows-latest
+          pyv: "3.11"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 1"
+        - os: windows-latest
+          pyv: "3.11"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 2"
+        - os: windows-latest
+          pyv: "3.11"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 3"
+        - os: windows-latest
+          pyv: "3.11"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 4"
+        - os: windows-latest
+          pyv: "3.12"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 1"
+        - os: windows-latest
+          pyv: "3.12"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 2"
+        - os: windows-latest
+          pyv: "3.12"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 3"
+        - os: windows-latest
+          pyv: "3.12"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 4"
+        - os: windows-latest
+          pyv: "3.13"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 1"
+        - os: windows-latest
+          pyv: "3.13"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 2"
+        - os: windows-latest
+          pyv: "3.13"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 3"
+        - os: windows-latest
+          pyv: "3.13"
+          pytestargs: "--splitting-algorithm=least_duration --splits 4 --group 4"
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
       with:
         fetch-depth: 0
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: ${{ matrix.pyv }}
-        cache: pip
-        cache-dependency-path: pyproject.toml
-    - name: install
-      run: |
-        pip install --upgrade pip wheel
-        pip install -e ".[dev]"
-    - uses: pre-commit/[email protected]
+    - uses: astral-sh/setup-uv@v6
+      with:
+        enable-cache: true
+        cache-dependency-glob: pyproject.toml
+        cache-suffix: ${{ matrix.pyv }}
+    - run: uv pip install -e ".[dev]" pytest-split --system
+      env:
+        UV_LINK_MODE: ${{ runner.os == 'Windows' && 'symlink' || 'hardlink' }}
+
     - name: run tests
       timeout-minutes: 40
       env:
+        COVERAGE_CORE: sysmon
         PYTHONUTF8: 1
       run: >
-        pytest -n=logical --timeout=300 --durations=100
-        --cov --cov-report=xml --cov-report=term
+        pytest ${{ matrix.pytestargs }} -n=logical --dist=worksteal --timeout=300 --durations=0
+        --cov --cov-report=xml --cov-report=term  --durations-path=./.github/.test_durations
     - name: upload coverage report
-      uses: codecov/codecov-action@v3
-      with:
-        file: ./coverage.xml
-        fail_ci_if_error: false
+      uses: codecov/codecov-action@v5
   check:
     if: always()
     needs: [tests]
@@ -66,7 +158,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Slack Notification
-      uses: rtCamp/[email protected].0
+      uses: rtCamp/[email protected].3
       env:
         SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
         SLACK_COLOR: ${{ job.status }}

.gitignore

@@ -43,7 +43,7 @@ scripts/ci/gcp-creds.json
 .gcp-creds.json
 
 *~
-/dvc/_dvc_version.py
+/dvc/_version.py
 
 .mypy_cache/
 .pytest_cache/

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v6.0.0
     hooks:
       - id: check-added-large-files
       - id: check-case-conflict
@@ -22,13 +22,13 @@ repos:
       - id: sort-simple-yaml
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.4.4'
+    rev: 'v0.13.2'
     hooks:
-      - id: ruff
+      - id: ruff-check
         args: [--fix, --exit-non-zero-on-fix]
       - id: ruff-format
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.4.1
     hooks:
       - id: codespell
         additional_dependencies: ["tomli"]
@@ -50,7 +50,7 @@ repos:
         language: system
         name: DVC pre-commit
         stages:
-          - commit
+          - pre-commit
         verbose: true
         require_serial: true
       - args:
@@ -61,7 +61,7 @@ repos:
         language: system
         name: DVC pre-push
         stages:
-          - push
+          - pre-push
         require_serial: true
       - always_run: true
         args:

.pre-commit-hooks.yaml

@@ -8,7 +8,7 @@
   name: DVC pre-commit
   require_serial: true
   stages:
-  - commit
+  - pre-commit
   verbose: true
 - args:
   - git-hook
@@ -20,7 +20,7 @@
   name: DVC pre-push
   require_serial: true
   stages:
-  - push
+  - pre-push
 - always_run: true
   args:
   - git-hook
@@ -29,7 +29,7 @@
   id: dvc-post-checkout
   language: python
   language_version: python3
-  minimum_pre_commit_version: 2.2.0
+  minimum_pre_commit_version: 3.2.0
   name: DVC post-checkout
   require_serial: true
   stages:

README.rst

@@ -213,7 +213,7 @@ Community and Support
 * `Forum <https://discuss.dvc.org/>`_
 * `Discord Chat <https://dvc.org/chat>`_
 * `Email <mailto:[email protected]>`_
-* `Mailing List <https://sweedom.us10.list-manage.com/subscribe/post?u=a08bf93caae4063c4e6a351f6&id=24c0ecc49a>`_
+* `Mailing List <https://dvc.org/community#subscribe>`_
 
 Copyright
 =========
@@ -240,11 +240,11 @@ Barrak, A., Eghan, E.E. and Adams, B. `On the Co-evolution of ML Pipelines and S
 .. |VS Code Extension Overview| image:: https://raw.githubusercontent.com/iterative/vscode-dvc/main/extension/docs/overview.gif
    :alt: DVC Extension for VS Code
 
-.. |CI| image:: https://github.com/iterative/dvc/workflows/Tests/badge.svg?branch=main
-   :target: https://github.com/iterative/dvc/actions
+.. |CI| image:: https://github.com/iterative/dvc/actions/workflows/tests.yaml/badge.svg
+   :target: https://github.com/iterative/dvc/actions/workflows/tests.yaml
    :alt: GHA Tests
 
-.. |Maintainability| image:: https://codeclimate.com/github/iterative/dvc/badges/gpa.svg
+.. |Maintainability| image:: https://img.shields.io/codeclimate/maintainability/iterative/dvc
    :target: https://codeclimate.com/github/iterative/dvc
    :alt: Code Climate
 
@@ -268,7 +268,7 @@ Barrak, A., Eghan, E.E. and Adams, B. `On the Co-evolution of ML Pipelines and S
    :target: https://formulae.brew.sh/formula/dvc
    :alt: Homebrew
 
-.. |Conda| image:: https://img.shields.io/conda/v/conda-forge/dvc.svg?label=conda&logo=conda-forge
+.. |Conda| image:: https://anaconda.org/conda-forge/dvc/badges/version.svg
    :target: https://anaconda.org/conda-forge/dvc
    :alt: Conda-forge
 

dvc/_debug.py

@@ -14,7 +14,7 @@ def viztracer_profile(
     log_async: bool = False,
 ):
     try:
-        import viztracer
+        import viztracer  # ty: ignore[unresolved-import]
     except ImportError:
         print("Failed to run profiler, viztracer is not installed")  # noqa: T201
         yield
@@ -37,7 +37,7 @@ def yappi_profile(
     separate_threads: Optional[bool] = False,
 ):
     try:
-        import yappi
+        import yappi  # ty: ignore[unresolved-import]
     except ImportError:
         print("Failed to run profiler, yappi is not installed")  # noqa: T201
         yield
@@ -79,7 +79,7 @@ def yappi_profile(
 def instrument(html_output=False):
     """Run a statistical profiler"""
     try:
-        from pyinstrument import Profiler
+        from pyinstrument import Profiler  # ty: ignore[unresolved-import]
     except ImportError:
         print("Failed to run profiler, pyinstrument is not installed")  # noqa: T201
         yield
@@ -123,7 +123,7 @@ def debug():
         yield
     except Exception:
         try:
-            import ipdb as pdb  # noqa: T100
+            import ipdb as pdb  # noqa: T100  # ty: ignore[unresolved-import]
         except ImportError:
             import pdb  # type: ignore[no-redef]  # noqa: T100
         pdb.post_mortem()

dvc/analytics.py

@@ -1,10 +1,14 @@
 import json
 import os
+from typing import TYPE_CHECKING, Optional
 
 from dvc.log import logger
 
 from .env import DVC_ANALYTICS_ENDPOINT, DVC_NO_ANALYTICS
 
+if TYPE_CHECKING:
+    from dvc.scm import Base
+
 logger = logger.getChild(__name__)
 
 
@@ -67,6 +71,7 @@ def send(path):
     thus, the need of removing such file afterwards.
     """
     import requests
+    from requests.exceptions import RequestException
 
     url = os.environ.get(DVC_ANALYTICS_ENDPOINT, "https://analytics.dvc.org")
     headers = {"content-type": "application/json"}
@@ -81,7 +86,7 @@ def send(path):
 
     try:
         requests.post(url, json=report, headers=headers, timeout=5)
-    except requests.exceptions.RequestException as e:
+    except RequestException as e:
         logger.trace("", exc_info=True)
         logger.debug("failed to send analytics report %s", str(e))
 
@@ -89,20 +94,62 @@ def send(path):
     os.remove(path)
 
 
-def _scm_in_use():
-    from dvc.exceptions import NotDvcRepoError
-    from dvc.repo import Repo
-    from dvc.scm import NoSCM
+def _git_remote_url(scm: Optional["Base"]) -> Optional[str]:
+    from dvc.scm import Git
 
-    from .scm import SCM, SCMError
+    if not isinstance(scm, Git):
+        return None
+
+    from dulwich.porcelain import get_remote_repo
+
+    dulwich_repo = scm.dulwich.repo
+    try:
+        _remote, url = get_remote_repo(dulwich_repo)
+    except IndexError:
+        # IndexError happens when the head is detached
+        _remote, url = get_remote_repo(dulwich_repo, b"origin")
+    # Dulwich returns (None, "origin") if no remote set
+    if (_remote, url) == (None, "origin"):
+        return None
+    return url
+
+
+def _scm_in_use(scm: Optional["Base"]) -> Optional[str]:
+    return type(scm).__name__ if scm else None
+
+
+def _parse_git_remote_path(remote_url: str) -> str:
+    from urllib.parse import urlparse
+
+    from scmrepo.urls import is_scp_style_url
+
+    parsed = urlparse(remote_url)
+    # Windows Path also gets parsed with a drive letter as scheme
+    # https://github.com/python/cpython/issues/86381
+    if parsed.scheme and parsed.scheme in ("http", "https", "git", "ssh"):
+        return parsed.path.strip("/")
+
+    if is_scp_style_url(remote_url):
+        # handle scp-style URL
+        parts = remote_url.split(":", 1)
+        if len(parts) == 2:
+            _, path = parts
+            return path.rstrip("/")
+    return remote_url
+
+
+def _git_remote_path_hash(scm: Optional["Base"]) -> Optional[str]:
+    """Return a hash of the git remote path."""
+    import hashlib
 
     try:
-        scm = SCM(root_dir=Repo.find_root())
-        return type(scm).__name__
-    except SCMError:
-        return NoSCM.__name__
-    except NotDvcRepoError:
-        pass
+        if remote_url := _git_remote_url(scm):
+            path = _parse_git_remote_path(remote_url)
+            h = hashlib.md5(path.encode("utf-8"), usedforsecurity=False)  # for FIPS
+            return h.hexdigest()
+    except Exception:  # noqa: BLE001
+        logger.debug("Failed to get git remote path", exc_info=True)
+    return None
 
 
 def _runtime_info():
@@ -112,6 +159,8 @@ def _runtime_info():
     from iterative_telemetry import _generate_ci_id, find_or_create_user_id
 
     from dvc import __version__
+    from dvc.info import _get_remotes
+    from dvc.repo import Repo
     from dvc.utils import is_binary
 
     ci_id = _generate_ci_id()
@@ -120,13 +169,24 @@ def _runtime_info():
     else:
         group_id, user_id = None, find_or_create_user_id()
 
+    scm = None
+    remotes = None
+    try:
+        repo = Repo()
+        scm = repo.scm
+        remotes = _get_remotes(repo.config)
+    except Exception as exc:  # noqa: BLE001
+        logger.debug("failed to open repo: %s", exc)
+
     return {
         "dvc_version": __version__,
         "is_binary": is_binary(),
-        "scm_class": _scm_in_use(),
+        "scm_class": _scm_in_use(scm),
         "system_info": _system_info(),
         "user_id": user_id,
         "group_id": group_id,
+        "remotes": remotes,
+        "git_remote_hash": _git_remote_path_hash(scm),
     }
 
 

dvc/api/__init__.py

@@ -1,7 +1,7 @@
 from dvc.fs.dvc import _DVCFileSystem as DVCFileSystem
 
 from .artifacts import artifacts_show
-from .data import get_url, open, read
+from .data import get_url, open, read  # noqa: A004
 from .dataset import get as get_dataset
 from .experiments import exp_save, exp_show
 from .scm import all_branches, all_commits, all_tags

dvc/api/data.py

@@ -285,7 +285,7 @@ def _open(
             if TYPE_CHECKING:
                 from dvc.fs import FileSystem
 
-            fs: Union["FileSystem", DataFileSystem, DVCFileSystem]
+            fs: Union[FileSystem, DataFileSystem, DVCFileSystem]
             if os.path.isabs(path):
                 fs = DataFileSystem(index=_repo.index.data["local"])
                 fs_path = path

dvc/api/dataset.py

@@ -1,8 +1,8 @@
 from typing import Literal, TypedDict, Union
 
 
-class DVCXDataset(TypedDict):
-    type: Literal["dvcx"]
+class DatachainDataset(TypedDict):
+    type: Literal["dc"]
     name: str
     version: int
 
@@ -20,7 +20,7 @@ class URLDataset(TypedDict):
     path: str
 
 
-def get(name: str) -> Union[DVCXDataset, DVCDataset, URLDataset]:
+def get(name: str) -> Union[DatachainDataset, DVCDataset, URLDataset]:
     from difflib import get_close_matches
 
     from dvc.fs import get_cloud_fs
@@ -46,9 +46,9 @@ def get(name: str) -> Union[DVCXDataset, DVCDataset, URLDataset]:
             path=dataset.lock.path,
             sha=dataset.lock.rev_lock,
         )
-    if dataset.type == "dvcx":
-        return DVCXDataset(
-            type="dvcx", name=dataset.name_version[0], version=dataset.lock.version
+    if dataset.type == "dc":
+        return DatachainDataset(
+            type="dc", name=dataset.name_version[0], version=dataset.lock.version
         )
     if dataset.type == "url":
         fs_cls, _, path = get_cloud_fs(repo.config, url=dataset.lock.url)
@@ -64,3 +64,4 @@ def get(name: str) -> Union[DVCXDataset, DVCDataset, URLDataset]:
             for file in dataset.lock.files
         ]
         return URLDataset(type="url", files=files, path=versioned_path)
+    raise AssertionError("unreachable")

dvc/api/show.py

@@ -27,8 +27,7 @@ def _postprocess(results):
             }
             processed[rev] = processed[rev] | to_merge
 
-    if "workspace" in processed:
-        del processed["workspace"]
+    processed.pop("workspace", None)
 
     return processed
 

dvc/cachemgr.py

@@ -86,7 +86,7 @@ class CacheManager:
         return FileStorage(
             key=(),
             fs=self.local.fs,
-            path=self.local.fs.join(self.default_local_cache_dir, self.FS_DIR),
+            path=self.local.fs.join(self.local_cache_dir, self.FS_DIR),
         )
 
     def _init_odb(self, schemes):

dvc/cli/__init__.py

@@ -157,6 +157,8 @@ def main(argv=None):  # noqa: C901, PLR0912, PLR0915
     Returns:
         int: command's return code.
     """
+    from contextlib import ExitStack
+
     from dvc._debug import debugtools
     from dvc.config import ConfigError
     from dvc.exceptions import DvcException, NotDvcRepoError
@@ -173,12 +175,11 @@ def main(argv=None):  # noqa: C901, PLR0912, PLR0915
         logging.disable(logging.INFO)
 
     args = None
-
-    outer_log_level = logger.level
-    level = None
+    stack = ExitStack()
     try:
         args = parse_args(argv)
 
+        level = None
         if args.quiet:
             level = logging.CRITICAL
         elif args.verbose == 1:
@@ -187,7 +188,7 @@ def main(argv=None):  # noqa: C901, PLR0912, PLR0915
             level = logging.TRACE  # type: ignore[attr-defined]
 
         if level is not None:
-            set_loggers_level(level)
+            stack.enter_context(set_loggers_level(level))
 
         if level and level <= logging.DEBUG:
             from platform import platform, python_implementation, python_version
@@ -247,7 +248,7 @@ def main(argv=None):  # noqa: C901, PLR0912, PLR0915
 
         return ret
     finally:
-        logger.setLevel(outer_log_level)
+        stack.close()
 
         from dvc.repo.open_repo import clean_repos
 

dvc/cli/command.py

@@ -18,8 +18,11 @@ class CmdBase(ABC):
 
         os.chdir(args.cd)
 
-        self.repo: "Repo" = Repo(uninitialized=self.UNINITIALIZED)
-        self.config: "Config" = self.repo.config
+        self.repo: Repo = Repo(
+            uninitialized=self.UNINITIALIZED,
+            _wait_for_lock=args.wait_for_lock,
+        )
+        self.config: Config = self.repo.config
         self.args = args
 
     def do_run(self):

dvc/cli/completion.py

@@ -22,6 +22,36 @@ _dvc_compgen_exps() {
     local _dvc_exps=($(dvc exp list -q --all-commits --names-only))
     compgen -W "${_dvc_exps[*]}" -- $1
 }
+
+_dvc_compgen_remotes() {
+    local _dvc_remotes=($(dvc remote list | cut -d' ' -f1))
+    compgen -W "${_dvc_remotes[*]}" -- $1
+}
+
+_dvc_compgen_config_vars() {
+    compgen -W "${_dvc_config_vars[*]}" -- $1
+}
+
+_dvc_compgen_remote_config_vars() {
+    local cur prev words cword remote_name filtered
+    _init_completion || return
+
+    # last non-option word before cursor
+    local nonopts=()
+    for w in "${words[@]:1:$((cword-1))}"; do
+        [[ $w == -* ]] || nonopts+=("$w")
+    done
+
+    remote_name="${nonopts[-1]}"
+    if [[ -n $remote_name ]]; then
+        local _dvc_remote_config_vars=($(
+            dvc config --available-options -q 2> /dev/null \
+            | grep "^remote\\.${remote_name}\\." \
+            | sed "s/^remote\\.${remote_name}\\.//"
+        ))
+        compgen -W "${_dvc_remote_config_vars[*]}" -- $1
+    fi
+}
 """
 
 ZSH_PREAMBLE = """
@@ -55,19 +85,149 @@ _dvc_compadd_stages_and_files() {
 _dvc_compadd_exps() {
     _describe 'experiments' "($(dvc exp list -q --all-commits --names-only))"
 }
+
+_dvc_compadd_remotes() {
+    _describe 'remotes' "($(dvc remote list | cut -d' ' -f1))"
+}
+
+_dvc_config_config_vars_for_completion() {
+    dvc config --available-options -q 2> /dev/null
+}
+
+_dvc_compadd_config_vars() {
+    _describe 'config_vars' _dvc_config_vars
+}
+
+_dvc_compadd_remote_config_vars() {
+  local remote_name filtered
+
+  # last non-option word before cursor
+  remote_name=${${words[1,CURRENT-1]##-*}[-1]}
+  if [[ -n $remote_name ]]; then
+    filtered=$(_dvc_config_config_vars_for_completion \\
+        | grep "^remote.${remote_name}\\\\." \\
+        | sed "s/^remote\\\\.${remote_name}\\\\.//"
+    )
+    compadd -- $=filtered
+  fi
+}
+"""
+
+FISH_PREAMBLE = """
+function __fish_complete_dvc_files
+    __fish_complete_path | string match -re '\\*?.dvc|Dvcfile|dvc\\.yaml'
+end
+
+function __fish_complete_dvc_stages
+    for line in (dvc stage list -q)
+        set -l parts (string split -m1 ' ' -- $line)
+        set -l name $parts[1]
+        set -l desc (string trim $parts[2])
+        echo -e "$name	$desc"
+    end
+end
+
+function __fish_complete_dvc_stages_and_files
+    __fish_complete_dvc_stages
+    __fish_complete_dvc_files
+end
+
+function __fish_complete_dvc_experiments
+    dvc exp list -q --all-commits --names-only
+end
+
+function __fish_complete_dvc_remotes
+    dvc remote list | cut -d' ' -f1
+end
+
+function __fish_complete_dvc_remote_config_vars
+    # last non-option word before cursor
+    set -l remote_name (commandline -opc | string match -rv '^-' | tail -n 1)
+
+    if test -n "$remote_name"
+        dvc config --available-options -q 2>/dev/null |
+            string match -re "^remote\\.$remote_name\\." |
+            string replace -r "^remote\\.$remote_name\\." ''
+    end
+end
 """
 
 PREAMBLE = {
     "bash": BASH_PREAMBLE,
     "zsh": ZSH_PREAMBLE,
+    "fish": FISH_PREAMBLE,
 }
 
 FILE = shtab.FILE
 DIR = shtab.DIRECTORY
-DVC_FILE = {"bash": "_dvc_compgen_DVCFiles", "zsh": "_dvc_compadd_DVCFiles"}
-STAGE = {"bash": "_dvc_compgen_stages", "zsh": "_dvc_compadd_stages"}
+DVC_FILE = {
+    "bash": "_dvc_compgen_DVCFiles",
+    "zsh": "_dvc_compadd_DVCFiles",
+    "fish": '-f -a "(__fish_complete_dvc_files)"',
+}
+STAGE = {
+    "bash": "_dvc_compgen_stages",
+    "zsh": "_dvc_compadd_stages",
+    "fish": '-f -a "(__fish_complete_dvc_stages)"',
+}
 DVCFILES_AND_STAGE = {
     "bash": "_dvc_compgen_stages_and_files",
     "zsh": "_dvc_compadd_stages_and_files",
+    "fish": '-f -a "(__fish_complete_dvc_stages_and_files)"',
 }
-EXPERIMENT = {"bash": "_dvc_compgen_exps", "zsh": "_dvc_compadd_exps"}
+EXPERIMENT = {
+    "bash": "_dvc_compgen_exps",
+    "zsh": "_dvc_compadd_exps",
+    "fish": '-f -a "(__fish_complete_dvc_experiments)"',
+}
+REMOTE = {
+    "bash": "_dvc_compgen_remotes",
+    "zsh": "_dvc_compadd_remotes",
+    "fish": '-f -a "(__fish_complete_dvc_remotes)"',
+}
+CONFIG_VARS = {
+    "bash": "_dvc_compgen_config_vars",
+    "zsh": "_dvc_compadd_config_vars",
+    "fish": '-f -a "(__fish_complete_dvc_config_vars)"',
+}
+REMOTE_CONFIG_VARS = {
+    "bash": "_dvc_compgen_remote_config_vars",
+    "zsh": "_dvc_compadd_remote_config_vars",
+    "fish": '-f -a "(__fish_complete_dvc_remote_config_vars)"',
+}
+
+
+def get_preamble() -> dict[str, str]:
+    from dvc.config_schema import config_vars_for_completion
+
+    ret: dict[str, str] = {}
+    config_vars = list(config_vars_for_completion())
+
+    nl = "\n\t".expandtabs(4)
+    config_vars_arr = f"""
+_dvc_config_vars=(
+    {nl.join(config_vars)}
+)
+"""
+    indent = "\t\t".expandtabs(4)  # 8 spaces
+    lines = (
+        "\n".join(
+            f"{indent}{c} \\"
+            for c in config_vars[:-1]  # all but last
+        )
+        + "\n"
+        + f"{indent}{config_vars[-1]}"
+    )  # last line without backslash
+    config_vars_arr_fish = f"""
+function __fish_complete_dvc_config_vars
+    set -l _dvc_config_vars \\
+{lines}
+    printf %s\\n $_dvc_config_vars
+end
+"""
+    for shell, preamble in PREAMBLE.items():
+        if shell != "fish":
+            ret[shell] = config_vars_arr + preamble
+        else:
+            ret[shell] = config_vars_arr_fish + preamble
+    return ret

dvc/cli/parser.py

@@ -200,6 +200,14 @@ def get_main_parser():
         type=str,
     )
 
+    parser.add_argument(
+        "--wait-for-lock",
+        action="store_true",
+        default=False,
+        help="Wait for the lock if it is already held by another process, instead of"
+        " failing immediately.",
+    )
+
     # Sub commands
     subparsers = parser.add_subparsers(
         title="Available Commands",

dvc/cli/utils.py

@@ -40,7 +40,7 @@ def hide_subparsers_from_help(subparsers):
     # from the 'positional arguments' choices list
     # see: https://bugs.python.org/issue22848
     # Need to set `add_help=False`, but avoid setting `help`
-    # (not even to `argparse.SUPPPRESS`).
+    # (not even to `argparse.SUPPRESS`).
     # NOTE: The argument is the parent subparser, not the subcommand parser.
     cmds = [cmd for cmd, parser in subparsers.choices.items() if parser.add_help]
     subparsers.metavar = "{{{}}}".format(",".join(cmds))

dvc/commands/add.py

@@ -101,7 +101,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         help="Remote storage to download to",
         metavar="<name>",
-    )
+    ).complete = completion.REMOTE
     parser.add_argument(
         "--remote-jobs",
         type=int,

dvc/commands/artifacts.py

@@ -13,6 +13,9 @@ class CmdArtifactsGet(CmdBaseNoRepo):
         from dvc.scm import CloneError
         from dvc.ui import ui
 
+        if self.args.show_url:
+            return self._show_url()
+
         try:
             count, out = Artifacts.get(
                 self.args.url,
@@ -36,6 +39,28 @@ class CmdArtifactsGet(CmdBaseNoRepo):
             )
             return 1
 
+    def _show_url(self):
+        from dvc.api import artifacts_show, get_url
+        from dvc.ui import ui
+
+        artifact = artifacts_show(
+            self.args.name,
+            version=self.args.rev,
+            stage=self.args.stage,
+            repo=self.args.url,
+        )
+
+        url = get_url(
+            artifact["path"],
+            repo=self.args.url,
+            rev=artifact["rev"],
+            remote=self.args.remote,
+            remote_config=self.args.remote_config,
+        )
+        ui.write(url, force=True)
+
+        return 0
+
 
 def add_parser(subparsers, parent_parser):
     ARTIFACTS_HELP = "DVC model registry artifact commands."
@@ -84,6 +109,14 @@ def add_parser(subparsers, parent_parser):
         help="Destination path to download artifact to",
         metavar="<path>",
     ).complete = completion.DIR
+    get_parser.add_argument(
+        "--show-url",
+        action="store_true",
+        help=(
+            "Print the storage location (URL) the target data would be "
+            "downloaded from, and exit."
+        ),
+    )
     get_parser.add_argument(
         "-j",
         "--jobs",
@@ -116,7 +149,7 @@ def add_parser(subparsers, parent_parser):
             "Remote name to set as a default in the target repository "
             "(only applicable when downloading from DVC remote)."
         ),
-    )
+    ).complete = completion.REMOTE
     get_parser.add_argument(
         "--remote-config",
         type=str,

dvc/commands/check_ignore.py

@@ -1,20 +1,28 @@
+from typing import TYPE_CHECKING
+
 from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
+if TYPE_CHECKING:
+    from dvc.ignore import CheckIgnoreResult
+
 
 class CmdCheckIgnore(CmdBase):
     def __init__(self, args):
         super().__init__(args)
         self.ignore_filter = self.repo.dvcignore
 
-    def _show_results(self, result):
-        if not result.match and not self.args.non_matching:
-            return
+    def _show_results(self, result: "CheckIgnoreResult"):
+        if not result.match and not self.args.details:
+            return None
 
         if self.args.details:
-            patterns = result.patterns
+            pattern_infos = result.pattern_infos
+            patterns = [str(pi) for pi in pattern_infos]
+            if not patterns and self.args.non_matching:
+                patterns = ["::"]
             if not self.args.all:
                 patterns = patterns[-1:]
 
@@ -22,13 +30,11 @@ class CmdCheckIgnore(CmdBase):
                 ui.write(pattern, result.file, sep="\t")
         else:
             ui.write(result.file)
+        return bool(result.pattern_infos)
 
     def _check_one_file(self, target):
         result = self.ignore_filter.check_ignore(target)
-        self._show_results(result)
-        if result.match:
-            return 0
-        return 1
+        return bool(self._show_results(result))
 
     def _interactive_mode(self):
         ret = 1
@@ -39,14 +45,14 @@ class CmdCheckIgnore(CmdBase):
                 break
             if not target:
                 break
-            if not self._check_one_file(target):
+            if self._check_one_file(target):
                 ret = 0
         return ret
 
     def _normal_mode(self):
         ret = 1
         for target in self.args.targets:
-            if not self._check_one_file(target):
+            if self._check_one_file(target):
                 ret = 0
         return ret
 
@@ -76,6 +82,8 @@ class CmdCheckIgnore(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
+    import argparse
+
     ADD_HELP = "Check whether files or directories are excluded due to `.dvcignore`."
 
     parser = subparsers.add_parser(
@@ -93,14 +101,7 @@ def add_parser(subparsers, parent_parser):
         help="Show the exclude patterns along with each target path.",
     )
     parser.add_argument(
-        "-a",
-        "--all",
-        action="store_true",
-        default=False,
-        help=(
-            "Include the target paths which don't match any pattern "
-            "in the `--details` list."
-        ),
+        "-a", "--all", action="store_true", default=False, help=argparse.SUPPRESS
     )
     parser.add_argument(
         "-n",

dvc/commands/checkout.py

@@ -1,5 +1,3 @@
-import operator
-
 from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
@@ -30,7 +28,7 @@ class CmdCheckout(CmdBase):
 
         stats, exc = None, None
         try:
-            stats = self.repo.checkout(
+            result = self.repo.checkout(
                 targets=self.args.targets,
                 with_deps=self.args.with_deps,
                 force=self.args.force,
@@ -40,14 +38,17 @@ class CmdCheckout(CmdBase):
             )
         except CheckoutError as _exc:
             exc = _exc
-            stats = exc.stats
+            result = exc.result
 
         if self.args.summary:
             default_message = "No changes."
-            msg = get_summary(sorted(stats.items(), key=operator.itemgetter(0)))
+            stats = result["stats"]
+            assert isinstance(stats, dict)
+            msg = get_summary(stats.items())
             ui.write(msg or default_message)
         else:
-            log_changes(stats)
+            result.pop("stats", {})
+            log_changes(result)
 
         if exc:
             raise exc

dvc/commands/completion.py

@@ -1,6 +1,6 @@
 from dvc.cli import formatter
 from dvc.cli.command import CmdBaseNoRepo
-from dvc.cli.completion import PREAMBLE
+from dvc.cli.completion import get_preamble
 from dvc.cli.utils import append_doc_link
 from dvc.log import logger
 from dvc.ui import ui
@@ -8,7 +8,7 @@ from dvc.ui import ui
 logger = logger.getChild(__name__)
 
 
-SUPPORTED_SHELLS = ["bash", "zsh"]
+SUPPORTED_SHELLS = ["bash", "zsh", "fish"]
 
 
 class CmdCompletion(CmdBaseNoRepo):
@@ -17,7 +17,7 @@ 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=get_preamble())
         ui.write(script, force=True)
         return 0
 

dvc/commands/config.py

@@ -3,7 +3,7 @@ import os
 
 from funcy import set_in
 
-from dvc.cli import formatter
+from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBaseNoRepo
 from dvc.cli.utils import append_doc_link
 from dvc.log import logger
@@ -40,6 +40,15 @@ class CmdConfig(CmdBaseNoRepo):
         self.config = Config.from_cwd(validate=False)
 
     def run(self):
+        if self.args.available_options:
+            from dvc.config_schema import contextual_config_vars_for_completion
+
+            ui.write(
+                "\n".join(list(contextual_config_vars_for_completion(self.config))),
+                force=True,
+            )
+            return 0
+
         if self.args.show_origin and (self.args.value or self.args.unset):
             logger.error(
                 "--show-origin can't be used together with any of these "
@@ -212,6 +221,9 @@ def add_parser(subparsers, parent_parser):
         help=CONFIG_HELP,
         formatter_class=formatter.RawDescriptionHelpFormatter,
     )
+    config_parser.add_argument(
+        "--available-options", default=False, action="store_true"
+    )
     config_parser.add_argument(
         "-u",
         "--unset",
@@ -224,7 +236,7 @@ def add_parser(subparsers, parent_parser):
         nargs="?",
         type=_name_type,
         help="Option name (section.option or remote.name.option).",
-    )
+    ).complete = completion.CONFIG_VARS
     config_parser.add_argument("value", nargs="?", help="Option value.")
     config_parser.add_argument(
         "-l",

dvc/commands/dag.py

@@ -17,7 +17,7 @@ def _show_ascii(graph: "DiGraph"):
 
     ret = []
     for pipeline in pipelines:
-        ret.append(draw(pipeline.nodes, pipeline.edges))
+        ret.append(draw(pipeline.nodes, pipeline.edges))  # noqa: PERF401
 
     return "\n".join(ret)
 

dvc/commands/data.py

@@ -2,7 +2,7 @@ from typing import TYPE_CHECKING, ClassVar
 
 from funcy import chunks, compact, log_durations
 
-from dvc.cli import formatter
+from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
 from dvc.log import logger
@@ -10,6 +10,7 @@ from dvc.ui import ui
 from dvc.utils import colorize
 
 if TYPE_CHECKING:
+    from dvc.repo.data import GitInfo
     from dvc.repo.data import Status as DataStatus
 
 
@@ -55,20 +56,15 @@ class CmdDataStatus(CmdBase):
     def _process_status(status: "DataStatus"):
         """Flatten stage status, and filter empty stage status contents."""
         for stage, stage_status in status.items():
-            items = stage_status
-            if isinstance(stage_status, dict):
-                items = {
-                    file: state
-                    for state, files in stage_status.items()
-                    for file in files
-                }
-            if not items:
+            if not stage_status or (
+                isinstance(stage_status, dict) and not any(stage_status.values())
+            ):
                 continue
-            yield stage, items
+            yield stage, stage_status
 
     @classmethod
     def _show_status(cls, status: "DataStatus") -> int:  # noqa: C901
-        git_info = status.pop("git")  # type: ignore[misc]
+        git_info: GitInfo = status.pop("git")  # type: ignore[misc]
         result = dict(cls._process_status(status))
         if not result:
             no_changes = "No changes"
@@ -90,7 +86,16 @@ class CmdDataStatus(CmdBase):
                     ui.write(f"  ({hint})")
 
             if isinstance(stage_status, dict):
-                items = [f"{state}: {file}" for file, state in stage_status.items()]
+                items = [
+                    f"{state}: "
+                    + (
+                        " -> ".join(change.values())
+                        if isinstance(change, dict)
+                        else change
+                    )
+                    for state, changes in stage_status.items()
+                    for change in changes
+                ]
             else:
                 items = stage_status
 
@@ -108,8 +113,10 @@ class CmdDataStatus(CmdBase):
     def run(self) -> int:
         with log_durations(logger.trace, "in data_status"):
             status = self.repo.data_status(
+                targets=self.args.targets,
                 granular=self.args.granular,
                 untracked_files=self.args.untracked_files,
+                remote=self.args.remote,
                 not_in_remote=self.args.not_in_remote,
                 remote_refresh=self.args.remote_refresh,
             )
@@ -126,9 +133,12 @@ class CmdDataStatus(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
+    data_help = "Commands related to data management."
     data_parser = subparsers.add_parser(
         "data",
         parents=[parent_parser],
+        description=append_doc_link(data_help, "data/status"),
+        help=data_help,
         formatter_class=formatter.RawDescriptionHelpFormatter,
     )
     data_subparsers = data_parser.add_subparsers(
@@ -147,6 +157,14 @@ def add_parser(subparsers, parent_parser):
         formatter_class=formatter.RawDescriptionHelpFormatter,
         help=DATA_STATUS_HELP,
     )
+    data_status_parser.add_argument(
+        "targets",
+        nargs="*",
+        help=(
+            "Limit command scope to these tracked files/directories, "
+            ".dvc files and stage names."
+        ),
+    ).complete = completion.FILE  # type: ignore[attr-defined]
     data_status_parser.add_argument(
         "--json",
         action="store_true",
@@ -173,6 +191,12 @@ def add_parser(subparsers, parent_parser):
         nargs="?",
         help="Show untracked files.",
     )
+    data_status_parser.add_argument(
+        "-r",
+        "--remote",
+        help="Remote storage to check (only applicable with --not-in-remote).",
+        metavar="<name>",
+    ).complete = completion.REMOTE
     data_status_parser.add_argument(
         "--not-in-remote",
         action="store_true",

dvc/commands/data_sync.py

@@ -22,17 +22,18 @@ class CmdDataBase(CmdBase):
 
 
 class CmdDataPull(CmdDataBase):
-    def log_summary(self, stats):
+    def log_summary(self, result):
         from dvc.commands.checkout import log_changes
 
-        log_changes(stats)
+        stats = result.pop("stats", {})
+        log_changes(result)
         super().log_summary(stats)
 
     def run(self):
         from dvc.exceptions import CheckoutError, DvcException
 
         try:
-            stats = self.repo.pull(
+            result = self.repo.pull(
                 targets=self.args.targets,
                 jobs=self.args.jobs,
                 remote=self.args.remote,
@@ -46,10 +47,10 @@ class CmdDataPull(CmdDataBase):
                 glob=self.args.glob,
                 allow_missing=self.args.allow_missing,
             )
-            self.log_summary(stats)
+            self.log_summary(result)
         except (CheckoutError, DvcException) as exc:
-            if stats := getattr(exc, "stats", {}):
-                self.log_summary(stats)
+            if result := getattr(exc, "result", {}):
+                self.log_summary(result)
             logger.exception("failed to pull data from the cloud")
             return 1
 
@@ -149,7 +150,7 @@ def add_parser(subparsers, _parent_parser):
     )
     pull_parser.add_argument(
         "-r", "--remote", help="Remote storage to pull from", metavar="<name>"
-    )
+    ).complete = completion.REMOTE
     pull_parser.add_argument(
         "-a",
         "--all-branches",
@@ -194,7 +195,7 @@ def add_parser(subparsers, _parent_parser):
     )
     pull_parser.add_argument(
         "--run-cache",
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         default=False,
         help="Fetch run history for all stages.",
     )
@@ -224,7 +225,7 @@ def add_parser(subparsers, _parent_parser):
     )
     push_parser.add_argument(
         "-r", "--remote", help="Remote storage to push to", metavar="<name>"
-    )
+    ).complete = completion.REMOTE
     push_parser.add_argument(
         "-a",
         "--all-branches",
@@ -262,7 +263,7 @@ def add_parser(subparsers, _parent_parser):
     )
     push_parser.add_argument(
         "--run-cache",
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         default=False,
         help="Push run history for all stages.",
     )
@@ -286,7 +287,7 @@ def add_parser(subparsers, _parent_parser):
     )
     fetch_parser.add_argument(
         "-r", "--remote", help="Remote storage to fetch from", metavar="<name>"
-    )
+    ).complete = completion.REMOTE
     fetch_parser.add_argument(
         "-a",
         "--all-branches",
@@ -324,7 +325,7 @@ def add_parser(subparsers, _parent_parser):
     )
     fetch_parser.add_argument(
         "--run-cache",
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         default=False,
         help="Fetch run history for all stages.",
     )
@@ -379,7 +380,7 @@ def add_parser(subparsers, _parent_parser):
         "--remote",
         help="Remote storage to compare local cache to",
         metavar="<name>",
-    )
+    ).complete = completion.REMOTE
     status_parser.add_argument(
         "-a",
         "--all-branches",

dvc/commands/dataset.py

@@ -34,7 +34,7 @@ class CmdDatasetAdd(CmdBase):
 
         url = dataset.spec.url
         ver: str = ""
-        if dataset.type == "dvcx":
+        if dataset.type == "dc":
             ver = f"v{dataset.lock.version}"
         if dataset.type == "dvc":
             if dataset.lock.path:
@@ -42,7 +42,7 @@ class CmdDatasetAdd(CmdBase):
             if rev := dataset.lock.rev:
                 ver = rev
 
-        ver_part: Optional["Text"] = None
+        ver_part: Optional[Text] = None
         if ver:
             ver_part = ui.rich_text.assemble(" @ ", (ver, "repr.number"))
         text = ui.rich_text.assemble("(", (url, "repr.url"), ver_part or "", ")")
@@ -55,7 +55,7 @@ class CmdDatasetAdd(CmdBase):
             raise DvcException("--path can't be used without --dvc")
 
         d = vars(self.args)
-        for key in ["dvc", "dvcx", "url"]:
+        for key in ["dvc", "dc", "url"]:
             if url := d.pop(key, None):
                 d.update({"type": key, "url": url})
                 break
@@ -83,13 +83,13 @@ class CmdDatasetUpdate(CmdBase):
             return CmdDatasetAdd.display(name, new, action)
         if dataset == new:
             ui.write("[yellow]Nothing to update[/]", styled=True)
-            return
+            return None
 
         assert new.lock
 
         v: Optional[tuple[str, str]] = None
-        if dataset.type == "dvcx":
-            assert new.type == "dvcx"
+        if dataset.type == "dc":
+            assert new.type == "dc"
             if new.lock.version < dataset.lock.version:
                 action = "Downgrading"
 
@@ -112,6 +112,7 @@ class CmdDatasetUpdate(CmdBase):
             assert new.type == "url"
             stats = diff_files(dataset.lock.files, new.lock.files)
             log_changes(stats)
+        return None
 
     def run(self):
         from difflib import get_close_matches
@@ -168,7 +169,7 @@ def add_parser(subparsers, parent_parser):
 
     url_exclusive_group = ds_add_parser.add_mutually_exclusive_group(required=True)
     url_exclusive_group.add_argument(
-        "--dvcx", metavar="name", help="Name of the dvcx dataset to track"
+        "--dc", metavar="name", help="Name of the DataChain dataset to track"
     )
     url_exclusive_group.add_argument(
         "--dvc",
@@ -219,7 +220,7 @@ remote://remote_name/path/to/file/or/dir (see `dvc remote`)
         "--rev",
         "--version",
         nargs="?",
-        help="DVCX dataset version or Git revision (e.g. SHA, branch, tag)",
+        help="DataChain dataset version or Git revision (e.g. SHA, branch, tag)",
         metavar="<version>",
     )
     ds_update_parser.set_defaults(func=CmdDatasetUpdate)

dvc/commands/du.py

@@ -60,7 +60,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         type=str,
         help="Remote name to set as a default in the target repository.",
-    )
+    ).complete = completion.REMOTE
     du_parser.add_argument(
         "--remote-config",
         type=str,

dvc/commands/experiments/__init__.py

@@ -58,6 +58,15 @@ def add_parser(subparsers, parent_parser):
     hide_subparsers_from_help(experiments_subparsers)
 
 
+def add_keep_selection_flag(experiments_subcmd_parser):
+    experiments_subcmd_parser.add_argument(
+        "--keep",
+        action="store_true",
+        default=False,
+        help="Keep the selected experiments instead of removing them.",
+    )
+
+
 def add_rev_selection_flags(
     experiments_subcmd_parser, command: str, default: bool = True
 ):

dvc/commands/experiments/pull.py

@@ -1,4 +1,6 @@
-from dvc.cli import formatter
+import argparse
+
+from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
 from dvc.log import logger
@@ -69,7 +71,7 @@ def add_parser(experiments_subparsers, parent_parser):
         dest="dvc_remote",
         metavar="<name>",
         help="Name of the DVC remote to use when pulling cached outputs.",
-    )
+    ).complete = completion.REMOTE
     experiments_pull_parser.add_argument(
         "-j",
         "--jobs",
@@ -81,7 +83,7 @@ def add_parser(experiments_subparsers, parent_parser):
     )
     experiments_pull_parser.add_argument(
         "--run-cache",
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         default=False,
         help="Pull run history for all stages.",
     )

dvc/commands/experiments/push.py

@@ -1,3 +1,4 @@
+import argparse
 from typing import Any
 
 from dvc.cli import completion, formatter
@@ -110,7 +111,7 @@ def add_parser(experiments_subparsers, parent_parser):
         dest="dvc_remote",
         metavar="<name>",
         help="Name of the DVC remote to use when pushing cached outputs.",
-    )
+    ).complete = completion.REMOTE
     experiments_push_parser.add_argument(
         "-j",
         "--jobs",
@@ -120,7 +121,7 @@ def add_parser(experiments_subparsers, parent_parser):
     )
     experiments_push_parser.add_argument(
         "--run-cache",
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         default=False,
         help="Push run history for all stages.",
     )

dvc/commands/experiments/remove.py

@@ -34,6 +34,7 @@ class CmdExperimentsRemove(CmdBase):
             num=self.args.num,
             queue=self.args.queue,
             git_remote=self.args.git_remote,
+            keep=self.args.keep,
         )
         if removed:
             ui.write(f"Removed experiments: {humanize.join(map(repr, removed))}")
@@ -44,7 +45,7 @@ class CmdExperimentsRemove(CmdBase):
 
 
 def add_parser(experiments_subparsers, parent_parser):
-    from . import add_rev_selection_flags
+    from . import add_keep_selection_flag, add_rev_selection_flags
 
     EXPERIMENTS_REMOVE_HELP = "Remove experiments."
     experiments_remove_parser = experiments_subparsers.add_parser(
@@ -57,6 +58,7 @@ def add_parser(experiments_subparsers, parent_parser):
     )
     remove_group = experiments_remove_parser.add_mutually_exclusive_group()
     add_rev_selection_flags(experiments_remove_parser, "Remove", False)
+    add_keep_selection_flag(experiments_remove_parser)
     remove_group.add_argument(
         "--queue", action="store_true", help="Remove all queued experiments."
     )

dvc/commands/experiments/show.py

@@ -1,6 +1,6 @@
 import argparse
 import re
-from collections.abc import Iterable
+from collections.abc import Collection, Iterable
 from datetime import date, datetime
 from typing import TYPE_CHECKING
 
@@ -59,17 +59,16 @@ def baseline_styler(typ):
 def show_experiments(
     td: "TabularData",
     headers: dict[str, Iterable[str]],
-    keep=None,
-    drop=None,
+    keep: Collection[str] = (),
+    drop: Collection[str] = (),
     pager=True,
     csv=False,
     markdown=False,
     **kwargs,
 ):
     if keep:
-        for col in td.keys():  # noqa: SIM118
-            if re.match(keep, col):
-                td.protect(col)
+        keep_re = re.compile("|".join(keep))
+        td.protect(*(col for col in td.keys() if keep_re.match(col)))  # noqa: SIM118
 
     for col in ("State", "Executor"):
         if td.is_empty(col):
@@ -110,8 +109,9 @@ def show_experiments(
         td.drop_duplicates("cols", ignore_empty=False)
 
     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
+    if drop:
+        drop_re = re.compile("|".join(drop))
+        cols_to_drop = {col for col in td.keys() if drop_re.match(col)}  # noqa: SIM118
     td.drop(*cols_to_drop)
 
     td.render(
@@ -150,6 +150,7 @@ class CmdExperimentsShow(CmdBase):
                 all_commits=self.args.all_commits,
                 hide_queued=self.args.hide_queued,
                 hide_failed=self.args.hide_failed,
+                hide_workspace=self.args.hide_workspace,
                 revs=self.args.rev,
                 num=self.args.num,
                 sha_only=self.args.sha,
@@ -236,11 +237,15 @@ def add_parser(experiments_subparsers, parent_parser):
     )
     experiments_show_parser.add_argument(
         "--drop",
+        action="append",
+        default=[],
         help="Remove the columns matching the specified regex pattern.",
         metavar="<regex_pattern>",
     )
     experiments_show_parser.add_argument(
         "--keep",
+        action="append",
+        default=[],
         help="Preserve the columns matching the specified regex pattern.",
         metavar="<regex_pattern>",
     )
@@ -279,6 +284,12 @@ def add_parser(experiments_subparsers, parent_parser):
         default=False,
         help="Hide queued experiments in the table.",
     )
+    experiments_show_parser.add_argument(
+        "--hide-workspace",
+        action="store_true",
+        default=False,
+        help="Hide workspace row in the table.",
+    )
     experiments_show_parser.add_argument(
         "--json",
         action="store_true",

dvc/commands/gc.py

@@ -1,6 +1,6 @@
 import os
 
-from dvc.cli import formatter
+from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBase
 from dvc.cli.utils import append_doc_link
 from dvc.log import logger
@@ -54,7 +54,7 @@ class CmdGC(CmdBase):
             msg += " and all experiments"
 
         if self.args.not_in_remote:
-            msg += " that are present in the DVC remote"
+            msg += " that are not present in the DVC remote"
 
         if self.args.repos:
             msg += " of the current and the following repos:"
@@ -188,7 +188,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         help="Remote storage to collect garbage in",
         metavar="<name>",
-    )
+    ).complete = completion.REMOTE
     gc_parser.add_argument(
         "--skip-failed",
         action="store_true",

dvc/commands/get.py

@@ -121,7 +121,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         type=str,
         help="Remote name to set as a default in the target repository.",
-    )
+    ).complete = completion.REMOTE
     get_parser.add_argument(
         "--remote-config",
         type=str,

dvc/commands/imp.py

@@ -115,7 +115,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         type=str,
         help="Remote name to set as a default in the target repository.",
-    )
+    ).complete = completion.REMOTE
     import_parser.add_argument(
         "--remote-config",
         type=str,

dvc/commands/imp_url.py

@@ -73,7 +73,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         help="Remote storage to download to",
         metavar="<name>",
-    )
+    ).complete = completion.REMOTE
     no_download_exec_group = import_parser.add_mutually_exclusive_group()
     no_download_exec_group.add_argument(
         "--no-exec",

dvc/commands/init.py

@@ -42,7 +42,7 @@ class CmdInit(CmdBaseNoRepo):
 
         try:
             with Repo.init(
-                ".",
+                self.args.directory,
                 no_scm=self.args.no_scm,
                 force=self.args.force,
                 subdir=self.args.subdir,
@@ -57,10 +57,11 @@ class CmdInit(CmdBaseNoRepo):
 
 def add_parser(subparsers, parent_parser):
     """Setup parser for `dvc init`."""
-    INIT_HELP = "Initialize DVC in the current directory."
+    INIT_HELP = "Initialize DVC repository."
     INIT_DESCRIPTION = (
-        "Initialize DVC in the current directory. Expects directory\n"
-        "to be a Git repository unless --no-scm option is specified."
+        "Initialize DVC repository in the given directory (defaults to the current "
+        "working directory).\n"
+        "Expects directory to be a Git repository unless --no-scm option is specified."
     )
 
     init_parser = subparsers.add_parser(
@@ -70,6 +71,14 @@ def add_parser(subparsers, parent_parser):
         help=INIT_HELP,
         formatter_class=formatter.RawDescriptionHelpFormatter,
     )
+    init_parser.add_argument(
+        "directory",
+        nargs="?",
+        default=".",
+        help=(
+            "Directory to initialize DVC in. Defaults to the current working directory."
+        ),
+    )
     init_parser.add_argument(
         "--no-scm",
         action="store_true",

dvc/commands/ls/__init__.py

@@ -1,3 +1,5 @@
+from typing import Callable
+
 from dvc.cli import completion, formatter
 from dvc.cli.command import CmdBaseNoRepo
 from dvc.cli.utils import DictAction, append_doc_link
@@ -9,54 +11,178 @@ from dvc.ui import ui
 logger = logger.getChild(__name__)
 
 
-def _format_entry(entry, fmt):
-    from dvc.utils.humanize import naturalsize
+def _get_formatter(with_color: bool = False) -> Callable[[dict], str]:
+    def fmt(entry: dict) -> str:
+        return entry["path"]
 
-    size = entry.get("size")
-    if size is None:
-        size = ""
-    else:
-        size = naturalsize(size)
-    return size, fmt(entry)
-
-
-def show_entries(entries, with_color=False, with_size=False):
     if with_color:
         ls_colors = LsColors()
-        fmt = ls_colors.format
-    else:
+        return ls_colors.format
 
-        def fmt(entry):
-            return entry["path"]
+    return fmt
 
+
+def _format_entry(entry, name, with_size=True, with_hash=False):
+    from dvc.utils.humanize import naturalsize
+
+    ret = []
     if with_size:
-        ui.table([_format_entry(entry, fmt) for entry in entries])
+        size = entry.get("size")
+        if size is None or (size <= 0 and entry.get("isdir")):
+            size = ""
+        else:
+            size = naturalsize(size)
+        ret.append(size)
+    if with_hash:
+        md5 = entry.get("md5", "")
+        ret.append(md5)
+    ret.append(name)
+    return ret
+
+
+def show_entries(entries, with_color=False, with_size=False, with_hash=False):
+    fmt = _get_formatter(with_color)
+    if with_size or with_hash:
+        colalign = ("right",) if with_size else None
+        ui.table(
+            [
+                _format_entry(
+                    entry,
+                    fmt(entry),
+                    with_size=with_size,
+                    with_hash=with_hash,
+                )
+                for entry in entries
+            ],
+            colalign=colalign,
+        )
         return
 
     # NOTE: this is faster than ui.table for very large number of entries
     ui.write("\n".join(fmt(entry) for entry in entries))
 
 
+class TreePart:
+    Edge = "├── "
+    Line = "│   "
+    Corner = "└── "
+    Blank = "    "
+
+
+def _build_tree_structure(
+    entries, with_color=False, with_size=False, with_hash=False, _depth=0, _prefix=""
+):
+    rows = []
+    fmt = _get_formatter(with_color)
+
+    num_entries = len(entries)
+    for i, (name, entry) in enumerate(entries.items()):
+        entry["path"] = name
+        is_last = i >= num_entries - 1
+        tree_part = ""
+        if _depth > 0:
+            tree_part = TreePart.Corner if is_last else TreePart.Edge
+
+        row = _format_entry(
+            entry,
+            _prefix + tree_part + fmt(entry),
+            with_size=with_size,
+            with_hash=with_hash,
+        )
+        rows.append(row)
+
+        if contents := entry.get("contents"):
+            new_prefix = _prefix
+            if _depth > 0:
+                new_prefix += TreePart.Blank if is_last else TreePart.Line
+            new_rows = _build_tree_structure(
+                contents,
+                with_color=with_color,
+                with_size=with_size,
+                with_hash=with_hash,
+                _depth=_depth + 1,
+                _prefix=new_prefix,
+            )
+            rows.extend(new_rows)
+
+    return rows
+
+
+def show_tree(entries, with_color=False, with_size=False, with_hash=False):
+    import tabulate
+
+    rows = _build_tree_structure(
+        entries,
+        with_color=with_color,
+        with_size=with_size,
+        with_hash=with_hash,
+    )
+
+    colalign = ("right",) if with_size else None
+
+    _orig = tabulate.PRESERVE_WHITESPACE
+    tabulate.PRESERVE_WHITESPACE = True
+    try:
+        ui.table(rows, colalign=colalign)
+    finally:
+        tabulate.PRESERVE_WHITESPACE = _orig
+
+
 class CmdList(CmdBaseNoRepo):
-    def run(self):
+    def _show_tree(self):
+        from dvc.repo.ls import ls_tree
+
+        entries = ls_tree(
+            self.args.url,
+            self.args.path,
+            rev=self.args.rev,
+            dvc_only=self.args.dvc_only,
+            config=self.args.config,
+            remote=self.args.remote,
+            remote_config=self.args.remote_config,
+            maxdepth=self.args.level,
+        )
+        show_tree(
+            entries,
+            with_color=True,
+            with_size=self.args.size,
+            with_hash=self.args.show_hash,
+        )
+        return 0
+
+    def _show_list(self):
         from dvc.repo import Repo
 
-        try:
-            entries = Repo.ls(
-                self.args.url,
-                self.args.path,
-                rev=self.args.rev,
-                recursive=self.args.recursive,
-                dvc_only=self.args.dvc_only,
-                config=self.args.config,
-                remote=self.args.remote,
-                remote_config=self.args.remote_config,
+        entries = Repo.ls(
+            self.args.url,
+            self.args.path,
+            rev=self.args.rev,
+            recursive=self.args.recursive,
+            dvc_only=self.args.dvc_only,
+            config=self.args.config,
+            remote=self.args.remote,
+            remote_config=self.args.remote_config,
+            maxdepth=self.args.level,
+        )
+        if self.args.json:
+            ui.write_json(entries)
+        elif entries:
+            show_entries(
+                entries,
+                with_color=True,
+                with_size=self.args.size,
+                with_hash=self.args.show_hash,
             )
-            if self.args.json:
-                ui.write_json(entries)
-            elif entries:
-                show_entries(entries, with_color=True, with_size=self.args.size)
-            return 0
+        return 0
+
+    def run(self):
+        if self.args.tree and self.args.json:
+            raise DvcException("Cannot use --tree and --json options together.")
+
+        try:
+            if self.args.tree:
+                return self._show_tree()
+            return self._show_list()
         except FileNotFoundError:
             logger.exception("")
             return 1
@@ -85,6 +211,19 @@ def add_parser(subparsers, parent_parser):
         action="store_true",
         help="Recursively list files.",
     )
+    list_parser.add_argument(
+        "-T",
+        "--tree",
+        action="store_true",
+        help="Recurse into directories as a tree.",
+    )
+    list_parser.add_argument(
+        "-L",
+        "--level",
+        metavar="depth",
+        type=int,
+        help="Limit the depth of recursion.",
+    )
     list_parser.add_argument(
         "--dvc-only", action="store_true", help="Show only DVC outputs."
     )
@@ -111,7 +250,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         type=str,
         help="Remote name to set as a default in the target repository.",
-    )
+    ).complete = completion.REMOTE
     list_parser.add_argument(
         "--remote-config",
         type=str,
@@ -123,6 +262,12 @@ def add_parser(subparsers, parent_parser):
         ),
     )
     list_parser.add_argument("--size", action="store_true", help="Show sizes.")
+    list_parser.add_argument(
+        "--show-hash",
+        help="Display hash value for each item.",
+        action="store_true",
+        default=False,
+    )
     list_parser.add_argument(
         "path",
         nargs="?",

dvc/commands/ls/ls_colors.py

@@ -32,7 +32,9 @@ class LsColors:
         if entry.get("isexec", False):
             return self._format(text, code="ex")
 
-        _, ext = os.path.splitext(text)
+        stem, ext = os.path.splitext(text)
+        if not ext and stem.startswith("."):
+            ext = stem
         return self._format(text, ext=ext)
 
     def _format(self, text, code=None, ext=None):

dvc/commands/ls_url.py

@@ -3,26 +3,45 @@ from dvc.cli.command import CmdBaseNoRepo
 from dvc.cli.utils import DictAction, append_doc_link
 from dvc.log import logger
 
-from .ls import show_entries
+from .ls import show_entries, show_tree
 
 logger = logger.getChild(__name__)
 
 
 class CmdListUrl(CmdBaseNoRepo):
-    def run(self):
-        from dvc.config import Config
+    def _show_tree(self, config):
+        from dvc.fs import parse_external_url
+        from dvc.repo.ls import _ls_tree
+
+        fs, fs_path = parse_external_url(
+            self.args.url, fs_config=self.args.fs_config, config=config
+        )
+        entries = _ls_tree(fs, fs_path, maxdepth=self.args.level)
+        show_tree(entries, with_color=True, with_size=self.args.size)
+        return 0
+
+    def _show_list(self, config):
         from dvc.repo import Repo
 
         entries = Repo.ls_url(
             self.args.url,
             recursive=self.args.recursive,
+            maxdepth=self.args.level,
             fs_config=self.args.fs_config,
-            config=Config.from_cwd(),
+            config=config,
         )
         if entries:
             show_entries(entries, with_color=True, with_size=self.args.size)
         return 0
 
+    def run(self):
+        from dvc.config import Config
+
+        config = Config.from_cwd()
+        if self.args.tree:
+            return self._show_tree(config=config)
+        return self._show_list(config=config)
+
 
 def add_parser(subparsers, parent_parser):
     LS_HELP = "List directory contents from URL."
@@ -40,6 +59,19 @@ def add_parser(subparsers, parent_parser):
     lsurl_parser.add_argument(
         "-R", "--recursive", action="store_true", help="Recursively list files."
     )
+    lsurl_parser.add_argument(
+        "-T",
+        "--tree",
+        action="store_true",
+        help="Recurse into directories as a tree.",
+    )
+    lsurl_parser.add_argument(
+        "-L",
+        "--level",
+        metavar="depth",
+        type=int,
+        help="Limit the depth of recursion.",
+    )
     lsurl_parser.add_argument("--size", action="store_true", help="Show sizes.")
     lsurl_parser.add_argument(
         "--fs-config",

dvc/commands/plots.py

@@ -72,7 +72,7 @@ class CmdPlots(CmdBase):
                 html_template_path = os.path.join(self.repo.dvc_dir, html_template_path)
         return html_template_path
 
-    def run(self) -> int:  # noqa: C901, PLR0911, PLR0912
+    def run(self) -> int:  # noqa: C901, PLR0911
         from pathlib import Path
 
         from dvc.render.match import match_defs_renderers

dvc/commands/remote.py

@@ -1,4 +1,4 @@
-from dvc.cli import formatter
+from dvc.cli import completion, formatter
 from dvc.cli.utils import append_doc_link
 from dvc.commands.config import CmdConfig
 from dvc.ui import ui
@@ -110,8 +110,16 @@ class CmdRemoteDefault(CmdRemote):
 class CmdRemoteList(CmdRemote):
     def run(self):
         conf = self.config.read(self.args.level)
+        default_remote = conf["core"].get("remote")
+
         for name, remote_conf in conf["remote"].items():
-            ui.write(name, remote_conf["url"], sep="\t")
+            if name == default_remote:
+                text = f"{name}\t{remote_conf['url']}\t(default)"
+                color = "green"
+            else:
+                text = f"{name}\t{remote_conf['url']}"
+                color = ""
+            ui.write(ui.rich_text(text, style=color), styled=True)
         return 0
 
 
@@ -202,7 +210,9 @@ def add_parser(subparsers, parent_parser):
         help=REMOTE_DEFAULT_HELP,
         formatter_class=formatter.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"
+    ).complete = completion.REMOTE
     remote_default_parser.add_argument(
         "-u",
         "--unset",
@@ -220,8 +230,12 @@ def add_parser(subparsers, parent_parser):
         help=REMOTE_MODIFY_HELP,
         formatter_class=formatter.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(
+        "name", help="Name of the remote"
+    ).complete = completion.REMOTE
+    remote_modify_parser.add_argument(
+        "option", help="Name of the option to modify."
+    ).complete = completion.REMOTE_CONFIG_VARS
     remote_modify_parser.add_argument(
         "value", nargs="?", help="(optional) Value of the option."
     )
@@ -252,7 +266,9 @@ def add_parser(subparsers, parent_parser):
         help=REMOTE_REMOVE_HELP,
         formatter_class=formatter.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."
+    ).complete = completion.REMOTE
     remote_remove_parser.set_defaults(func=CmdRemoteRemove)
     REMOTE_RENAME_HELP = "Rename a DVC remote"
     remote_rename_parser = remote_subparsers.add_parser(

dvc/commands/repro.py

@@ -117,10 +117,7 @@ and then the stage name name.
         "--pull",
         action="store_true",
         default=False,
-        help=(
-            "Try automatically pulling missing cache for outputs restored "
-            "from the run-cache."
-        ),
+        help="Try automatically pulling missing data.",
     )
     repro_parser.add_argument(
         "--allow-missing",

dvc/commands/stage.py

@@ -68,7 +68,7 @@ def prepare_stages_data(
 class CmdStageList(CmdBase):
     def _get_stages(self) -> Iterable["Stage"]:
         if self.args.all:
-            stages: list["Stage"] = self.repo.index.stages
+            stages: list[Stage] = self.repo.index.stages
             logger.trace("%d no. of stages found", len(stages))
             return stages
 

dvc/commands/status.py

@@ -71,7 +71,7 @@ class CmdDataStatus(CmdDataBase):
                 return 0
 
             if self.args.quiet:
-                return bool(st)
+                return int(bool(st))
 
             if st:
                 self._show(st, indent)

dvc/commands/studio.py

@@ -18,11 +18,16 @@ class CmdStudioLogin(CmdConfig):
         from dvc.utils.studio import STUDIO_URL
         from dvc_studio_client.auth import StudioAuthError, get_access_token
 
+        studio = self.config.get("studio", {})
         name = self.args.name
-        hostname = self.args.hostname or os.environ.get(DVC_STUDIO_URL) or STUDIO_URL
+        hostname = (
+            self.args.hostname
+            or os.environ.get(DVC_STUDIO_URL)
+            or studio.get("url")
+            or STUDIO_URL
+        )
         scopes = self.args.scopes
 
-        studio = self.config.get("studio", {})
         if studio.get("url", hostname) == hostname and "token" in studio:
             raise DvcException(
                 "Token already exists. "

dvc/commands/update.py

@@ -74,7 +74,7 @@ def add_parser(subparsers, parent_parser):
         "--remote",
         help="Remote storage to perform updates to",
         metavar="<name>",
-    )
+    ).complete = completion.REMOTE
     update_parser.add_argument(
         "-j",
         "--jobs",

dvc/compare.py

@@ -160,7 +160,7 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
             if key not in keys:
                 self.add_column(key)
 
-        row: list["CellT"] = [
+        row: list[CellT] = [
             with_value(d.get(key), self._fill_value) for key in self.keys()
         ]
         self.append(row)

dvc/config.py

@@ -1,6 +1,8 @@
 """DVC config objects."""
 
+import ntpath
 import os
+import posixpath
 import re
 from contextlib import contextmanager
 from functools import partial
@@ -137,6 +139,7 @@ class Config(dict):
             return global_config_dir()
         if level == "system":
             return system_config_dir()
+        return None
 
     @cached_property
     def files(self) -> dict[str, str]:
@@ -268,12 +271,17 @@ class Config(dict):
         if re.match(r"\w+://", path):
             return path
 
+        if os.name == "nt" and posixpath.isabs(path) and ntpath.sep not in path:
+            return path
+
         if os.path.isabs(path):
             return path
 
         # on windows convert slashes to backslashes
         # to have path compatible with abs_conf_dir
         if os.path.sep == "\\" and "/" in path:
+            if path.startswith("/"):
+                path = path.replace("/", "\\\\", 1)
             path = path.replace("/", "\\")
 
         expanded = os.path.expanduser(path)
@@ -305,6 +313,9 @@ class Config(dict):
         if os.path.expanduser(path) != path:
             return localfs.as_posix(path)
 
+        if os.name == "nt" and posixpath.isabs(path) and ntpath.sep not in path:
+            return path
+
         if isinstance(path, RelPath) or not os.path.isabs(path):
             path = relpath(path, conf_dir)
             return localfs.as_posix(path)
@@ -330,6 +341,7 @@ class Config(dict):
                     "gdrive_user_credentials_file": func,
                     "gdrive_service_account_json_file_path": func,
                     "credentialpath": func,
+                    "configpath": func,
                     "keyfile": func,
                     "cert_path": func,
                     "key_path": func,

dvc/config_schema.py

@@ -1,4 +1,5 @@
 import os
+from typing import TYPE_CHECKING
 from urllib.parse import urlparse
 
 from funcy import once, walk_values
@@ -10,6 +11,7 @@ from voluptuous import (
     Exclusive,
     Invalid,
     Lower,
+    Marker,
     Optional,
     Range,
     Schema,
@@ -17,6 +19,9 @@ from voluptuous import (
 
 from dvc.log import logger
 
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
 logger = logger.getChild(__name__)
 
 Bool = All(
@@ -55,23 +60,27 @@ def Choices(*choices):  # noqa: N802
     return Any(*choices, msg="expected one of {}".format(", ".join(choices)))
 
 
+def _get_schema_from_url(url: str) -> str:
+    parsed = urlparse(url)
+    # Windows absolute paths should really have scheme == "" (local)
+    if os.name == "nt" and len(parsed.scheme) == 1 and not parsed.netloc:
+        return ""
+    if not parsed.netloc:
+        return ""
+    return parsed.scheme
+
+
 def ByUrl(mapping):  # noqa: N802
-    schemas = walk_values(Schema, mapping)
+    schemas: dict[str, Schema] = walk_values(Schema, mapping)
 
     def validate(data):
         if "url" not in data:
             raise Invalid("expected 'url'")
 
-        parsed = urlparse(data["url"])
-        # Windows absolute paths should really have scheme == "" (local)
-        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}://")
-
-        return schemas[parsed.scheme](data)
+        scheme = _get_schema_from_url(data["url"])
+        if scheme not in schemas:
+            raise Invalid(f"Unsupported URL type {scheme}://")
+        return schemas[scheme](data)
 
     return validate
 
@@ -112,17 +121,19 @@ class FeatureSchema(Schema):
         return ret
 
 
+DEPRECATED = "==DEPRECATED=="
+
 REMOTE_COMMON = {
     "url": str,
     "checksum_jobs": All(Coerce(int), Range(1)),
     "jobs": All(Coerce(int), Range(1)),
     Optional("worktree"): Bool,
-    Optional("no_traverse"): Bool,  # obsoleted
+    Optional("no_traverse", description=DEPRECATED): Bool,  # obsoleted
     Optional("version_aware"): Bool,
 }
 LOCAL_COMMON = {
     "type": supported_cache_type,
-    Optional("protected", default=False): Bool,  # obsoleted
+    Optional("protected", default=False, description=DEPRECATED): Bool,  # obsoleted
     "shared": All(Lower, Choices("group")),
     Optional("slow_link_warning", default=True): Bool,
     Optional("verify", default=False): Bool,
@@ -152,6 +163,127 @@ WEBDAV_COMMON = {
     Optional("verify", default=False): Bool,
 }
 
+REMOTE_SCHEMAS = {
+    "": LOCAL_COMMON | REMOTE_COMMON,
+    "s3": {
+        "region": str,
+        "profile": str,
+        "credentialpath": str,
+        "configpath": str,
+        "endpointurl": str,
+        "access_key_id": str,
+        "secret_access_key": str,
+        "session_token": str,
+        Optional(
+            "listobjects", default=False, description=DEPRECATED
+        ): Bool,  # obsoleted
+        Optional("use_ssl", default=True): Bool,
+        Optional("allow_anonymous_login", default=False): Bool,
+        "ssl_verify": Any(Bool, str),
+        "sse": str,
+        "sse_kms_key_id": str,
+        "sse_customer_algorithm": str,
+        "sse_customer_key": str,
+        "acl": str,
+        "grant_read": str,
+        "grant_read_acp": str,
+        "grant_write_acp": str,
+        "grant_full_control": str,
+        "cache_regions": bool,
+        "read_timeout": Coerce(int),
+        "connect_timeout": Coerce(int),
+        Optional("verify", default=False): Bool,
+        **REMOTE_COMMON,
+    },
+    "gs": {
+        "projectname": str,
+        "credentialpath": str,
+        "endpointurl": str,
+        Optional("verify", default=False): Bool,
+        Optional("allow_anonymous_login", default=False): Bool,
+        **REMOTE_COMMON,
+    },
+    "ssh": {
+        "type": supported_cache_type,
+        "port": Coerce(int),
+        "user": str,
+        "password": str,
+        "ask_password": Bool,
+        "passphrase": str,
+        "ask_passphrase": Bool,
+        "keyfile": str,
+        "timeout": Coerce(int),
+        "gss_auth": Bool,
+        "allow_agent": Bool,
+        "max_sessions": Coerce(int),
+        Optional("verify", default=False): Bool,
+        **REMOTE_COMMON,
+    },
+    "hdfs": {
+        "user": str,
+        "kerb_ticket": str,
+        "replication": int,
+        **REMOTE_COMMON,
+    },
+    "webhdfs": {
+        "kerberos": Bool,
+        "kerberos_principal": str,
+        "proxy_to": str,
+        "ssl_verify": Any(Bool, str),
+        "token": str,
+        "use_https": Bool,
+        "user": str,
+        "password": str,
+        "data_proxy_target": str,
+        Optional("verify", default=False): Bool,
+        **REMOTE_COMMON,
+    },
+    "azure": {
+        "connection_string": str,
+        "sas_token": str,
+        "account_name": str,
+        "account_key": str,
+        "tenant_id": str,
+        "client_id": str,
+        "client_secret": str,
+        "allow_anonymous_login": Bool,
+        "exclude_environment_credential": Bool,
+        "exclude_visual_studio_code_credential": Bool,
+        "exclude_shared_token_cache_credential": Bool,
+        "exclude_managed_identity_credential": Bool,
+        Optional("verify", default=False): Bool,
+        "timeout": Coerce(int),
+        "read_timeout": Coerce(int),
+        "connection_timeout": Coerce(int),
+        **REMOTE_COMMON,
+    },
+    "oss": {
+        "oss_key_id": str,
+        "oss_key_secret": str,
+        "oss_endpoint": str,
+        Optional("verify", default=True): Bool,
+        **REMOTE_COMMON,
+    },
+    "gdrive": {
+        "profile": str,
+        "gdrive_use_service_account": Bool,
+        "gdrive_client_id": str,
+        "gdrive_client_secret": str,
+        "gdrive_user_credentials_file": str,
+        "gdrive_service_account_user_email": str,
+        "gdrive_service_account_json_file_path": str,
+        Optional("gdrive_trash_only", default=False): Bool,
+        Optional("gdrive_acknowledge_abuse", default=False): Bool,
+        Optional("verify", default=True): Bool,
+        **REMOTE_COMMON,
+    },
+    "http": HTTP_COMMON | REMOTE_COMMON,
+    "https": HTTP_COMMON | REMOTE_COMMON,
+    "webdav": WEBDAV_COMMON | REMOTE_COMMON,
+    "webdavs": WEBDAV_COMMON | REMOTE_COMMON,
+    "remote": {str: object},  # Any of the above options are valid
+}
+
 SCHEMA = {
     "core": {
         "remote": Lower,
@@ -161,151 +293,37 @@ SCHEMA = {
         Optional("hardlink_lock", default=False): Bool,
         Optional("no_scm", default=False): Bool,
         Optional("autostage", default=False): Bool,
-        Optional("experiments"): Bool,  # obsoleted
+        Optional("experiments", description=DEPRECATED): Bool,  # obsoleted
         Optional("check_update", default=True): Bool,
         "site_cache_dir": str,
         "machine": Lower,
     },
     "cache": {
-        "local": str,  # obsoleted
-        "s3": str,  # obsoleted
-        "gs": str,  # obsoleted
-        "hdfs": str,  # obsoleted
-        "webhdfs": str,  # obsoleted
-        "ssh": str,  # obsoleted
-        "azure": str,  # obsoleted
+        Marker("local", description=DEPRECATED): str,  # obsoleted
+        Marker("s3", description=DEPRECATED): str,  # obsoleted
+        Marker("gs", description=DEPRECATED): str,  # obsoleted
+        Marker("hdfs", description=DEPRECATED): str,  # obsoleted
+        Marker("webhdfs", description=DEPRECATED): str,  # obsoleted
+        Marker("ssh", description=DEPRECATED): str,  # obsoleted
+        Marker("azure", description=DEPRECATED): str,  # obsoleted
         # This is for default local cache
         "dir": str,
         **LOCAL_COMMON,
     },
     "remote": {
-        str: ByUrl(
-            {
-                "": LOCAL_COMMON | REMOTE_COMMON,
-                "s3": {
-                    "region": str,
-                    "profile": str,
-                    "credentialpath": str,
-                    "configpath": str,
-                    "endpointurl": str,
-                    "access_key_id": str,
-                    "secret_access_key": str,
-                    "session_token": str,
-                    Optional("listobjects", default=False): Bool,  # obsoleted
-                    Optional("use_ssl", default=True): Bool,
-                    Optional("allow_anonymous_login", default=False): Bool,
-                    "ssl_verify": Any(Bool, str),
-                    "sse": str,
-                    "sse_kms_key_id": str,
-                    "sse_customer_algorithm": str,
-                    "sse_customer_key": str,
-                    "acl": str,
-                    "grant_read": str,
-                    "grant_read_acp": str,
-                    "grant_write_acp": str,
-                    "grant_full_control": str,
-                    "cache_regions": bool,
-                    "read_timeout": Coerce(int),
-                    "connect_timeout": Coerce(int),
-                    Optional("verify", default=False): Bool,
-                    **REMOTE_COMMON,
-                },
-                "gs": {
-                    "projectname": str,
-                    "credentialpath": str,
-                    "endpointurl": str,
-                    Optional("verify", default=False): Bool,
-                    **REMOTE_COMMON,
-                },
-                "ssh": {
-                    "type": supported_cache_type,
-                    "port": Coerce(int),
-                    "user": str,
-                    "password": str,
-                    "ask_password": Bool,
-                    "passphrase": str,
-                    "ask_passphrase": Bool,
-                    "keyfile": str,
-                    "timeout": Coerce(int),
-                    "gss_auth": Bool,
-                    "allow_agent": Bool,
-                    "max_sessions": Coerce(int),
-                    Optional("verify", default=False): Bool,
-                    **REMOTE_COMMON,
-                },
-                "hdfs": {
-                    "user": str,
-                    "kerb_ticket": str,
-                    "replication": int,
-                    **REMOTE_COMMON,
-                },
-                "webhdfs": {
-                    "kerberos": Bool,
-                    "kerberos_principal": str,
-                    "proxy_to": str,
-                    "ssl_verify": Any(Bool, str),
-                    "token": str,
-                    "use_https": Bool,
-                    "user": str,
-                    "password": str,
-                    "data_proxy_target": str,
-                    Optional("verify", default=False): Bool,
-                    **REMOTE_COMMON,
-                },
-                "azure": {
-                    "connection_string": str,
-                    "sas_token": str,
-                    "account_name": str,
-                    "account_key": str,
-                    "tenant_id": str,
-                    "client_id": str,
-                    "client_secret": str,
-                    "allow_anonymous_login": Bool,
-                    "exclude_environment_credential": Bool,
-                    "exclude_visual_studio_code_credential": Bool,
-                    "exclude_shared_token_cache_credential": Bool,
-                    "exclude_managed_identity_credential": Bool,
-                    Optional("verify", default=False): Bool,
-                    "timeout": Coerce(int),
-                    "read_timeout": Coerce(int),
-                    "connection_timeout": Coerce(int),
-                    **REMOTE_COMMON,
-                },
-                "oss": {
-                    "oss_key_id": str,
-                    "oss_key_secret": str,
-                    "oss_endpoint": str,
-                    Optional("verify", default=True): Bool,
-                    **REMOTE_COMMON,
-                },
-                "gdrive": {
-                    "profile": str,
-                    "gdrive_use_service_account": Bool,
-                    "gdrive_client_id": str,
-                    "gdrive_client_secret": str,
-                    "gdrive_user_credentials_file": str,
-                    "gdrive_service_account_user_email": str,
-                    "gdrive_service_account_json_file_path": str,
-                    Optional("gdrive_trash_only", default=False): Bool,
-                    Optional("gdrive_acknowledge_abuse", default=False): Bool,
-                    Optional("verify", default=True): Bool,
-                    **REMOTE_COMMON,
-                },
-                "http": HTTP_COMMON | REMOTE_COMMON,
-                "https": HTTP_COMMON | REMOTE_COMMON,
-                "webdav": WEBDAV_COMMON | REMOTE_COMMON,
-                "webdavs": WEBDAV_COMMON | REMOTE_COMMON,
-                "remote": {str: object},  # Any of the above options are valid
-            }
-        )
+        str: ByUrl(REMOTE_SCHEMAS),
     },
     "state": {
-        "dir": str,  # obsoleted
-        "row_limit": All(Coerce(int), Range(1)),  # obsoleted
-        "row_cleanup_quota": All(Coerce(int), Range(0, 100)),  # obsoleted
+        Marker("dir", description=DEPRECATED): str,  # obsoleted
+        Marker("row_limit", description=DEPRECATED): All(
+            Coerce(int), Range(1)
+        ),  # obsoleted
+        Marker("row_cleanup_quota", description=DEPRECATED): All(
+            Coerce(int), Range(0, 100)
+        ),  # obsoleted
     },
     "index": {
-        "dir": str,  # obsoleted
+        Marker("dir", description=DEPRECATED): str,  # obsoleted
     },
     "machine": {
         str: {
@@ -335,13 +353,13 @@ SCHEMA = {
         "out_dir": str,
     },
     "exp": {
-        "code": str,
-        "data": str,
-        "models": str,
-        "metrics": str,
-        "params": str,
-        "plots": str,
-        "live": str,
+        Marker("code", description=DEPRECATED): str,
+        Marker("data", description=DEPRECATED): str,
+        Marker("models", description=DEPRECATED): str,
+        Marker("metrics", description=DEPRECATED): str,
+        Marker("params", description=DEPRECATED): str,
+        Marker("plots", description=DEPRECATED): str,
+        Marker("live", description=DEPRECATED): str,
         "auto_push": Bool,
         "git_remote": str,
     },
@@ -370,3 +388,37 @@ SCHEMA = {
         },
     },
 }
+
+
+def config_vars_for_completion(d: dict = SCHEMA, path: str = "") -> "Iterator[str]":
+    for k, v in d.items():
+        if k in ("machine", "feature"):
+            continue
+        if isinstance(k, Marker):
+            if k.description == DEPRECATED:
+                continue
+            k = k.schema
+        if not isinstance(k, str):
+            continue
+        keypath = f"{path}.{k}" if path else k
+        if isinstance(v, dict):
+            yield from config_vars_for_completion(v, keypath)
+        else:
+            yield keypath
+
+
+def contextual_config_vars_for_completion(config) -> "Iterator[str]":
+    yield from config_vars_for_completion()
+    for name, data in config["remote"].items():
+        if "url" not in data:
+            continue
+        scheme = _get_schema_from_url(data["url"])
+        if scheme not in REMOTE_SCHEMAS:
+            continue
+        schema = REMOTE_SCHEMAS[scheme]
+        if schema:
+            yield from config_vars_for_completion(schema, f"remote.{name}")  # type: ignore[arg-type]
+
+    db_schema = SCHEMA["db"][str]  # type: ignore[index]
+    for name in config["db"]:
+        yield from config_vars_for_completion(db_schema, f"db.{name}")  # type: ignore[arg-type]

dvc/daemon.py

@@ -32,10 +32,10 @@ def _win_detached_subprocess(args: Sequence[str], **kwargs) -> int:
     assert os.name == "nt"
 
     from subprocess import (  # type: ignore[attr-defined]
-        CREATE_NEW_PROCESS_GROUP,
-        CREATE_NO_WINDOW,
-        STARTF_USESHOWWINDOW,
-        STARTUPINFO,
+        CREATE_NEW_PROCESS_GROUP,  # ty: ignore[unresolved-import]
+        CREATE_NO_WINDOW,  # ty: ignore[unresolved-import]
+        STARTF_USESHOWWINDOW,  # ty: ignore[unresolved-import]
+        STARTUPINFO,  # ty: ignore[unresolved-import]
     )
 
     # https://stackoverflow.com/a/7006424
@@ -44,10 +44,10 @@ def _win_detached_subprocess(args: Sequence[str], **kwargs) -> int:
 
     startupinfo = STARTUPINFO()
     startupinfo.dwFlags |= STARTF_USESHOWWINDOW
-    popen = subprocess.Popen(
+    popen = subprocess.Popen(  # noqa: S603
         args,
         close_fds=True,
-        shell=False,  # noqa: S603
+        shell=False,
         startupinfo=startupinfo,
         creationflags=creationflags,
         **kwargs,
@@ -149,7 +149,7 @@ def _spawn(
     env: Optional[Mapping[str, str]] = None,
     output_file: Optional[str] = None,
 ) -> int:
-    file: "AbstractContextManager[Any]" = nullcontext()
+    file: AbstractContextManager[Any] = nullcontext()
     kwargs = {}
     if output_file:
         file = open(output_file, "ab")  # noqa: SIM115
@@ -164,7 +164,7 @@ def _spawn(
         return _detached_subprocess(executable + args, env=env, **kwargs)
 
 
-def daemonize(args: list[str], executable: Union[None, str, list[str]] = None) -> None:
+def daemonize(args: list[str], executable: Union[str, list[str], None] = None) -> None:
     if os.name not in ("posix", "nt"):
         return
 

dvc/dagascii.py

@@ -104,21 +104,21 @@ class AsciiCanvas:
                 if dx == 0:
                     y = y0
                 else:
-                    y = y0 + int(round((x - x0) * dy / float(dx)))
+                    y = y0 + round((x - x0) * dy / float(dx))
                 self.point(x, y, char)
         elif y0 < y1:
             for y in range(y0, y1 + 1):
                 if dy == 0:
                     x = x0
                 else:
-                    x = x0 + int(round((y - y0) * dx / float(dy)))
+                    x = x0 + round((y - y0) * dx / float(dy))
                 self.point(x, y, char)
         else:
             for y in range(y1, y0 + 1):
                 if dy == 0:
                     x = x0
                 else:
-                    x = x1 + int(round((y - y1) * dx / float(dy)))
+                    x = x1 + round((y - y1) * dx / float(dy))
                 self.point(x, y, char)
 
     def text(self, x, y, text):
@@ -195,7 +195,7 @@ def _build_sugiyama_layout(vertices, edges):
 
     sug.yspace = VertexViewer.HEIGHT
     sug.xspace = minw
-    sug.route_edge = route_with_lines
+    sug.route_edge = route_with_lines  # ty: ignore[unresolved-attribute]
 
     sug.draw()
 
@@ -258,8 +258,8 @@ def draw(vertices, edges):
     maxx = max(Xs)
     maxy = max(Ys)
 
-    canvas_cols = int(math.ceil(math.ceil(maxx) - math.floor(minx))) + 1
-    canvas_lines = int(round(maxy - miny))
+    canvas_cols = math.ceil(math.ceil(maxx) - math.floor(minx)) + 1
+    canvas_lines = round(maxy - miny)
 
     canvas = AsciiCanvas(canvas_cols, canvas_lines)
 
@@ -270,10 +270,10 @@ def draw(vertices, edges):
             start = edge.view._pts[index - 1]
             end = edge.view._pts[index]
 
-            start_x = int(round(start[0] - minx))
-            start_y = int(round(start[1] - miny))
-            end_x = int(round(end[0] - minx))
-            end_y = int(round(end[1] - miny))
+            start_x = round(start[0] - minx)
+            start_y = round(start[1] - miny)
+            end_x = round(end[0] - minx)
+            end_y = round(end[1] - miny)
 
             assert start_x >= 0
             assert start_y >= 0
@@ -288,12 +288,12 @@ def draw(vertices, edges):
         y = vertex.view.xy[1]
 
         canvas.box(
-            int(round(x - minx)),
-            int(round(y - miny)),
+            round(x - minx),
+            round(y - miny),
             vertex.view.w,
             vertex.view.h,
         )
 
-        canvas.text(int(round(x - minx)) + 1, int(round(y - miny)) + 1, vertex.data)
+        canvas.text(round(x - minx) + 1, round(y - miny) + 1, vertex.data)
 
     return canvas.draw()

dvc/database.py

@@ -84,7 +84,7 @@ class Client:
         except Exception as exc:
             if callable(onerror):
                 onerror()
-            logger.exception(
+            logger.exception(  # noqa: LOG007
                 "Could not connect to the database. "
                 "Check your database credentials and try again.",
                 exc_info=False,

dvc/dependency/base.py

@@ -45,7 +45,7 @@ class Dependency(Output):
             self.fs_path = self.fs.version_path(self.fs_path, self.meta.version_id)
 
     def download(self, to, jobs=None):
-        fs_download(self.fs, self.fs_path, to.fs_path, jobs=jobs)
+        return fs_download(self.fs, self.fs_path, to.fs_path, jobs=jobs)
 
     def save(self):
         super().save()

dvc/dependency/db.py

@@ -37,13 +37,17 @@ class AbstractDependency(Dependency):
     """Dependency without workspace/fs/fs_path"""
 
     def __init__(self, stage: "Stage", info: dict[str, Any], *args, **kwargs):
-        self.repo: "Repo" = stage.repo
+        self.repo: Repo = stage.repo
         self.stage = stage
         self.fs = None
         self.fs_path = None
         self.def_path = None  # type: ignore[assignment]
         self.info = info or {}
 
+    @property
+    def is_in_repo(self):
+        return False
+
 
 class DbDependency(AbstractDependency):
     PARAM_CONNECTION = "connection"
@@ -70,8 +74,8 @@ class DbDependency(AbstractDependency):
         return self.db_info.get(self.PARAM_QUERY) or self.db_info.get(self.PARAM_TABLE)
 
     def __repr__(self):
-        return "{}:{}".format(
-            self.__class__.__name__, "".join(f"{k}=={v}" for k, v in self.info.items())
+        return "{}: {}".format(
+            self.__class__.__name__, "".join(f"{k}={v}" for k, v in self.info.items())
         )
 
     def __str__(self):

dvc/dependency/repo.py

@@ -9,7 +9,9 @@ from .base import Dependency
 
 if TYPE_CHECKING:
     from dvc.fs import DVCFileSystem
+    from dvc.output import Output
     from dvc.stage import Stage
+    from dvc_data.hashfile.hash_info import HashInfo
 
 
 class RepoDependency(Dependency):
@@ -35,7 +37,7 @@ class RepoDependency(Dependency):
         super().__init__(stage, *args, **kwargs)
 
         self.fs = self._make_fs()
-        self.fs_path = as_posix(self.def_path)
+        self.fs_path = as_posix(self.fs.normpath(self.def_path))
 
     def _parse_path(self, fs, fs_path):  # noqa: ARG002
         return None
@@ -91,6 +93,27 @@ class RepoDependency(Dependency):
             self.PARAM_REPO: self._dump_def_repo(self.def_repo),
         }
 
+    def download(self, to: "Output", jobs: Optional[int] = None):
+        from dvc.fs import LocalFileSystem
+
+        files = super().download(to=to, jobs=jobs)
+        if not isinstance(to.fs, LocalFileSystem):
+            return
+
+        hashes: list[tuple[str, HashInfo, dict[str, Any]]] = []
+        for src_path, dest_path, maybe_info in files:
+            try:
+                info = maybe_info or self.fs.info(src_path)
+                hash_info = info["dvc_info"]["entry"].hash_info
+                dest_info = to.fs.info(dest_path)
+            except (KeyError, AttributeError):
+                # If no hash info found, just keep going and output will be hashed later
+                continue
+            if hash_info:
+                hashes.append((dest_path, hash_info, dest_info))
+        cache = to.cache if to.use_cache else to.local_cache
+        cache.state.save_many(hashes, to.fs)
+
     def update(self, rev: Optional[str] = None):
         if rev:
             self.def_repo[self.PARAM_REV] = rev
@@ -123,11 +146,15 @@ class RepoDependency(Dependency):
         else:
             config = Config.load_file(conf)
 
+        # Setup config to the new DVCFileSystem to use the remote repo, but rely on the
+        # local cache instead of the remote's cache. This avoids re-streaming of data,
+        # but messes up the call to `_get_remote_config()` downstream, which will need
+        # to ignore cache parameters.
         config["cache"] = self.repo.config["cache"]
         config["cache"]["dir"] = self.repo.cache.local_cache_dir
 
         return DVCFileSystem(
-            url=self.def_repo[self.PARAM_URL],
+            repo=self.def_repo[self.PARAM_URL],
             rev=rev or self._get_rev(locked=locked),
             subrepos=True,
             config=config,

dvc/dirs.py

@@ -1,4 +1,5 @@
 import os
+from typing import Optional
 
 import platformdirs
 
@@ -20,7 +21,24 @@ def global_config_dir():
     )
 
 
-def site_cache_dir():
-    return os.getenv(env.DVC_SITE_CACHE_DIR) or platformdirs.site_cache_dir(
-        APPNAME, APPAUTHOR, opinion=True
-    )
+def site_cache_dir(config_site_cache_dir: Optional[str] = None):
+    from platformdirs import PlatformDirs
+    from platformdirs.unix import Unix
+
+    if dvc_site_cache_dir := os.getenv(env.DVC_SITE_CACHE_DIR):
+        return dvc_site_cache_dir
+
+    if config_site_cache_dir is not None:
+        return config_site_cache_dir
+
+    if issubclass(Unix, PlatformDirs):
+        # Return the cache directory shared by users, e.g. `/var/tmp/$appname`
+        # NOTE: platformdirs>=5 changed `site_cache_dir` to return /var/cache/$appname.
+        # as the following path is considered insecure.
+        # For details, see: https://github.com/tox-dev/platformdirs/pull/239
+
+        # FIXME: keeping the old behavior temporarily to avoid dependency conflict.
+        #        In the future, consider migrating to a more secure directory.
+        return f"/var/tmp/{APPNAME}"  # noqa: S108
+
+    return platformdirs.site_cache_dir(APPNAME, APPAUTHOR, opinion=True)

dvc/dvcfile.py

@@ -162,6 +162,9 @@ class FileMixin:
     def dump(self, stage, **kwargs):
         raise NotImplementedError
 
+    def dump_stages(self, stages, **kwargs):
+        raise NotImplementedError
+
     def merge(self, ancestor, other, allowed=None):
         raise NotImplementedError
 
@@ -198,6 +201,13 @@ class SingleStageFile(FileMixin):
         dump_yaml(self.path, serialize.to_single_stage_file(stage, **kwargs))
         self.repo.scm_context.track_file(self.relpath)
 
+    def dump_stages(self, stages, **kwargs) -> None:
+        if not stages:
+            return None
+
+        assert len(stages) == 1, "SingleStageFile can only dump one stage."
+        return self.dump(stages[0], **kwargs)
+
     def remove_stage(self, stage):  # noqa: ARG002
         self.remove()
 
@@ -228,17 +238,27 @@ class ProjectFile(FileMixin):
 
     def dump(self, stage, update_pipeline=True, update_lock=True, **kwargs):
         """Dumps given stage appropriately in the dvcfile."""
+        return self.dump_stages(
+            [stage], update_pipeline=update_pipeline, update_lock=update_lock, **kwargs
+        )
+
+    def dump_stages(self, stages, update_pipeline=True, update_lock=True, **kwargs):
         from dvc.stage import PipelineStage
 
-        assert isinstance(stage, PipelineStage)
+        if not stages:
+            return
+
+        for stage in stages:
+            assert isinstance(stage, PipelineStage)
+
         if self.verify:
             check_dvcfile_path(self.repo, self.path)
 
-        if update_pipeline and not stage.is_data_source:
-            self._dump_pipeline_file(stage)
+        if update_pipeline:
+            self._dump_pipeline_file(stages)
 
         if update_lock:
-            self._dump_lockfile(stage, **kwargs)
+            self._dump_lockfile(stages, **kwargs)
 
     def dump_dataset(self, dataset):
         with modify_yaml(self.path, fs=self.repo.fs) as data:
@@ -260,32 +280,37 @@ class ProjectFile(FileMixin):
                 raw.append(dataset)
         self.repo.scm_context.track_file(self.relpath)
 
-    def _dump_lockfile(self, stage, **kwargs):
-        self._lockfile.dump(stage, **kwargs)
+    def _dump_lockfile(self, stages, **kwargs):
+        self._lockfile.dump_stages(stages, **kwargs)
 
     @staticmethod
     def _check_if_parametrized(stage, action: str = "dump") -> None:
         if stage.raw_data.parametrized:
             raise ParametrizedDumpError(f"cannot {action} a parametrized {stage}")
 
-    def _dump_pipeline_file(self, stage):
-        self._check_if_parametrized(stage)
-        stage_data = serialize.to_pipeline_file(stage)
+    def _dump_pipeline_file(self, stages):
+        stages = stages if isinstance(stages, list) else [stages]
+        if not stages:
+            return
+
+        for stage in stages:
+            self._check_if_parametrized(stage)
 
         with modify_yaml(self.path, fs=self.repo.fs) as data:
             if not data:
                 logger.info("Creating '%s'", self.relpath)
 
             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)
-
-            if existing_entry:
-                orig_stage_data = data["stages"][stage.name]
-                apply_diff(stage_data[stage.name], orig_stage_data)
-            else:
-                data["stages"].update(stage_data)
+            for stage in stages:
+                stage_data = serialize.to_pipeline_file(stage)
+                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)
+                if existing_entry:
+                    orig_stage_data = data["stages"][stage.name]
+                    apply_diff(stage_data[stage.name], orig_stage_data)
+                else:
+                    data["stages"].update(stage_data)
 
         self.repo.scm_context.track_file(self.relpath)
 
@@ -399,9 +424,12 @@ class Lockfile(FileMixin):
             data.setdefault("stages", {})
         self.repo.scm_context.track_file(self.relpath)
 
-    def dump(self, stage, **kwargs):
-        stage_data = serialize.to_lockfile(stage, **kwargs)
+    def dump_stages(self, stages, **kwargs):
+        if not stages:
+            return
 
+        is_modified = False
+        log_updated = False
         with modify_yaml(self.path, fs=self.repo.fs) as data:
             if not data:
                 data.update({"schema": "2.0"})
@@ -409,17 +437,24 @@ class Lockfile(FileMixin):
                 logger.info("Generating lock file '%s'", self.relpath)
 
             data["stages"] = data.get("stages", {})
-            modified = data["stages"].get(stage.name, {}) != stage_data.get(
-                stage.name, {}
-            )
-            if modified:
-                logger.info("Updating lock file '%s'", self.relpath)
+            for stage in stages:
+                stage_data = serialize.to_lockfile(stage, **kwargs)
+                modified = data["stages"].get(stage.name, {}) != stage_data.get(
+                    stage.name, {}
+                )
+                if modified:
+                    is_modified = True
+                    if not log_updated:
+                        logger.info("Updating lock file '%s'", self.relpath)
+                        log_updated = True
+                data["stages"].update(stage_data)
 
-            data["stages"].update(stage_data)
-
-        if modified:
+        if is_modified:
             self.repo.scm_context.track_file(self.relpath)
 
+    def dump(self, stage, **kwargs):
+        self.dump_stages([stage], **kwargs)
+
     def remove_stage(self, stage):
         if not self.exists():
             return

dvc/exceptions.py

@@ -9,7 +9,7 @@ if TYPE_CHECKING:
     from dvc.stage import Stage
 
 
-class DvcException(Exception):
+class DvcException(Exception):  # noqa: N818
     """Base class for all dvc exceptions."""
 
     def __init__(self, msg, *args):
@@ -242,11 +242,11 @@ class UploadError(FileTransferError):
 
 
 class CheckoutError(DvcException):
-    def __init__(self, target_infos: list[str], stats: dict[str, list[str]]):
+    def __init__(self, target_infos: list[str], result: dict):
         from dvc.utils import error_link
 
         self.target_infos = target_infos
-        self.stats = stats
+        self.result = result
         targets = [str(t) for t in target_infos]
         m = (
             "Checkout failed for following targets:\n{}\nIs your "

dvc/fs/__init__.py

@@ -1,4 +1,5 @@
 import glob
+from itertools import repeat
 from typing import Optional
 from urllib.parse import urlparse
 
@@ -19,7 +20,7 @@ from dvc_objects.fs import (  # noqa: F401
     system,
     utils,
 )
-from dvc_objects.fs.base import AnyFSPath, FileSystem  # noqa: F401, TCH001
+from dvc_objects.fs.base import AnyFSPath, FileSystem  # noqa: F401, TC001
 from dvc_objects.fs.errors import (  # noqa: F401
     AuthError,
     ConfigError,
@@ -47,28 +48,12 @@ known_implementations.update(
 
 def download(
     fs: "FileSystem", fs_path: str, to: str, jobs: Optional[int] = None
-) -> int:
+) -> list[tuple[str, str, Optional[dict]]]:
     from dvc.scm import lfs_prefetch
 
     from .callbacks import TqdmCallback
 
     with TqdmCallback(desc=f"Downloading {fs.name(fs_path)}", unit="files") as cb:
-        # NOTE: We use dvc-objects generic.copy over fs.get since it makes file
-        # download atomic and avoids fsspec glob/regex path expansion.
-        if fs.isdir(fs_path):
-            from_infos = [
-                path for path in fs.find(fs_path) if not path.endswith(fs.flavour.sep)
-            ]
-            if not from_infos:
-                localfs.makedirs(to, exist_ok=True)
-                return 0
-            to_infos = [
-                localfs.join(to, *fs.relparts(info, fs_path)) for info in from_infos
-            ]
-        else:
-            from_infos = [fs_path]
-            to_infos = [to]
-
         if isinstance(fs, DVCFileSystem):
             lfs_prefetch(
                 fs,
@@ -78,10 +63,29 @@ def download(
                     else glob.escape(fs_path)
                 ],
             )
+            if not glob.has_magic(fs_path):
+                return fs._get(fs_path, to, batch_size=jobs, callback=cb)
+
+        # NOTE: We use dvc-objects generic.copy over fs.get since it makes file
+        # download atomic and avoids fsspec glob/regex path expansion.
+        if fs.isdir(fs_path):
+            from_infos = [
+                path for path in fs.find(fs_path) if not path.endswith(fs.flavour.sep)
+            ]
+            if not from_infos:
+                localfs.makedirs(to, exist_ok=True)
+                return []
+            to_infos = [
+                localfs.join(to, *fs.relparts(info, fs_path)) for info in from_infos
+            ]
+        else:
+            from_infos = [fs_path]
+            to_infos = [to]
+
         cb.set_size(len(from_infos))
         jobs = jobs or fs.jobs
         generic.copy(fs, from_infos, localfs, to_infos, callback=cb, batch_size=jobs)
-        return len(to_infos)
+        return list(zip(from_infos, to_infos, repeat(None)))
 
 
 def parse_external_url(url, fs_config=None, config=None):

dvc/fs/callbacks.py

@@ -1,8 +1,8 @@
 from contextlib import ExitStack
 from typing import TYPE_CHECKING, BinaryIO, Optional, Union
 
-import fsspec
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback  # noqa: F401
+from fsspec.callbacks import TqdmCallback as _TqdmCallback
 
 from dvc.progress import Tqdm
 from dvc.utils.objects import cached_property
@@ -14,7 +14,7 @@ if TYPE_CHECKING:
     from dvc.ui._rich_progress import RichTransferProgress
 
 
-class TqdmCallback(fsspec.callbacks.TqdmCallback):
+class TqdmCallback(_TqdmCallback):
     def __init__(
         self,
         size: Optional[int] = None,

dvc/fs/dvc.py

@@ -4,22 +4,28 @@ import ntpath
 import os
 import posixpath
 import threading
-from collections import deque
-from contextlib import ExitStack, suppress
+from collections import defaultdict, deque
+from contextlib import ExitStack, nullcontext, suppress
+from glob import has_magic
 from typing import TYPE_CHECKING, Any, Callable, Optional, Union
 
-from fsspec.spec import AbstractFileSystem
+from fsspec.spec import DEFAULT_CALLBACK, AbstractFileSystem
 from funcy import wrap_with
 
 from dvc.log import logger
-from dvc_objects.fs.base import FileSystem
+from dvc.utils.threadpool import ThreadPoolExecutor
+from dvc_objects.fs.base import AnyFSPath, FileSystem
 
 from .data import DataFileSystem
 
 if TYPE_CHECKING:
+    from contextlib import AbstractContextManager
+
     from dvc.repo import Repo
     from dvc.types import DictStrAny, StrPath
 
+    from .callbacks import Callback
+
 logger = logger.getChild(__name__)
 
 RepoFactory = Union[Callable[..., "Repo"], type["Repo"]]
@@ -77,11 +83,10 @@ class _DVCFileSystem(AbstractFileSystem):
     cachable = False
     root_marker = "/"
 
-    def __init__(  # noqa: PLR0913
+    def __init__(
         self,
-        url: Optional[str] = None,
+        repo: Union["Repo", os.PathLike[str], str, None] = None,
         rev: Optional[str] = None,
-        repo: Optional["Repo"] = None,
         subrepos: bool = False,
         repo_factory: Optional[RepoFactory] = None,
         fo: Optional[str] = None,
@@ -95,7 +100,8 @@ class _DVCFileSystem(AbstractFileSystem):
         """DVC + git-tracked files fs.
 
         Args:
-            path (str, optional): URL or path to a DVC/Git repository.
+            repo (str | os.PathLike[str] | Repo, optional): A url or a path to a DVC/Git
+                repository, or a `Repo` instance.
                 Defaults to a DVC repository in the current working directory.
                 Both HTTP and SSH protocols are supported for remote Git repos
                 (e.g. [user@]server:project.git).
@@ -105,7 +111,6 @@ class _DVCFileSystem(AbstractFileSystem):
                 In case of a local repository, if rev is unspecified, it will
                 default to the working directory.
                 If the repo is not a Git repo, this option is ignored.
-            repo (:obj:`Repo`, optional): `Repo` instance.
             subrepos (bool): traverse to subrepos.
                 By default, it ignores subrepos.
             repo_factory (callable): A function to initialize subrepo with.
@@ -130,13 +135,23 @@ class _DVCFileSystem(AbstractFileSystem):
             ...    rev="main",
             ... )
         """
+        from dvc.repo import Repo
+
+        # kwargs.get("url") is for maintaining backward compatibility
+        repo = repo or fo or kwargs.get("url")
+        if isinstance(repo, Repo):
+            self._repo: Optional[Repo] = repo
+            url = None
+        else:
+            self._repo = None
+            url = os.fspath(repo) if repo else None
+
         super().__init__()
-        self._repo = repo
         self._repo_factory = repo_factory
         self._traverse_subrepos = subrepos
         self._repo_stack = ExitStack()
         self._repo_kwargs = {
-            "url": url if url is not None else fo,
+            "url": url,
             "rev": rev,
             "subrepos": subrepos,
             "config": config,
@@ -429,7 +444,7 @@ class _DVCFileSystem(AbstractFileSystem):
         ignore_subrepos = kwargs.get("ignore_subrepos", True)
         return self._info(key, path, ignore_subrepos=ignore_subrepos)
 
-    def _info(  # noqa: C901, PLR0912
+    def _info(  # noqa: C901
         self, key, path, ignore_subrepos=True, check_ignored=True
     ):
         repo, dvc_fs, subkey = self._get_subrepo_info(key)
@@ -474,9 +489,128 @@ class _DVCFileSystem(AbstractFileSystem):
         info["name"] = path
         return info
 
+    def get(
+        self,
+        rpath,
+        lpath,
+        recursive=False,
+        callback=DEFAULT_CALLBACK,
+        maxdepth=None,
+        batch_size=None,
+        **kwargs,
+    ):
+        self._get(
+            rpath,
+            lpath,
+            recursive=recursive,
+            callback=callback,
+            maxdepth=maxdepth,
+            batch_size=batch_size,
+            **kwargs,
+        )
+
+    def _get(  # noqa: C901, PLR0912, PLR0915
+        self,
+        rpath,
+        lpath,
+        recursive=False,
+        callback=DEFAULT_CALLBACK,
+        maxdepth=None,
+        batch_size=None,
+        **kwargs,
+    ) -> list[tuple[str, str, Optional[dict]]]:
+        if (
+            isinstance(rpath, list)
+            or isinstance(lpath, list)
+            or has_magic(rpath)
+            or not self.exists(rpath)
+            or not recursive
+        ):
+            super().get(
+                rpath,
+                lpath,
+                recursive=recursive,
+                callback=callback,
+                maxdepth=maxdepth,
+                **kwargs,
+            )
+            return []
+
+        if os.path.isdir(lpath) or lpath.endswith(os.path.sep):
+            lpath = self.join(lpath, os.path.basename(rpath))
+
+        if self.isfile(rpath):
+            with callback.branched(rpath, lpath) as child:
+                self.get_file(rpath, lpath, callback=child, **kwargs)
+                return [(rpath, lpath, None)]
+
+        result: list[tuple[str, str, Optional[dict]]] = []
+        _dirs: list[str] = []
+        _files: dict[FileSystem, list[tuple[str, str, Optional[dict]]]]
+        _files = defaultdict(list)
+
+        for root, dirs, files in self.walk(rpath, maxdepth=maxdepth, detail=True):
+            if files:
+                callback.set_size((callback.size or 0) + len(files))
+
+            parts = self.relparts(root, rpath)
+            if parts in ((os.curdir,), ("",)):
+                parts = ()
+            dest_root = os.path.join(lpath, *parts)
+            if not maxdepth or len(parts) < maxdepth - 1:
+                _dirs.extend(f"{dest_root}{os.path.sep}{d}" for d in dirs)
+
+            key = self._get_key_from_relative(root)
+            _, dvc_fs, _ = self._get_subrepo_info(key)
+
+            for name, info in files.items():
+                dvc_info = info.get("dvc_info")
+                fs_info = info.get("fs_info")
+                if dvc_fs and dvc_info and not fs_info:
+                    fs = dvc_fs
+                    fs_path = dvc_info["name"]
+                else:
+                    fs = self.repo.fs
+                    fs_path = fs_info["name"]
+
+                src_path = f"{root}{self.sep}{name}"
+                dest_path = f"{dest_root}{os.path.sep}{name}"
+                _files[fs].append((fs_path, dest_path, dvc_info))
+                result.append((src_path, dest_path, info))
+
+        os.makedirs(lpath, exist_ok=True)
+        for d in _dirs:
+            os.makedirs(d, exist_ok=True)
+
+        def get_file(arg: tuple[FileSystem, tuple[str, str, Optional[dict]]]):
+            fs, (src, dest, info) = arg
+            kw = kwargs
+            if isinstance(fs, DataFileSystem):
+                kw = kw | {"info": info}
+            with callback.branched(src, dest) as child:
+                fs.get_file(src, dest, callback=child, **kw)
+
+        if batch_size == 1:
+            ctx: AbstractContextManager = nullcontext()
+            map_fn: Callable = map
+        else:
+            ctx = ThreadPoolExecutor(max_workers=batch_size)
+            map_fn = ctx.imap_unordered
+
+        with ctx:
+            it = ((fs, f) for fs, files in _files.items() for f in files)
+            deque(callback.wrap(map_fn(get_file, it)), maxlen=0)
+        return result
+
     def get_file(self, rpath, lpath, **kwargs):
+        dvc_info = kwargs.pop("info", {}).pop("dvc_info", None)
         key = self._get_key_from_relative(rpath)
         fs_path = self._from_key(key)
+        dirpath = os.path.dirname(lpath)
+        if dirpath:
+            # makedirs raises error if the string is empty
+            os.makedirs(dirpath, exist_ok=True)
+
         try:
             return self.repo.fs.get_file(fs_path, lpath, **kwargs)
         except FileNotFoundError:
@@ -485,7 +619,7 @@ class _DVCFileSystem(AbstractFileSystem):
                 raise
 
         dvc_path = _get_dvc_path(dvc_fs, subkey)
-        return dvc_fs.get_file(dvc_path, lpath, **kwargs)
+        return dvc_fs.get_file(dvc_path, lpath, info=dvc_info, **kwargs)
 
     def du(self, path, total=True, maxdepth=None, withdirs=False, **kwargs):
         if maxdepth is not None:
@@ -553,6 +687,45 @@ class DVCFileSystem(FileSystem):
     def getcwd(self):
         return self.fs.getcwd()
 
+    def _get(
+        self,
+        from_info: Union[AnyFSPath, list[AnyFSPath]],
+        to_info: Union[AnyFSPath, list[AnyFSPath]],
+        callback: "Callback" = DEFAULT_CALLBACK,
+        recursive: bool = False,
+        batch_size: Optional[int] = None,
+        **kwargs,
+    ) -> list[tuple[str, str, Optional[dict]]]:
+        # FileSystem.get is non-recursive by default if arguments are lists
+        # otherwise, it's recursive.
+        recursive = not (isinstance(from_info, list) and isinstance(to_info, list))
+        return self.fs._get(
+            from_info,
+            to_info,
+            callback=callback,
+            recursive=recursive,
+            batch_size=batch_size,
+            **kwargs,
+        )
+
+    def get(
+        self,
+        from_info: Union[AnyFSPath, list[AnyFSPath]],
+        to_info: Union[AnyFSPath, list[AnyFSPath]],
+        callback: "Callback" = DEFAULT_CALLBACK,
+        recursive: bool = False,
+        batch_size: Optional[int] = None,
+        **kwargs,
+    ) -> None:
+        self._get(
+            from_info,
+            to_info,
+            callback=callback,
+            batch_size=batch_size,
+            recursive=recursive,
+            **kwargs,
+        )
+
     @property
     def fsid(self) -> str:
         return self.fs.fsid
@@ -569,9 +742,10 @@ class DVCFileSystem(FileSystem):
         return self.fs.repo_url
 
     def from_os_path(self, path: str) -> str:
-        if os.path.isabs(path):
+        if os.path.isabs(path) or (
+            os.name == "nt" and posixpath.isabs(path) and ntpath.sep not in path
+        ):
             path = os.path.relpath(path, self.repo.root_dir)
-
         return as_posix(path)
 
     def close(self):

dvc/fs/dvc_path.py

@@ -15,7 +15,7 @@ Examples
 
 from urllib.parse import urlsplit
 
-from upath import UPath
+from upath import UPath  # ty: ignore[unresolved-import]
 
 
 class DVCPath(UPath):

dvc/ignore.py

@@ -1,8 +1,9 @@
+import functools
 import os
 import re
-from collections import namedtuple
+from collections.abc import Iterable, Iterator
 from itertools import chain, groupby, takewhile
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING, Any, Literal, NamedTuple, Optional, Union, overload
 
 from pathspec.patterns import GitWildMatchPattern
 from pathspec.util import normalize_file
@@ -13,7 +14,9 @@ from dvc.log import logger
 from dvc.pathspec_math import PatternInfo, merge_patterns
 
 if TYPE_CHECKING:
-    from dvc.fs import AnyFSPath, FileSystem
+    from typing_extensions import Self
+
+    from dvc.fs import FileSystem
 
 logger = logger.getChild(__name__)
 
@@ -21,36 +24,79 @@ logger = logger.getChild(__name__)
 class DvcIgnore:
     DVCIGNORE_FILE = ".dvcignore"
 
-    def __call__(self, root, dirs, files):
+    def __call__(
+        self, root: str, dirs: list[str], files: list[str]
+    ) -> tuple[list[str], list[str]]:
         raise NotImplementedError
 
 
 class DvcIgnorePatterns(DvcIgnore):
-    def __init__(self, pattern_list, dirname, sep):
+    def __init__(
+        self, pattern_list: Iterable[Union[PatternInfo, str]], dirname: str, sep: str
+    ) -> None:
         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]
-
-        self.sep = sep
-        self.pattern_list = pattern_list
-        self.dirname = dirname
-
-        self.regex_pattern_list = []
-        for count, pattern in enumerate(pattern_list):
-            pattern, group = GitWildMatchPattern.pattern_to_regex(pattern.patterns)
-            if pattern:
-                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])
-            if ignore is not None
+        pattern_infos = [
+            pattern if isinstance(pattern, PatternInfo) else PatternInfo(pattern, "")
+            for pattern in pattern_list
         ]
 
+        self.sep = sep
+        self.pattern_list: list[PatternInfo] = []
+        self.dirname = dirname
+        self.find_matching_pattern = functools.cache(self._find_matching_pattern)
+
+        regex_pattern_list: list[tuple[str, bool, bool, PatternInfo]] = []
+        for count, pattern_info in enumerate(pattern_infos):
+            regex, ignore = GitWildMatchPattern.pattern_to_regex(pattern_info.patterns)
+            if regex is not None and ignore is not None:
+                self.pattern_list.append(pattern_info)
+                regex = regex.replace(f"<{_DIR_MARK}>", f"<{_DIR_MARK}{count}>")
+                regex_pattern_list.append(
+                    (regex, ignore, pattern_info.patterns.endswith("/"), pattern_info)
+                )
+
+        def keyfunc(item: tuple[str, bool, bool, PatternInfo]) -> tuple[bool, bool]:
+            _, ignore, dir_only_pattern, _ = item
+            return ignore, dir_only_pattern
+
+        self.ignore_spec: list[
+            tuple[
+                re.Pattern[str],
+                bool,
+                bool,
+                dict[Optional[str], tuple[str, PatternInfo]],
+            ]
+        ]
+        self.ignore_spec = []
+        for (ignore, dir_only_pattern), group in groupby(
+            regex_pattern_list, key=keyfunc
+        ):
+            if ignore:
+                # For performance, we combine all exclude patterns.
+                # But we still need to figure out which pattern matched which rule,
+                # (eg: to show in `dvc check-ignore`).
+                # So, we use named groups and keep a map of group name to pattern.
+                pattern_map: dict[Optional[str], tuple[str, PatternInfo]] = {
+                    f"rule_{i}": (regex, pi)
+                    for i, (regex, _, _, pi) in enumerate(group)
+                }
+                combined_regex = "|".join(
+                    f"(?P<{name}>{regex})" for name, (regex, _) in pattern_map.items()
+                )
+                self.ignore_spec.append(
+                    (re.compile(combined_regex), ignore, dir_only_pattern, pattern_map)
+                )
+            else:
+                # unignored patterns are not combined with `|`.
+                for regex, _, _, pi in group:
+                    pattern_map = {None: (regex, pi)}
+                    self.ignore_spec.append(
+                        (re.compile(regex), ignore, dir_only_pattern, pattern_map)
+                    )
+
     @classmethod
-    def from_file(cls, path, fs, name):
+    def from_file(cls, path: str, fs: "FileSystem", name: str) -> "Self":
         assert fs.isabs(path)
         dirname = fs.normpath(fs.dirname(path))
         with fs.open(path, encoding="utf-8") as fobj:
@@ -62,13 +108,15 @@ class DvcIgnorePatterns(DvcIgnore):
 
         return cls(path_spec_lines, dirname, fs.sep)
 
-    def __call__(self, root: list[str], dirs: list[str], files: list[str]):
+    def __call__(
+        self, root: str, dirs: list[str], files: list[str]
+    ) -> tuple[list[str], list[str]]:
         files = [f for f in files if not self.matches(root, f)]
         dirs = [d for d in dirs if not self.matches(root, d, True)]
 
         return dirs, files
 
-    def _get_normalize_path(self, dirname, basename):
+    def _get_normalize_path(self, dirname: str, basename: str) -> Optional[str]:
         # NOTE: `relpath` is too slow, so we have to assume that both
         # `dirname` and `self.dirname` are relative or absolute together.
 
@@ -81,62 +129,105 @@ class DvcIgnorePatterns(DvcIgnore):
             # NOTE: `os.path.join` is ~x5.5 slower
             path = f"{rel}{self.sep}{basename}"
         else:
-            return False
+            return None
 
         if os.name == "nt":
             return normalize_file(path)
         return path
 
-    def matches(self, dirname, basename, is_dir=False, details: bool = False):
+    @overload
+    def matches(
+        self,
+        dirname: str,
+        basename: str,
+        is_dir: bool = False,
+        details: Literal[False] = ...,
+    ) -> bool: ...
+
+    @overload
+    def matches(
+        self,
+        dirname: str,
+        basename: str,
+        is_dir: bool = False,
+        details: Literal[True] = ...,
+    ) -> tuple[bool, list[PatternInfo]]: ...
+
+    @overload
+    def matches(
+        self,
+        dirname: str,
+        basename: str,
+        is_dir: bool = False,
+        details: bool = False,
+    ) -> Union[bool, tuple[bool, list[PatternInfo]]]: ...
+
+    def matches(
+        self,
+        dirname: str,
+        basename: str,
+        is_dir: bool = False,
+        details: bool = False,
+    ) -> Union[bool, tuple[bool, list[PatternInfo]]]:
         path = self._get_normalize_path(dirname, basename)
-        if not path:
-            return False
-
-        if details:
-            return self._ignore_details(path, is_dir)
-        return self.ignore(path, is_dir)
-
-    def ignore(self, path, is_dir):
-        def matches(pattern, path, is_dir) -> bool:
-            matches_ = bool(pattern.match(path))
-
-            if is_dir:
-                matches_ |= bool(pattern.match(f"{path}/"))
-
-            return matches_
-
         result = False
+        _match: list[PatternInfo] = []
+        if path:
+            result, _match = self._ignore(path, is_dir)
+        return (result, _match) if details else result
 
-        for ignore, pattern in self.ignore_spec[::-1]:
-            if matches(pattern, path, is_dir):
-                result = ignore
-                break
-        return result
+    def _find_matching_pattern(
+        self, path: str, is_dir: bool
+    ) -> tuple[bool, list[PatternInfo]]:
+        paths = [path]
+        if is_dir and not path.endswith("/"):
+            paths.append(f"{path}/")
 
-    def _ignore_details(self, path, is_dir: bool):
-        result = []
-        for (regex, _), pattern_info in list(
-            zip(self.regex_pattern_list, self.pattern_list)
+        for pattern, ignore, dir_only_pattern, pattern_map in reversed(
+            self.ignore_spec
         ):
-            # skip system pattern
-            if not pattern_info.file_info:
+            if dir_only_pattern and not is_dir:
                 continue
+            for p in paths:
+                match = pattern.match(p)
+                if not match:
+                    continue
+                if ignore:
+                    group_name, _match = next(
+                        (
+                            (name, _match)
+                            for name, _match in match.groupdict().items()
+                            if name.startswith("rule_") and _match is not None
+                        )
+                    )
+                else:
+                    # unignored patterns are not combined with `|`,
+                    # so there are no groups.
+                    group_name = None
+                _regex, pattern_info = pattern_map[group_name]
+                return ignore, [pattern_info]
+        return False, []
 
-            regex = re.compile(regex)
+    def _ignore(self, path: str, is_dir: bool) -> tuple[bool, list[PatternInfo]]:
+        parts = path.split("/")
+        result = False
+        matches: list[PatternInfo] = []
+        for i in range(1, len(parts) + 1):
+            rel_path = "/".join(parts[:i])
+            result, _matches = self.find_matching_pattern(
+                rel_path, is_dir or i < len(parts)
+            )
+            if i < len(parts) and not result:
+                continue
+            matches.extend(_matches)
+            if result:
+                break
+        return result, matches
 
-            matches = bool(regex.match(path))
-            if is_dir:
-                matches |= bool(regex.match(f"{path}/"))
-
-            if matches:
-                result.append(pattern_info.file_info)
-
-        return result
-
-    def __hash__(self):
+    def __hash__(self) -> int:
         return hash(self.dirname + ":" + str(self.pattern_list))
 
-    def __eq__(self, other):
+    def __eq__(self, other: object) -> bool:
         if not isinstance(other, DvcIgnorePatterns):
             return NotImplemented
         return (self.dirname == other.dirname) & (
@@ -144,21 +235,18 @@ class DvcIgnorePatterns(DvcIgnore):
             == [pattern.patterns for pattern in other.pattern_list]
         )
 
-    def __bool__(self):
+    def __bool__(self) -> bool:
         return bool(self.pattern_list)
 
 
-CheckIgnoreResult = namedtuple(  # noqa: PYI024
-    "CheckIgnoreResult", ["file", "match", "patterns"]
-)
-
-
-def _no_match(path):
-    return CheckIgnoreResult(path, False, ["::"])
+class CheckIgnoreResult(NamedTuple):
+    file: str
+    match: bool
+    pattern_infos: list[PatternInfo]
 
 
 class DvcIgnoreFilter:
-    def __init__(self, fs, root_dir):
+    def __init__(self, fs: "FileSystem", root_dir: str) -> None:
         from dvc.repo import Repo
 
         default_ignore_patterns = [
@@ -193,7 +281,7 @@ class DvcIgnoreFilter:
             ignore_subrepos=True,
         )
 
-    def _get_key(self, path):
+    def _get_key(self, path: str) -> tuple[str, ...]:
         parts = self.fs.relparts(path, self.root_dir)
         if parts == (os.curdir,):
             return ()
@@ -241,7 +329,7 @@ class DvcIgnoreFilter:
             for dname in dnames:
                 self._update_sub_repo(self.fs.join(dirname, dname), ignore_trie)
 
-    def _update_sub_repo(self, path, ignore_trie: Trie):
+    def _update_sub_repo(self, path: str, ignore_trie: Trie) -> None:
         from dvc.repo import Repo
 
         if path == self.root_dir:
@@ -268,7 +356,9 @@ class DvcIgnoreFilter:
         else:
             ignore_trie[key] = new_pattern
 
-    def __call__(self, root, dirs, files, ignore_subrepos=True):
+    def __call__(
+        self, root: str, dirs: list[str], files: list[str], ignore_subrepos: bool = True
+    ) -> tuple[list[str], list[str]]:
         abs_root = self.fs.abspath(root)
         ignore_pattern = self._get_trie_pattern(
             abs_root, dnames=dirs, ignore_subrepos=ignore_subrepos
@@ -277,7 +367,24 @@ class DvcIgnoreFilter:
             dirs, files = ignore_pattern(abs_root, dirs, files)
         return dirs, files
 
-    def ls(self, fs, path, detail=True, **kwargs):
+    @overload
+    def ls(
+        self, fs: "FileSystem", path: str, detail: Literal[True], **kwargs: Any
+    ) -> list[dict[str, Any]]: ...
+
+    @overload
+    def ls(
+        self, fs: "FileSystem", path: str, detail: Literal[False], **kwargs
+    ) -> list[str]: ...
+
+    @overload
+    def ls(
+        self, fs: "FileSystem", path: str, detail: bool = True, **kwargs
+    ) -> Union[list[str], list[dict[str, Any]]]: ...
+
+    def ls(
+        self, fs: "FileSystem", path: str, detail: bool = True, **kwargs: Any
+    ) -> Union[list[str], list[dict[str, Any]]]:
         fs_dict = {}
         dirs = []
         nondirs = []
@@ -297,22 +404,29 @@ class DvcIgnoreFilter:
 
         return [fs_dict[name] for name in chain(dirs, nondirs)]
 
-    def walk(self, fs: "FileSystem", path: "AnyFSPath", **kwargs):
+    def walk(
+        self, fs: "FileSystem", path: str, **kwargs: Any
+    ) -> Iterator[
+        Union[
+            tuple[str, list[str], list[str]],
+            tuple[str, dict[str, dict], dict[str, dict]],
+        ]
+    ]:
         detail = kwargs.get("detail", False)
         ignore_subrepos = kwargs.pop("ignore_subrepos", True)
         if fs.protocol == Schemes.LOCAL:
             for root, dirs, files in fs.walk(path, **kwargs):
                 if detail:
-                    all_dnames = set(dirs.keys())
-                    all_fnames = set(files.keys())
+                    assert isinstance(dirs, dict)
+                    assert isinstance(files, dict)
                     dnames, fnames = self(
                         root,
-                        all_dnames,
-                        all_fnames,
+                        list(dirs),
+                        list(files),
                         ignore_subrepos=ignore_subrepos,
                     )
-                    list(map(dirs.pop, all_dnames - set(dnames)))
-                    list(map(files.pop, all_fnames - set(fnames)))
+                    list(map(dirs.pop, dirs.keys() - set(dnames)))
+                    list(map(files.pop, files.keys() - set(fnames)))
                 else:
                     dirs[:], files[:] = self(
                         root, dirs, files, ignore_subrepos=ignore_subrepos
@@ -321,7 +435,7 @@ class DvcIgnoreFilter:
         else:
             yield from fs.walk(path, **kwargs)
 
-    def find(self, fs: "FileSystem", path: "AnyFSPath", **kwargs):
+    def find(self, fs: "FileSystem", path: str, **kwargs: Any) -> Iterator[str]:
         if fs.protocol == Schemes.LOCAL:
             for root, _, files in self.walk(fs, path, **kwargs):
                 for file in files:
@@ -331,7 +445,7 @@ class DvcIgnoreFilter:
             yield from fs.find(path)
 
     def _get_trie_pattern(
-        self, dirname, dnames: Optional["list"] = None, ignore_subrepos=True
+        self, dirname: str, dnames: Optional[list[str]] = None, ignore_subrepos=True
     ) -> Optional["DvcIgnorePatterns"]:
         if ignore_subrepos:
             ignores_trie = self.ignores_trie_fs
@@ -367,7 +481,7 @@ class DvcIgnoreFilter:
 
     def _is_ignored(
         self, path: str, is_dir: bool = False, ignore_subrepos: bool = True
-    ):
+    ) -> bool:
         if self._outside_repo(path):
             return False
         dirname, basename = self.fs.split(self.fs.normpath(path))
@@ -389,24 +503,23 @@ class DvcIgnoreFilter:
         path = self.fs.abspath(path)
         return self._is_ignored(path, False, ignore_subrepos=ignore_subrepos)
 
-    def _outside_repo(self, path):
+    def _outside_repo(self, path: str) -> bool:
         return not self.fs.isin_or_eq(path, self.root_dir)
 
-    def check_ignore(self, target):
+    def check_ignore(self, target: str) -> CheckIgnoreResult:
         # NOTE: can only be used in `dvc check-ignore`, see
         # https://github.com/iterative/dvc/issues/5046
         full_target = self.fs.abspath(target)
+        matched_patterns: list[PatternInfo] = []
+        ignore = False
         if not self._outside_repo(full_target):
             dirname, basename = self.fs.split(self.fs.normpath(full_target))
             pattern = self._get_trie_pattern(dirname)
             if pattern:
-                matches = pattern.matches(
-                    dirname, basename, self.fs.isdir(full_target), True
+                ignore, matched_patterns = pattern.matches(
+                    dirname, basename, self.fs.isdir(full_target), details=True
                 )
-
-                if matches:
-                    return CheckIgnoreResult(target, True, matches)
-        return _no_match(target)
+        return CheckIgnoreResult(target, ignore, matched_patterns)
 
     def is_ignored(
         self, fs: "FileSystem", path: str, ignore_subrepos: bool = True
@@ -424,7 +537,7 @@ class DvcIgnoreFilter:
         )
 
 
-def init(path):
+def init(path: Union[str, os.PathLike[str]]) -> str:
     dvcignore = os.path.join(path, DvcIgnore.DVCIGNORE_FILE)
     if os.path.exists(dvcignore):
         return dvcignore
@@ -439,7 +552,7 @@ def init(path):
     return dvcignore
 
 
-def destroy(path):
+def destroy(path: Union[str, os.PathLike[str]]) -> None:
     from dvc.utils.fs import remove
 
     dvcignore = os.path.join(path, DvcIgnore.DVCIGNORE_FILE)

dvc/info.py

@@ -48,7 +48,10 @@ def get_dvc_info():
                 info.append("Cache types: " + error_link("no-dvc-cache"))
 
             info.append(f"Caches: {_get_caches(repo.cache)}")
-            info.append(f"Remotes: {_get_remotes(repo.config)}")
+
+            configured_remotes = _get_remotes(repo.config)
+            remotes = ", ".join(configured_remotes) if configured_remotes else None
+            info.append(f"Remotes: {remotes}")
 
             root_directory = repo.root_dir
             fs_root = _get_fs_type(os.path.abspath(root_directory))
@@ -75,12 +78,10 @@ def _get_caches(cache):
 
 
 def _get_remotes(config):
-    schemes = (
+    return [
         get_fs_cls(get_fs_config(config, name=remote)).protocol
         for remote in config["remote"]
-    )
-
-    return ", ".join(schemes) or "None"
+    ]
 
 
 def _get_linktype_support_info(repo):
@@ -123,7 +124,7 @@ def _get_supported_remotes():
         if not fs_cls.get_missing_deps():
             dependencies = []
             for requirement in fs_cls.REQUIRES:
-                dependencies.append(
+                dependencies.append(  # noqa: PERF401
                     f"{requirement} = {importlib_metadata.version(requirement)}"
                 )
 

dvc/lock.py

@@ -2,12 +2,13 @@
 
 import hashlib
 import os
+import time
 from abc import ABC, abstractmethod
 from datetime import timedelta
+from typing import Optional, Union
 
 import flufl.lock
 import zc.lockfile
-from funcy import retry
 
 from dvc.exceptions import DvcException
 from dvc.progress import Tqdm
@@ -87,9 +88,10 @@ class Lock(LockBase):
     Uses zc.lockfile as backend.
     """
 
-    def __init__(self, lockfile, friendly=False, **kwargs):
+    def __init__(self, lockfile, friendly=False, wait=False, **kwargs):
         super().__init__(lockfile)
         self._friendly = friendly
+        self._wait = wait
         self._lock = None
         self._lock_failed = False
 
@@ -100,23 +102,38 @@ class Lock(LockBase):
     def _do_lock(self):
         try:
             self._lock_failed = False
-            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")
-                ),
-            ):
-                self._lock = zc.lockfile.LockFile(self._lockfile)
+            self._lock = zc.lockfile.LockFile(self._lockfile)
         except zc.lockfile.LockError:
             self._lock_failed = True
             raise LockError(FAILED_TO_LOCK_MESSAGE)  # noqa: B904
 
     def lock(self):
-        retries = 6
-        delay = DEFAULT_TIMEOUT / retries
-        lock_retry = retry(retries, LockError, timeout=delay)(self._do_lock)
-        lock_retry()
+        """Acquire the lock, either waiting forever, or after default_retries."""
+        default_retries = 6
+        delay = DEFAULT_TIMEOUT / default_retries
+        attempts = 0
+
+        max_retries = float("inf") if self._wait else default_retries
+
+        with Tqdm(
+            bar_format="{desc}",
+            disable=not self._friendly,
+            desc="Waiting to acquire lock. "
+            "If DVC froze, see `hardlink_lock` in {}.".format(
+                format_link("https://man.dvc.org/config#core")
+            ),
+        ) as pbar:
+            while True:
+                try:
+                    self._do_lock()
+                    return
+                except LockError:
+                    attempts += 1
+                    if attempts > max_retries:
+                        raise
+                    time.sleep(delay)
+                finally:
+                    pbar.update()
 
     def unlock(self):
         if self._lock_failed:
@@ -149,7 +166,7 @@ class HardlinkLock(flufl.lock.Lock, LockBase):
         tmp_dir (str): a directory to store claim files.
     """
 
-    def __init__(self, lockfile, tmp_dir=None, **kwargs):
+    def __init__(self, lockfile, tmp_dir=None, wait=False, **kwargs):
         import socket
 
         self._tmp_dir = tmp_dir
@@ -172,11 +189,21 @@ class HardlinkLock(flufl.lock.Lock, LockBase):
         self._separator = flufl.lock.SEP
         self._set_claimfile()
         self._owned = True
+        self._wait = wait
         self._retry_errnos = []
+        self._friendly = kwargs.get("friendly", False)
 
-    def lock(self):
+    def lock(self, timeout: Optional[Union[timedelta, int]] = None):
         try:
-            super().lock(timedelta(seconds=DEFAULT_TIMEOUT))
+            if not self._wait:
+                timeout = timeout or timedelta(seconds=DEFAULT_TIMEOUT)
+
+            with Tqdm(
+                bar_format="{desc}",
+                disable=not (self._wait and self._friendly),
+                desc="Waiting to acquire lock",
+            ):
+                super().lock(timeout)
         except flufl.lock.TimeOutError:
             raise LockError(FAILED_TO_LOCK_MESSAGE)  # noqa: B904
 
@@ -185,11 +212,11 @@ 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(self._claimfile.encode(), usedforsecurity=False)
             filename = hasher.hexdigest()
             self._claimfile = os.path.join(self._tmp_dir, filename + ".lock")
 
 
-def make_lock(lockfile, tmp_dir=None, friendly=False, hardlink_lock=False):
+def make_lock(lockfile, tmp_dir=None, friendly=False, hardlink_lock=False, wait=False):
     cls = HardlinkLock if hardlink_lock else Lock
-    return cls(lockfile, tmp_dir=tmp_dir, friendly=friendly)
+    return cls(lockfile, tmp_dir=tmp_dir, friendly=friendly, wait=wait)

dvc/logger.py

@@ -5,6 +5,8 @@ import logging.config
 import logging.handlers
 import os
 import sys
+from collections.abc import Iterator
+from contextlib import contextmanager
 from typing import ClassVar
 
 import colorama
@@ -36,7 +38,7 @@ def add_logging_level(level_name, level_num, method_name=None):
             self._log(level_num, message, args, **kwargs)
 
     def log_to_root(message, *args, **kwargs):
-        logging.log(level_num, message, *args, **kwargs)
+        logging.log(level_num, message, *args, **kwargs)  # noqa: LOG015
 
     # getLevelName resolves the numeric log level if already defined,
     # otherwise returns a string
@@ -53,7 +55,7 @@ def add_logging_level(level_name, level_num, method_name=None):
         setattr(logging, method_name, log_to_root)
 
 
-class LoggingException(Exception):
+class LoggingException(Exception):  # noqa: N818
     def __init__(self, record):
         msg = f"failed to log {record!s}"
         super().__init__(msg)
@@ -174,9 +176,19 @@ def _iter_causes(exc):
         exc = exc.__cause__
 
 
-def set_loggers_level(level: int = logging.INFO) -> None:
+@contextmanager
+def set_loggers_level(level: int = logging.INFO) -> Iterator[None]:
+    ret: dict[logging.Logger, int] = {}
     for name in ["dvc", "dvc_objects", "dvc_data"]:
-        logging.getLogger(name).setLevel(level)
+        _logger = logging.getLogger(name)
+        ret[_logger] = _logger.getEffectiveLevel()
+        _logger.setLevel(level)
+
+    try:
+        yield
+    finally:
+        for _logger, old_lvl in ret.items():
+            _logger.setLevel(old_lvl)
 
 
 def setup(level: int = logging.INFO, log_colors: bool = True) -> None:

dvc/output.py

@@ -45,7 +45,7 @@ if TYPE_CHECKING:
     from dvc_data.hashfile.obj import HashFile
     from dvc_data.index import DataIndexKey
 
-    from .ignore import DvcIgnoreFilter
+    from .ignore import CheckIgnoreResult, DvcIgnoreFilter
 
 logger = logger.getChild(__name__)
 
@@ -267,9 +267,9 @@ class OutputIsStageFileError(DvcException):
 
 
 class OutputIsIgnoredError(DvcException):
-    def __init__(self, match):
-        lines = "\n".join(match.patterns)
-        super().__init__(f"Path '{match.file}' is ignored by\n{lines}")
+    def __init__(self, result: "CheckIgnoreResult"):
+        pi = result.pattern_infos[-1]
+        super().__init__(f"Path {result.file!r} is ignored by {pi!s}")
 
 
 class CheckoutCallback(TqdmCallback):
@@ -390,7 +390,7 @@ class Output:
         self.can_push = push
 
         self.fs_path = self._parse_path(self.fs, fs_path)
-        self.obj: Optional["HashFile"] = None
+        self.obj: Optional[HashFile] = None
 
         self.remote = remote
 
@@ -431,7 +431,7 @@ class Output:
             self.meta.nfiles = len(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:
+        elif self.meta.nfiles or (self.hash_info and self.hash_info.isdir):
             self.meta.isdir = True
             if not self.hash_info and self.hash_name not in ("md5", "md5-dos2unix"):
                 md5 = getattr(self.meta, "md5", None)
@@ -542,7 +542,9 @@ class Output:
             desc=f"Collecting files and computing hashes in {self}",
             disable=no_progress_bar,
         ) as pb:
-            return build(*args, callback=pb.as_callback(), **kwargs)
+            kwargs["callback"] = pb.as_callback()
+            kwargs.setdefault("checksum_jobs", self.fs.hash_jobs)
+            return build(*args, **kwargs)
 
     def _get_hash_meta(self):
         if self.use_cache:
@@ -730,6 +732,7 @@ class Output:
         from dvc_data.hashfile.checkout import LinkError, PromptError
 
         kwargs.setdefault("ignore", self.dvcignore)
+        kwargs.setdefault("checksum_jobs", self.fs.hash_jobs)
         try:
             return checkout(*args, **kwargs)
         except PromptError as exc:
@@ -749,11 +752,9 @@ class Output:
             granular = (
                 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
+            hardlink = relink and next(iter(self.cache.cache_types), None) == "hardlink"
             if granular:
-                obj = self._commit_granular_dir(filter_info, hardlink)
+                obj = self._commit_granular_dir(filter_info, hardlink=hardlink)
             else:
                 staging, _, obj = self._build(
                     self.cache,
@@ -786,6 +787,7 @@ class Output:
                         state=self.repo.state,
                         prompt=prompt.confirm,
                         progress_callback=cb,
+                        old=obj,
                     )
                 self.set_exec()
 
@@ -902,7 +904,7 @@ class Output:
     def get_obj(
         self, filter_info: Optional[str] = None, **kwargs
     ) -> Optional["HashFile"]:
-        obj: Optional["HashFile"] = None
+        obj: Optional[HashFile] = None
         if self.obj:
             obj = self.obj
         elif self.files:
@@ -1158,7 +1160,7 @@ class Output:
             logger.warning(msg)
             return {}
 
-        obj: Optional["HashFile"]
+        obj: Optional[HashFile]
         if self.is_dir_checksum:
             obj = self._collect_used_dir_cache(**kwargs)
         else:
@@ -1201,8 +1203,9 @@ class Output:
         if stage:
             abs_path = os.path.join(stage.wdir, path)
             if self._is_path_dvcignore(abs_path):
-                check = stage.repo.dvcignore.check_ignore(abs_path)
-                raise self.IsIgnoredError(check)
+                check: CheckIgnoreResult = stage.repo.dvcignore.check_ignore(abs_path)
+                if check.match:
+                    raise self.IsIgnoredError(check)
 
     def _check_can_merge(self, out):
         if self.protocol != out.protocol:
@@ -1353,7 +1356,7 @@ class Output:
         cache = self.cache if self.use_cache else self.local_cache
         assert isinstance(cache, HashFileDB)
 
-        new: "HashFile"
+        new: HashFile
         try:
             assert self.hash_name
             staging, meta, obj = self._build(
@@ -1398,12 +1401,14 @@ class Output:
 
         assert staging
         assert obj.hash_info
+
+        hardlink = relink and next(iter(self.cache.cache_types), None) == "hardlink"
         with TqdmCallback(desc=f"Adding {self} to cache", unit="file") as cb:
             otransfer(
                 staging,
                 self.cache,
                 {obj.hash_info},
-                hardlink=relink,
+                hardlink=hardlink,
                 shallow=False,
                 callback=cb,
             )
@@ -1421,6 +1426,7 @@ class Output:
                     state=self.repo.state,
                     prompt=prompt.confirm,
                     progress_callback=callback,
+                    old=obj,
                 )
             self.set_exec()
         return obj
@@ -1447,25 +1453,44 @@ class Output:
         self.remote = other.remote
         self.can_push = other.can_push
 
-    def merge_version_meta(self, other: "Output"):
+    def _get_versioned_meta(
+        self,
+    ) -> Optional[
+        tuple["HashInfo", Optional["Meta"], Optional[Union["HashFile", "Tree"]]]
+    ]:
+        if self.files is not None or (
+            self.meta is not None and self.meta.version_id is not None
+        ):
+            old_obj = self.obj if self.obj is not None else self.get_obj()
+            return self.hash_info, self.meta, old_obj
+        return None
+
+    def merge_version_meta(
+        self,
+        old_hi: "HashInfo",
+        old_meta: Optional["Meta"],
+        old_obj: Optional[Union["HashFile", "Tree"]],
+    ):
         """Merge version meta for files which are unchanged from other."""
         if not self.hash_info:
-            return
+            return None
         if self.hash_info.isdir:
-            return self._merge_dir_version_meta(other)
-        if self.hash_info != other.hash_info:
-            return
-        self.meta = other.meta
+            return self._merge_dir_version_meta(old_hi, old_obj)
+        if self.hash_info != old_hi:
+            return None
+        self.meta = old_meta
+        return None
 
-    def _merge_dir_version_meta(self, other: "Output"):
+    def _merge_dir_version_meta(
+        self, old_hi: "HashInfo", old_obj: Optional[Union["HashFile", "Tree"]]
+    ):
         from dvc_data.hashfile.tree import update_meta
 
-        if not self.obj or not other.hash_info.isdir:
+        if not self.obj or not old_hi.isdir:
             return
-        other_obj = other.obj if other.obj is not None else other.get_obj()
         assert isinstance(self.obj, Tree)
-        assert isinstance(other_obj, Tree)
-        updated = update_meta(self.obj, other_obj)
+        assert isinstance(old_obj, Tree)
+        updated = update_meta(self.obj, old_obj)
         assert updated.hash_info == self.obj.hash_info
         self.obj = updated
         self.files = updated.as_list(with_meta=True)

dvc/parsing/__init__.py

@@ -563,10 +563,10 @@ class MatrixDefinition:
         iterable = self.resolved_iterable
         assert isinstance(iterable, Mapping)
 
-        ret: dict[str, "DictStrAny"] = {}
+        ret: dict[str, DictStrAny] = {}
         matrix = {key: enumerate(v) for key, v in iterable.items()}
         for combination in product(*matrix.values()):
-            d: "DictStrAny" = {}
+            d: DictStrAny = {}
             fragments: list[str] = []
             for k, (i, v) in zip(matrix.keys(), combination):
                 d[k] = v

dvc/parsing/context.py

@@ -66,7 +66,7 @@ class ParamsLoadError(ContextError):
     pass
 
 
-class KeyNotInContext(ContextError, KeyError):
+class KeyNotInContext(ContextError, KeyError):  # noqa: N818
     def __init__(self, key: str) -> None:
         self.key: str = key
         super().__init__(f"Could not find '{key}'")
@@ -75,7 +75,7 @@ class KeyNotInContext(ContextError, KeyError):
         return self.msg
 
 
-class VarsAlreadyLoaded(ContextError):
+class VarsAlreadyLoaded(ContextError):  # noqa: N818
     pass
 
 
@@ -105,7 +105,7 @@ class Meta:
 
     @staticmethod
     def update_path(meta: "Meta", path: Union[str, int]):
-        dpaths = meta.dpaths[:] + [str(path)]
+        dpaths = [*meta.dpaths, str(path)]
         return replace(meta, dpaths=dpaths)
 
     def __str__(self):
@@ -155,7 +155,7 @@ class Value(Node):
 PRIMITIVES = (int, float, str, bytes, bool)
 
 
-class Container(Node, ABC):
+class Container(Node, ABC):  # noqa: PLW1641
     meta: Meta
     data: Union[list, dict]
     _key_transform = staticmethod(identity)
@@ -176,8 +176,9 @@ class Container(Node, ABC):
             return value
         if isinstance(value, (list, dict)):
             assert meta
-            container = CtxDict if isinstance(value, dict) else CtxList
-            return container(value, meta=meta)
+            if isinstance(value, dict):
+                return CtxDict(value, meta=meta)
+            return CtxList(value, meta=meta)
         msg = f"Unsupported value of type '{type(value).__name__}' in '{meta}'"
         raise TypeError(msg)
 
@@ -271,7 +272,7 @@ class CtxDict(Container, MutableMapping):
         if not isinstance(key, str):
             # limitation for the interpolation
             # ignore other kinds of keys
-            return
+            return None
         return super().__setitem__(key, value)
 
     def merge_update(self, other, overwrite=False):

dvc/parsing/interpolate.py

@@ -202,6 +202,7 @@ def validate_value(value, key):
         if isinstance(value, dict) and key == "cmd":
             return True
         raise ParseError(f"Cannot interpolate data of type '{type(value).__name__}'")
+    return None
 
 
 def str_interpolate(

dvc/pathspec_math.py

@@ -2,13 +2,19 @@
 # Including changing base dir of path specification patterns and merging
 # of two path specification patterns with different base
 # All the operations follow the documents of `gitignore`
-from collections import namedtuple
+from typing import NamedTuple
 
 from pathspec.util import normalize_file
 
 from dvc.utils import relpath
 
-PatternInfo = namedtuple("PatternInfo", ["patterns", "file_info"])  # noqa: PYI024
+
+class PatternInfo(NamedTuple):
+    patterns: str
+    file_info: str
+
+    def __str__(self) -> str:
+        return self.file_info or f":{self.patterns}"
 
 
 def _not_ignore(rule):
@@ -27,11 +33,9 @@ def _remove_slash(rule):
 
 def _match_all_level(rule):
     if rule[:-1].find("/") >= 0 and not rule.startswith("**/"):
-        if rule.startswith("/"):
-            rule = rule[1:]
+        rule = rule.removeprefix("/")
         return False, rule
-    if rule.startswith("**/"):
-        rule = rule[3:]
+    rule = rule.removeprefix("**/")
     return True, rule
 
 

dvc/progress.py

@@ -41,7 +41,7 @@ class Tqdm(tqdm):
         "miniters": 1,
     }
 
-    def __init__(  # noqa: PLR0913
+    def __init__(
         self,
         iterable=None,
         disable=None,

dvc/render/converter/vega.py

@@ -23,7 +23,7 @@ def _lists(blob: Union[dict, list]) -> Iterable[list]:
     if isinstance(blob, list):
         yield blob
     else:
-        for _, value in blob.items():
+        for value in blob.values():
             if isinstance(value, dict):
                 yield from _lists(value)
             elif isinstance(value, list):
@@ -167,7 +167,7 @@ class VegaConverter(Converter):
         if isinstance(y, list):
             return "y"
         if not isinstance(y, dict):
-            return
+            return None
 
         fields = {field for _, field in _file_field(y)}
         if len(fields) == 1:

dvc/repo/__init__.py

@@ -144,10 +144,11 @@ class Repo:
         scm: Optional[Union["Git", "NoSCM"]] = None,
         remote: Optional[str] = None,
         remote_config: Optional["DictStrAny"] = None,
+        _wait_for_lock: bool = False,
     ):
         from dvc.cachemgr import CacheManager
         from dvc.data_cloud import DataCloud
-        from dvc.fs import GitFileSystem, LocalFileSystem, localfs
+        from dvc.fs import GitFileSystem, LocalFileSystem
         from dvc.lock import LockNoop, make_lock
         from dvc.repo.artifacts import Artifacts
         from dvc.repo.datasets import Datasets
@@ -161,12 +162,13 @@ class Repo:
 
         self.url = url
         self._fs_conf = {"repo_factory": repo_factory}
-        self._fs = fs or localfs
+        self._fs = fs or LocalFileSystem()
         self._scm = scm
         self._config = config
         self._remote = remote
         self._remote_config = remote_config
-        self._data_index = None
+        self._data_index: Optional[DataIndex] = None
+        self._wait_for_lock = _wait_for_lock
 
         if rev and not fs:
             self._scm = scm = SCM(root_dir or os.curdir)
@@ -184,12 +186,12 @@ class Repo:
         # used by DVCFileSystem to determine if it should traverse subrepos
         self.subrepos = subrepos
 
-        self.cloud: "DataCloud" = DataCloud(self)
-        self.stage: "StageLoad" = StageLoad(self)
+        self.cloud: DataCloud = DataCloud(self)
+        self.stage: StageLoad = StageLoad(self)
 
-        self.lock: "LockBase"
+        self.lock: LockBase
         self.cache: CacheManager
-        self.state: "StateBase"
+        self.state: StateBase
         if isinstance(self.fs, GitFileSystem) or not self.dvc_dir:
             self.lock = LockNoop()
             self.state = StateNoop()
@@ -204,8 +206,14 @@ class Repo:
                     tmp_dir=self.tmp_dir,
                     hardlink_lock=self.config["core"].get("hardlink_lock", False),
                     friendly=True,
+                    wait=self._wait_for_lock,
                 )
                 os.makedirs(self.site_cache_dir, exist_ok=True)
+                if not fs and (
+                    checksum_jobs := self.config["core"].get("checksum_jobs")
+                ):
+                    self.fs.hash_jobs = checksum_jobs
+
                 self.state = State(self.root_dir, self.site_cache_dir, self.dvcignore)
             else:
                 self.lock = LockNoop()
@@ -604,7 +612,7 @@ class Repo:
         from dvc.fs import GitFileSystem
         from dvc.version import version_tuple
 
-        cache_dir = self.config["core"].get("site_cache_dir") or site_cache_dir()
+        cache_dir = site_cache_dir(self.config["core"].get("site_cache_dir"))
 
         subdir = None
         if isinstance(self.fs, GitFileSystem):
@@ -633,10 +641,11 @@ class Repo:
         # that just happened to be at the same path as old deleted ones.
         btime = self._btime or getattr(os.stat(root_dir), "st_birthtime", None)
 
-        md5 = hashlib.md5(  # noqa: S324
+        md5 = hashlib.md5(
             str(
                 (root_dir, subdir, btime, getpass.getuser(), version_tuple[0], salt)
-            ).encode()
+            ).encode(),
+            usedforsecurity=False,
         )
         repo_token = md5.hexdigest()
         return os.path.join(repos_dir, repo_token)

dvc/repo/artifacts.py

@@ -137,14 +137,12 @@ class Artifacts:
 
         assert not (version and stage)
         name = _reformat_name(name)
-        tags: list["GitTag"] = find(
-            name=name, version=version, stage=stage, scm=self.scm
-        )
+        tags: list[GitTag] = find(name=name, version=version, stage=stage, scm=self.scm)
         if not tags:
             raise ArtifactNotFoundError(name, version=version, stage=stage)
         if version or stage:
             return tags[-1].target
-        gto_tags: list["GTOTag"] = sort_versions(parse_tag(tag) for tag in tags)
+        gto_tags: list[GTOTag] = sort_versions(parse_tag(tag) for tag in tags)
         return gto_tags[0].tag.target
 
     @classmethod
@@ -222,7 +220,7 @@ class Artifacts:
 
             out = resolve_output(path, out, force=force)
             fs = self.repo.dvcfs
-            count = fs_download(fs, path, os.path.abspath(out), jobs=jobs)
+            count = len(fs_download(fs, path, os.path.abspath(out), jobs=jobs))
         return count, out
 
     @staticmethod
@@ -285,7 +283,7 @@ class Artifacts:
         return len(to_infos), relpath(localfs.commonpath(to_infos))
 
     @classmethod
-    def get(  # noqa: PLR0913
+    def get(
         cls,
         url: str,
         name: str,
@@ -314,6 +312,13 @@ class Artifacts:
 
         name = _reformat_name(name)
         saved_exc: Optional[Exception] = None
+
+        local_dvc_studio_config = Config().get("studio", {})
+        args_dvc_studio_config = {}
+        if config and not isinstance(config, dict):
+            config = Config.load_file(config)
+            args_dvc_studio_config = config.get("studio", {})
+
         try:
             logger.trace("Trying studio-only config")
             return cls._download_studio(
@@ -324,14 +329,13 @@ class Artifacts:
                 out=out,
                 force=force,
                 jobs=jobs,
+                dvc_studio_config=local_dvc_studio_config | args_dvc_studio_config,
             )
         except FileExistsLocallyError:
             raise
         except Exception as exc:  # noqa: BLE001
             saved_exc = exc
 
-        if config and not isinstance(config, dict):
-            config = Config.load_file(config)
         with Repo.open(
             url=url,
             subrepos=True,
@@ -341,7 +345,7 @@ class Artifacts:
             remote_config=remote_config,
         ) as repo:
             logger.trace("Trying repo [studio] config")
-            dvc_studio_config = dict(repo.config.get("studio"))
+            repo_dvc_studio_config = repo.config.get("studio", {})
             try:
                 return cls._download_studio(
                     url,
@@ -351,7 +355,9 @@ class Artifacts:
                     out=out,
                     force=force,
                     jobs=jobs,
-                    dvc_studio_config=dvc_studio_config,
+                    dvc_studio_config=local_dvc_studio_config
+                    | repo_dvc_studio_config
+                    | args_dvc_studio_config,
                 )
             except FileExistsLocallyError:
                 raise

dvc/repo/checkout.py

@@ -1,4 +1,5 @@
 import os
+from collections import defaultdict
 from typing import TYPE_CHECKING
 
 from dvc.exceptions import (
@@ -14,7 +15,9 @@ from dvc.utils import relpath
 from . import locked
 
 if TYPE_CHECKING:
-    from dvc_data.index import BaseDataIndex, DataIndexEntry
+    from dvc.repo.index import IndexView
+    from dvc_data.index import BaseDataIndex, DataIndexEntry, DataIndexKey
+    from dvc_data.index.diff import Change
     from dvc_objects.fs.base import FileSystem
 
 logger = logger.getChild(__name__)
@@ -36,10 +39,12 @@ def _remove_unused_links(repo):
     return ret
 
 
-def _build_out_changes(index, changes):
+def _build_out_changes(
+    index: "IndexView", changes: dict["DataIndexKey", "Change"]
+) -> dict["DataIndexKey", tuple[str, dict[str, int]]]:
     from dvc_data.index.checkout import MODIFY
 
-    out_keys = []
+    out_keys: list[DataIndexKey] = []
     for out in index.outs:
         if not out.use_cache:
             continue
@@ -47,19 +52,28 @@ def _build_out_changes(index, changes):
         ws, key = out.index_key
         if ws != "repo":
             continue
-
         out_keys.append(key)
 
-    out_changes = {}
+    out_stats: dict[DataIndexKey, dict[str, int]]
+    out_stats = defaultdict(lambda: defaultdict(int))
+
+    out_changes: dict[DataIndexKey, tuple[str, dict[str, int]]] = {}
     for key, change in changes.items():
+        typ = change.typ
+        isdir = change.new and change.new.isdir
         for out_key in out_keys:
             if len(out_key) > len(key) or key[: len(out_key)] != out_key:
                 continue
 
+            stats = out_stats[out_key]
+            if not isdir:
+                stats[typ] += 1
+
             if key == out_key:
-                out_changes[out_key] = change.typ
-            elif not out_changes.get(out_key):
-                out_changes[out_key] = MODIFY
+                out_changes[out_key] = typ, stats
+            elif out_key not in out_changes:
+                typ = MODIFY
+                out_changes[out_key] = typ, stats
             break
 
     return out_changes
@@ -107,14 +121,13 @@ def checkout(  # noqa: C901
     from dvc.stage.exceptions import StageFileBadNameError, StageFileDoesNotExistError
     from dvc_data.index.checkout import ADD, DELETE, MODIFY, apply, compare
 
-    stats: dict[str, list[str]] = {
-        "added": [],
-        "deleted": [],
-        "modified": [],
-    }
+    stats = {"modified": 0, "added": 0, "deleted": 0}
+    changes: dict[str, list[str]] = {"modified": [], "added": [], "deleted": []}
+
     if not targets:
         targets = [None]
-        stats["deleted"] = _remove_unused_links(self)
+        changes["deleted"] = _remove_unused_links(self)
+        stats["deleted"] = len(changes["deleted"])
 
     if isinstance(targets, str):
         targets = [targets]
@@ -125,10 +138,12 @@ def checkout(  # noqa: C901
             (StageFileDoesNotExistError, StageFileBadNameError, NoOutputOrStageError),
         ):
             raise CheckoutErrorSuggestGit(target) from exc
-        raise
+        raise  # noqa: PLE0704
 
-    view = self.index.targets_view(
-        targets, recursive=recursive, with_deps=with_deps, onerror=onerror
+    from .index import index_from_targets
+
+    view = index_from_targets(
+        self, targets=targets, recursive=recursive, with_deps=with_deps, onerror=onerror
     )
 
     with ui.progress(unit="entry", desc="Building workspace index", leave=True) as pb:
@@ -149,7 +164,10 @@ def checkout(  # noqa: C901
 
     def checkout_onerror(src_path, dest_path, _exc):
         logger.debug(
-            "failed to create '%s' from '%s'", dest_path, src_path, exc_info=True
+            "failed to create '%s' from '%s'",
+            dest_path,
+            src_path,
+            exc_info=True,  # noqa: LOG014
         )
 
         for out_path in out_paths:
@@ -171,16 +189,26 @@ def checkout(  # noqa: C901
     out_changes = _build_out_changes(view, diff.changes)
 
     typ_map = {ADD: "added", DELETE: "deleted", MODIFY: "modified"}
-    for key, typ in out_changes.items():
+    for key, (typ, _stats) in out_changes.items():
         out_path = self.fs.join(self.root_dir, *key)
 
         if out_path in failed:
             self.fs.remove(out_path, recursive=True)
-        else:
-            self.state.save_link(out_path, self.fs)
-            stats[typ_map[typ]].append(_fspath_dir(out_path))
+            continue
 
+        self.state.save_link(out_path, self.fs)
+        for t, count in _stats.items():
+            stats_typ = typ_map[t]
+            stats[stats_typ] += count
+
+        changes[typ_map[typ]].append(_fspath_dir(out_path))
+
+    for changelist in changes.values():
+        # group directories first, then files. But keep them alphabetically sorted
+        changelist.sort(key=lambda p: (not p.endswith(os.sep), p))
+
+    result = changes | {"stats": stats}
     if failed and not allow_missing:
-        raise CheckoutError([relpath(out_path) for out_path in failed], stats)
-
-    return stats
+        result["failed"] = [relpath(out_path) for out_path in failed]
+        raise CheckoutError([relpath(out_path) for out_path in failed], result)
+    return result

dvc/repo/collect.py

@@ -43,13 +43,13 @@ def _collect_paths(
 
 
 def _filter_outs(
-    outs: Outputs, fs_paths: StrPaths, duplicates=False
+    repo: "Repo", outs: Outputs, fs_paths: StrPaths, duplicates=False
 ) -> tuple[Outputs, StrPaths]:
     res_outs: Outputs = []
     fs_res_paths = fs_paths
 
     for out in outs:
-        fs_path = out.repo.dvcfs.from_os_path(out.fs_path)
+        fs_path = repo.dvcfs.from_os_path(out.fs_path)
         if fs_path in fs_paths:
             res_outs.append(out)
             if not duplicates:
@@ -77,4 +77,4 @@ def collect(
 
     target_paths = _collect_paths(repo, targets, recursive=recursive)
 
-    return _filter_outs(outs, target_paths, duplicates=duplicates)
+    return _filter_outs(repo, outs, target_paths, duplicates=duplicates)

dvc/repo/commit.py

@@ -1,3 +1,4 @@
+from itertools import groupby
 from typing import TYPE_CHECKING
 
 from dvc import prompt
@@ -52,29 +53,38 @@ def commit(
     data_only=False,
     relink=True,
 ):
-    stages_info = [
-        info
-        for info in self.stage.collect_granular(
-            target, with_deps=with_deps, recursive=recursive
-        )
-        if not data_only or info.stage.is_data_source
-    ]
-    for stage_info in stages_info:
-        stage = stage_info.stage
-        if force:
-            stage.save(allow_missing=allow_missing)
-        else:
-            changes = stage.changed_entries()
-            if any(changes):
-                prompt_to_commit(stage, changes, force=force)
+    committed_stages = []
+    groups = groupby(
+        [
+            info
+            for info in self.stage.collect_granular(
+                target, with_deps=with_deps, recursive=recursive
+            )
+            if not data_only or info.stage.is_data_source
+        ],
+        key=lambda info: info.stage.dvcfile,
+    )
+
+    for dvcfile, stages_info_group in groups:
+        to_dump = []
+        for stage_info in stages_info_group:
+            stage = stage_info.stage
+            if force:
                 stage.save(allow_missing=allow_missing)
-        stage.commit(
-            filter_info=stage_info.filter_info,
-            allow_missing=allow_missing,
-            relink=relink,
-        )
-        stage.dump(update_pipeline=False)
-    return [s.stage for s in stages_info]
+            else:
+                changes = stage.changed_entries()
+                if any(changes):
+                    prompt_to_commit(stage, changes, force=force)
+                    stage.save(allow_missing=allow_missing)
+            stage.commit(
+                filter_info=stage_info.filter_info,
+                allow_missing=allow_missing,
+                relink=relink,
+            )
+            to_dump.append(stage)
+        dvcfile.dump_stages(to_dump, update_pipeline=False)
+        committed_stages.extend(to_dump)
+    return committed_stages
 
 
 @locked

dvc/repo/data.py

@@ -1,38 +1,34 @@
 import os
 import posixpath
-from collections.abc import Iterable
-from typing import TYPE_CHECKING, Any, TypedDict, Union
+from collections import defaultdict
+from collections.abc import Iterable, Iterator, Mapping
+from typing import TYPE_CHECKING, Optional, TypedDict, Union
 
-from dvc.fs.callbacks import DEFAULT_CALLBACK
+from dvc.fs.callbacks import DEFAULT_CALLBACK, Callback, TqdmCallback
+from dvc.log import logger
 from dvc.ui import ui
+from dvc_data.index import DataIndexDirError
 
 if TYPE_CHECKING:
-    from dvc.fs.callbacks import Callback
     from dvc.repo import Repo
     from dvc.scm import Git, NoSCM
-    from dvc_data.index import DataIndex
+    from dvc_data.index import (
+        BaseDataIndex,
+        DataIndex,
+        DataIndexEntry,
+        DataIndexKey,
+        DataIndexView,
+    )
     from dvc_data.index.diff import Change
+    from dvc_objects.fs.base import FileSystem
+
+logger = logger.getChild(__name__)
 
 
 def posixpath_to_os_path(path: str) -> str:
     return path.replace(posixpath.sep, os.path.sep)
 
 
-def _adapt_typ(typ: str) -> str:
-    from dvc_data.index.diff import ADD, DELETE, MODIFY
-
-    if typ == MODIFY:
-        return "modified"
-
-    if typ == ADD:
-        return "added"
-
-    if typ == DELETE:
-        return "deleted"
-
-    return typ
-
-
 def _adapt_path(change: "Change") -> str:
     isdir = False
     if change.new and change.new.meta:
@@ -45,27 +41,98 @@ def _adapt_path(change: "Change") -> str:
     return os.path.sep.join(key)
 
 
+def _adapt_path_from_entry(entry: "DataIndexEntry") -> str:
+    key = entry.key
+    assert key
+    if entry.meta and entry.meta.isdir:
+        key = (*key, "")
+    return os.sep.join(key)
+
+
+def _get_missing_paths(
+    to_check: Mapping["FileSystem", Mapping[str, Iterable["DataIndexEntry"]]],
+    batch_size: Optional[int] = None,
+    callback: "Callback" = DEFAULT_CALLBACK,
+) -> Iterator[str]:
+    for fs, paths_map in to_check.items():
+        if batch_size == 1 or (batch_size is None and fs.protocol == "local"):
+            results = list(callback.wrap(map(fs.exists, paths_map)))
+        else:
+            results = fs.exists(
+                list(paths_map), batch_size=batch_size, callback=callback
+            )
+
+        for cache_path, exists in zip(paths_map, results):
+            if exists:
+                continue
+
+            for entry in paths_map[cache_path]:
+                yield _adapt_path_from_entry(entry)
+
+
+class StorageCallback(Callback):
+    def __init__(self, parent_cb: Callback) -> None:
+        super().__init__(size=0, value=0)
+        self.parent_cb = parent_cb
+
+    def set_size(self, size: int) -> None:
+        # This is a no-op to prevent `fs.exists` from trying to set the size
+        pass
+
+    def relative_update(self, value: int = 1) -> None:
+        self.parent_cb.relative_update(value)
+
+    def absolute_update(self, value: int) -> None:
+        self.parent_cb.relative_update(value - self.value)
+
+
+class Rename(TypedDict):
+    old: str
+    new: str
+
+
+class DiffResult(TypedDict, total=False):
+    modified: list[str]
+    added: list[str]
+    deleted: list[str]
+    renamed: list[Rename]
+    unchanged: list[str]
+    unknown: list[str]
+    not_in_cache: list[str]
+
+
 def _diff(
-    old: "DataIndex",
-    new: "DataIndex",
+    old: "BaseDataIndex",
+    new: "BaseDataIndex",
     *,
+    filter_keys: Optional[Iterable["DataIndexKey"]] = None,
     granular: bool = False,
     not_in_cache: bool = False,
-    not_in_remote: bool = False,
-    remote_refresh: bool = False,
+    batch_size: Optional[int] = None,
     callback: "Callback" = DEFAULT_CALLBACK,
-) -> dict[str, list[str]]:
-    from dvc_data.index import StorageError
-    from dvc_data.index.diff import UNCHANGED, UNKNOWN, diff
+    with_renames: bool = False,
+) -> DiffResult:
+    from dvc_data.index.diff import (
+        ADD,
+        DELETE,
+        MODIFY,
+        RENAME,
+        UNCHANGED,
+        UNKNOWN,
+        diff,
+    )
 
-    ret: dict[str, list[str]] = {}
+    ret: DiffResult = defaultdict(list)  # type: ignore[assignment]
+    change_types = {
+        MODIFY: "modified",
+        ADD: "added",
+        DELETE: "deleted",
+        RENAME: "renamed",
+    }
 
-    def _add_change(typ, change):
-        typ = _adapt_typ(typ)
-        if typ not in ret:
-            ret[typ] = []
-
-        ret[typ].append(_adapt_path(change))
+    to_check: dict[FileSystem, dict[str, list[DataIndexEntry]]] = defaultdict(
+        lambda: defaultdict(list)
+    )
 
     for change in diff(
         old,
@@ -74,45 +141,72 @@ def _diff(
         shallow=not granular,
         hash_only=True,
         with_unknown=True,
+        with_renames=with_renames,
         callback=callback,
     ):
+        typ = change.typ
+
+        # The index is a trie, so even when we filter by a specific path
+        # like `dir/file`, all parent nodes leading to that path (e.g., `dir/`)
+        # still appear in the view. As a result, keys like `dir/` will be present
+        # even if only `dir/file` matches the filter.
+        # We need to skip such entries to avoid showing root of tracked directories.
+        if filter_keys:
+            # RENAME does not have a `change.key`
+            if typ == RENAME:
+                assert change.new
+                key = change.new.key
+                # match with "new" key only
+                assert key
+            else:
+                key = change.key
+
+            if not any(key[: len(fk)] == fk for fk in filter_keys):
+                continue
+
         if (
-            change.typ == UNCHANGED
+            typ == UNCHANGED
             and (not change.old or not change.old.hash_info)
             and (not change.new or not change.new.hash_info)
         ):
             # NOTE: emulating previous behaviour
             continue
 
-        if change.typ == UNKNOWN and not change.new:
+        if typ == UNKNOWN and not change.new:
             # NOTE: emulating previous behaviour
             continue
 
-        if (
-            not_in_cache
-            and change.old
-            and change.old.hash_info
-            and not old.storage_map.cache_exists(change.old)
-        ):
-            # NOTE: emulating previous behaviour
-            _add_change("not_in_cache", change)
+        if not_in_cache and change.old and change.old.hash_info:
+            old_entry = change.old
+            cache_fs, cache_path = old.storage_map.get_cache(old_entry)
+            # check later in batches
+            to_check[cache_fs][cache_path].append(old_entry)
 
-        try:
-            if (
-                not_in_remote
-                and change.old
-                and change.old.hash_info
-                and not old.storage_map.remote_exists(
-                    change.old, refresh=remote_refresh
-                )
-            ):
-                _add_change("not_in_remote", change)
-        except StorageError:
-            pass
+        change_typ = change_types.get(typ, typ)
+        if typ == RENAME:
+            assert change.old is not None
+            assert change.new is not None
+            ret["renamed"].append(
+                {
+                    "old": _adapt_path_from_entry(change.old),
+                    "new": _adapt_path_from_entry(change.new),
+                }
+            )
+        else:
+            ret[change_typ].append(_adapt_path(change))  # type: ignore[literal-required]
 
-        _add_change(change.typ, change)
-
-    return ret
+    total_items = sum(
+        len(entries) for paths in to_check.values() for entries in paths.values()
+    )
+    with TqdmCallback(size=total_items, desc="Checking cache", unit="entry") as cb:
+        missing_items = list(
+            _get_missing_paths(
+                to_check, batch_size=batch_size, callback=StorageCallback(cb)
+            ),
+        )
+        if missing_items:
+            ret["not_in_cache"] = missing_items
+    return dict(ret)  # type: ignore[return-value]
 
 
 class GitInfo(TypedDict, total=False):
@@ -151,7 +245,49 @@ def _git_info(scm: Union["Git", "NoSCM"], untracked_files: str = "all") -> GitIn
     )
 
 
-def _diff_index_to_wtree(repo: "Repo", **kwargs: Any) -> dict[str, list[str]]:
+def filter_index(
+    index: Union["DataIndex", "DataIndexView"],
+    filter_keys: Optional[Iterable["DataIndexKey"]] = None,
+) -> "BaseDataIndex":
+    from dvc_data.index.view import DataIndexView
+
+    if not filter_keys:
+        return index
+
+    if isinstance(index, DataIndexView):
+        orig_index = index._index
+        parent_filter_fn = index.filter_fn
+    else:
+        orig_index = index
+        parent_filter_fn = None
+
+    def filter_fn(key: "DataIndexKey") -> bool:
+        if parent_filter_fn is not None and not parent_filter_fn(key):
+            return False
+
+        for filter_key in filter_keys:
+            # eg: if key is "dir/file" and filter_key is "dir/", return True
+            if key[: len(filter_key)] == filter_key:
+                return True
+            # eg: if key is `dir/` and filter_key is `dir/file`, also return True.
+            # This ensures we include parent prefixes needed to reach matching leaves.
+            # Intermediate prefixes must be retained to access nested keys.
+            if filter_key[: len(key)] == key:
+                return True
+        return False
+
+    from dvc_data.index import view
+
+    return view(orig_index, filter_fn=filter_fn)
+
+
+def _diff_index_to_wtree(
+    repo: "Repo",
+    filter_keys: Optional[Iterable["DataIndexKey"]] = None,
+    granular: bool = False,
+    batch_size: Optional[int] = None,
+    with_renames: bool = False,
+) -> DiffResult:
     from .index import build_data_index
 
     with ui.progress(desc="Building workspace index", unit="entry") as pb:
@@ -162,37 +298,69 @@ def _diff_index_to_wtree(repo: "Repo", **kwargs: Any) -> dict[str, list[str]]:
             compute_hash=True,
             callback=pb.as_callback(),
         )
+        workspace_view = filter_index(workspace, filter_keys=filter_keys)
 
     with ui.progress(
         desc="Calculating diff between index/workspace",
         unit="entry",
     ) as pb:
+        index = repo.index.data["repo"]
+        view = filter_index(index, filter_keys=filter_keys)
         return _diff(
-            repo.index.data["repo"],
-            workspace,
+            view,
+            workspace_view,
+            filter_keys=filter_keys,
+            granular=granular,
             not_in_cache=True,
+            with_renames=with_renames,
+            batch_size=batch_size,
             callback=pb.as_callback(),
-            **kwargs,
         )
 
 
 def _diff_head_to_index(
-    repo: "Repo", head: str = "HEAD", **kwargs: Any
-) -> dict[str, list[str]]:
-    index = repo.index.data["repo"]
+    repo: "Repo",
+    head: str = "HEAD",
+    filter_keys: Optional[Iterable["DataIndexKey"]] = None,
+    granular: bool = False,
+    with_renames: bool = False,
+) -> DiffResult:
+    from dvc.exceptions import NotDvcRepoError
+    from dvc.scm import RevError
+    from dvc_data.index import DataIndex
 
-    with repo.switch(head):
-        head_index = repo.index.data["repo"]
+    index = repo.index.data["repo"]
+    index_view = filter_index(index, filter_keys=filter_keys)
+
+    try:
+        with repo.switch(head):
+            head_index = repo.index.data["repo"]
+            head_view = filter_index(head_index, filter_keys=filter_keys)
+    except RevError:
+        logger.debug("failed to switch to '%s'", head)
+        head_view = DataIndex()
+    except NotDvcRepoError as exc:
+        # NOTE: this only gets raised on subdir repos at the moment,
+        # which looks like a bug in `repo.switch`.
+        logger.warning(exc)
+        head_view = DataIndex()
 
     with ui.progress(desc="Calculating diff between head/index", unit="entry") as pb:
-        return _diff(head_index, index, callback=pb.as_callback(), **kwargs)
+        return _diff(
+            head_view,
+            index_view,
+            filter_keys=filter_keys,
+            granular=granular,
+            with_renames=with_renames,
+            callback=pb.as_callback(),
+        )
 
 
 class Status(TypedDict):
     not_in_cache: list[str]
     not_in_remote: list[str]
-    committed: dict[str, list[str]]
-    uncommitted: dict[str, list[str]]
+    committed: DiffResult
+    uncommitted: DiffResult
     untracked: list[str]
     unchanged: list[str]
     git: GitInfo
@@ -217,27 +385,158 @@ def _transform_git_paths_to_dvc(repo: "Repo", files: Iterable[str]) -> list[str]
     return [repo.fs.relpath(file, start) for file in files]
 
 
-def status(repo: "Repo", untracked_files: str = "no", **kwargs: Any) -> Status:
+def _get_entries_not_in_remote(
+    repo: "Repo",
+    filter_keys: Optional[Iterable["DataIndexKey"]] = None,
+    granular: bool = False,
+    remote_refresh: bool = False,
+) -> list[str]:
+    """Get entries that are not in remote storage."""
+    from dvc.repo.worktree import worktree_view
+    from dvc_data.index import StorageKeyError
+
+    entries: dict[DataIndexKey, DataIndexEntry] = {}
+
+    def _onerror(entry, exc):
+        if not isinstance(exc, DataIndexDirError):
+            raise exc
+        # We don't have the contents of this dir file, so we will only check this key.
+        entries[entry.key] = entry
+
+    # View into the index, with only pushable entries
+    index = worktree_view(repo.index, push=True)
+    data_index = index.data["repo"]
+
+    orig_data_index_onerror = data_index.onerror
+    data_index.onerror = _onerror
+
+    view = filter_index(data_index, filter_keys=filter_keys)  # type: ignore[arg-type]
+
+    missing_entries = []
+
+    storage_map = view.storage_map
+
+    n = 0
+    with TqdmCallback(size=n, desc="Checking remote", unit="entry") as cb:
+        for key, entry in view.iteritems(shallow=not granular):
+            if not (entry and entry.hash_info):
+                continue
+
+            # The index is a trie, so even when we filter by a specific path
+            # like `dir/file`, all parent nodes leading to that path (e.g., `dir/`)
+            # still appear in the view. As a result, keys like `dir/` will be present
+            # even if only `dir/file` matches the filter.
+            # We need to skip such entries to avoid showing root of tracked directories.
+            if filter_keys and not any(
+                key[: len(filter_key)] == filter_key for filter_key in filter_keys
+            ):
+                continue
+
+            entries[key] = entry
+            n += 1
+            cb.set_size(n)
+
+        for key, entry in entries.items():
+            k = (*key, "") if entry.meta and entry.meta.isdir else key
+            try:
+                if not storage_map.remote_exists(entry, refresh=remote_refresh):
+                    missing_entries.append(os.path.sep.join(k))
+            except StorageKeyError:
+                pass
+            finally:
+                cb.relative_update()
+    data_index.onerror = orig_data_index_onerror
+    return missing_entries
+
+
+def _matches_target(p: str, targets: Iterable[str]) -> bool:
+    sep = os.sep
+    return any(p == t or p.startswith(t + sep) for t in targets)
+
+
+def _prune_keys(filter_keys: Iterable["DataIndexKey"]) -> list["DataIndexKey"]:
+    sorted_keys = sorted(set(filter_keys), key=len)
+    result: list[DataIndexKey] = []
+
+    for key in sorted_keys:
+        if not any(key[: len(prefix)] == prefix for prefix in result):
+            result.append(key)
+    return result
+
+
+def status(  # noqa: PLR0913
+    repo: "Repo",
+    targets: Optional[Iterable[Union[os.PathLike[str], str]]] = None,
+    *,
+    granular: bool = False,
+    untracked_files: str = "no",
+    remote: Optional[str] = None,
+    not_in_remote: bool = False,
+    remote_refresh: bool = False,
+    config: Optional[dict] = None,
+    batch_size: Optional[int] = None,
+    head: str = "HEAD",
+    with_renames: bool = True,
+) -> Status:
     from dvc.scm import NoSCMError, SCMError
 
-    head = kwargs.pop("head", "HEAD")
-    uncommitted_diff = _diff_index_to_wtree(repo, **kwargs)
+    config = config or {}
+    if remote and not_in_remote:
+        logger.debug("Using remote %r", remote)
+        core = config.setdefault("core", {})
+        core["remote"] = remote
+    repo.config.merge(config)
+
+    targets = targets or []
+    filter_keys: list[DataIndexKey] = [repo.fs.relparts(os.fspath(t)) for t in targets]
+    # try to remove duplicate and overlapping keys
+    filter_keys = _prune_keys(filter_keys)
+
+    uncommitted_diff = _diff_index_to_wtree(
+        repo,
+        filter_keys=filter_keys,
+        granular=granular,
+        batch_size=batch_size,
+        with_renames=with_renames,
+    )
     unchanged = set(uncommitted_diff.pop("unchanged", []))
 
+    entries_not_in_remote: list[str] = []
+    if not_in_remote:
+        entries_not_in_remote = _get_entries_not_in_remote(
+            repo,
+            filter_keys=filter_keys,
+            granular=granular,
+            remote_refresh=remote_refresh,
+        )
+
     try:
-        committed_diff = _diff_head_to_index(repo, head=head, **kwargs)
+        committed_diff = _diff_head_to_index(
+            repo,
+            filter_keys=filter_keys,
+            head=head,
+            granular=granular,
+            with_renames=with_renames,
+        )
     except (SCMError, NoSCMError):
         committed_diff = {}
     else:
         unchanged &= set(committed_diff.pop("unchanged", []))
 
     git_info = _git_info(repo.scm, untracked_files=untracked_files)
-    untracked = git_info.get("untracked", [])
-    untracked = _transform_git_paths_to_dvc(repo, untracked)
+    scm_filter_targets = {
+        os.path.relpath(os.path.abspath(t), repo.scm.root_dir) for t in targets
+    }
+    untracked_it: Iterable[str] = git_info.get("untracked", [])
+    if scm_filter_targets:
+        untracked_it = (
+            f for f in untracked_it if _matches_target(f, scm_filter_targets)
+        )
+    untracked = _transform_git_paths_to_dvc(repo, untracked_it)
     # order matters here
     return Status(
         not_in_cache=uncommitted_diff.pop("not_in_cache", []),
-        not_in_remote=uncommitted_diff.pop("not_in_remote", []),
+        not_in_remote=entries_not_in_remote,
         committed=committed_diff,
         uncommitted=uncommitted_diff,
         untracked=untracked,

dvc/repo/datasets.py

@@ -16,7 +16,7 @@ from dvc.types import StrPath
 from dvc_data.hashfile.meta import Meta
 
 if TYPE_CHECKING:
-    from dvcx.dataset import DatasetRecord, DatasetVersion  # type: ignore[import]
+    from datachain.dataset import DatasetRecord, DatasetVersion  # type: ignore[import]
     from typing_extensions import Self
 
     from dvc.repo import Repo
@@ -29,10 +29,10 @@ def _get_dataset_record(name: str) -> "DatasetRecord":
     from dvc.exceptions import DvcException
 
     try:
-        from dvcx.catalog import get_catalog  # type: ignore[import]
+        from datachain.catalog import get_catalog  # type: ignore[import]
 
     except ImportError as exc:
-        raise DvcException("dvcx is not installed") from exc
+        raise DvcException("datachain is not installed") from exc
 
     catalog = get_catalog()
     return catalog.get_remote_dataset(name)
@@ -76,7 +76,7 @@ class SerDe:
         return asdict(self, filter=filter_defaults, value_serializer=value_serializer)
 
     @classmethod
-    def from_dict(cls: type["Self"], d: dict[str, Any]) -> "Self":
+    def from_dict(cls, d: dict[str, Any]) -> "Self":
         _fields = fields(cast("type[AttrsInstance]", cls))
         kwargs = {f.name: d[f.name] for f in _fields if f.name in d}
         return cls(**kwargs)
@@ -86,7 +86,7 @@ class SerDe:
 class DatasetSpec(SerDe):
     name: str
     url: str
-    type: Literal["dvc", "dvcx", "url"]
+    type: Literal["dvc", "dc", "url"]
 
 
 @frozen(kw_only=True)
@@ -108,7 +108,7 @@ class DVCDatasetLock(DVCDatasetSpec):
 
 
 @frozen(kw_only=True)
-class DVCXDatasetLock(DatasetSpec):
+class DatachainDatasetLock(DatasetSpec):
     version: int
     created_at: datetime = field(converter=to_datetime)
 
@@ -160,13 +160,13 @@ class DVCDataset:
 
 
 @frozen(kw_only=True)
-class DVCXDataset:
+class DatachainDataset:
     manifest_path: str
     spec: "DatasetSpec"
-    lock: "Optional[DVCXDatasetLock]" = field(default=None)
+    lock: "Optional[DatachainDatasetLock]" = field(default=None)
     _invalidated: bool = field(default=False, eq=False, repr=False)
 
-    type: ClassVar[Literal["dvcx"]] = "dvcx"
+    type: ClassVar[Literal["dc"]] = "dc"
 
     @property
     def pinned(self) -> bool:
@@ -193,7 +193,7 @@ class DVCXDataset:
         name, _version = self.name_version
         version = version if version is not None else _version
         version_info = _get_dataset_info(name, record=record, version=version)
-        lock = DVCXDatasetLock(
+        lock = DatachainDatasetLock(
             **self.spec.to_dict(),
             version=version_info.version,
             created_at=version_info.created_at,
@@ -226,9 +226,9 @@ class URLDataset:
         return evolve(self, lock=lock)
 
 
-Lock = Union[DVCDatasetLock, DVCXDatasetLock, URLDatasetLock]
+Lock = Union[DVCDatasetLock, DatachainDatasetLock, URLDatasetLock]
 Spec = Union[DatasetSpec, DVCDatasetSpec]
-Dataset = Union[DVCDataset, DVCXDataset, URLDataset]
+Dataset = Union[DVCDataset, DatachainDataset, URLDataset]
 
 
 class DatasetNotFoundError(DvcException, KeyError):
@@ -242,7 +242,7 @@ class DatasetNotFoundError(DvcException, KeyError):
 
 class Datasets(Mapping[str, Dataset]):
     def __init__(self, repo: "Repo") -> None:
-        self.repo: "Repo" = repo
+        self.repo: Repo = repo
 
     def __repr__(self):
         return repr(dict(self))
@@ -307,13 +307,13 @@ class Datasets(Mapping[str, Dataset]):
             raise ValueError("type should be present in spec")
         if typ == "dvc":
             return DVCDatasetSpec.from_dict(spec)
-        if typ in {"dvcx", "url"}:
+        if typ in {"dc", "url"}:
             return DatasetSpec.from_dict(spec)
         raise ValueError(f"unknown dataset type: {spec.get('type', '')}")
 
     @staticmethod
     def _lock_from_info(lock: Optional[dict[str, Any]]) -> Optional[Lock]:
-        kl = {"dvc": DVCDatasetLock, "dvcx": DVCXDatasetLock, "url": URLDatasetLock}
+        kl = {"dvc": DVCDatasetLock, "dc": DatachainDatasetLock, "url": URLDatasetLock}
         if lock and (cls := kl.get(lock.get("type", ""))):  # type: ignore[assignment]
             return cls.from_dict(lock)  # type: ignore[attr-defined]
         return None
@@ -356,9 +356,9 @@ class Datasets(Mapping[str, Dataset]):
                 lock=lock,
                 invalidated=_invalidated,
             )
-        if spec.type == "dvcx":
-            assert lock is None or isinstance(lock, DVCXDatasetLock)
-            return DVCXDataset(
+        if spec.type == "dc":
+            assert lock is None or isinstance(lock, DatachainDatasetLock)
+            return DatachainDataset(
                 manifest_path=manifest_path,
                 spec=spec,
                 lock=lock,
@@ -374,7 +374,7 @@ class Datasets(Mapping[str, Dataset]):
         manifest_path: StrPath = "dvc.yaml",
         **kwargs: Any,
     ) -> Dataset:
-        assert type in {"dvc", "dvcx", "url"}
+        assert type in {"dvc", "dc", "url"}
         kwargs.update({"name": name, "url": url, "type": type})
         dataset = self._build_dataset(os.path.abspath(manifest_path), kwargs)
         dataset = dataset.update(self.repo)
@@ -389,13 +389,16 @@ class Datasets(Mapping[str, Dataset]):
 
         if dataset.type == "url" and (version or kwargs.get("rev")):
             raise ValueError("cannot update version/revision for a url")
-        if dataset.type == "dvcx" and version is not None:
+        if dataset.type == "dc" and version is not None:
             if not isinstance(version, int):
                 raise TypeError(
-                    f"dvcx version has to be an integer, got {type(version).__name__!r}"
+                    "DataChain dataset version has to be an integer, "
+                    f"got {type(version).__name__!r}"
                 )
             if version < 1:
-                raise ValueError(f"dvcx version should be >=1, got {version}")
+                raise ValueError(
+                    f"DataChain dataset version should be >=1, got {version}"
+                )
 
         new = dataset.update(self.repo, **kwargs)
 

dvc/repo/diff.py

@@ -26,7 +26,7 @@ def _diff(old, new, data_keys, with_missing=False):
     from dvc_data.index.diff import ADD, DELETE, MODIFY, RENAME
     from dvc_data.index.diff import diff as idiff
 
-    ret: "dict[str, list[dict]]" = {
+    ret: dict[str, list[dict]] = {
         "added": [],
         "deleted": [],
         "modified": [],
@@ -45,6 +45,12 @@ def _diff(old, new, data_keys, with_missing=False):
         with_renames=True,
         meta_cmp_key=meta_cmp_key,
         roots=data_keys,
+        # Include unknown entries from missing dir entry, so that they don't
+        # get reported as added/modified/deleted.
+        # Also return unchanged entries so that we can check if they are missing
+        # from cache.
+        with_unknown=True,
+        with_unchanged=with_missing,
     ):
         if (change.old and change.old.isdir and not change.old.hash_info) or (
             change.new and change.new.isdir and not change.new.hash_info

dvc/repo/du.py

@@ -6,7 +6,7 @@ def du(
     path: Optional[str] = None,
     rev: Optional[str] = None,
     summarize: bool = False,
-    config: Union[None, dict[str, Any], str] = None,
+    config: Union[dict[str, Any], str, None] = None,
     remote: Optional[str] = None,
     remote_config: Optional[dict] = None,
 ):

dvc/repo/experiments/__init__.py

@@ -119,7 +119,7 @@ class Experiments:
         **kwargs,
     ):
         """Reproduce and checkout a single (standalone) experiment."""
-        exp_queue: "BaseStashQueue" = (
+        exp_queue: BaseStashQueue = (
             self.tempdir_queue if tmp_dir else self.workspace_queue
         )
         self.queue_one(exp_queue, **kwargs)
@@ -205,7 +205,7 @@ class Experiments:
         Experiment will be derived from the current workspace.
         """
 
-        name = kwargs.get("name", None)
+        name = kwargs.get("name")
         baseline_sha = kwargs.get("baseline_rev") or self.repo.scm.get_rev()
 
         if name:
@@ -249,7 +249,7 @@ class Experiments:
         exec_results = queue.reproduce(copy_paths=copy_paths, message=message)
 
         results: dict[str, str] = {}
-        for _, exp_result in exec_results.items():
+        for exp_result in exec_results.values():
             results.update(exp_result)
         return results
 

dvc/repo/experiments/apply.py

@@ -25,7 +25,7 @@ def apply(repo: "Repo", rev: str, **kwargs):
     from dvc.repo.checkout import checkout as dvc_checkout
     from dvc.scm import RevError, resolve_rev
 
-    exps: "Experiments" = repo.experiments
+    exps: Experiments = repo.experiments
 
     is_stash: bool = False
 
@@ -57,7 +57,7 @@ def apply(repo: "Repo", rev: str, **kwargs):
 
 
 def _apply(repo: "Repo", rev: str, name: Optional[str] = None, is_stash: bool = False):
-    exps: "Experiments" = repo.experiments
+    exps: Experiments = repo.experiments
 
     with exps.apply_stash.preserve_workspace(rev, name=name):
         with repo.scm.detach_head(rev, force=True):

dvc/repo/experiments/collect.py

@@ -69,11 +69,11 @@ def collect_rev(
 
 def _collect_rev(
     repo: "Repo",
-    rev: str,
+    revision: str,
     param_deps: bool = False,
     **kwargs,
 ) -> SerializableExp:
-    with repo.switch(rev) as rev:
+    with repo.switch(revision) as rev:
         if rev == "workspace":
             timestamp: Optional[datetime] = None
         else:
@@ -174,7 +174,7 @@ def collect_active(
     """
     if not baseline_revs:
         return {}
-    result: dict[str, list["ExpRange"]] = {}
+    result: dict[str, list[ExpRange]] = {}
     exps = repo.experiments
     for queue in (exps.workspace_queue, exps.tempdir_queue, exps.celery_queue):
         for baseline, active_exps in queue.collect_active_data(
@@ -220,7 +220,7 @@ def collect_successful(
     Returns:
         Dict mapping baseline revision to successful experiments.
     """
-    result: dict[str, list["ExpRange"]] = {}
+    result: dict[str, list[ExpRange]] = {}
     for baseline_rev in baseline_revs:
         result[baseline_rev] = list(_collect_baseline(repo, baseline_rev, **kwargs))
     return result
@@ -274,6 +274,7 @@ def collect(
     num: int = 1,
     hide_queued: bool = False,
     hide_failed: bool = False,
+    hide_workspace: bool = False,
     sha_only: bool = False,
     **kwargs,
 ) -> list["ExpState"]:
@@ -303,8 +304,11 @@ def collect(
             repo.scm, baseline_revs, refs=cached_refs, logger=logger
         )
 
-    workspace_data = collect_rev(repo, "workspace", **kwargs)
-    result: list["ExpState"] = [workspace_data]
+    result: list[ExpState] = []
+    if not hide_workspace:
+        workspace_data = collect_rev(repo, "workspace", **kwargs)
+        result.append(workspace_data)
+
     queued = collect_queued(repo, baseline_revs, **kwargs) if not hide_queued else {}
     active = collect_active(repo, baseline_revs, **kwargs)
     failed = collect_failed(repo, baseline_revs, **kwargs) if not hide_failed else {}

dvc/repo/experiments/exceptions.py

@@ -50,7 +50,7 @@ class MultipleBranchError(DvcException):
         self.ref_infos = ref_infos
 
 
-class AmbiguousExpRefInfo(InvalidArgumentError):
+class AmbiguousExpRefInfo(InvalidArgumentError):  # noqa: N818
     def __init__(self, exp_name: str, exp_ref_list: Iterable["ExpRefInfo"]):
         msg = [
             (

dvc/repo/experiments/executor/base.py

@@ -1,20 +1,21 @@
-import logging
 import os
 import pickle
 import shutil
 from abc import ABC, abstractmethod
 from collections.abc import Iterable, Iterator
-from contextlib import contextmanager
+from contextlib import AbstractContextManager, contextmanager
 from dataclasses import asdict, dataclass
 from enum import IntEnum
 from itertools import chain
 from typing import TYPE_CHECKING, Any, Callable, NamedTuple, Optional, Union
 
+from funcy import nullcontext
 from scmrepo.exceptions import SCMError
 
 from dvc.env import DVC_EXP_AUTO_PUSH, DVC_EXP_GIT_REMOTE
 from dvc.exceptions import DvcException
 from dvc.log import logger
+from dvc.logger import set_loggers_level
 from dvc.repo.experiments.exceptions import ExperimentExistsError
 from dvc.repo.experiments.refs import EXEC_BASELINE, EXEC_BRANCH, ExpRefInfo
 from dvc.repo.experiments.utils import to_studio_params
@@ -199,7 +200,7 @@ class BaseExecutor(ABC):
     @classmethod
     def from_info(cls, info: "ExecutorInfo") -> "Self":
         if info.result_hash:
-            result: Optional["ExecutorResult"] = ExecutorResult(
+            result: Optional[ExecutorResult] = ExecutorResult(
                 info.result_hash,
                 (ExpRefInfo.from_ref(info.result_ref) if info.result_ref else None),
                 info.result_force,
@@ -288,7 +289,7 @@ class BaseExecutor(ABC):
             stages = []
             if targets:
                 for target in targets:
-                    stages.append(
+                    stages.append(  # noqa: PERF401
                         dvc.commit(
                             target, recursive=recursive, force=True, relink=False
                         )
@@ -297,7 +298,9 @@ class BaseExecutor(ABC):
                 stages = dvc.commit([], recursive=recursive, force=True, relink=False)
             exp_hash = cls.hash_exp(stages)
             if include_untracked:
-                dvc.scm.add(include_untracked, force=True)  # type: ignore[call-arg]
+                from dvc.scm import add_no_submodules
+
+                add_no_submodules(dvc.scm, include_untracked, force=True)  # type: ignore[call-arg]
 
             with cls.auto_push(dvc):
                 cls.commit(
@@ -466,24 +469,27 @@ class BaseExecutor(ABC):
 
         if queue is not None:
             queue.put((rev, os.getpid()))
-        if log_errors and log_level is not None:
-            cls._set_log_level(log_level)
+
+        log_ctx = cls._set_log_level(log_level) if log_errors else nullcontext()
 
         exp_hash: Optional[str] = None
-        exp_ref: Optional["ExpRefInfo"] = None
+        exp_ref: Optional[ExpRefInfo] = None
         repro_force: bool = False
 
         if info.name:
             ui.write(f"Reproducing experiment '{info.name}'")
 
-        with cls._repro_dvc(
-            info,
-            infofile,
-            log_errors=log_errors,
-            copy_paths=copy_paths,
-            message=message,
-            **kwargs,
-        ) as dvc:
+        with (
+            log_ctx,
+            cls._repro_dvc(
+                info,
+                infofile,
+                log_errors=log_errors,
+                copy_paths=copy_paths,
+                message=message,
+                **kwargs,
+            ) as dvc,
+        ):
             args, kwargs = cls._repro_args(dvc)
             if args:
                 targets: Optional[Union[list, str]] = args[0]
@@ -509,7 +515,9 @@ class BaseExecutor(ABC):
             stages = dvc.reproduce(*args, **kwargs)
             if paths := cls._get_top_level_paths(dvc):
                 logger.debug("Staging top-level files: %s", paths)
-                dvc.scm_context.add(paths)
+                from dvc.scm import add_no_submodules
+
+                add_no_submodules(dvc.scm, paths)
 
             exp_hash = cls.hash_exp(stages)
             if not repro_dry:
@@ -559,7 +567,7 @@ class BaseExecutor(ABC):
             )
 
         ref: Optional[str] = dvc.scm.get_ref(EXEC_BRANCH, follow=False)
-        exp_ref: Optional["ExpRefInfo"] = ExpRefInfo.from_ref(ref) if ref else None
+        exp_ref: Optional[ExpRefInfo] = ExpRefInfo.from_ref(ref) if ref else None
         if cls.WARN_UNTRACKED:
             untracked = dvc.scm.untracked_files()
             if untracked:
@@ -786,13 +794,10 @@ class BaseExecutor(ABC):
         return orig_rev
 
     @staticmethod
-    def _set_log_level(level):
-        # When executor.reproduce is run in a multiprocessing child process,
-        # dvc.cli.main will not be called for that child process so we need to
-        # setup logging ourselves
-        dvc_logger = logging.getLogger("dvc")
+    def _set_log_level(level: Optional[int]) -> AbstractContextManager[None]:
         if level is not None:
-            dvc_logger.setLevel(level)
+            return set_loggers_level(level)
+        return nullcontext()
 
     @staticmethod
     def _copy_path(src, dst):

dvc/repo/experiments/executor/local.py

@@ -201,7 +201,7 @@ class WorkspaceExecutor(BaseLocalExecutor):
     @classmethod
     def from_stash_entry(cls, repo: "Repo", entry: "ExpStashEntry", **kwargs):
         root_dir = repo.scm.root_dir
-        executor: "WorkspaceExecutor" = cls._from_stash_entry(
+        executor: WorkspaceExecutor = cls._from_stash_entry(
             repo, entry, root_dir, **kwargs
         )
         logger.debug("Init workspace executor in '%s'", root_dir)

dvc/repo/experiments/pull.py

@@ -30,7 +30,7 @@ def pull(  # noqa: C901
     pull_cache: bool = False,
     **kwargs,
 ) -> Iterable[str]:
-    exp_ref_set: set["ExpRefInfo"] = set()
+    exp_ref_set: set[ExpRefInfo] = set()
     if all_commits:
         exp_ref_set.update(exp_refs(repo.scm, git_remote))
     elif exp_names:
@@ -55,7 +55,7 @@ def pull(  # noqa: C901
         rev_dict = iter_revs(repo.scm, rev, num)
         rev_set = set(rev_dict.keys())
         ref_info_dict = exp_refs_by_baseline(repo.scm, rev_set, git_remote)
-        for _, ref_info_list in ref_info_dict.items():
+        for ref_info_list in ref_info_dict.values():
             exp_ref_set.update(ref_info_list)
 
     pull_result = _pull(repo, git_remote, exp_ref_set, force)
@@ -97,7 +97,7 @@ def _pull(
     def group_result(refspec):
         return results[str(refspec)]
 
-    pull_result: Mapping[SyncStatus, list["ExpRefInfo"]] = group_by(group_result, refs)
+    pull_result: Mapping[SyncStatus, list[ExpRefInfo]] = group_by(group_result, refs)
 
     return pull_result
 

dvc/repo/experiments/push.py

@@ -78,7 +78,7 @@ def exp_refs_from_rev(scm: "Git", rev: list[str], num: int = 1) -> set["ExpRefIn
     rev_dict = iter_revs(scm, rev, num)
     rev_set = set(rev_dict.keys())
     ref_info_dict = exp_refs_by_baseline(scm, rev_set)
-    for _, ref_info_list in ref_info_dict.items():
+    for ref_info_list in ref_info_dict.values():
         exp_ref_set.update(ref_info_list)
     return exp_ref_set
 
@@ -96,7 +96,7 @@ def push(
     push_cache: bool = False,
     **kwargs: Any,
 ) -> dict[str, Any]:
-    exp_ref_set: set["ExpRefInfo"] = set()
+    exp_ref_set: set[ExpRefInfo] = set()
     assert isinstance(repo.scm, Git)
     if all_commits:
         exp_ref_set.update(exp_refs(repo.scm))
@@ -162,7 +162,7 @@ def _push(
     def group_result(refspec):
         return results[str(refspec)]
 
-    pull_result: Mapping[SyncStatus, list["ExpRefInfo"]] = group_by(group_result, refs)
+    pull_result: Mapping[SyncStatus, list[ExpRefInfo]] = group_by(group_result, refs)
 
     return pull_result
 

dvc/repo/experiments/queue/base.py

@@ -38,7 +38,7 @@ logger = logger.getChild(__name__)
 
 
 @dataclass(frozen=True)
-class QueueEntry:
+class QueueEntry:  # noqa: PLW1641
     dvc_root: str
     scm_root: str
     stash_ref: str
@@ -372,7 +372,7 @@ class BaseStashQueue(ABC):
         )
 
     def _stash_commit_deps(self, *args, **kwargs):
-        if len(args):
+        if args:
             targets = args[0]
         else:
             targets = kwargs.get("targets")
@@ -609,9 +609,9 @@ class BaseStashQueue(ABC):
                 result[exp_name] = entry_name_dict[exp_name]
                 continue
             if self.scm.is_sha(exp_name):
-                for rev in entry_rev_dict:
+                for rev, entry in entry_rev_dict.items():
                     if rev.startswith(exp_name.lower()):
-                        result[exp_name] = entry_rev_dict[rev]
+                        result[exp_name] = entry
                         break
 
         return result

dvc/repo/experiments/queue/celery.py

@@ -1,3 +1,4 @@
+import glob
 import hashlib
 import locale
 import logging
@@ -323,7 +324,7 @@ class LocalCeleryQueue(BaseStashQueue):
     def _get_running_task_ids(self) -> set[str]:
         running_task_ids: set[str] = set()
         active_workers = self.worker_status()
-        for _, tasks in active_workers.items():
+        for tasks in active_workers.values():
             task = first(tasks)
             if task:
                 running_task_ids.add(task["id"])
@@ -434,9 +435,13 @@ class LocalCeleryQueue(BaseStashQueue):
         try:
             proc_info = self.proc[queue_entry.stash_rev]
         except KeyError:
-            raise DvcException(  # noqa: B904
-                f"No output logs found for experiment '{rev}'"
-            )
+            message = f"No output logs found for experiment '{rev}'"
+            if self.match_queue_entry_by_name({rev}, self.iter_failed()).get(rev):
+                message += "\nExperiment likely failed during setup."
+                if celery_logs := glob.glob(os.path.join(self.wdir, "*.out")):
+                    message += " Check the celery logs for more details:"
+                    message += f"\n\tcat {' '.join(celery_logs)}".expandtabs(4)
+            raise DvcException(message)  # noqa: B904
         with open(
             proc_info.stdout, encoding=encoding or locale.getpreferredencoding()
         ) as fobj:
@@ -470,11 +475,11 @@ class LocalCeleryQueue(BaseStashQueue):
             exp_names = [exp_names]
         results: dict[str, ExpRefAndQueueEntry] = {}
 
-        exp_ref_match: dict[str, Optional["ExpRefInfo"]] = resolve_name(
+        exp_ref_match: dict[str, Optional[ExpRefInfo]] = resolve_name(
             self.scm, exp_names, git_remote
         )
         if not git_remote:
-            queue_entry_match: dict[str, Optional["QueueEntry"]] = (
+            queue_entry_match: dict[str, Optional[QueueEntry]] = (
                 self.match_queue_entry_by_name(
                     exp_names, self.iter_queued(), self.iter_done()
                 )
@@ -613,7 +618,7 @@ class LocalCeleryQueue(BaseStashQueue):
         """Map exp refs to any available successful executors."""
         from dvc.repo.experiments.serialize import ExpExecutor, LocalExpExecutor
 
-        result: dict[str, "ExpExecutor"] = {}
+        result: dict[str, ExpExecutor] = {}
         for entry, exec_result in self.iter_success():
             if baseline_revs and entry.baseline_rev not in baseline_revs:
                 continue